Role of Soft Computing Approaches in HealthCare Domain: A Mini Review.

Area of Science:

• Computational Intelligence
• Medical Informatics
• Artificial Intelligence in Healthcare

Background:

• Soft computing approaches offer adaptive and efficient solutions for complex problems.
• Their application in healthcare data analysis provides superior disease diagnosis and prediction compared to traditional methods.
• Key strengths include adaptability and a balanced exploration-exploitation mechanism.

Purpose of the Study:

• To identify soft computing approaches used for disease diagnosis and prediction.
• To determine the range of diseases addressed by these computational methods.
• To categorize soft computing techniques within clinical support systems.

Main Methods:

• Comprehensive literature review of soft computing applications in healthcare over the past decade.
• Categorization of identified techniques into five methodologies: classification model-based, expert, fuzzy and neuro-fuzzy, rule-based, and case-based systems.
• Analysis and summarization of techniques, including author details, methods, diseases targeted, and accuracy rates.

Main Results:

• Numerous soft computing techniques, including particle swarm optimization, genetic algorithms, artificial neural networks, and support vector machines, are widely applied.
• These methods are categorized into five distinct groups based on their underlying methodology.
• Tabular summaries provide detailed information on technique utility and accuracy for various diseases.

Conclusions:

• Soft computing techniques are powerful, reliable, and efficient tools for healthcare data analysis.
• The review provides a structured overview of available methods, aiding in the selection of appropriate techniques for clinical decision support.
• Further research can leverage these categorized insights to advance computational approaches in medical diagnosis and prediction.