Key result
Machine learning models, particularly L1 logistic regression, predicted incident myocardial infarction better than the Framingham Cox function beyond 1500 days.
Why the study?
How to identify the optimal time horizon for risk prediction using machine-learning approaches is not well known.
Do machine learning models improve the prediction of incident myocardial infarction over varying time horizons compared to the Framingham Cox function in a population free of coronary heart disease?
Cohort (n=4,190)
Do machine learning models improve the prediction of incident myocardial infarction over varying time horizons compared to the Framingham Cox function in a population free of coronary heart disease?
Machine learning models, particularly L1 logistic regression, can predict incident myocardial infarction with reasonable accuracy and outperform the Framingham risk score at moderate follow-up periods.
Answers are grounded in this paper and cite their sources.
May improve long-term MI prediction in CHD-free adults; leaves open prospective validation before clinical use.
BACKGROUND Many machine-learning (ML) approaches are limited to classification of outcomes, rather than longitudinal prediction. One strategy to use ML in clinical risk prediction is to classify outcomes over a given time horizon. However, it is not well-known how to identify the optimal time horizon for risk prediction. OBJECTIVE Here we aim to identify an optimal time horizon for classification of incident myocardial infarction using ML approaches looped over outcomes with increasing time horizons. METHODS We analyzed data from a single clinic visit of 5201 participants of the Cardiovascular Health Study. We examined 61 variables collected from this baseline exam including demographic and biologic data, medical history, medications, serum biomarkers, electrocardiographic, and echocardiographic data. We compared several machine learning methods (Random Forest, L1 Regression, Gradient Boosted Decision Tree, Support Vector Machines, and K-Nearest Neighbor) trained to predict incident MI that occurred within time horizons ranging from 500 through 10000 days of follow up. Models were compared on a 20% held-out testing set using area-under-receiver operator curve (AUC). Variable importance was performed for Random Forest and L1 Regression models across timepoints. We compared results with the Framingham coronary heart disease sex-specific Cox proportional hazards regression functions. RESULTS There were 4190 participants included in the analysis with 60.2% female and an average age of 72.6 years. Over the 10000 days of follow up, there were 813 incident myocardial infarction events. The ML models were most predictive over moderate follow up time horizons (1500-2500 days). Overall, the L1 (Lasso) logistic regression demonstrated the strongest classification accuracy across all time horizons. This model was most predictive at 1500 days follow up with an AUC of 0.71. The most influential variables differed by follow up time and model with gender being the most important feature for the L1 regression and weight for the random forest across all timeframes. Compared with the Framingham Cox function, the L1 and random forest models performed better across all timeframes beyond 1500 days. CONCLUSIONS In a population free of coronary heart disease, machine learning techniques can be utilized to predict incident myocardial infarction at varying time horizons with reasonable accuracy, with strongest prediction accuracy at moderate follow up periods. Validation across additional populations is needed to confirm a role for this approach in risk prediction.
No takes yet. Share an insight, caveat, or question.
Simon et al. (2022) conducted a cohort in incident myocardial infarction (n=4,190). Machine learning models vs. Framingham Cox function was evaluated on incident myocardial infarction (AUC 0.71). Machine learning models, particularly L1 logistic regression, predicted incident myocardial infarction better than the Framingham Cox function beyond 1500 days.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: