Key result
Dynamic CVD risk prediction using repeat EHR measures yields good discrimination with a C-index of 0.77.
Why the study?
Does a dynamic landmark model using repeated EHR measurements accurately predict 10-year cardiovascular disease risk in primary care patients?
Cohort (n=41,373)
Yes
Does a dynamic landmark model using repeated EHR measurements accurately predict 10-year cardiovascular disease risk in primary care patients?
Effect estimate: C-index 0.768 (95% CI 0.759-0.777)
Absolute Event Rate: 0.768% vs 0.752%
Utilizing historical repeat measures of risk factors in EHRs via dynamic landmark models provides a computationally feasible approach to accurately predict 10-year CVD risk.
May improve primary care CVD risk stratification via routine EHR data; leaves open prospective outcome benefit versus static models.
The benefits of using electronic health records (EHRs) for disease risk screening and personalized health-care decisions are being increasingly recognized. Here we present a computationally feasible statistical approach with which to address the methodological challenges involved in utilizing historical repeat measures of multiple risk factors recorded in EHRs to systematically identify patients at high risk of future disease. The approach is principally based on a 2-stage dynamic landmark model. The first stage estimates current risk factor values from all available historical repeat risk factor measurements via landmark-age-specific multivariate linear mixed-effects models with correlated random intercepts, which account for sporadically recorded repeat measures, unobserved data, and measurement 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. We exemplify these methods by developing and validating a dynamic 10-year cardiovascular disease risk prediction model using primary-care EHRs for age, diabetes status, hypertension treatment, smoking status, systolic blood pressure, total cholesterol, and high-density lipoprotein cholesterol in 41,373 persons from 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% confidence interval: 0.039, 0.042) and had good discrimination (C-index = 0.768, 95% confidence interval: 0.759, 0.777).
No takes yet. Share an insight, caveat, or question.
Paige et al. (2018) conducted a cohort in Cardiovascular disease risk prediction (n=41,373). Dynamic landmark model using repeated EHR measurements vs. Basic landmark-age model was evaluated on Model discrimination (C-index) (C-index 0.768, 95% CI 0.759-0.777). A dynamic 10-year cardiovascular disease risk prediction model using repeated EHR measurements demonstrated good discrimination (C-index 0.768) and calibration (Brier score 0.041).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: