UMMS Affiliation

Department of Population and Quantitative Health Sciences; Department of Medicine

Publication Date


Document Type



Artificial Intelligence and Robotics | Bioinformatics | Databases and Information Systems | Diagnosis | Health Information Technology | Health Services Administration | Health Services Research


OBJECTIVE: Identifying drug discontinuation (DDC) events and understanding their reasons are important for medication management and drug safety surveillance. Structured data resources are often incomplete and lack reason information. In this article, we assessed the ability of natural language processing (NLP) systems to unlock DDC information from clinical narratives automatically.

MATERIALS AND METHODS: We collected 1867 de-identified providers' notes from the University of Massachusetts Medical School hospital electronic health record system. Then 2 human experts chart reviewed those clinical notes to annotate DDC events and their reasons. Using the annotated data, we developed and evaluated NLP systems to automatically identify drug discontinuations and reasons at the sentence level using a novel semantic enrichment-based vector representation (SEVR) method for enhanced feature representation.

RESULTS: Our SEVR-based NLP system achieved the best performance of 0.785 (AUC-ROC) for detecting discontinuation events and 0.745 (AUC-ROC) for identifying reasons when testing this highly imbalanced data, outperforming 2 state-of-the-art non-SEVR-based models. Compared with a rule-based baseline system for discontinuation detection, our system improved the sensitivity significantly (57.75% vs 18.31%, absolute value) while retaining a high specificity of 99.25%, leading to a significant improvement in AUC-ROC by 32.83% (absolute value).

CONCLUSION: Experiments have shown that a high-performance NLP system can be developed to automatically identify DDCs and their reasons from providers' notes. The SEVR model effectively improved the system performance showing better generalization and robustness on unseen test data. Our work is an important step toward identifying reasons for drug discontinuation that will inform drug safety surveillance and pharmacovigilance.


drug surveillance, electronic health records, knowledge representation, natural language processing, supervised machine learning

Rights and Permissions

This work is written by US Government employees and is in the public domain in the US.

DOI of Published Version



J Am Med Inform Assoc. 2019 Apr 29. pii: ocz048. doi: 10.1093/jamia/ocz048. [Epub ahead of print] Link to article on publisher's site

Journal/Book/Conference Title

Journal of the American Medical Informatics Association : JAMIA

PubMed ID


Related Resources

Link to Article in PubMed