Cardiac disease risk prediction using machine learning algorithms.

Area of Science:

• Cardiology
• Medical Informatics
• Machine Learning

Background:

• Heart attacks, often caused by coronary disease, are a leading cause of death.
• Early detection and management of heart disease risk are crucial for prevention and reducing healthcare costs.
• Machine learning (ML) is increasingly vital for predicting disease occurrence in healthcare.

Purpose of the Study:

• To develop a predictive system for heart attack risk assessment.
• To analyze diverse data sources, including electronic health records and clinical reports.
• To leverage ML for improved diagnostic capabilities in cardiovascular health.

Main Methods:

• Application of various machine learning algorithms for predictive analysis.
• Comparison of Random Forest, Regression models, K-nearest neighbour imputation (KNN), and Naïve Bayes algorithms.
• Utilizing patient data from electronic health records and clinical diagnosis reports.

Main Results:

• The Random Forest algorithm demonstrated superior performance in forecasting heart attack risk.
• An accuracy of 88.52% was achieved by the Random Forest model.
• Comparative analysis highlighted the effectiveness of Random Forest over other tested ML methods.

Conclusions:

• Machine learning, particularly the Random Forest algorithm, shows significant potential for accurate heart attack risk prediction.
• This approach could revolutionize the diagnosis and treatment of cardiovascular illnesses.
• Early prediction systems can enhance patient outcomes and optimize medical resource allocation.