Electronic phenotyping of health outcomes of interest using a linked claims-electronic health record database: Findings from a machine learning pilot project. (13th March 2021)

• Record Type: Journal Article
• Authors: Gibson, Teresa B; Nguyen, Michael D; Burrell, Timothy; Yoon, Frank; Wong, Jenna; Dharmarajan, Sai; Ouellet-Hellstrom, Rita; Hua, Wei; Ma, Yong; Baro, Elande; Bloemers, Sarah; Pack, Cory; Kennedy, Adee; Toh, Sengwee; Ball, Robert
• Is Part Of: Journal of the American Medical Informatics Association. Volume 28:Number 7(2021)
• Page Start: 1507
• Page End: 1517
• Publication Date: 2021-03-13
• Subjects: supervised machine learning -- administrative claims -- healthcare -- electronic health records -- rhabdomyolysis -- electronic phenotyping; Medical informatics -- Periodicals; Information Services -- Periodicals; Medical Informatics -- Periodicals; Médecine -- Informatique -- Périodiques; Informatica; Geneeskunde; Informatique médicale; Computer network resources; Electronic journals; 610.285
• DOI: 10.1093/jamia/ocab036
• Languages: English
• ISSNs: 1067-5027

Abstract

Abstract: Objective: Claims-based algorithms are used in the Food and Drug Administration Sentinel Active Risk Identification and Analysis System to identify occurrences of health outcomes of interest (HOIs) for medical product safety assessment. This project aimed to apply machine learning classification techniques to demonstrate the feasibility of developing a claims-based algorithm to predict an HOI in structured electronic health record (EHR) data. Materials and Methods: We used the 2015-2019 IBM MarketScan Explorys Claims-EMR Data Set, linking administrative claims and EHR data at the patient level. We focused on a single HOI, rhabdomyolysis, defined by EHR laboratory test results. Using claims-based predictors, we applied machine learning techniques to predict the HOI: logistic regression, LASSO (least absolute shrinkage and selection operator), random forests, support vector machines, artificial neural nets, and an ensemble method (Super Learner). Results: The study cohort included 32 956 patients and 39 499 encounters. Model performance (positive predictive value [PPV], sensitivity, specificity, area under the receiver-operating characteristic curve) varied considerably across techniques. The area under the receiver-operating characteristic curve exceeded 0.80 in most model variations. Discussion: For the main Food and Drug Administration use case of assessing risk of rhabdomyolysis after drug use, a model with a high PPV is typically preferred. The Super Learner ensemble model without adjustment for class imbalance achieved a PPV of 75.6%, substantially better than a previously used human expert-developed model (PPV = 44.0%). Conclusions: It is feasible to use machine learning methods to predict an EHR-derived HOI with claims-based predictors. Modeling strategies can be adapted for intended uses, including surveillance, identification of cases for chart review, and outcomes research.