Key result
Machine learning achieves ~0.77 AUC for predicting CV events, though Framingham outperforms in Kyrgyz patients.
Why the study?
Traditional cardiovascular risk scales like SCORE and Framingham have statistical drawbacks that may reduce predictive value, prompting evaluation of machine learning technologies.
Do machine learning algorithms improve the prediction of coronary heart disease and acute cerebrovascular accident compared to SCORE and Framingham scales in a prospective cohort?
Cohort (n=2,391)
Yes
Do machine learning algorithms improve the prediction of coronary heart disease and acute cerebrovascular accident compared to SCORE and Framingham scales in a prospective cohort?
Machine learning algorithms generally improved cardiovascular risk prediction compared to traditional scales, though performance varied by specific cohort.
Answers are grounded in this paper and cite their sources.
ML performance varied by cohort and did not consistently surpass traditional scales; hypothesis-generating for validation in diverse populations.
The main ways to assess cardiovascular risk are SCORE, SCORE-2, Framingham scales, etc. However, these scales have several statistical drawbacks that may reduce their predictive value. Therefore, many researchers are encouraged to use machine learning technologies to predict cardiovascular risk. Objective. To compare the predictive value of the SCORE, Framingham and one of the machine learning methods based on the «INTEREPID» study. Material and methods. The study was conducted based on the data from the international prospective study «INTEREPID» conducted in 2011—2016 (n=2391). Endpoints: cases of coronary heart disease and acute cerebrovascular accident for Samara (n=253; 24.1%) and for the Kyrgyz Republic (n=280; 20.9%), total n=533 (22.5%). ExtraTreesClassifier was used as a machine learning algorithm for the Samara cohort, GradientBoostingClassifier for the Kyrgyz cohort and the entire «INTEREPID» cohort. The SCORE and the Framingham scales were used for comparison. Results. For the Samara cohort, the best AUC indicator is ExtraTreesClassifier — 0.609; for the Kyrgyz cohort — Framingham scale with an AUC of 0.828; and for the entire cohort, GradientBoostingClassifier with an AUC of 0.766. Conclusion. The results of this study indicate that the quality of determination by the level of cardiovascular risk is better in most cases when using machine learning algorithms; however, in some cases, conflicting data were obtained. In both cases, attention should be paid to the quality of the sample based on which the mathematical model was built and the validation methods.
No takes yet. Share an insight, caveat, or question.
Mishkin et al. (2024) conducted a cohort in Cardiovascular risk (n=2,391). Machine learning algorithms vs. SCORE and Framingham scales was evaluated on Cases of coronary heart disease and acute cerebrovascular accident. Machine learning algorithms (GradientBoostingClassifier) achieved an AUC of 0.766 for predicting cardiovascular events in the overall cohort, though Framingham performed best in the Kyrgyz cohort.
Synapse has enriched 10 related papers. Consider them for comparative context: