MedTime is an Apache UIMA based temporal information extraction system developed by the Mayo Clinic NLP program. It extracts and normalizes TIMEX3-based temporal expressions from clinical text. MedTime has been adapted from the open-source temporal tagger, HeidelTime (https://github.com/HeidelTime/heideltime) but re-engineered toward the clinical domain.
Updated temporal expression extraction module for general purpose clinical texts, which does not require section times or specific text metadata.
Java requirement: Java 1.7.
If you are using UNIX, simply:
./runCPE.sh
In the menu of the CPE window, go to "File" -> "Open CPE Descriptor" and select ./desc/medtimedesc/collection_process_engine/MedTaggerTimerCPE.xml.
You may change the "Input Directory" and "Output Dir" as needed. We suggest to use the default FileCollectionReader and MedTaggerTimerWriter.
Implementation details can be found in project wiki.
MedTime 1.0: https://ohnlp.org/index.php/MedTime_Project_Page
If you use MedTime, please kindly consider citing the following papers:
MedTimer 2.0
- Liu S et al. Correlating Lab Test Results in Clinical Notes with Structured Lab Data: A Case Study in HbA1c and Glucose. Proc. AMIA Joint Summits on Translational Science, 2017: p221-228.
MedTime 1.0
- Sohn S et al. Comprehensive temporal information detection from clinical text: medical events, time, and TLINK identification. J Am Med Inform Assoc. 2013 Sep 1;20(5):836-42.
A review paper of clinical information extraction in NLP:
- Wang Y et al. Clinical Information Extraction Applications: A Literature Review. Journal of Biomedical Informatics, 2017