Drug and supplement interactions (DSIs) have drawn widespread attention due to their potential to affect therapeutic response and adverse event risk. Electronic health records provide a valuable source where the signals of DSIs can be identified and characterized. We detected signals of interactions between warfarin and seven dietary supplements, viz., alfalfa, garlic, ginger, ginkgo, ginseng, St. John's Wort, and Vitamin E by analyzing structured clinical data and unstructured clinical notes from the University of Minnesota Clinical Data Repository. A machine learning-based natural language processing module was further developed to classify supplement use status and applied to filter out irrelevant clinical notes. Cox proportional hazards models were fitted, controlling for a set of confounding factors: age, gender, and Charlson Index of Comorbidity. There was a statistically significant association of warfarin concurrently used with supplements which can potentially increase the risk of adverse events, such as gastrointestinal bleeding.
|Original language||English (US)|
|Title of host publication||MEDINFO 2017|
|Subtitle of host publication||Precision Healthcare through Informatics - Proceedings of the 16th World Congress on Medical and Health Informatics|
|Editors||Adi V. Gundlapalli, Jaulent Marie-Christine, Zhao Dongsheng|
|Publisher||IOS Press BV|
|Number of pages||5|
|State||Published - 2017|
|Event||16th World Congress of Medical and Health Informatics: Precision Healthcare through Informatics, MedInfo 2017 - Hangzhou, China|
Duration: Aug 21 2017 → Aug 25 2017
|Name||Studies in Health Technology and Informatics|
|Other||16th World Congress of Medical and Health Informatics: Precision Healthcare through Informatics, MedInfo 2017|
|Period||8/21/17 → 8/25/17|
Bibliographical noteFunding Information:
The project was partly supported by the National Center for Complementary & Integrative Health Award (R01AT009457) (Zhang), the Agency for Healthcare Research & Quality grant (#1R01HS022085-01) (Melton), the University of Minnesota Clinical and Translational Science Award (8UL1TR000114) (Blazer), and the UMN grant-in-aid award (Zhang). The clinical data was provided by the University of Minnesota’s Clinical Translational Science Institute (CTSI) Informatics Consulting Service. The authors thank Fairview Health Services for their data support of this research.
© 2017 International Medical Informatics Association (IMIA) and IOS Press.
- Electronic health records
- Natural language processing