Ankit,Subham,Anurag,Mayank

PROBLEM:

1)With the growing number of the aged population, the number of Parkinson’s disease (PD) affected people is also mounting. Unfortunately, due to insufficient resources and awareness in underdeveloped countries, proper and timely PD detection is highly challenged. Besides, all PD patients’ voice features are neither the same nor do they all become pronounced at the same stage of the illness. Therefore, our work aims to combine more than one voice feature for detecting PD patients in developing countries. 2)There is no single test which can be administered for diagnosis. Instead, doctors must perform a careful clinical analysis of the patient’s medical history. Unfortunately, this method of diagnosis is highly inaccurate. A National Institute of Neurological Disorders study finds that early diagnosis (having symptoms for 5 years or less) is only 53% accurate. Solution: Because of these difficulties in the traditional method of detecting we came up with an idea or a machine learning approach by creating a web app to accurately diagnose Parkinson’s Our work aims to combine more than one voice feature (17) for detecting the PD patients We have implemented gender-based and age-based analyses

canva link : https://www.canva.com/design/DAFge63NnjI/fBV92lUSQxWror7KGzxCEw/edit?utm_content=DAFge63NnjI&utm_campaign=designshare&utm_medium=link2&utm_source=sharebutton devfolio link: https://devfolio.co/projects/pdetect-9d83

TECHNOLOGIES: Flask React.js xg booster neural networks(rnn) hyper parameter tuning lda css node js knn javascript Figma

Data Analysis in general, the models tended to perform the best (both in terms of accuracy and Matthews Correlation Coefficient) on the rescaled dataset with a 75-25 train-test split. The two highest performing algorithms, xg boost and the Neural Network, both achieved an accuracy of 94%. The NN achieved a MCC of 0.93, while xg boost achieved a MCC of 0.94. These figures outperform most existing literature and significantly outperform current methods of diagnosis.

For using this code :

• One must have a stable Python (version greter than 3.7 and less then 3.10.11) and node.js installed on their system.
• One must clone this repo to their device and then open terminal in the cloned directory.
• run the command npm i to install all the requirements.
• then run few more commansds to install the modules used in the project: npm i -D react-router-dom npm i -D react-router-dom@latest pip install flask pip install librosa

-run the frontend using npm run dev -run the backend using python app.py