Key result
Machine learning models outperform traditional Cox models for CVD risk prediction, reaching a 0.80 C-index.
Why the study?
It is unclear whether the predictors of 10-year versus lifetime cardiovascular events are similar when considering lifetime risk alongside 10-year risk for primary prevention.
Do machine learning and deep learning survival models improve 10-year and lifetime cardiovascular disease risk prediction compared to traditional risk models in young adults?
Cohort (n=4,314)
Yes
Do machine learning and deep learning survival models improve 10-year and lifetime cardiovascular disease risk prediction compared to traditional risk models in young adults?
Machine learning models incorporating deep phenotyping, particularly echocardiography and kidney function, significantly improve 10-year cardiovascular risk prediction in young adults compared to traditional risk scores, though traditional factors remain adequate for lifetime risk.
Answers are grounded in this paper and cite their sources.
ML models may enhance 10-year CVD prediction in young adults; hypothesis-generating and should not change practice without prospective validation.
Importance National guidelines for primary prevention suggest consideration of lifetime risk for cardiovascular (CV) disease in addition to 10-year risk, however, it is unclear if the predictors of 10-year vs lifetime (10-26 years) CV events are similar. Objective To use a combination of machine learning methods with deep phenotyping to differentiate 10-year versus lifetime predictors of CV outcomes. Design, Setting, and Participants This retrospective analysis used the prospectively collected data from the CARDIA (Coronary Artery Risk Development in Young Adults) study, a cohort of White and Black participants recruited from four clinical centers in the US. The analysis included 4314 participants, aged 23-35 years who were then followed up over 25 years through August 2018. Main Outcomes and Measures 449 variables collected in 1990-91 from imaging and noninvasive tests, questionnaires, and biomarker panels were included. We used machine learning techniques to identify the top-20 predictors of both 10-year and lifetime (10-26 years) CV events (coronary heart disease, myocardial infarction, acute coronary syndrome, stroke, transient ischemic attack, heart failure, peripheral arterial disease, and CV death). Results Kidney disease, family history of CV disease, and echocardiographic parameters of left ventricular systolic and diastolic dysfunction, and hypertrophy were important markers of 10-year CV events. Traditional risk factors and indices of body size featured heavily as top predictors of lifetime CV risk. Among the different machine learning techniques, Random Survival Forest and Nnet-survival performed the best (C-index of 0.80 for 10-year and 0.72 for lifetime). These models outperformed Cox models including traditional CV risk factors. Conclusions and Relevance Family history of CVD, kidney disease, and subclinical phenotyping of CVD using echocardiography are important for 10-year risk estimation. However, traditional CV risk factors alone may be adequate in estimating lifetime CV risk. K ey P oints Question Do machine learning (ML) and deep learning (DL)-based survival analysis models help differentiate 10-year versus lifetime predictors of cardiovascular (CV) outcomes in young adults? Findings In this retrospective analysis of 4314 participants in the CARDIA study, ML and DL survival analysis improved CVD risk prediction over traditional Cox models and revealed the top 20 predictors among 449 variables. Top 10-year risk predictors include kidney disease, family history of CV disease, and echocardiographic parameters, where as traditional risk factors and indices of body size featured heavily as top predictors of lifetime CV risk. Meaning Family history, kidney disease, and subclinical phenotyping of CVD using echocardiography play a prominent role for 10-year risk estimation, while traditional CV risk factors alone may be adequate in estimating lifetime CV risk in young adults.
No takes yet. Share an insight, caveat, or question.
Ambale‐Venkatesh et al. (2022) conducted a cohort in Cardiovascular disease (n=4,314). Machine learning and deep learning survival models (Random Survival Forest and Nnet-survival) vs. Traditional Cox models and ASCVD risk score was evaluated on C-index for 10-year incident cardiovascular disease prediction. Machine learning models, specifically Random Survival Forest and Nnet-survival, improved 10-year cardiovascular disease risk prediction compared to traditional Cox models.
Synapse has enriched 10 related papers. Consider them for comparative context: