Assessment of a Machine Learning Model Applied to Harmonized Electronic Health Record Data for the Prediction of Incident Atrial Fibrillation

IMPORTANCE: Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, and its early detection could lead to significant improvements in outcomes through the appropriate prescription of anticoagulation medication. Although a variety of methods exist for screening for AF, a targeted approach, which requires an efficient method for identifying patients at risk, would be preferred. OBJECTIVE: To examine machine learning approaches applied to electronic health record data that have been harmonized to the Observational Medical Outcomes Partnership Common Data Model for identifying risk of AF. DESIGN, SETTING, AND PARTICIPANTS: This diagnostic study used data from 2 252 219 individuals cared for in the UCHealth hospital system, which comprises 3 large hospitals in Colorado, from January 1, 2011, to October 1, 2018. Initial analysis was performed in December 2018; follow-up analysis was performed in July 2019. EXPOSURES: All Observational Medical Outcomes Partnership Common Data Model–harmonized electronic health record features, including diagnoses, procedures, medications, age, and sex. MAIN OUTCOMES AND MEASURES: Classification of incident AF in designated 6-month intervals, adjudicated retrospectively, based on area under the receiver operating characteristic curve and F1 statistic. RESULTS: Of 2 252 219 individuals (1 225 533 [54.4%] women; mean [SD] age, 42.9 [22.3] years), 28 036 (1.2%) developed incident AF during a designated 6-month interval. The machine learning model that used the 200 most common electronic health record features, including age and sex, and random oversampling with a single-layer, fully connected neural network provided the optimal prediction of 6-month incident AF, with an area under the receiver operating characteristic curve of 0.800 and an F1 score of 0.110. This model performed only slightly better than a more basic logistic regression model composed of known clinical risk factors for AF, which had an area under the receiver operating characteristic curve of 0.794 and an F1 score of 0.079. CONCLUSIONS AND RELEVANCE: Machine learning approaches to electronic health record data offer a promising method for improving risk prediction for incident AF, but more work is needed to show improvement beyond standard risk factors.