CN116612899A - Cardiovascular surgery data processing method and service platform based on Internet - Google Patents
Cardiovascular surgery data processing method and service platform based on Internet Download PDFInfo
- Publication number
- CN116612899A CN116612899A CN202310883664.6A CN202310883664A CN116612899A CN 116612899 A CN116612899 A CN 116612899A CN 202310883664 A CN202310883664 A CN 202310883664A CN 116612899 A CN116612899 A CN 116612899A
- Authority
- CN
- China
- Prior art keywords
- data
- cardiovascular surgery
- cardiovascular
- feature
- generate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013130 cardiovascular surgery Methods 0.000 title claims abstract description 296
- 238000003672 processing method Methods 0.000 title claims abstract description 16
- 230000002526 effect on cardiovascular system Effects 0.000 claims abstract description 139
- 239000011159 matrix material Substances 0.000 claims abstract description 124
- 238000000034 method Methods 0.000 claims abstract description 121
- 238000012545 processing Methods 0.000 claims abstract description 91
- 230000002452 interceptive effect Effects 0.000 claims abstract description 62
- 230000000007 visual effect Effects 0.000 claims abstract description 36
- 238000000605 extraction Methods 0.000 claims abstract description 22
- 238000012800 visualization Methods 0.000 claims abstract description 16
- 238000012216 screening Methods 0.000 claims abstract description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 96
- 230000008569 process Effects 0.000 claims description 47
- 238000004458 analytical method Methods 0.000 claims description 36
- 239000013598 vector Substances 0.000 claims description 36
- 238000001514 detection method Methods 0.000 claims description 25
- 230000006870 function Effects 0.000 claims description 24
- 238000005070 sampling Methods 0.000 claims description 24
- 238000000354 decomposition reaction Methods 0.000 claims description 22
- 238000013135 deep learning Methods 0.000 claims description 22
- 238000010586 diagram Methods 0.000 claims description 21
- 125000004122 cyclic group Chemical group 0.000 claims description 20
- 206010002091 Anaesthesia Diseases 0.000 claims description 19
- 230000037005 anaesthesia Effects 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 17
- 238000011176 pooling Methods 0.000 claims description 16
- 238000007781 pre-processing Methods 0.000 claims description 16
- 238000012407 engineering method Methods 0.000 claims description 14
- 230000009466 transformation Effects 0.000 claims description 11
- 238000012880 independent component analysis Methods 0.000 claims description 9
- 210000004556 brain Anatomy 0.000 claims description 8
- 238000007621 cluster analysis Methods 0.000 claims description 7
- 238000013079 data visualisation Methods 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 5
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 4
- 239000008280 blood Substances 0.000 claims description 4
- 210000004369 blood Anatomy 0.000 claims description 4
- 230000036772 blood pressure Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000007418 data mining Methods 0.000 claims description 4
- 229910052760 oxygen Inorganic materials 0.000 claims description 4
- 239000001301 oxygen Substances 0.000 claims description 4
- 230000002787 reinforcement Effects 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000036760 body temperature Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000005520 cutting process Methods 0.000 claims description 2
- 238000007726 management method Methods 0.000 abstract description 5
- 238000013523 data management Methods 0.000 abstract description 3
- 238000001356 surgical procedure Methods 0.000 description 25
- 239000000523 sample Substances 0.000 description 21
- 230000005540 biological transmission Effects 0.000 description 11
- 238000003860 storage Methods 0.000 description 10
- 238000011282 treatment Methods 0.000 description 10
- 238000007405 data analysis Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 9
- 238000012544 monitoring process Methods 0.000 description 9
- 230000003993 interaction Effects 0.000 description 8
- 238000010606 normalization Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 6
- 238000009826 distribution Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000000513 principal component analysis Methods 0.000 description 5
- 238000000844 transformation Methods 0.000 description 5
- 230000003444 anaesthetic effect Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 208000024172 Cardiovascular disease Diseases 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 230000010339 dilation Effects 0.000 description 3
- 238000005065 mining Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000004393 prognosis Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013131 cardiovascular procedure Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000008846 dynamic interplay Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000003213 activating effect Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000003339 best practice Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000011068 loading method Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000006461 physiological response Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000004659 sterilization and disinfection Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
- 238000007794 visualization technique Methods 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Medical Informatics (AREA)
- Bioethics (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Public Health (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to an internet-based cardiovascular surgery data processing method and a service platform, wherein the method comprises the following steps: acquiring first cardiovascular surgical data; feature extraction is carried out on the first cardiovascular surgery data, rule screening is carried out on the user service feature data, and second cardiovascular surgery data is generated; performing interactive visualization processing on the second cardiovascular surgical data to generate a cardiovascular surgical data interactive view; visual projection is carried out on the interactive view of the cardiovascular surgical data, and a cardiovascular surgical data feature matrix projection chart is generated; performing expansion convolution on the interactive view for generating cardiovascular surgery data to generate a cardiovascular surgery convolution characteristic model; symmetrically encrypting the cardiovascular surgery convolution characteristic model; the cardiovascular surgery symmetric encryption model is uploaded to the cardiovascular surgery data processing service platform, and the cardiovascular surgery data management method and system realize orderly and accurate management of cardiovascular surgery data.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a cardiovascular surgery data processing method and a service platform based on the Internet.
Background
The traditional cardiovascular surgery data processing method is characterized in that a series of handwritten documents, medical records, pictures and the like are recorded and stored, the manner is easy to cause confusion of surgery data and inaccurate information recording, care and treatment of patients are seriously influenced, and the paper recording manner is unfavorable for improving the working efficiency and information sharing of medical staff, so that all data are recorded and integrated on the data processing service platform in real time on an operation site through the cardiovascular surgery data processing service platform based on the Internet, the data processing and data analysis flow of cardiovascular surgery can be greatly simplified, on the basis, more perfect surgery data processing and processing services can be provided for the medical staff by combining the technologies of artificial intelligence, cloud computing and the like, and the medical staff can perform real-time diagnosis monitoring and operation guidance through uploading surgery visual image data, thereby improving the surgery success rate; the cardiovascular surgery data processing service platform based on the Internet realizes information exchange and remote collaboration among medical institutions, doctors and patients through the Internet and a network communication technology, and can optimize and improve the surgery environment and minimize surgery risks and patient infection rate through real-time monitoring and analysis of data.
Disclosure of Invention
The invention provides a cardiovascular surgery data processing method and a service platform based on the Internet to solve at least one technical problem.
In order to achieve the above object, the present invention provides an internet-based cardiovascular surgery data processing method, comprising the steps of:
step S1: acquiring first cardiovascular surgical data by using an information acquisition system; the first cardiovascular surgical data includes cardiovascular surgical video, cardiovascular surgical audio data, patient vital sign data, anesthesia detection data, and surgical instrument device data;
step S2: performing feature extraction on the first cardiovascular surgery data by using a feature engineering method to generate cardiovascular surgery data feature data; performing rule screening on the user service characteristic data by using an association rule analysis method to generate second cardiovascular surgery data;
step S3: performing interactive visual processing on the second cardiovascular surgical data by using a deep learning algorithm to generate a cardiovascular surgical data interactive view;
step S3: visual projection is carried out on the cardiovascular surgery data interactive view by utilizing a matrix decomposition method, and a cardiovascular surgery data feature matrix projection diagram is generated;
Step S5: performing expansion convolution and multi-scale sampling on the interactive view for generating cardiovascular surgery data by using a cyclic convolution network to generate a cardiovascular surgery convolution characteristic model;
step S6: symmetrically encrypting the cardiovascular surgery convolution feature model by using a symmetrical encryption algorithm to generate a cardiovascular surgery symmetrical encryption model; and uploading the cardiovascular surgery symmetric encryption model to a cardiovascular surgery data processing service platform by utilizing an HTTPS protocol based on the Internet, so as to realize cardiovascular surgery data processing.
The invention provides a cardiovascular surgery data processing method based on the Internet, which can collect and record various data information in the cardiovascular surgery process by using an information acquisition system, including video, audio, vital sign monitoring, anesthesia detection, surgical instrument use condition and the like. The comprehensive data collection can ensure that doctors and researchers acquire detailed operation process information, so that subsequent analysis and decision are facilitated, and by applying the feature engineering method, the system can extract key features from a large amount of original data, reduce redundancy and noise of the data and improve the expression and interpretation capability of the features. This will help doctors and researchers to more quickly acquire relevant information, discover patterns and trends in the data, provide a reliable basis for medical decisions using deep learning algorithms and interactive visualization processes, and the system can transform abstract data into intuitive interactive views such as graphics, images or dynamic figures. This allows doctors and researchers to understand and analyze the data in a more intuitive manner, exploring relationships and variations between the data, and thereby better identifying and interpreting potential problems or anomalies. By applying a matrix factorization method, the system may reduce complex interactive views to a more manageable matrix form. The simplification and projection can provide more efficient data processing and calculation modes, reduce calculation complexity and improve the speed and accuracy of data analysis. By means of a cyclic convolution network, the system is able to learn and extract rich cardiovascular surgical data features, including timing and spatial dependencies. The multi-scale sampling and expansion convolution can capture characteristic information on different layers and scales, provide more comprehensive and accurate data expression, and assist doctors and researchers in making diagnosis and treatment decisions. By protecting the cardiovascular surgical convolution feature model using a symmetric encryption algorithm, the system ensures security and privacy protection during data transmission and storage. Such security measures help to prevent unauthorized access and data leakage, ensuring confidentiality of sensitive patient information. Meanwhile, the system ensures the orderly and accurate management of cardiovascular surgical data.
In one embodiment of the present specification, there is provided an internet-based cardiovascular surgical data processing service platform, including:
the cardiovascular surgery data acquisition module acquires first cardiovascular surgery data by using a high-definition camera, a sound recorder and medical equipment; the medical equipment comprises a cardio-cerebral wave instrument and an X-ray detector, and the first cardiovascular surgery data comprise cardiovascular surgery video, cardiovascular surgery audio data, patient vital sign data, anesthesia detection data and surgical instrument data;
the feature extraction module is used for carrying out feature extraction on the first cardiovascular surgery data by using a feature engineering method to generate cardiovascular surgery data feature data; performing rule screening on the user service characteristic data by using an association rule analysis method to generate second cardiovascular surgery data;
the interactive view module is used for performing interactive visual processing on the second cardiovascular surgical data by using a deep learning algorithm to generate a cardiovascular surgical data interactive view;
the matrix projection module is used for carrying out visual projection on the cardiovascular surgery data interactive view by utilizing a matrix decomposition method to generate a cardiovascular surgery data characteristic matrix projection diagram;
The feature model module is used for performing expansion convolution and multi-scale sampling on the interactive view generated by the cardiovascular surgery data by using a circular convolution network to generate a cardiovascular surgery convolution feature model;
the data encryption module is used for symmetrically encrypting the cardiovascular surgery convolution characteristic model by utilizing a symmetrical encryption algorithm to generate a cardiovascular surgery symmetrical encryption model; and uploading the cardiovascular surgery symmetric encryption model to a cardiovascular surgery data processing service platform by utilizing an HTTPS protocol based on the Internet, so as to realize cardiovascular surgery data processing.
The invention establishes the cardiovascular surgery data processing service platform based on the Internet, and performs data acquisition on the whole surgery process by combining medical equipment such as a medical camera, a heart brain wave instrument, an X-ray detector and the like, including surgery video data, surgery audio data, patient vital sign data, anesthesia detection data and surgery instrument data, thereby improving the quality and reliability of the surgery process data, ensuring the accuracy and reliability of the data in the surgery process by comprehensively monitoring the medical equipment during the data acquisition process, providing a solid data basis for subsequent data processing and analysis, optimizing the data processing flow by using technologies such as artificial intelligence, deep learning and the like, automatically eliminating irrelevant data by the system, extracting valuable information, generating a normative and clean data set, greatly reducing the working pressure of doctors and researchers, improving the data processing efficiency, converting the surgery process data into visual interactive views and convolution characteristic model diagrams which are easy to understand and analyze, ensuring that doctors and researchers can grasp key characteristics and change conditions in the surgery process more easily, helping to acquire the diagnosis and treatment data and obtaining statistics and deep understanding of the cardiovascular surgery platform more deeply. Through data analysis, relevant information in aspects of risk factors, etiology, treatment schemes, prognosis and the like of cardiovascular diseases can be explored, and development of medical scientific research and clinical decision can be promoted. The cardiovascular surgery data processing platform adopts a safe encryption and authentication mechanism in the data transmission and storage process, so that the privacy and the data safety of patients are protected. Only authorized users can access and manipulate the sensitive information, ensuring confidentiality and integrity of patient data. Through an automatic and standardized process, the cardiovascular surgery data processing platform can help medical staff to improve working efficiency, reduce manual errors and optimize the working process. For example, automatically generating reports, providing intelligent auxiliary diagnostic tools, reminding tasks and key time points, etc., all help to improve the efficiency of medical and administrative work. The cardiovascular surgery data processing service platform based on the Internet can fully exert technical advantages, realize informatization and intellectualization aiming at the requirements and characteristics of the medical industry, and provide comprehensive and high-quality medical guarantee service for hospitals.
Drawings
FIG. 1 is a flow chart of steps of an Internet-based cardiovascular surgical data processing method according to the present application;
FIG. 2 is a detailed implementation step flow diagram of step S1;
FIG. 3 is a detailed implementation step flow diagram of step S2;
fig. 4 is a detailed implementation step flow diagram of step S3.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The embodiment of the application provides an Internet-based cardiovascular surgery data processing method and a service platform. The execution main body of the cardiovascular surgery data processing method and the service platform based on the Internet comprises, but is not limited to, the system: mechanical devices, data processing platforms, cloud server nodes, network uploading devices, etc. may be considered general purpose computing nodes of the present application, including but not limited to: at least one of an audio image management system, a data processing system and a cloud data management system.
Referring to fig. 1 to 4, the present application provides a cardiovascular surgery data processing service method on the internet, the method comprising the following steps:
step S1: acquiring first cardiovascular surgical data by using an information acquisition system; the first cardiovascular surgical data includes cardiovascular surgical video, cardiovascular surgical audio data, patient vital sign data, anesthesia detection data, and surgical instrument device data;
Step S2: performing feature extraction on the first cardiovascular surgery data by using a feature engineering method to generate cardiovascular surgery data feature data; performing rule screening on the user service characteristic data by using an association rule analysis method to generate second cardiovascular surgery data;
step S3: performing interactive visual processing on the second cardiovascular surgical data by using a deep learning algorithm to generate a cardiovascular surgical data interactive view;
step S3: visual projection is carried out on the cardiovascular surgery data interactive view by utilizing a matrix decomposition method, and a cardiovascular surgery data feature matrix projection diagram is generated;
step S5: performing expansion convolution and multi-scale sampling on the interactive view for generating cardiovascular surgery data by using a cyclic convolution network to generate a cardiovascular surgery convolution characteristic model;
step S6: symmetrically encrypting the cardiovascular surgery convolution feature model by using a symmetrical encryption algorithm to generate a cardiovascular surgery symmetrical encryption model; and uploading the cardiovascular surgery symmetric encryption model to a cardiovascular surgery data processing service platform by utilizing an HTTPS protocol based on the Internet, so as to realize cardiovascular surgery data processing.
The invention provides a cardiovascular surgery data processing method based on the Internet, which collects and records various data information in the cardiovascular surgery process by using an information acquisition system, including video, audio, vital sign monitoring, anesthesia detection, surgical instrument use condition and the like. The comprehensive data collection can ensure that doctors and researchers acquire detailed operation process information, so that subsequent analysis and decision are facilitated, and by applying the feature engineering method, the system can extract key features from a large amount of original data, reduce redundancy and noise of the data and improve the expression and interpretation capability of the features. This will help doctors and researchers to more quickly acquire relevant information, discover patterns and trends in the data, provide a reliable basis for medical decisions using deep learning algorithms and interactive visualization processes, and the system can transform abstract data into intuitive interactive views such as graphics, images or dynamic figures. This allows doctors and researchers to understand and analyze the data in a more intuitive manner, exploring relationships and variations between the data, and thereby better identifying and interpreting potential problems or anomalies. By applying a matrix factorization method, the system may reduce complex interactive views to a more manageable matrix form. The simplification and projection can provide more efficient data processing and calculation modes, reduce calculation complexity and improve the speed and accuracy of data analysis. By means of a cyclic convolution network, the system is able to learn and extract rich cardiovascular surgical data features, including timing and spatial dependencies. The multi-scale sampling and expansion convolution can capture characteristic information on different layers and scales, provide more comprehensive and accurate data expression, and assist doctors and researchers in making diagnosis and treatment decisions. By protecting the cardiovascular surgical convolution feature model using a symmetric encryption algorithm, the system ensures security and privacy protection during data transmission and storage. Such security measures help to prevent unauthorized access and data leakage, ensuring confidentiality of sensitive patient information. Meanwhile, the system ensures the orderly and accurate management of cardiovascular surgical data.
In the embodiment of the present invention, as described with reference to fig. 1, a flowchart of steps of an internet-based cardiovascular surgery data processing method and a service platform of the present invention is provided, where in this example, the steps of the internet-based cardiovascular surgery data processing method include:
step S1: acquiring first cardiovascular surgical data by using an information acquisition system; the first cardiovascular surgical data includes cardiovascular surgical video, cardiovascular surgical audio data, patient vital sign data, anesthesia detection data, and surgical instrument device data;
in the embodiment of the invention, the normal operation of equipment such as an information acquisition system and the like is ensured, the equipment is well connected with a computer or a data acquisition system, and a high-definition camera and a recorder are properly placed in an operating room, so that the cardiovascular surgical procedure can be comprehensively recorded. Ensuring that the camera can capture a clear image of the surgical field and the recorder can capture the sound during surgery. Medical equipment such as a heart brain wave instrument and an X-ray detector is properly connected with a patient, and the equipment can accurately record physiological data and anesthesia conditions of the patient. The camera, recorder and medical equipment are turned on, ensuring that they are in operation and the necessary calibration and adjustment is made. Before surgery is performed, it is ensured that all devices are properly recorded and ready to receive data. After the operation starts, the camera will record the video of the operation process in its whole course, and the recorder will record the sound during the operation. And acquiring and storing video data acquired by the camera, audio data acquired by the recorder, vital sign data acquired by the medical equipment, anesthesia detection data and surgical instrument data. The data may be processed and stored using a dedicated data acquisition system or transmitted to a computer. By using a high definition camera, a sound recorder and medical equipment, such as a heart brain wave device and an X-ray detector, first cardiovascular surgical data including video, audio, vital signs, anesthesia status and instrument data can be acquired. These data are very valuable for the recording, analysis and subsequent study of cardiovascular surgery.
Step S2: performing feature extraction on the first cardiovascular surgery data by using a feature engineering method to generate cardiovascular surgery data feature data; and carrying out rule screening on the user service characteristic data by using an association rule analysis method to generate second cardiovascular surgery data.
In the embodiment of the invention, the cardiovascular surgical data is preprocessed, noise data is removed, missing values and abnormal values are processed, and operations such as data smoothing and normalization are performed, so that the reliability and consistency of the data are ensured. The features related to the task are selected from the first cardiovascular surgical data, and the feature selection can be performed by adopting a statistical method, a correlation analysis method, an information gain method and the like. Transforming the selected features may reduce feature dimensions by dimension reduction techniques (e.g., principal component analysis) or may enhance feature expression by mathematical transformations (e.g., log, exponential, polynomial transformations). And converting the first cardiovascular surgery data processed by the feature engineering into cardiovascular surgery data feature data, and retaining key information contained in the feature. And converting the user service characteristic data into a format suitable for carrying out association rule analysis, and encoding the discrete characteristic data. And (3) using an Apriori algorithm or other frequent item set mining methods to find out frequent item sets, namely characteristic item combinations which frequently occur simultaneously, from the encoded data. And generating association rules meeting the minimum support and minimum confidence threshold conditions according to the frequent item sets. And screening the generated association rules according to the service requirements and rule quality evaluation indexes (such as support degree, confidence degree, lifting degree and the like), and selecting the rules which are related to the tasks and have a certain confidence degree. And according to the screened association rules, converting the user service characteristic data into second cardiovascular surgery data, wherein the data comprises characteristic information associated according to the rules. Through the feature engineering and association rule analysis method, important features can be extracted from the first cardiovascular surgery data, and second cardiovascular surgery data is generated according to the user service feature data, so that data analysis and subsequent application are further optimized.
Step S3: and performing interactive visual processing on the second cardiovascular surgical data by using a deep learning algorithm to generate a cardiovascular surgical data interactive view.
