Landmark Models for Optimizing the Use of Repeated Measurements of Risk Factors in Electronic Health Records to Predict Future Disease Risk.pdf (341.39 kB)
Download file

Landmark Models for Optimizing the Use of Repeated Measurements of Risk Factors in Electronic Health Records to Predict Future Disease Risk.

Download (341.39 kB)
journal contribution
posted on 17.09.2019, 15:37 by E Paige, J Barrett, D Stevens, RH Keogh, MJ Sweeting, I Nazareth, I Petersen, AM Wood
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).


This work was funded by the Medical Research Council (MRC) (grant MR/K014811/1). J.B. was supported by an MRC fellowship (grant G0902100) and the MRC Unit Program (grant MC_UU_00002/5). R.H.K. was supported by an MRC Methodology Fellowship (grant MR/M014827/1).



American Journal of Epidemiology, 2018, 187 (7), pp. 1530-1538

Author affiliation

/Organisation/COLLEGE OF LIFE SCIENCES/School of Medicine/Department of Health Sciences


VoR (Version of Record)

Published in

American Journal of Epidemiology


Oxford University Press (OUP) for Johns Hopkins University, Bloomberg School of Public Health



Acceptance date


Copyright date


Available date


Publisher version