Melax Tech released a fully automated Natural Language Processing (NLP) pipeline to extract COVID-19-related sign and symptom mentions from electronic health records (EHRs) notes. The pipeline is built on top of the award-winning CLAMP tool and can be quickly customized on the local dataset for the most optimized performance.
Please read more from this article: https://academic.oup.com/jamia/article/28/6/1275/6155732
The COVID-19 pandemic swept across the world, rapidly infecting millions of people. An efficient tool that can accurately recognize important clinical concepts of COVID-19 from free text in electronic health records (EHRs) will be significantly valuable to accelerate various applications of COVID-19 research. To this end, the existing clinical NLP tool CLAMP is quickly adapted to COVID-19 information. An automated tool called COVID-19 SignSym was built, which can extract signs/symptoms from clinical text and the following eight attributes:
body location
severity
temporal expression
subject
condition
uncertainty
negation
course
The extracted information is also mapped to standard clinical concepts in the common data model of OHDSI OMOP. Evaluations of clinical notes and medical dialogues demonstrate promising results.
This tool is freely accessible to the community as a downloadable package of APIs (https://clamp.uth.edu/covid/nlp.php). Our fully automated NLP pipeline, COVID-19 SignSym, will provide fundamental support to the secondary use of EHRs, thus accelerating the global research of COVID-19.