In the embodiment of the invention, the second cardiovascular surgery data is imported into a development environment used by a deep learning algorithm, so that the format and structure of the data are ensured to meet the input requirements of the algorithm. And importing the second cardiovascular surgical data into a development environment used by the deep learning algorithm to ensure that the format and structure of the data meet the input requirements of the algorithm. And performing feature representation learning on the second cardiovascular surgical data through a deep learning model to acquire the spatial and temporal relationship in the data. Thus, high-level semantic information of the data can be captured, and rich feature expression is provided for subsequent visual presentation. Based on the features extracted by the deep learning model, interactive views of cardiovascular surgical data are designed. Various data visualization techniques, such as scatter plots, line graphs, thermodynamic diagrams, timing diagrams, and 3D visualizations, may be considered for exposing the dimensions and associations of data. Interactive functions such as zoom, rotate, filter, and linkage may also be added for flexible data exploration and analysis by the user. And according to the designed interactive view, performing visualization implementation on the second cardiovascular surgery data by using corresponding data visualization tools or programming libraries, such as matplotlib, d3.Js, tableau and the like. Ensuring usability and effect of the view. Through the interactive function, the user can freely operate and explore the view as required. For example, zooming in on a particular area to view details, selecting a particular time period or feature for data filtering, viewing trends in the data in real time, and so forth. The second cardiovascular surgery data is processed by using a deep learning algorithm, and an interactive visual view is designed, so that an intuitive, comprehensive and flexible data presentation mode can be provided.
Step S3: and visually projecting the cardiovascular surgical data interactive view by using a matrix decomposition method to generate a cardiovascular surgical data characteristic matrix projection diagram.
In an embodiment of the invention, the data required for the interactive view of cardiovascular surgical data is converted into a matrix form. In particular, features and samples in the view are transformed into a feature matrix, where each row represents a sample and each column represents a feature. The data required for the interactive view of cardiovascular surgical data is converted into a matrix form. In particular, features and samples in the view are transformed into a feature matrix, where each row represents a sample and each column represents a feature. And projecting the feature matrix by utilizing a low-dimensional subspace obtained by matrix decomposition. This means that the original high-dimensional features are mapped into a lower-dimensional space in order to better visualize the data. And designing and generating a cardiovascular surgery data feature matrix projection graph according to the feature matrix projection result. Visualization techniques such as scatter plots, thermodynamic diagrams, parallel graphs, and the like may be used to demonstrate the distribution of data in a low-dimensional space. The clear and visual projection diagram is ensured, and the structure and the association relation of the data can be accurately transmitted. Interactive functions are added to the generated feature matrix projection graph so that the user can freely explore the data. For example, interactive operations such as adding mouse-over cues, selecting subsets or regions, zooming, rotating, etc., are added so that the user has an in-depth knowledge of the inherent characteristics of the data. Interactive functions are added to the generated feature matrix projection graph so that the user can freely explore the data. For example, interactive operations such as adding mouse-over cues, selecting subsets or regions, zooming, rotating, etc., are added so that the user has an in-depth knowledge of the inherent characteristics of the data.
Step S5: and performing dilation convolution and multi-scale sampling on the interactive view for generating cardiovascular surgery data by using a circular convolution network to generate a cardiovascular surgery convolution characteristic model.
In embodiments of the present invention, the data required for the interactive view of cardiovascular surgical data is prepared and necessary pre-processing tasks, such as data cleansing, normalization, etc., are performed. Ensuring that the data meets the input requirements of the cyclic convolution network. A cyclic convolution network model suitable for processing the cardiovascular surgical data interactive view is selected. Common cyclic convolution networks include long and short term memory networks (LSTM), gated cyclic units (GRU), and the like. And selecting a proper network model according to task requirements and data characteristics. And constructing a network structure according to the selected cyclic convolution network model. Including setting the number of layers of the network, the number of nodes of the hidden layer, the activation function, the loss function, etc. Ensuring that the network is able to effectively extract the convolution characteristics of the cardiovascular surgical data. The dilation convolution operation is introduced in a layer or layers of the cyclic convolution network. The expansion convolution can increase the size of the receptive field, capture wider information context and improve the performance of the network in the characteristic extraction process. To capture feature information of different scales, a multi-scale sampling operation may be introduced in the network. For example, convolution with filters of different sizes in the network, or introduction of a pyramid structure to handle features of different sizes. The cardiovascular surgical convolution feature model is trained using the prepared dataset. According to task demands, a proper optimization algorithm (such as random gradient descent) is selected, reasonable learning rate and batch size are set, and model parameters are iteratively adjusted through a back propagation algorithm, so that the model can be gradually optimized and learn effective convolution characteristic representation. The performance of the trained model is evaluated using the test set. According to the evaluation result, model tuning can be performed, such as network structure adjustment, super parameter adjustment, regularization technology addition, and the like, so that the performance of the model is further improved.
Step S6: symmetrically encrypting the cardiovascular surgery convolution feature model by using a symmetrical encryption algorithm to generate a cardiovascular surgery symmetrical encryption model; and uploading the cardiovascular surgery symmetric encryption model to a cardiovascular surgery data processing service platform by utilizing an HTTPS protocol based on the Internet, so as to realize cardiovascular surgery data processing.
In an embodiment of the invention, the symmetric encryption algorithm uses the same key for encryption and decryption. A powerful symmetric encryption algorithm suitable for protecting the cardiovascular surgical convolution feature model, such as AES (advanced encryption standard), is selected. A key (secret key) is generated using a selected symmetric encryption algorithm. The length and security of the key depend on the algorithm and requirements, and secure random number generation methods are used to generate the key. The cardiovascular surgical convolution feature model is encrypted using the generated key. And taking the convolution characteristic model as input, and performing encryption operation by using a selected symmetric encryption algorithm to generate the cardiovascular surgery symmetric encryption model. And the HTTPS protocol is utilized to ensure the safety of data transmission, and the cardiovascular surgery symmetric encryption model is uploaded to a cardiovascular surgery data processing service platform. And managing and processing cardiovascular surgical data by using the cardiovascular surgical symmetric encryption model on a cardiovascular surgical data processing service platform. The model can be decrypted from the encrypted state to a usable form by a symmetric decryption algorithm, and subsequent data processing operations such as feature extraction, prediction, analysis and the like can be performed.
In the embodiment of the present invention, as described with reference to fig. 2, a detailed implementation step flow diagram of the step S1 is shown, and in one embodiment of the present specification, the detailed implementation step of the step S1 includes:
step S11: shooting a cardiovascular surgery process by using a high-definition camera to obtain a cardiovascular surgery video;
step S12: recording the whole process of the operation process by using a recorder to obtain cardiovascular surgery audio data;
step S13: the method comprises the steps of detecting the vital sign of a patient by using an electrocardiograph to obtain vital sign data and anesthesia detection data of the patient, wherein the vital sign data of the patient comprise body temperature data, heart rate data, blood oxygen saturation data, blood pressure data, brain wave data and electrocardiograph wave data;
step S14: and carrying out laser scanning on the surgical instrument and equipment data by using an X-ray detector to acquire the surgical instrument and equipment data.
According to the invention, the operation process is accurately recorded through the camera, the cardiovascular surgery video can accurately record details such as operation steps of doctors, instrument use and anatomical structure display in the operation process, detailed observation materials are provided for doctors and researchers, and after high-quality cardiovascular surgery video is collected, the cardiovascular surgery video can be used for teaching and training purposes. These videos can be used by doctors to demonstrate best practices, new techniques and surgical strategies, improving the quality of medical education and research. The operation process is completely recorded, and the whole process of recording is carried out through the recorder, so that communication, operation step description, instrument use sounds and the like in the operation process can be captured. This helps to fully record critical information during the procedure and provides detailed information for subsequent analysis and playback. Transmitting operation related information: through audio recordings, critical information such as operational guidance, patient changes, emergency, etc. can be shared between the surgical teams. This helps to promote communication and collaboration between teams, improving surgical safety and efficiency. The heart brain wave instrument is used for detecting the vital sign of the patient, acquiring vital sign data and anesthesia detection data of the patient, and monitoring the vital sign of the patient in real time, and can monitor the vital sign data of the patient in real time, such as heart rate, blood pressure, blood oxygen saturation and the like. This helps to discover the physiological changes of the patient in time, guiding the doctor to perform the corresponding treatments and interventions. The anesthetic effect and the patient state are evaluated, and the anesthetic detection data can provide information about the anesthetic depth and physiological response of the patient, so that an anesthesiologist can evaluate the anesthetic effect, and the patient can be ensured to be in a safe and stable state during operation. The device is beneficial to doctors to accurately track the position of the instrument in the patient, and reduces errors and risks in operation. Surgical instrument data may be incorporated into an operating room data processing system for the management and tracking of surgical instruments. Doctors and operating room staff can check the use condition, disinfection condition, storage position and the like of the instruments in real time through the system, so that the efficiency and safety in the operation process are improved. By implementing these steps, the cardiovascular surgery data processing system can provide accurate, complete, real-time cardiovascular surgery related data, provide important information support for doctors and researchers, and provide beneficial effects on monitoring, analysis and decision making of surgical procedures.
In the embodiment of the invention, a high-quality high-definition camera is selected, so that clear video images can be captured. A professional medical imaging apparatus or a high-resolution camera may be considered. The camera is mounted in a proper position so as to cover the whole operation area. Ensure that the camera position is stable and the angle is suitable. By connecting the camera to a video recording device or computer and starting recording software or an application. Suitable recording parameters such as resolution, frame rate and storage format are set. A cardiovascular surgical procedure is started. The camera is ensured to capture key operation steps and scenes, and stable shooting quality is maintained. After the cardiovascular surgery is finished, stopping recording and storing the video file. Ensuring that the saved files have sufficient storage space and readability of the file format. During cardiovascular surgery, recording begins and ensures that the recorder is able to capture sound throughout the procedure. The microphone is placed in the proper position to obtain clear audio. And stopping recording after the operation is finished, and storing a recording file. Ensuring the compatibility of file formats and the integrity of saved files. The sensor is properly mounted on the patient according to the equipment requirements. The sensor generally relates to a body temperature sensor, a heart rate sensor, a blood oxygen saturation sensor, a blood pressure sensor, a brain wave sensor, an electrocardiograph wave sensor, and the like. And starting the cardio-cerebral wave instrument equipment and ensuring that the connection between the cardio-cerebral wave instrument equipment and a monitoring system is normal. Depending on the equipment requirements, necessary calibration and adjustment are performed to ensure the accuracy of the measurement. The patient's vital sign data and anesthesia detection data are initially monitored. The necessary time stamps and identifications are ensured to be recorded for subsequent analysis and processing. And storing the collected vital sign data and anesthesia detection data of the patient into a safe storage medium or system to ensure the integrity and privacy safety of the data. The surgical instrument device is laser scanned using an X-ray detector. Laser scanning will generate a three-dimensional model or image of the instrument. The laser scanned data is processed and analyzed for each scanned surgical instrument device. Image processing algorithms and software can be applied to extract useful information as desired.
