Deep learning models for predicting heart disease risk using the UCI database: methods, performance, and clinical...

Area of Science:

• Cardiology
• Artificial Intelligence
• Machine Learning

Background:

• Heart disease remains a leading cause of mortality worldwide.
• Accurate prediction of heart disease risk is crucial for timely intervention.
• Existing machine learning models have limitations in predicting complex cardiovascular conditions.

Purpose of the Study:

• To develop and evaluate deep learning models for heart disease prediction.
• To compare the performance of deep learning models against classical machine learning approaches.
• To identify key predictors of heart disease using advanced analytical techniques.

Main Methods:

• Utilized the University of California Irvine (UCI) heart disease dataset, comprising 1,025 patients and 14 attributes.
• Applied deep learning models for analyzing patient data and predicting heart disease risk.
• Compared deep learning model performance with established machine learning algorithms.

Main Results:

• Deep learning models achieved high accuracy in predicting heart disease risk.
• The Random Forest model demonstrated a 99% accuracy.
• Key predictors identified include exercise-induced angina, downsloping ST segments, and patient demographics.

Conclusions:

• Deep learning models offer significant potential for enhancing heart disease risk prediction.
• These models can lead to improved diagnostic accuracy and personalized treatment strategies.
• Early detection and intervention facilitated by these models can improve patient outcomes.