Key result
UKCRP model outperforms existing clinical scores for predicting 10-year CVD risk with 0.762 AUC.
Why the study?
Previous cardiovascular disease prediction algorithms were largely established using empirical clinical knowledge rather than predictors identified from a comprehensive variable space using machine learning.
Does a machine learning-based risk prediction model improve the prediction of 10-year incident cardiovascular disease compared to existing clinical models in CVD-free adults?
Population
473 611 CVD-free participants aged between 37 and 73 years old from the UK Biobank
Comparison
Novel machine learning risk prediction model vs multiple existing clinical models
Design
Prospective cohort study
Follow-up
Median follow-up of 12.2 years
Authors
Loading...
Should not yet change practice; challenges existing models but leaves generalizability and outcome impact open.
Cohort (n=473,611)
Yes
Does a machine learning-based risk prediction model improve the prediction of 10-year incident cardiovascular disease compared to existing clinical models in CVD-free adults?
Effect estimate: AUC 0.762±0.010
p-value: p=<0.001
A machine learning-based model using 10 predictors (UKCRP) demonstrated superior discriminative performance for 10-year cardiovascular disease risk compared to established clinical models like ASCVD and SCORE.
You et al. (2023) conducted a cohort in Cardiovascular disease (CVD) (n=473,611). UK Biobank CVD risk prediction model (UKCRP) vs. Existing cardiovascular disease prediction models (e.g., QRISK V.3, SCORE V.2, AHA/ASCVD, FGCRS) was evaluated on 10-year risk of incident cardiovascular disease (CVD) (AUC 0.762±0.010, p=<0.001). The UK Biobank CVD risk prediction model (UKCRP) achieved an AUC of 0.762 for predicting 10-year incident cardiovascular disease, outperforming multiple existing models (p<0.001).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: