Landmark models for optimizing the use of repeated measurements of risk factors in electronic health records to predict future disease risk

Abstract

The benefits of using electronic health records for disease risk screening and personalized heathcare decisions are becoming increasingly recognized. We present a computationally feasible statistical approach to address the methodological challenges in utilizing historical repeat measures of multiple risk factors recorded in electronic health records to systematically identify patients at high risk of future disease. The approach is principally based on a two-stage dynamic landmark model. The first stage estimates current risk factor values from all available historical repeat risk factor measurements by landmark-age-specific multivariate linear mixed-effects models with correlated random-intercepts, which account for sporadically recorded repeat measures, unobserved data and measurements errors. The second stage predicts future disease risk from a sex-stratified Cox proportional hazards model, with estimated current risk factor values from the first stage. Methods are exemplified by developing and validating a dynamic 10-year cardiovascular disease risk prediction model using electronic primary care records for age, diabetes status, hypertension treatment, smoking status, systolic blood pressure, total and high-density lipoprotein cholesterol from 41,373 individuals in 10 primary care practices in England and Wales contributing to The Health Improvement Network (1997-2016). Using cross-validation, the model was well-calibrated (Brier score = 0.041 [95%CI: 0.039, 0.042]) and had good discrimination (C-index = 0.768 [95%CI: 0.759, 0.777]).