Abstract
This study presents a web application for predicting cardiovascular disease (CVD) and hypertension (HTN) among mine workers using machine learning (ML) techniques. The dataset, collected from 699 participants at the Gol-Gohar mine in Iran between 2016 and 2020, includes demographic, occupational, lifestyle, and medical information. After preprocessing and feature engineering, the Random Forest algorithm was identified as the best-performing model, achieving 99% accuracy for HTN prediction and 97% for CVD, outperforming other algorithms such as Logistic Regression and Support Vector Machines. These high accuracies are crucial for occupational health management, where early detection of health risks can significantly reduce morbidity and mortality among workers exposed to environmental and occupational hazards. The web application provides personalized risk assessments based on key factors, such as age, employment history, family health background, and exposure to environmental risks like dust and noise. By offering actionable insights, the model enables targeted interventions, including workplace modifications and lifestyle recommendations, to mitigate the risk of CVD and HTN. This tool demonstrates the potential of ML to enhance preventive health strategies in high-risk occupational settings.