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?
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?
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.
Answers are grounded in this paper and cite their sources.
Should not yet change practice; challenges existing models but leaves generalizability and outcome impact open.
Background Previous prediction algorithms for cardiovascular diseases (CVD) were established using risk factors retrieved largely based on empirical clinical knowledge. This study sought to identify predictors among a comprehensive variable space, and then employ machine learning (ML) algorithms to develop a novel CVD risk prediction model. Methods From a longitudinal population-based cohort of UK Biobank, this study included 473 611 CVD-free participants aged between 37 and 73 years old. We implemented an ML-based data-driven pipeline to identify predictors from 645 candidate variables covering a comprehensive range of health-related factors and assessed multiple ML classifiers to establish a risk prediction model on 10-year incident CVD. The model was validated through a leave-one-center-out cross-validation. Results During a median follow-up of 12.2 years, 31 466 participants developed CVD within 10 years after baseline visits. A novel UK Biobank CVD risk prediction (UKCRP) model was established that comprised 10 predictors including age, sex, medication of cholesterol and blood pressure, cholesterol ratio (total/high-density lipoprotein), systolic blood pressure, previous angina or heart disease, number of medications taken, cystatin C, chest pain and pack-years of smoking. Our model obtained satisfied discriminative performance with an area under the receiver operating characteristic curve (AUC) of 0.762±0.010 that outperformed multiple existing clinical models, and it was well-calibrated with a Brier Score of 0.057±0.006. Further, the UKCRP can obtain comparable performance for myocardial infarction (AUC 0.774±0.011) and ischaemic stroke (AUC 0.730±0.020), but inferior performance for haemorrhagic stroke (AUC 0.644±0.026). Conclusion ML-based classification models can learn expressive representations from potential high-risked CVD participants who may benefit from earlier clinical decisions.
No takes yet. Share an insight, caveat, or question.
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.
Synapse has enriched 10 related papers. Consider them for comparative context: