Identifying Heart Attack Risk in Vulnerable Population: A Machine Learning Approach

TL;DR

This study uses a hybrid machine learning approach on diverse epidemiological data to identify and categorize vulnerable populations at risk of heart attack, especially post-COVID-19, revealing strong associations with key risk factors.

Contribution

It introduces a novel hybrid machine learning method combining demographic, biochemical, ECG, and stress-test data to classify and analyze heart attack risk in vulnerable populations.

Findings

Strong association between 13 risk factors and heart attack likelihood

Postmenopausal women show increased risk due to estrogen depletion

Clustering effectively separates at-risk and not-at-risk groups

Abstract

The COVID-19 pandemic has significantly increased the incidence of post-infection cardiovascular events, particularly myocardial infarction, in individuals over 40. While the underlying mechanisms remain elusive, this study employs a hybrid machine learning approach to analyze epidemiological data in assessing 13 key heart attack risk factors and their susceptibility. Based on a unique dataset that combines demographic, biochemical, ECG, and thallium stress-tests, this study categorizes distinct subpopulations against varying risk profiles and then divides the population into 'at-risk' (AR) and 'not-at-risk' (NAR) groups using clustering algorithms. The study reveals strong association between the likelihood of experiencing a heart attack on the 13 risk factors studied. The aggravated risk for postmenopausal patients indicates compromised individual risk factors due to estrogen depletion that may be, further compromised by extraneous stress impacts, like anxiety and fear, aspects that have traditionally eluded data modeling predictions.