In the embodiment of the present invention, as described with reference to fig. 3, a detailed implementation step flow diagram of step S2 is shown, and in one embodiment of the present specification, the detailed implementation step of step S2 includes:
step S21: performing feature detection on the first cardiovascular surgery data by using a feature point detection algorithm to generate a cardiovascular surgery data feature code;
step S22: feature extraction is carried out on the feature codes of the cardiovascular surgery data by using a feature engineering method, and the feature data of the cardiovascular surgery data are generated;
step S23: performing cluster analysis on the cardiovascular surgery data characteristic data by using a cluster analysis method to generate a cardiovascular surgery data characteristic data set;
step S24: and carrying out rule screening on the characteristic data set of the cardiovascular surgery data by using a correlation rule analysis method to generate second cardiovascular surgery data.
The invention can identify and mark key characteristic points in cardiovascular surgery video or images, such as vascular structures, lesion areas and the like through a characteristic point detection algorithm. This helps to extract representative feature information, provides a basis for subsequent analysis and identification, and by encoding feature points, complex cardiovascular surgical data can be converted into compact feature codes. The method is helpful for reducing the dimension and redundancy of the data, improving the efficiency of data processing and storage, and extracting the most representative and distinguishing features from a large amount of feature data by a feature engineering method. This helps to further compress the dimensions of the data and extract feature information that is significant to cardiovascular surgical tasks. The data can be optimized and processed in the feature extraction process, so that noise and redundant information are removed, and the reliability and the interpretability of the data are enhanced. The cluster analysis groups similar cardiovascular surgical data characteristic data into different clusters or categories. This helps to discover potential data patterns, structures, and associations, providing basis for subsequent data analysis and classification. Cluster analysis can separate data into groups with similar characteristics to better understand different types of cardiovascular surgical conditions and provide support and reference for doctors and researchers. Through association rule analysis, the association and the correlation between the characteristic data of the cardiovascular surgical data can be found, and the frequently-occurring modes and rules can be found. This helps to mine knowledge and information hidden behind the data. The association rule analysis may generate rules with accuracy for screening and predicting specific attributes or behaviors of cardiovascular surgical data. This helps to provide decision support and predict the risk of disease for the patient. Through the implementation of these steps, feature detection, encoding, extraction, cluster analysis and rule screening can be performed on the cardiovascular surgical data to obtain more accurate, comprehensive and useful second cardiovascular surgical data. These data can provide a physician with more insight and judgment to help improve patient treatment regimens and prognosis.
In the embodiment of the invention, a selected feature point detection algorithm is applied to the first cardiovascular surgery data, the position and other attribute information of the feature points are extracted, the position and the attribute of the feature points are converted into feature codes, and a descriptor extraction algorithm (such as SIFT or SURF) can be used for generating feature vectors or local feature descriptors (such as HOG, LBP and the like) can be used. The feature codes of the cardiovascular surgical data are selected by proper feature engineering methods, such as Principal Component Analysis (PCA), linear Discriminant Analysis (LDA), feature selection algorithms (such as variance-based, mutual information, recursive feature elimination, etc.), feature transformations (such as polynomial transformations, box transformations), etc. The selected feature engineering method is applied to process and convert the feature codes of the cardiovascular surgical data to obtain more useful and differentiated feature data. Suitable clustering algorithms, such as K-means clustering, hierarchical clustering, DBSCAN (density-based clustering), are selected to apply the selected clustering algorithm to the cardiovascular surgical data feature data, dividing the data samples into different clusters. The clustering result is evaluated, the quality and the performance of the clustering can be evaluated by using an internal index (such as compactness, separation degree and the like) and an external index (such as a contour coefficient, a Rand index and the like), an association rule mining algorithm (such as an Apriori algorithm, an FP-Growth algorithm and the like) is applied to analyze the characteristic data set of the cardiovascular surgery data, find out a frequent item set and an association rule, an association rule mining algorithm (such as an Apriori algorithm, an FP-Growth algorithm and the like) is applied to analyze the characteristic data set of the cardiovascular surgery data, find out the frequent item set and the association rule, set a proper support degree and a confidence threshold according to application requirements, screen out the association rule meeting requirements, generate second cardiovascular surgery data, and the data contains new rules or data items mined based on the association rule and can be used for further analysis, prediction or decision and the like.
In the embodiment of the present invention, as described with reference to fig. 4, a detailed implementation step flow diagram of step S3 is shown, and in one embodiment of the present invention, the detailed implementation step of step S3 includes:
step S31: performing data preprocessing on the second cardiovascular surgical data to generate a cardiovascular surgical data preprocessing pipeline, wherein the data preprocessing comprises cleaning, integration and standardization;
step S32: performing matrix division on the cardiovascular surgery data preprocessing pipeline by using an adaptive division method to obtain a plurality of cardiovascular surgery data submatrices;
step S33: performing non-negative matrix factorization on the cardiovascular surgical data submatrices by using a matrix factorization method to generate a principal component matrix and a minimum error matrix;
step S34: performing feature extraction according to the principal component matrix and the minimum error matrix to generate a cardiovascular surgery feature weight matrix;
step S35: and performing visual projection on the cardiovascular surgery feature weight matrix by using an application visual projection method to generate a cardiovascular surgery feature matrix projection chart.
By data cleaning, the invention can remove errors, deletions or abnormal values in the patient data and improve the quality and accuracy of the data. This helps to avoid producing inaccurate or misleading results in subsequent analyses. Integrating data from different sources can construct a more comprehensive and comprehensive cardiovascular surgical data set. By integrating multiple data sources, more comprehensive and diversified information can be obtained, and the reliability and accuracy of analysis are improved. Cardiovascular surgical data is standardized to have uniform dimensions and dimensions. Normalization may eliminate dimensional differences between different features so that the data is comparable between the different features. This helps to improve the effectiveness of subsequent analysis and modeling. The cardiovascular surgical data preprocessing pipeline may be partitioned into a plurality of sub-matrices using an adaptive partitioning method. Such partitioning can better capture complex associations and patterns in the data, improving the expressive power and presentation effect of the data. The cardiovascular surgical data submatrices are decomposed into a principal component matrix and a minimum error matrix using a matrix decomposition method. The decomposition can extract potential characteristics and important information of the data, reduce the dimension of the data and improve the representation and processing efficiency of the data. Key features of cardiovascular surgical data can be extracted through the principal component matrix and the minimum error matrix. These features may reflect important patterns, structures, and variability in the data, facilitating further analysis and understanding of the data. The generated cardiovascular surgical feature weight matrix may represent the importance and contribution of different features. This helps determine which features are more critical to the cardiovascular surgical task, guiding the subsequent model building and decision making process. The generated cardiovascular surgical feature weight matrix may represent the importance and contribution of different features. This helps determine which features are more critical to the cardiovascular surgical task, guiding the subsequent model building and decision making process. Through implementation of the steps, cardiovascular surgical data can be preprocessed, matrix divided, nonnegative matrix factorized, feature extracted and visually projected, so that a cardiovascular surgical feature matrix projection map with better expressive and explanatory properties is obtained. These images can help doctors and researchers to better understand the data, extract important features about cardiovascular diseases, and support clinical decisions and disease studies.
In the embodiment of the invention, the abnormal value, the missing value, the repeated value, etc. in the second cardiovascular surgery data are checked and processed. The missing values may be filled in or deleted, duplicate values removed, outliers corrected, etc., using suitable techniques or algorithms. If the second cardiovascular data is not consistent from a different source or format, data integration is required to have a consistent data structure and format. Data may be integrated into a consistent data set using techniques such as data conversion, merging, and the like. The second cardiovascular surgical data was normalized to have similar dimensions and ranges. Common normalization methods include mean normalization, maximum minimum normalization, Z-score normalization, and the like. The choice of an appropriate normalization method depends on the nature of the data and the requirements of the analysis. The cardiovascular surgical data preprocessing pipeline is applied to a selected self-adaptive partitioning method to obtain a plurality of cardiovascular surgical data submatrices, and a proper matrix decomposition method such as non-Negative Matrix Factorization (NMF), singular Value Decomposition (SVD) and the like is selected. The nonnegative matrix factorization has better effect in the aspect of processing nonnegative data, a selected matrix factorization method is applied to the cardiovascular surgery data submatrix to obtain a principal component matrix and a minimum error matrix, the principal component matrix is analyzed to extract principal components with high weight, the principal components represent the most representative and critical characteristics in the data, the minimum error matrix is combined with the extracted principal components to weight the principal components to obtain a cardiovascular surgery characteristic weight matrix, a proper visualization tool or algorithm such as Principal Component Analysis (PCA), a scatter diagram, a thermodynamic diagram and the like is used for visualizing the cardiovascular surgery characteristic weight matrix, and according to the visualization result of the characteristic weight matrix, the similarity and correlation among the characteristics, the important contribution degree of the cardiovascular surgery data and the like can be observed. This will aid in further data analysis and decision making processes.
In one embodiment of the present specification, the specific steps of step S33 are as follows:
step S331: performing non-negative matrix transformation on the cardiovascular surgery data submatrices to generate cardiovascular surgery data non-negative submatrices;
step S332: initializing a matrix of the non-negative submatrix of the cardiovascular surgical data by using a matrix decomposition method to generate an original data submatrix;
step S333: and carrying out non-negative matrix factorization on the original data submatrices to generate a principal component matrix and a minimum error matrix.
