Machine-learning versus traditional approaches for atherosclerotic cardiovascular risk prognostication in primary prevention cohorts: a systematic review and meta-analysis
Pooled result · Summary C-statisticResult — go to the resultDifference in C-statistic 0.0139 95% CI 0.0139–0.140Authors' conclusion
ML models outperformed traditional risk scores in the discrimination of CVD risk prognostication.
Study context
- Population
- Adult (≥18 years) primary prevention populations
- Participants
- 3,302 515 participants16 studies
- Comparison
- Machine learning (ML) models vs traditional risk scores for cardiovascular disease (CVD) risk prediction
- Outcome
- Discrimination (C-statistic) for CVD risk prediction
Methodological details11 studies at high risk of bias (PROBAST), 3 of 16 studies externally validated models; 11 reported calibration metrics
- 11 studies at high risk of bias (PROBAST)
- 3 of 16 studies externally validated models; 11 reported calibration metrics
Pooled result
Summary C-statistic
Difference in C-statistic
0.0139
95% CI 0.0139–0.140
P < 0.0001
By group
ML models
0.773
C-statistic · 95% CI 0.740–0.806
Traditional risk scores
0.759
C-statistic · 95% CI 0.726–0.792
As reported in the abstract
Original publication
Machine-learning versus traditional approaches for atherosclerotic cardiovascular risk prognostication in primary prevention cohorts: a systematic review and meta-analysis. Eur Heart J Qual Care Clin Outcomes. Published 3 March 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →