Key result
Random Forest model incorporating treatment exposure predicts incident cardiovascular events with ~0.84 F1 score.
Why the study?
Assessing cardiovascular risk factor influence on cardiovascular events with machine learning offers advantages over preexisting scoring systems and better enables personalized prevention.
Does incorporating treatment adherence improve the prediction of incident cardiovascular events using machine learning algorithms in middle-aged men with cardiovascular risk factors?
Cohort (n=3,746)
No
Does incorporating treatment adherence improve the prediction of incident cardiovascular events using machine learning algorithms in middle-aged men with cardiovascular risk factors?
Effect estimate: F1 score 0.84
Incorporating pharmacological adherence significantly improves the performance of machine learning algorithms for predicting cardiovascular events.
May enhance CVE prediction accuracy when treatment exposure is added to ML models in men; leaves open prospective validation and clinical adoption.
Assessment of the influence of cardiovascular risk factors (CVRF) on cardiovascular event (CVE) using machine learning algorithms offers some advantages over preexisting scoring systems, and better enables personalized medicine approaches to cardiovascular prevention. Using data from four different sources, we evaluated the outcomes of three machine learning algorithms for CVE prediction using different combinations of predictive variables and analysed the influence of different CVRF-related variables on CVE prediction when included in these algorithms. A cohort study based on a male cohort of workers applying populational data was conducted. The population of the study consisted of 3746 males. For descriptive analyses, mean and standard deviation were used for quantitative variables, and percentages for categorical ones. Machine learning algorithms used were XGBoost, Random Forest and Naïve Bayes (NB). They were applied to two groups of variables: i) age, physical status, Hypercholesterolemia (HC), Hypertension, and Diabetes Mellitus (DM) and ii) these variables plus treatment exposure, based on the adherence to the treatment for DM, hypertension and HC. All methods point out to the age as the most influential variable in the incidence of a CVE. When considering treatment exposure, it was more influential than any other CVRF, which changed its influence depending on the model and algorithm applied. According to the performance of the algorithms, the most accurate was Random Forest when treatment exposure was considered (F1 score 0.84), followed by XGBoost. Adherence to treatment showed to be an important variable in the risk of having a CVE. These algorithms could be applied to create models for every population, and they can be used in primary care to manage interventions personalized for every subject.
No takes yet. Share an insight, caveat, or question.
Castel-Feced et al. (2023) conducted a cohort in Cardiovascular risk (n=3,746). Treatment exposure (adherence to therapy for cardiovascular risk factors) vs. Non-exposure/non-adherence to therapy was evaluated on Prediction of incident cardiovascular events using machine learning models (F1 score 0.84). The Random Forest machine learning algorithm that included cardiovascular risk factors and treatment exposure accurately predicted incident cardiovascular events with an F1 score of 0.84, identifying age and treatment exposure as the most influential variables.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: