Web application using machine learning to predict cardiovascular disease and hypertension in mine workers

Area of Science:

• Occupational Health
• Machine Learning Applications
• Cardiovascular Health

Background:

• Mine workers face elevated risks of cardiovascular disease (CVD) and hypertension (HTN) due to occupational and environmental hazards.
• Early detection and intervention are critical for reducing morbidity and mortality in this high-risk population.

Purpose of the Study:

• To develop and validate a machine learning-based web application for predicting CVD and HTN risk in mine workers.
• To provide personalized risk assessments and actionable insights for preventive health strategies.

Main Methods:

• A dataset of 699 mine workers (2016-2020) including demographic, occupational, lifestyle, and medical data was utilized.
• Data preprocessing and feature engineering were performed, followed by model training using algorithms like Random Forest, Logistic Regression, and Support Vector Machines.
• The Random Forest algorithm was selected as the best-performing model.

Main Results:

• The Random Forest model achieved high prediction accuracy: 99% for HTN and 97% for CVD.
• The model identified key risk factors including age, employment history, family health, and exposure to dust and noise.
• The developed web application provides personalized risk scores and intervention recommendations.

Conclusions:

• Machine learning, specifically the Random Forest algorithm, offers a highly accurate tool for predicting CVD and HTN in occupational settings.
• The web application facilitates proactive occupational health management through early risk identification and targeted interventions.
• This approach demonstrates the potential of AI to enhance preventive healthcare for workers exposed to significant environmental and occupational risks.