Introduction:
CMedTEX is a rule-based temporal expression extraction and normalization system for Chinese electronic medical records, which can identify four types of temporal expressions (Date, Time, Duration and Frequency) and normalize the value to standard format (as TIMEX3). Evaluation on the independent manually annotated Chinese clinical set (include 1,778 records) shows that our system achieves a precision of 90.83%, a recall of 96.11% and an F-score of 93.40% on TE extraction, and an accuracy of 92.58% on TE normalization under exact-match criterion, which are promising.
There is a online demon system of CMedTEX tool at: http://icrc.hitsz.edu.cn:8096/CMedTEX/
References:
[1] Zengjian Liu, Buzhou Tang, Xiaolong Wang, Qingcai Chen. CMedTEX: A Rule-based Temporal Expression Extraction and Normalization System for Chinese Clinical Notes[C]. AMIA 2016 Annual Symposium, 2016.
DownLoad:
Please fill the [Application Form] and send to Zengjian liu (liuzhengjian.hit@gmail.com) or Buzhou Tang (tangbuzhou@gmail.com) to get the source code of CMedTEX.
Usage:
1) Environmental Requirement:
Operating System (Linux or Windows)
Python 2.7.*
2) Show the help infomation.
#python runCMedTEX.py -h
3) Ensure the "resources" directory and "src" are existed.
4) Run CMedTEX must assign a input directory.
#python runCMedTEX.py -i [inputdir]
-- The default output directory is: "CMedTEX/output/",
-- or use '-o' parameter to assign a new output directory.
Contact:
Author: Zengjian Liu, Buzhou Tang
Email: liuzengjian.hit@gmail.com, tangbuzhou@gmail.com
Address: Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, China, 518055.
