An optimal method for diagnosing heart disease using combination of grasshopper evalutionary algorithm and support...

Area of Science:

• Computational intelligence
• Medical informatics
• Cardiovascular disease research

Background:

• Heart disease is a leading cause of mortality globally.
• Accurate and timely diagnosis is crucial for effective heart disease management.
• Existing diagnostic methods require enhancement for improved accuracy and efficiency.

Purpose of the Study:

• To develop and evaluate a novel hybrid data mining approach for enhanced heart disease diagnosis.
• To improve the accuracy and efficiency of early heart disease detection and treatment planning.

Main Methods:

• A three-step data normalization process was employed, including data pre-processing to handle outliers.
• The locust evolutionary algorithm was utilized for optimal feature selection.
• A support vector machine classifier was applied for data set classification.

Main Results:

• The proposed hybrid method demonstrated significant improvements in diagnostic accuracy.
• Accuracy increased by 18% compared to Niobizin methods, 30% versus neural networks, and 24% over J48 trees.
• The method effectively integrated feature selection and classification for robust diagnosis.

Conclusions:

• The hybrid locust evolutionary algorithm and support vector machine approach offers a promising solution for accurate heart disease diagnosis.
• This computational method can aid clinicians in making better decisions for patient care.
• Further research can explore this hybrid model for other complex medical diagnostic challenges.