Temporal information extraction from clinical texts
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: http://ohnlp.org/index.php/MedTime_Project_Page
If you use MedTime, please kindly consider citing the following papers:
MedTimer 2.0
MedTime 1.0
A review paper of clinical information extraction in NLP: