A comprehensive review on heart disease prognostication using different artificial intelligence algorithms

Area of Science:

• Cardiology
• Artificial Intelligence
• Machine Learning
• Deep Learning
• Medical Informatics

Background:

• Timely prediction of heart disease is crucial for life preservation.
• Conventional prediction methods face challenges including high cost, long computation times, and reduced accuracy with large datasets.
• Existing approaches struggle with the complexity of analyzing extensive patient data and risk factors.

Purpose of the Study:

• To review Artificial Intelligence (AI) based algorithms for heart disease prognostication.
• To highlight the benefits of AI in diagnosing cardiac conditions.
• To provide a comparative analysis of AI algorithms' performance in heart disease prediction.

Main Methods:

• Review of existing literature on AI, Machine Learning (ML), and Deep Learning (DL) algorithms for heart disease prediction.
• Comparative analysis of algorithm accuracies and utilization in traditional studies.
• Critical assessment of AI's capacity to learn from massive patient data, including risk factors like age, obesity, and hypertension.

Main Results:

• AI and ML algorithms demonstrate improved accuracy and efficiency in heart disease detection compared to conventional methods.
• AI excels at learning from large datasets, identifying patterns, and analyzing historical data for disease occurrence.
• Significant evolution and continuous exploration of AI techniques are evident in heart disease prediction research.

Conclusions:

• AI-driven approaches offer a promising solution to overcome the limitations of traditional heart disease prediction methods.
• Future research should focus on identifying dimensions with high and low prediction accuracies to guide further investigation.
• AI holds significant potential for advancing cardiac disease diagnosis and improving patient outcomes.