An Informatics Framework for Discovery and Ascertainment of Drug-Supplement Interactions
The majority (68%) of U.S. adults take dietary supplements and there is increasing evidence of drug-supplement interactions (DSIs); our ability to readily identify interactions between dietary supplements with prescription medications is currently very limited. To optimize the use of dietary supplements, there remains a critical and unmet need for informatics methods to detect DSIs. Our rationale is that an innovative translational informatics framework to discover potential DSIs from biomedical literature with subsequent screening using clinical evidence from electronic health records (EHR) will enable a new line of research for targeted validation of DSIs and investigation of their biological mechanisms.
Goals & Aims
The objective of this application is to develop a translational informatics framework to enable the discovery of DSIs by linking scientific evidence from biomedical literature and clinical evidence from EHR data. Towards these objectives, we propose the following specific aims: (1) Compile a comprehensive terminology of drug supplements from online resources and EHR data; (2) Discover potential DSIs from biomedical literature; and (3) Evaluate potential DSIs using clinical evidence obtained from EHR. The successful accomplishment of this project will deliver a novel informatics paradigm and resources for identifying most clinically significant DSI signals and their biological mechanisms. This information is critical to subsequent efforts aimed at improving patient safety and efficacy of therapeutic interventions. The results from this study are imperative in order to achieve the ultimate goal of reducing an individual’s risk of potential DSIs.
This work is funded by the NIH National Center for Complementary and Integrative Health grant R01AT009457.
Rubina Rizvi, MBBS, PhD
Jake Vasilakes, MS
- Jian Z, Guo X, Lou S, Ma H, Zhang S, Zhang R, Lei J. A Cascaded Approach for Chinese Clinical Text De-Identification with Less Annotation Effort. Journal of Biomedical Informatics, 2017; 73: 76-83.
- Zhang R, Simon G, Yu F. Advancing Alzheimer's Research: A Review of Big Data Promises. International Journal of Medical Informatics. 2017;106:48-56.
- Sun D, Simon G, Skube S, Blaes A, Melton GB, Zhang R, Causal Phenotyping for Susceptibility to Cardiotoxicity from Antineoplastic Breast Cancer Medications. Proceedings of the American Medical Informatics Association Symposium. 2017.
- Zhang R, Pakhomov S, Arsoniadis E, Lee T, Wang Y, Melton G. Detecting clinically relevant new information in clinical notes across specialties and settings, BMC Medical Informatics and Decision Making, 2017 (17) Sp 2:68.
- Fan Y, Adam T, McEwan R, Pakhomov S, Melton G, Zhang R. Detecting Signals of Interactions between Warfarin and Supplements in Electronic Health Records. Stud Health Techno Inform 2017.
- Wang Y, Gunashekar R, Adam T, Zhang R. Mining Adverse Events of Dietary Supplements from Product Labels by Topic Modeling. Stud Health Techno Inform 2017.
- Sun D, Sarda G, Skube S, Blaes A, Khairat S, Melton G, Zhang R. Phenotyping and Visualizing Infustion-related Reactions for Breast Cancer Patients. Stud Health Techno Inform 2017.
The BioMedical Information Collection and Understanding System (BioMedICUS) leverages open source solutions for text analysis and provides new analytic tools for processing and analyzing text of biomedical and clinical reports.