What question did this study set out to answer?

This study aims to enhance cardiovascular mortality risk prediction by integrating air pollution data into machine learning models.

May 25, 2026Open Access

Machine-learning-based cardiovascular mortality prediction using a cumulative PM2.5 exposure metric in high risk groups: a retrospective cohort study

Key Points

This study aims to enhance cardiovascular mortality risk prediction by integrating air pollution data into machine learning models.
Retrospective analysis of 6935 patients with a median observation period of 3140 days.
Integration of the ePM-years Index into mortality risk prediction models using machine learning techniques.
Analysis of 21 classical risk factors related to cardiovascular mortality.
The machine learning model achieved a Matthew's correlation coefficient of 0.657 ± 0.027 after incorporating the ePM-years Index, correctly classifying 92.75% of patients.
Long-term exposure to PM2.5 was associated with a significantly higher cardiovascular mortality risk.
The Area Under the Curve for the machine learning model with the ePM-years Index ranged from 0.88 to 0.91.

Abstract

Classical risk factors for cardiovascular disease (CVD) are well established. Although the association between air pollution (AP) and CVD is also well recognized, its integration into cardiovascular mortality risk prediction models remains limited, particularly in the context of machine learning approaches. We conducted a study within the prospective EP-PARTICLES cohort to quantify the improvement in CVD mortality risk prediction achieved by integrating environmental factors into prediction models using the ‘ePM-years Index’ which reflects the proportion of cumulative long-term PM2.5 exposure exceeding a reference threshold relative to total exposure and advanced machine learning (ML) techniques. The study included 6935 patients (mean age 64.5 ± 10.1 years; 46% women) with a median observation period of 3140 days (IQR 2377–4169 days). We analysed 21 classical risk factors with CV death as the primary endpoint. The ‘ePM-years Index’ was calculated for each patient. The χ2 test and Monte Carlo strategy selected the most discriminating predictors. ML techniques were applied to improve the accuracy of mortality risk predictions and to identify key risk factors. Among the patients, 2646 (38.2%) had prevalent CVD, and 927 (13.4%) died from CVD. Feature selection identified 14/21 (66.7%) most discriminative predictors. The best ML model without the ePM-years Index achieved the Matthews correlation coefficient (MCC) of 0.281 ± 0.021, correctly classifying 72.59% of patients. Adding the ‘ePM-years Index’ improved the ML model’s performance to an MCC of 0.657 ± 0.027, correctly classifying 92.75% of patients. The Area Under the Curve for the ML model exploiting the ‘ePM-years Index’ ranged from 0.88 to 0.91. Long-term exposure to PM2.5 was associated with higher CVD mortality risk in high risk groups. ML incorporating PM2.5 demonstrated greater predictive abilities and clinical utility. Including environmental factors into CVD mortality risk scales improves risk stratification, and ML tools can help build simpler, more clinically useful models. Trial registration The study was registered at ClinicalTrials.gov (NCT05198492).

Demander à l'IA

Bookmark

View Full Paper