The invention performs non-negative matrix transformation on the cardiovascular surgical data submatrices, and all elements are non-negative numbers. Such a conversion can better accommodate the characteristics of non-negative data, and can better extract and represent positive-valued correlation features in the data. Initializing a non-negative submatrix of cardiovascular surgical data by a matrix decomposition method to obtain an original data submatrix. In the initialization process, a proper initial value can be selected by using methods such as priori knowledge, an optimization algorithm and the like so as to better capture the mode and the associated information in the data. The original data submatrices are decomposed into a principal component matrix and a minimum error matrix by performing non-negative matrix decomposition on the original data submatrices. Non-negative matrix factorization represents data as non-negative combinations that help extract potential topic, pattern, and structural information. The principal component matrix contains key features and important components of the original data submatrices. The most representative features in the data can be known through the principal component matrix, which is helpful for understanding and explaining the data. The minimum error matrix represents the reconstruction error of the non-negative matrix factorization, i.e., the difference between the product of the original data submatrices and the principal component matrix. Minimizing the minimum error matrix may improve the accuracy and interpretability of the decomposition. The non-negative matrix transformation, matrix initialization and non-negative matrix factorization may be performed on the sub-matrices of cardiovascular surgical data to obtain non-negative sub-matrices, raw data sub-matrices, principal component matrices and minimum error matrices of the cardiovascular surgical data. The results can extract key characteristics, modes and structural information in the data, provide important basis for subsequent analysis and application, and can be used for tasks such as characteristic selection, data compression, mode identification and the like.
In an embodiment of the invention, a non-negative matrix transformation is applied to the cardiovascular surgical data submatrices. Non-negative matrix transformation is an operation of replacing negative or zero elements in a matrix with a non-negative number, during which different methods may be used, such as replacing the negative element with zero, or taking an absolute value for each element, etc., to ensure that the elements in the matrix are all non-negative, matrix initializing the non-negative sub-matrix of cardiovascular surgical data using a selected matrix decomposition method, such as non-negative matrix decomposition (NMF) or other suitable method, during which the non-negative sub-matrix is initialized with an initial value or algorithm to begin the matrix decomposition process, and decomposing the original data sub-matrix into two non-negative matrices using the non-negative matrix decomposition: a principal component matrix and a minimum error matrix, the principal component matrix comprising column vectors representing principal patterns or features in the data. The minimum error matrix represents the error or approximate residual error in the decomposition process, and the principal component matrix and the minimum error matrix are generated for further analysis and application through the preprocessing and feature extraction of the cardiovascular surgery data submatrices.
In one embodiment of the present specification, the specific step of step S4 is:
step S41: performing feature data dimension reduction on the cardiovascular surgery feature matrix projection graph by using an independent component analysis method to generate cardiovascular surgery feature vector data;
step S42: performing data visualization processing on the cardiovascular surgery feature vector data by using a deep learning algorithm to generate a cardiovascular surgery feature visualization view;
step S43: and carrying out interactive processing on the visual view of the cardiovascular surgical feature by using a JavaScript library to generate an interactive view of the cardiovascular surgical feature.
The invention reduces the dimension of the cardiovascular surgery feature matrix projection graph by an Independent Component Analysis (ICA) method. The ICA can extract independent feature vectors in the data, so that each feature vector has the maximum mutual independence, redundant information among the features is reduced, and the purpose of data dimension reduction is realized. The cardiovascular surgical feature vector data is converted into a visual representation using a deep learning algorithm, for example, using an automatic encoder or a method of generating an countermeasure network. This allows mapping of high-dimensional feature data into low-dimensional space and maintaining important features in the data for better understanding and presentation of the information of the data. After processing by the deep learning algorithm, the resulting visual view of the cardiovascular surgical features may show the relationship and distribution between the features in an image, chart, or other intuitive form. Such visualization results help discover patterns, trends, and anomalies in the data, and may provide a more intuitive understanding of the data. After processing by the deep learning algorithm, the resulting visual view of the cardiovascular surgical features may show the relationship and distribution between the features in an image, chart, or other intuitive form. Such visualization results help discover patterns, trends, and anomalies in the data, and may provide a more intuitive understanding of the data. After processing by the deep learning algorithm, the resulting visual view of the cardiovascular surgical features may show the relationship and distribution between the features in an image, chart, or other intuitive form. Such visualization results help discover patterns, trends, and anomalies in the data, and may provide a more intuitive understanding of the data. Through the steps, after the processing through the deep learning algorithm, the generated visual view of the cardiovascular surgical features can show the relationship and distribution among the features in the form of images, charts or other visual forms. Such visualization results help discover patterns, trends, and anomalies in the data, and may provide a more intuitive understanding of the data.
In the embodiment of the invention, cardiovascular surgery feature matrix projection graph data are prepared, the matrix comprises projection values of different cardiovascular surgery features, an independent component analysis (Independent Component Analysis, ICA) method is applied to carry out data dimension reduction on the feature matrix projection graph, ICA is a classical blind signal processing method, observation data can be decomposed into statistically independent signal sources, a deep learning algorithm, such as an automatic encoder (Autoencoder) or a variation self-encoder (Variational Autoencoder), the cardiovascular surgery feature vector data are subjected to data visualization processing, the automatic encoder is an unsupervised learning algorithm, compressed representation of the data can be learned, a hidden layer is constructed between the encoder and the decoder to extract the features, the cardiovascular surgery feature vector data are mapped to a low-dimensional space through a training deep learning model, and a feature visualization view is generated so as to better understand and analyze the data, a cardiovascular surgery feature visualization database (such as D3.js, plly.js or Chart.js) is used for loading data and graphic components of the surgical feature visualization view, the cardiovascular surgery feature vector data is integrated with a dynamic interaction effect, and the interaction effect is realized, such as a dynamic interaction effect is realized, and a visual interaction effect is enlarged, and a visual interaction effect is realized by a user interaction method is realized, and an interaction effect is realized by a visual interaction method, and a visual interaction method is realized.
In one embodiment of the present specification, the specific steps of step S5 are as follows:
step S51: performing convolution preprocessing on the cardiovascular surgical feature interactive view by using a cyclic convolution network to generate a cardiovascular surgical feature sample set;
step S52: performing convolution data cutting on the cardiovascular surgery feature sample set by using a super-pixel algorithm to generate a cardiovascular surgery sample low-dimensional convolution feature sequence;
step S53: performing edge feature reinforcement processing on the cardiovascular surgery sample low-dimensional convolution feature sequence by using an expansion convolution algorithm to generate a cardiovascular surgery feature network;
step S54: performing spatial pyramid pooling multi-layer sampling on the cardiovascular surgery feature network by using a multi-scale sampling algorithm to generate a cardiovascular surgery feature map;
step S55: performing data mining algorithm modeling based on association rules on the cardiovascular surgery feature map by utilizing a combined classifier weighted comprehensive calculation formula based on a combined classifier algorithm to generate a cardiovascular surgery convolution feature model;
the invention carries out convolution pretreatment on the cardiovascular surgery feature interactable view through the cyclic convolution network, the cyclic convolution network carries out convolution pretreatment on the cardiovascular surgery feature interactable view, and the cyclic convolution network can be utilized to extract useful features from the cardiovascular surgery feature interactable view, thereby helping to distinguish different cardiovascular surgery features. By convolution preprocessing, the dimensionality of the data can be reduced, and the efficiency of the subsequent processing steps is improved. By convolution preprocessing, the dimensionality of the data can be reduced, and the efficiency of the subsequent processing steps is improved. By convolving the cardiovascular surgical feature sample set with a convolution data cut, it can be divided into smaller regions, each region having similar features. The resulting low-dimensional convolution signature sequence of cardiovascular surgical samples will be used for the next step of processing. The super-pixel algorithm divides the cardiovascular surgical feature sample set into regions with similar features, facilitating independent processing of each region in subsequent steps. By dividing regions of similar features into the same low-dimensional convolution feature sequence, similar features can be aggregated, improving understanding and analysis capabilities of cardiovascular surgical samples. The dilation convolution algorithm can enhance edge features in the cardiovascular surgical sample low-dimensional convolution feature sequence to make the edge features clearer and more remarkable. The edge characteristics in the cardiovascular surgical sample low-dimensional convolution characteristic sequence can be enhanced by the expansion convolution algorithm, so that the cardiovascular surgical sample low-dimensional convolution characteristic sequence is clearer and more remarkable, and abstract characteristic representations of different levels can be learned by the expansion convolution algorithm through applying convolution kernels of different scales to the characteristic sequence. Through the multi-layer sampling of the space pyramid pooling, the features with different scales can be fused, and the global understanding capability of the cardiovascular surgical features is improved. The combined classifier algorithm can integrate the prediction results of a plurality of classifiers, and improves the accuracy and the robustness of classification. The association rule-based data mining algorithm can find the association relation between different cardiovascular surgical features, and helps understand and explain the prediction result of the model. The generated cardiovascular surgery convolution feature model can be applied to prediction and classification tasks of cardiovascular surgery and helps medical diagnosis and treatment decision.
In the embodiment of the invention, a cyclic convolution network (Recurrent Convolutional Network, RCN) is used for carrying out convolution pretreatment on video data, the cyclic convolution network combines the characteristics of the convolution neural network and the cyclic neural network, data with a time sequence relationship can be processed, spatial characteristics are reserved, the view data is input into the cyclic convolution network, characteristic representations in the view are extracted and learned, a cardiovascular surgery characteristic sample set is generated, the cardiovascular surgery characteristic sample set is subjected to super-pixel segmentation, the cardiovascular surgery characteristic sample set is divided into continuous areas with similar characteristics, an original data set is cut into a group of interconnected areas by a super-pixel algorithm, each area is called a super-pixel, convolution operation is applied to each super-pixel, a low-dimensional convolution characteristic sequence is extracted, the low-dimensional convolution characteristic sequence is characteristic representation of the super-pixel area, the dimension of the data is reduced, spatial information of the area is reserved, an expansion convolution (Dilated Convolution) algorithm is used for carrying out edge characteristic reinforcement treatment on the low-dimensional convolution characteristic sequence, the expansion convolution operation can sense a wider local area by introducing a cavity (direction) into a convolution kernel, the edge characteristic reinforcement operation can sense the local area, the edge characteristic sample can capture the characteristic of the cardiovascular surgery characteristic sequence in a multi-dimensional area under the condition that the multi-dimensional characteristic sample pool is better, the characteristic of the surgical area can be sampled under the condition that the characteristic of the multi-dimensional feature is sampled by the multi-dimensional feature of the multi-dimensional feature network, after the characteristic is better sampled by the multi-dimensional feature of the algorithm, the method comprises the steps of dividing a feature map into areas with different scales by using spatial pyramid pooling, pooling each area to obtain feature representation with fixed length, dividing the feature map into the areas with different scales by using the spatial pyramid pooling, pooling each area to obtain feature representation with fixed length, integrating results of different classifiers by using a combined classifier, improving prediction accuracy and robustness, weighting and combining the results of the combined classifier by using a weighted comprehensive calculation formula, finding out associated modes and rules from a cardiovascular surgery feature map by using data mining algorithm modeling based on association rules, and using the associated modes and rules for prediction and decision to finally generate a cardiovascular surgery convolution feature model, and classifying and predicting new data.
In one embodiment of the present disclosure, the combined classifier weighted synthesis calculation formula in step S55 is specifically:
；
wherein ,for combining classifier weight coefficients, +.>Is->Personal classifier, < >>For the number of basis classifiers, +.>Is->Weights of the individual basis classifier in the combined classifier,/->Is->Predictive value of weight by the individual basis classifier, < +.>Is the delivery ofSample values into the initial basis classifier, +.>Sum of predicted results for the result values for the basis classifier,/->Is->Predictive outcome of the outcome value by the personal classifier, < >>Is->Accuracy of the prediction of the radix classifier, +.>For the number of classification results, +.>Is->The personal classifier pair->Weights of the individual basis classifier, +.>Is->Classifying results of the individual basis classifier on the sample, < >>For sample->In->The value of the individual basis classifier.
The invention is realized byRepresenting the sum of the base classifier weight coefficients multiplied by the predicted value of each base classifier pair weight. By weighted summing the predicted values of the individual base classifiers, the degree of contribution of each base classifier to the final combined classifier can be captured. This is beneficial for taking into account the predictive power of the different base classifiers in combination. By passing throughRepresenting the product of the base classifier's predicted outcome and the number of classified outcomes for the outcome value multiplied by and square root divided. It may consider a balanced relationship between the number of classification results and the predicted results of the base classifier on the result values. This is beneficial in adjusting the final weight according to the number of classification results and the predictive accuracy of each classification result. By means of The Sigmoid function maps the predicted values of the base classifier weights, converting the predicted values into probability values ranging from 0 to 1. This is beneficial to normalize the predictors so that they can represent the degree of weight impact of the individual basis classifiers and can be interpreted and understood by means of probability values. By->Representing the classification result of the base classifier on the samples multiplied by the weights between the base classifiers. This may allow for further adjustment of the final weights taking into account interactions and dependencies between different base classifiers. The formula calculates and adjusts the weight coefficient of the combined classifier by comprehensively considering the factors such as weight prediction, result prediction, accuracy, quantity and sample classification result of the base classifier. This is beneficial to more fully evaluating the contribution of the base classifier, balancing the different factors, and further improving the performance and accuracy of the combined classifier.
In one embodiment of the present specification, the specific steps of step S54 are as follows:
step S541: performing spatial pyramid pooling multi-layer sampling on the cardiovascular surgery feature network by using a multi-scale sampling algorithm to generate cardiovascular surgery convolution feature data;
step S542: performing convolution feature mapping on the cardiovascular surgery convolution feature data to generate a cardiovascular surgery convolution feature vector;
Step S543: vector stitching is carried out by using the cardiovascular surgery convolution feature vector, and a cardiovascular surgery feature map is generated.
The invention can sample the cardiovascular surgical images on different scales through the multi-scale sampling algorithm, thereby realizing multi-scale feature extraction. Features at different scales may capture different details and structural information of the image, providing a more comprehensive representation of the features. Spatial pyramid pooling is a method of maintaining spatial structure information. By performing pooling operations on different scales, different portions of the image can be aggregated and their relative positional relationship preserved. This helps the network to better understand the spatial structure in the image and improves the perceptibility of cardiovascular surgical features. Spatial pyramid pooling is a method of maintaining spatial structure information. By performing pooling operations on different scales, different portions of the image can be aggregated and their relative positional relationship preserved. This helps the network to better understand the spatial structure in the image and improves the perceptibility of cardiovascular surgical features. The convolution feature map converts the cardiovascular surgical convolution feature data into a higher-level feature representation. Through convolution operation, the network can extract local features in the input data and perform advanced feature combination. This helps to improve the expressive power and distinguishability of features, providing more meaningful feature vectors for subsequent analysis tasks. Vector stitching using the cardiovascular surgical convolution feature vectors may generate a cardiovascular surgical feature map. By combining a plurality of feature vectors, more comprehensive feature information can be obtained. This helps to increase the diversity and richness of features and provides a more powerful input for further image analysis and processing.
In the embodiment of the invention, a multi-scale sampling algorithm is utilized for sampling operation. The algorithm can sample the characteristic under different scales, capture the characteristic information in different receptive fields, carry on space pyramid pooling multilayer sampling to the cardiovascular surgery characteristic network, divide the characteristic map into a plurality of areas of different scales, and carry on pooling operation to each area, extract the characteristic descriptor of fixed length, the multiscale sampling operation can capture the characteristic information of different levels effectively, improve the perception ability of the model to the cardiovascular surgery structure, finally obtain the cardiovascular surgery convolution characteristic data, contain the characteristic descriptor under a plurality of scales, input the convolution characteristic data into the convolution layer to carry on convolution operation, the convolution operation moves on the characteristic map through the way of sliding window, carry on convolution calculation, extract the local characteristic in the characteristic map, after these local characteristics are through activating function, pooling operation, can obtain convolution characteristic map, characteristic vector used for representing the cardiovascular surgery structure, finally produce the cardiovascular surgery convolution characteristic vector, arrange the characteristic value in order of each characteristic map and combine into a vector, splice different characteristic vectors according to certain order, form a higher dimension characteristic vector, can splice a plurality of characteristic vectors, can be used for the feature vector to be completely, the feature vector is produced after the feature vector is completely, the feature vector is completely can be produced by the feature vector is completely, the feature vector is completely is generated, the feature vector is completely, the feature vector is can be used for the feature is completely, and the feature is completely, the feature is analyzed, and has the feature is completely, and has the feature is used for the feature is completely, and has the feature is the feature.
In one embodiment of the present specification, the specific steps of step S6 are as follows:
step S61: performing data ciphertext conversion on the cardiovascular surgery convolution feature model by using a symmetric encryption algorithm to generate a cardiovascular surgery symmetric data ciphertext;
step S62: symmetrically encrypting the cardiovascular surgery symmetric data ciphertext by using a cardiovascular surgery data symmetric encryption calculation formula to generate a cardiovascular surgery symmetric encryption model;
step S63: performing network scheduling slicing on the cardiovascular surgery symmetric encryption model by using a linear programming method to generate a plurality of cardiovascular surgery symmetric encryption model slices;
step S64: uploading a plurality of cardiovascular surgery symmetric encryption model slices to a cardiovascular surgery data processing service platform by using an HTTPS protocol based on a mobile internet to realize cardiovascular surgery data processing;
the invention can convert the cardiovascular surgery convolution characteristic model into the data ciphertext through the symmetrical encryption algorithm, thereby ensuring the confidentiality of the cardiovascular surgery convolution characteristic model in the transmission and storage processes. Only authorized users with the correct keys can decrypt and restore the data, thereby preventing unauthorized access and information disclosure. By converting the cardiovascular surgery convolution feature model into the data ciphertext, the data security in the transmission process can be ensured. Even in network transmission, an attacker cannot decrypt and acquire the original data even if the data is intercepted. This protects the confidentiality and integrity of the cardiovascular surgical convolution feature model. The symmetric encryption algorithm uses an encryption key to convert data in the encryption process, so that the integrity of the data is ensured. Any tampering with the data ciphertext may result in the decrypted data not matching the original data, thereby providing data integrity protection. Symmetric encryption algorithms use a shared key for encryption and decryption. By verifying that the receiver decrypts with the legitimate key, the authenticity of the data can be ensured, i.e. the data is proven to be indeed from the legitimate sender. The system resources can be reasonably distributed and utilized by the network scheduling slice of the linear programming method. Therefore, the waste and redundancy of resources can be reduced, and the efficiency and performance of the system are improved. The system resources can be reasonably distributed and utilized by the network scheduling slice of the linear programming method. Therefore, the waste and redundancy of resources can be reduced, and the efficiency and performance of the system are improved. The system resources can be reasonably distributed and utilized by the network scheduling slice of the linear programming method. Therefore, the waste and redundancy of resources can be reduced, and the efficiency and performance of the system are improved. Remote cardiovascular surgery data processing can be achieved by uploading cardiovascular surgery symmetric encryption model slices to a data processing service platform. The user can access the data processing service platform through the Internet at any time and any place, and analyze, store and share the cardiovascular surgical data.
In the embodiment of the invention, the weight and the parameter in the cardiovascular surgery convolution characteristic model are converted into the data ciphertext by using a selected symmetric encryption algorithm, the symmetric encryption algorithm uses the same key to encrypt and decrypt, so that only authorized users can decrypt the data, the generated cardiovascular surgery symmetric data ciphertext is obtained, further encryption operation is carried out on the cardiovascular surgery symmetric data ciphertext according to the cardiovascular surgery data and a preset symmetric encryption calculation formula, the cardiovascular surgery data possibly comprises sensitive data such as personal identity information of a patient, medical records and the like, the symmetric encryption calculation formula is defined by combining with specific conditions, the network scheduling slicing is carried out on the cardiovascular surgery symmetric encryption model by using a linear programming method, the network scheduling slicing can segment the large model into a plurality of smaller model segments, the method comprises the steps of processing and transmitting the data in a distributed environment, a linear programming method considers the problems of resource constraint and task optimization, the calculation and transmission efficiency is improved by reasonably dividing model slices, the generated cardiovascular surgery symmetric encryption model slices are transmitted to a cardiovascular surgery data processing service platform in a communication mode of a mobile internet, data transmission is carried out by using an HTTPS (hypertext transfer security protocol) protocol, confidentiality and integrity of the data are ensured, the HTTPS protocol is used for protecting the data from being stolen or tampered in the transmission process by establishing a secure encryption connection, and corresponding data management and analysis can be carried out after the cardiovascular surgery symmetric encryption model slices are uploaded to the cardiovascular surgery data processing service platform so as to support decisions and applications related to cardiovascular surgery.
In one embodiment of the present disclosure, the calculation formula of symmetric encryption of cardiovascular surgical data in step S62 is specifically:
；
wherein ,representing the use of the public key pk for the input data>The encryption result obtained by the symmetric encryption is,ciphertext for data of input model, ++>Encryption key generator for symmetric encryption algorithm, < ->A randomly selected cardinal number for an encryption algorithm, +.>Modulus being a specific power of power, < >>For hash function value->As a function of the hash function of the random number,hash value obtained by inputting a hash function for model plaintext data, < >>To encrypt the first piece of ciphertext taken,constructing a generator of an encryption key for the first section of ciphertext, ">Hash function value with radix for random selection, < +.>Second section of ciphertext taken for encryption, < >>The weight coefficient of the generator for the first section of ciphertext and the second section of ciphertext,the hash function value based on the randomly selected cardinality for the second ciphertext.
The invention is realized byA product of a randomly selected ri power modulus bi and a hash function value h (x) representing the generator gi of the symmetric encryption key. By exponentiating and multiplying these values, the generator of each encryption key and the hash function value can be made to participate in the encryption process in a specific manner. This helps to increase the randomness and security of the encryption. By- >And the generated element weight coefficient between the first section of ciphertext and the second section of ciphertext is represented, and the square root of the randomly selected hash function value with the base is represented. By multiplying and dividing these values, the weights of the different parts can be adjusted to maintain a certain balance. This helps to ensure stability and reliability of the encryption result. By means ofThe second ciphertext is represented based on a randomly selected radix hash function value. By using different cardinalities and random numbers, the randomness of the hash function can be increased, and the protection capability of data is improved. This helps to protect the integrity and security of the ciphertext data.
In one embodiment of the present specification, there is provided an internet-based cardiovascular surgical data processing service platform, including:
the cardiovascular surgery data acquisition module acquires first cardiovascular surgery data; the medical equipment comprises a cardio-cerebral wave instrument and an X-ray detector, and the first cardiovascular surgery data comprise cardiovascular surgery video, cardiovascular surgery audio data, patient vital sign data, anesthesia detection data and surgical instrument data;
the feature extraction module is used for carrying out feature extraction on the first cardiovascular surgery data by using a feature engineering method to generate cardiovascular surgery data feature data; performing rule screening on the user service characteristic data by using an association rule analysis method to generate second cardiovascular surgery data;
The interactive view module is used for performing interactive visual processing on the second cardiovascular surgical data by using a deep learning algorithm to generate a cardiovascular surgical data interactive view;
the matrix projection module is used for carrying out visual projection on the cardiovascular surgery data interactive view by utilizing a matrix decomposition method to generate a cardiovascular surgery data characteristic matrix projection diagram;
the feature model module is used for performing expansion convolution and multi-scale sampling on the interactive view generated by the cardiovascular surgery data by using a circular convolution network to generate a cardiovascular surgery convolution feature model;
the data encryption module is used for symmetrically encrypting the cardiovascular surgery convolution characteristic model by utilizing a symmetrical encryption algorithm to generate a cardiovascular surgery symmetrical encryption model; and uploading the cardiovascular surgery symmetric encryption model to a cardiovascular surgery data processing service platform by utilizing an HTTPS protocol based on the Internet, so as to realize cardiovascular surgery data processing.
The invention establishes the cardiovascular surgery data processing service platform based on the Internet, and performs data acquisition on the whole surgery process by combining medical equipment such as a medical camera, a heart brain wave instrument, an X-ray detector and the like, including surgery video data, surgery audio data, patient vital sign data, anesthesia detection data and surgery instrument data, thereby improving the quality and reliability of the surgery process data, ensuring the accuracy and reliability of the data in the surgery process by comprehensively monitoring the medical equipment during the data acquisition process, providing a solid data basis for subsequent data processing and analysis, optimizing the data processing flow by using technologies such as artificial intelligence, deep learning and the like, automatically eliminating irrelevant data by the system, extracting valuable information, generating a normative and clean data set, greatly reducing the working pressure of doctors and researchers, improving the data processing efficiency, converting the surgery process data into visual interactive views and convolution characteristic model diagrams which are easy to understand and analyze, ensuring that doctors and researchers can grasp key characteristics and change conditions in the surgery process more easily, helping to acquire the diagnosis and treatment data and obtaining statistics and deep understanding of the cardiovascular surgery platform more deeply. Through data analysis, relevant information in aspects of risk factors, etiology, treatment schemes, prognosis and the like of cardiovascular diseases can be explored, and development of medical scientific research and clinical decision can be promoted. The cardiovascular surgery data processing platform adopts a safe encryption and authentication mechanism in the data transmission and storage process, so that the privacy and the data safety of patients are protected. Only authorized users can access and manipulate the sensitive information, ensuring confidentiality and integrity of patient data. Through an automatic and standardized process, the cardiovascular surgery data processing platform can help medical staff to improve working efficiency, reduce manual errors and optimize the working process. For example, automatically generating reports, providing intelligent auxiliary diagnostic tools, reminding tasks and key time points, etc., all help to improve the efficiency of medical and administrative work. The cardiovascular surgery data processing service platform based on the Internet can fully exert technical advantages, realize informatization and intellectualization aiming at the requirements and characteristics of the medical industry, and provide comprehensive and high-quality medical guarantee service for hospitals.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. An internet-based cardiovascular surgery data processing method, which is characterized by comprising the following steps:
step S1: acquiring first cardiovascular surgical data by using an information acquisition system; the first cardiovascular surgical data includes cardiovascular surgical video, cardiovascular surgical audio data, patient vital sign data, anesthesia detection data, and surgical instrument device data;
step S2: performing feature extraction on the first cardiovascular surgery data by using a feature engineering method to generate cardiovascular surgery data feature data; performing rule screening on the user service characteristic data by using an association rule analysis method to generate second cardiovascular surgery data;
step S3: performing interactive visual processing on the second cardiovascular surgical data by using a deep learning algorithm to generate a cardiovascular surgical data interactive view;
step S3: visual projection is carried out on the cardiovascular surgery data interactive view by utilizing a matrix decomposition method, and a cardiovascular surgery data feature matrix projection diagram is generated;
step S5: performing expansion convolution and multi-scale sampling on the interactive view for generating cardiovascular surgery data by using a cyclic convolution network to generate a cardiovascular surgery convolution characteristic model;
step S6: symmetrically encrypting the cardiovascular surgery convolution feature model by using a symmetrical encryption algorithm to generate a cardiovascular surgery symmetrical encryption model; and uploading the cardiovascular surgery symmetric encryption model to a cardiovascular surgery data processing service platform by utilizing an HTTPS protocol based on the Internet, so as to realize cardiovascular surgery data processing.
2. The method according to claim 1, wherein the information acquisition system comprises a high-definition camera, a recorder, an electrocardiograph and an X-ray detector, and the specific steps of step S1 are as follows:
step S11: shooting a cardiovascular surgery process by using a high-definition camera to obtain a cardiovascular surgery video;
step S12: recording the whole process of the operation process by using a recorder to obtain cardiovascular surgery audio data;
step S13: the method comprises the steps of detecting the vital sign of a patient by using an electrocardiograph to obtain vital sign data and anesthesia detection data of the patient, wherein the vital sign data of the patient comprise body temperature data, heart rate data, blood oxygen saturation data, blood pressure data, brain wave data and electrocardiograph wave data;
step S14: and carrying out laser scanning on the surgical instrument and equipment data by using an X-ray detector to acquire the surgical instrument and equipment data.
3. The method according to claim 2, wherein the specific steps of step S2 are:
step S21: performing feature detection on the first cardiovascular surgery data by using a feature point detection algorithm to generate a cardiovascular surgery data feature code;
step S22: feature extraction is carried out on the feature codes of the cardiovascular surgery data by using a feature engineering method, and the feature data of the cardiovascular surgery data are generated;
Step S23: performing cluster analysis on the cardiovascular surgery data characteristic data by using a cluster analysis method to generate a cardiovascular surgery data characteristic data set;
step S24: and carrying out rule screening on the characteristic data set of the cardiovascular surgery data by using a correlation rule analysis method to generate second cardiovascular surgery data.
4. A method according to claim 3, wherein the specific step of step S3 is:
step S31: performing data preprocessing on the second cardiovascular surgical data to generate a cardiovascular surgical data preprocessing pipeline, wherein the data preprocessing comprises cleaning, integration and standardization;
step S32: performing matrix division on the cardiovascular surgery data preprocessing pipeline by using an adaptive division method to obtain a plurality of cardiovascular surgery data submatrices;
step S33: performing non-negative matrix factorization on the cardiovascular surgical data submatrices by using a matrix factorization method to generate a principal component matrix and a minimum error matrix;
step S34: performing feature extraction according to the principal component matrix and the minimum error matrix to generate a cardiovascular surgery feature weight matrix;
step S35: and performing visual projection on the cardiovascular surgery feature weight matrix by using an application visual projection method to generate a cardiovascular surgery feature matrix projection chart.
5. The method according to claim 4, wherein the specific steps of step S33 are:
step S331: performing non-negative matrix transformation on the cardiovascular surgery data submatrices to generate cardiovascular surgery data non-negative submatrices;
step S332: initializing a matrix of the non-negative submatrix of the cardiovascular surgical data by using a matrix decomposition method to generate an original data submatrix;
step S333: and carrying out non-negative matrix factorization on the original data submatrices to generate a principal component matrix and a minimum error matrix.
6. The method according to claim 5, wherein the specific step of step S4 is:
step S41: performing feature data dimension reduction on the cardiovascular surgery feature matrix projection graph by using an independent component analysis method to generate cardiovascular surgery feature vector data;
step S42: performing data visualization processing on the cardiovascular surgery feature vector data by using a deep learning algorithm to generate a cardiovascular surgery feature visualization view;
step S43: and carrying out interactive processing on the visual view of the cardiovascular surgical feature by using a JavaScript library to generate an interactive view of the cardiovascular surgical feature.
7. The method according to claim 6, wherein the specific steps of step S5 are:
Step S51: performing convolution preprocessing on the cardiovascular surgical feature interactive view by using a cyclic convolution network to generate a cardiovascular surgical feature sample set;
step S52: performing convolution data cutting on the cardiovascular surgery feature sample set by using a super-pixel algorithm to generate a cardiovascular surgery sample low-dimensional convolution feature sequence;
step S53: performing edge feature reinforcement processing on the cardiovascular surgery sample low-dimensional convolution feature sequence by using an expansion convolution algorithm to generate a cardiovascular surgery feature network;
step S54: performing spatial pyramid pooling multi-layer sampling on the cardiovascular surgery feature network by using a multi-scale sampling algorithm to generate a cardiovascular surgery feature map;
step S55: performing data mining algorithm modeling based on association rules on the cardiovascular surgery feature map by utilizing a combined classifier weighted comprehensive calculation formula based on a combined classifier algorithm to generate a cardiovascular surgery convolution feature model;
the combined classifier weighting comprehensive calculation formula in step S55 specifically includes:
；
wherein ,for combining classifier weight coefficients, +.>Is->Personal classifier, < >>For the number of basis classifiers, +.>Is->Weights of the individual basis classifier in the combined classifier,/- >Is->Predictive value of weight by the individual basis classifier, < +.>For inputting sample values of the initial basis classifier, < +.>Sum of predicted results for the result values for the basis classifier,/->Is->Predictive outcome of the outcome value by the personal classifier, < >>Is->Accuracy of the prediction of the radix classifier, +.>For the number of classification results, +.>Is->The personal classifier pair->Weights of the individual basis classifier, +.>Is->Classifying results of the individual basis classifier on the sample, < >>For sample->In->The value of the individual basis classifier.
8. The method according to claim 7, wherein the specific steps of step S54 are:
step S541: performing spatial pyramid pooling multi-layer sampling on the cardiovascular surgery feature network by using a multi-scale sampling algorithm to generate cardiovascular surgery convolution feature data;
step S542: performing convolution feature mapping on the cardiovascular surgery convolution feature data to generate a cardiovascular surgery convolution feature vector;
step S543: vector stitching is carried out by using the cardiovascular surgery convolution feature vector, and a cardiovascular surgery feature map is generated.
9. The method according to claim 8, wherein the specific step of step S6 is:
step S61: performing data ciphertext conversion on the cardiovascular surgery convolution feature model by using a symmetric encryption algorithm to generate a cardiovascular surgery symmetric data ciphertext;
Step S62: symmetrically encrypting the cardiovascular surgery symmetric data ciphertext by using a cardiovascular surgery data symmetric encryption calculation formula to generate a cardiovascular surgery symmetric encryption model;
step S63: performing network scheduling slicing on the cardiovascular surgery symmetric encryption model by using a linear programming method to generate a plurality of cardiovascular surgery symmetric encryption model slices;
step S64: uploading a plurality of cardiovascular surgery symmetric encryption model slices to a cardiovascular surgery data processing service platform by using an HTTPS protocol based on a mobile internet to realize cardiovascular surgery data processing;
the calculation formula of the symmetric encryption of the cardiovascular surgical data in step S62 specifically includes:
；
wherein ,representing the use of the public key pk for the input data>Encryption result obtained by symmetric encryption, +.>Ciphertext for data of input model, ++>Encryption key generator for symmetric encryption algorithm, < ->A randomly selected cardinal number for an encryption algorithm, +.>Modulus being a specific power of power, < >>For hash function value->Random number for hash function, < >>Hash value obtained by inputting a hash function for model plaintext data, < >>First section of ciphertext taken for encryption, < >>Constructing a generator of an encryption key for the first section of ciphertext, " >Hash function value with radix for random selection, < +.>Second section of ciphertext taken for encryption, < >>Weight coefficient for generating element of first section ciphertext and second section ciphertext, ++>The hash function value based on the randomly selected cardinality for the second ciphertext.
10. An internet-based cardiovascular surgical data processing service platform, comprising:
the cardiovascular surgery data acquisition module acquires first cardiovascular surgery data; the first cardiovascular surgical data comprises cardiovascular surgical video, cardiovascular surgical audio data, patient vital sign data, anesthesia detection data and surgical instrument data;
the feature extraction module is used for carrying out feature extraction on the first cardiovascular surgery data by using a feature engineering method to generate cardiovascular surgery data feature data; performing rule screening on the user service characteristic data by using an association rule analysis method to generate second cardiovascular surgery data;
the interactive view module is used for performing interactive visual processing on the second cardiovascular surgical data by using a deep learning algorithm to generate a cardiovascular surgical data interactive view;
the matrix projection module is used for carrying out visual projection on the cardiovascular surgery data interactive view by utilizing a matrix decomposition method to generate a cardiovascular surgery data characteristic matrix projection diagram;
The feature model module is used for performing expansion convolution and multi-scale sampling on the interactive view generated by the cardiovascular surgery data by using a circular convolution network to generate a cardiovascular surgery convolution feature model;
the data encryption module is used for symmetrically encrypting the cardiovascular surgery convolution characteristic model by utilizing a symmetrical encryption algorithm to generate a cardiovascular surgery symmetrical encryption model; and uploading the cardiovascular surgery symmetric encryption model to a cardiovascular surgery data processing service platform by utilizing an HTTPS protocol based on the Internet, so as to realize cardiovascular surgery data processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310883664.6A CN116612899B (en) | 2023-07-19 | 2023-07-19 | Cardiovascular surgery data processing method and service platform based on Internet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310883664.6A CN116612899B (en) | 2023-07-19 | 2023-07-19 | Cardiovascular surgery data processing method and service platform based on Internet |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116612899A true CN116612899A (en) | 2023-08-18 |
| CN116612899B CN116612899B (en) | 2023-10-10 |
Family
ID=87685714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310883664.6A Active CN116612899B (en) | 2023-07-19 | 2023-07-19 | Cardiovascular surgery data processing method and service platform based on Internet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116612899B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107981858A (en) * | 2017-11-27 | 2018-05-04 | 乐普（北京）医疗器械股份有限公司 | Electrocardiogram heartbeat automatic recognition classification method based on artificial intelligence |
| CN109377470A (en) * | 2018-03-20 | 2019-02-22 | 任昊星 | A kind of heart disease risk forecasting system |
| CN110633368A (en) * | 2019-09-12 | 2019-12-31 | 淮阴工学院 | Deep learning classification method for early colorectal cancer unstructured data |
| KR102334485B1 (en) * | 2020-08-20 | 2021-12-06 | 이마고웍스 주식회사 | Automated method for aligning 3d dental data and computer readable medium having program for performing the method |
| CN114999638A (en) * | 2022-07-19 | 2022-09-02 | 武汉蓝嵊科技有限公司 | Big data visualization processing method and system for medical diagnosis based on artificial intelligence |
| CN116204927A (en) * | 2023-05-04 | 2023-06-02 | 邹城市人民医院 | Intracardiac sign data processing system and method |
-
2023
- 2023-07-19 CN CN202310883664.6A patent/CN116612899B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107981858A (en) * | 2017-11-27 | 2018-05-04 | 乐普（北京）医疗器械股份有限公司 | Electrocardiogram heartbeat automatic recognition classification method based on artificial intelligence |
| US20200237246A1 (en) * | 2017-11-27 | 2020-07-30 | Lepu Medical Technology (Bejing) Co., Ltd. | Automatic recognition and classification method for electrocardiogram heartbeat based on artificial intelligence |
| CN109377470A (en) * | 2018-03-20 | 2019-02-22 | 任昊星 | A kind of heart disease risk forecasting system |
| CN110633368A (en) * | 2019-09-12 | 2019-12-31 | 淮阴工学院 | Deep learning classification method for early colorectal cancer unstructured data |
| KR102334485B1 (en) * | 2020-08-20 | 2021-12-06 | 이마고웍스 주식회사 | Automated method for aligning 3d dental data and computer readable medium having program for performing the method |
| CN114999638A (en) * | 2022-07-19 | 2022-09-02 | 武汉蓝嵊科技有限公司 | Big data visualization processing method and system for medical diagnosis based on artificial intelligence |
| CN116204927A (en) * | 2023-05-04 | 2023-06-02 | 邹城市人民医院 | Intracardiac sign data processing system and method |
Non-Patent Citations (3)
| Title |
|---|
| SIVARAMAKRISHNAN RAJARAMAN等: "Detection and visualization of abnormality in chest radiographs using modality-specific convolutional neural network ensembles", PEERJ * |
| 张莉萍: "基于因果稳定学习的糖尿病性心血管疾病风险评估", 《医药卫生科技;信息科技》, pages 328 - 329 * |
| 顾大川;郑哲;赵;张恒;饶辰飞;袁靖;高华炜;张士举;侯剑峰;赵艳;张颖;李卫;王杨;: "中国成人心血管外科注册登记数据库的构建", 中国循环杂志, no. 10 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116612899B (en) | 2023-10-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117238458B (en) | Critical care cross-mechanism collaboration platform system based on cloud computing | |
| Qayyum et al. | Secure and robust machine learning for healthcare: A survey | |
| RU2703679C2 (en) | Method and system for supporting medical decision making using mathematical models of presenting patients | |
| US11923070B2 (en) | Automated visual reporting technique for medical imaging processing system | |
| US9529968B2 (en) | System and method of integrating mobile medical data into a database centric analytical process, and clinical workflow | |
| Papastergiou et al. | Tensor Decomposition for Multiple‐Instance Classification of High‐Order Medical Data | |
| Aparna et al. | A blind medical image watermarking for secure e-healthcare application using crypto-watermarking system | |
| CN116825293B (en) | Visual obstetrical image examination processing method | |
| US12063202B2 (en) | Privacy firewalls for identified information detection | |
| CN116825264B (en) | Gynaecology and obstetrics information processing method and system based on Internet | |
| CN116204927A (en) | Intracardiac sign data processing system and method | |
| CN113592769A (en) | Abnormal image detection method, abnormal image model training method, abnormal image detection device, abnormal image model training device and abnormal image model training medium | |
| Dogan et al. | Automated accurate emotion classification using Clefia pattern-based features with EEG signals | |
| CN109817297A (en) | Generation method, device, computer equipment and the computer storage medium of medical report | |
| CN116612899B (en) | Cardiovascular surgery data processing method and service platform based on Internet | |
| US11853455B2 (en) | Access control in privacy firewalls | |
| CN116805536A (en) | Data processing method and system based on tumor case follow-up | |
| Rani et al. | Skin disease diagnosis using vgg19 algorithm and treatment recommendation system | |
| CN113241198B (en) | User data processing method, device, equipment and storage medium | |
| Nagaraj et al. | Design of Intelligent Healthcare Information System Using Data Analytics | |
| US20240020417A1 (en) | Systems and methods for federated feedback and secure multi-model training within a zero-trust environment | |
| Birajdar et al. | Transform domain robust watermarking method using Riesz wavelet transform for medical data security and privacy | |
| Munna | A Novel Image Processing Methodology for X-ray Image Compression and Enhancement | |
| EP3982321A1 (en) | System for processing radiographic images and outputting the result to a user | |
| Nguyen et al. | A Highly Secure and Accurate System for COVID-19 Diagnosis from Chest X-ray Images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |