Study using routinely collected electronic medical records (EMRs) from 680 Australian general practices (Lumos programme, linked to hospital and death records) in 850,216 patients aged 30-74 years without prior CVD. Over a mean follow-up of 4.9 years, 33,578 cardiovascular events occurred. Sex-specific Cox models with 28 predictors achieved Harrell's C 0.803 (95% CI 0.801-0.804) in females and 0.772 (95% CI 0.770-0.773) in males; simpler LASSO models with 12-15 predictors performed similarly. Models were well calibrated across age, socioeconomic strata, and smoking status, with consistent discrimination across 10 regional Primary Health Networks. Net reclassification improvement up to 0.185 versus existing AusCVDRisk variables. EMR-based models are suitable for automated integration into primary-care software for real-time CVD risk assessment — an important scalability step for primary prevention.
Recent cardiovascular risk equations from the USA and United Kingdom use routinely collected electronic medical records (EMRs), while current equations used in Australia (AusCVDRisk) have not been validated locally. We assessed the feasibility and performance of using routinely collected EMRs from Australian primary care software systems to predict absolute risk of cardiovascular disease (CVD).
We used primary care EMR data from the New South Wales Health Lumos programme, covering 680 general practices, linked with hospital and death records. Individuals aged 30–74 years on 1 January 2017 with no prior CVD history and at least one record for an anthropometric measurement or pathology test were included. Sex-specific Cox proportional hazards models were used to estimate 5-year risk of a fatal or non-fatal CVD event. Predictors included demographics, smoking, chronic conditions, clinical variables and medications. Modelling used a 5x2 cross-validation approach. Discrimination, calibration and reclassification performance were assessed.
Over a mean follow-up of 4.91 years, 33 578 CVD events were recorded in 850 216 patients. Full models with 28 predictors had Harrell’s C of 0.803 (95% CI 0.801 to 0.804) for females and 0.772 (95% CI 0.770 to 0.773) for males. Least absolute shrinkage and selection operator models with 12–15 predictors performed similarly. Models were well calibrated across age, socioeconomic and smoking strata. Geographic (internal–external) validation across 10 Primary Health Networks confirmed consistent discrimination (C-index range 0.747–0.788 for males; 0.772–0.827 for females). Percentile-based net reclassification improvement showed enhanced event detection compared with a model based on AusCVDRisk variables (event-Net Reclassification Improvement up to 0.185).
CVD risk equations based on routine Australian primary care data performed strongly and generalised well across diverse settings. These models offer potential for automated integration into general practice software to support real-time CVD risk assessment.
