An Enhanced Grey Wolf Optimization Based Feature Selection Wrapped Kernel Extreme Learning Machine for Medical...

Area of Science:

• Computational intelligence
• Medical informatics
• Machine learning for healthcare

Background:

• Accurate medical diagnosis is crucial for effective patient treatment.
• Feature selection is vital for improving the performance of diagnostic models.
• Existing optimization algorithms may not provide optimal feature subsets for complex medical data.

Purpose of the Study:

• To propose a new predictive framework, IGWO-KELM, for enhanced medical diagnosis.
• To develop an improved grey wolf optimization (IGWO) approach for optimal feature selection.
• To evaluate the performance of the proposed IGWO-KELM model against established methods.

Main Methods:

• Integration of improved grey wolf optimization (IGWO) with kernel extreme learning machine (KELM).
• Utilizing genetic algorithm (GA) for initial population diversification in IGWO.
• Applying IGWO for optimal feature subset selection in discrete search spaces for KELM classification.

Main Results:

• The IGWO-KELM framework demonstrated superior performance in medical diagnosis tasks.
• The proposed IGWO feature selection method identified optimal subsets, enhancing classification accuracy.
• Comparative analysis showed the IGWO-KELM approach outperformed original GA and GWO methods across key metrics.

Conclusions:

• The IGWO-KELM framework offers a robust and effective solution for medical diagnosis.
• The novel IGWO feature selection technique significantly improves classification performance.
• This study validates the superiority of the proposed integrated approach for disease diagnosis.