Weakly Supervised Medical Entity Extraction and Linking for Chief Complaints
This addresses the challenge of inconsistent medical notations in chief complaints for healthcare professionals and text mining applications, though it is incremental as it builds on existing BERT-based methods.
The authors tackled the problem of standardizing medical entity extraction and linking from chief complaints without human annotation, achieving superior performance over previous methods using a weakly supervised approach on 1.2 million records.
A Chief complaint (CC) is the reason for the medical visit as stated in the patient's own words. It helps medical professionals to quickly understand a patient's situation, and also serves as a short summary for medical text mining. However, chief complaint records often take a variety of entering methods, resulting in a wide variation of medical notations, which makes it difficult to standardize across different medical institutions for record keeping or text mining. In this study, we propose a weakly supervised method to automatically extract and link entities in chief complaints in the absence of human annotation. We first adopt a split-and-match algorithm to produce weak annotations, including entity mention spans and class labels, on 1.2 million real-world de-identified and IRB approved chief complaint records. Then we train a BERT-based model with generated weak labels to locate entity mentions in chief complaint text and link them to a pre-defined ontology. We conducted extensive experiments, and the results showed that our Weakly Supervised Entity Extraction and Linking (\ours) method produced superior performance over previous methods without any human annotation.