Snake-Efficient Feature Selection-Based Framework for Precise Early Detection of Chronic Kidney Disease

Area of Science:

• Nephrology
• Artificial Intelligence
• Bioinformatics

Background:

• Chronic kidney disease (CKD) is a progressive condition requiring early detection for effective management.
• Manual screening for CKD is labor-intensive and prone to subjective errors.
• Machine learning (ML) and feature selection offer automated solutions for early CKD detection.

Purpose of the Study:

• To develop a novel snake-optimized (SO) framework, named CKD-SO, for enhanced CKD data analysis.
• To improve the accuracy and efficiency of early CKD detection systems.
• To leverage natural-inspired algorithms for medical data analysis.

Main Methods:

• The study employed a snake optimization (SO) algorithm for feature selection in CKD datasets.
• Five distinct machine learning algorithms were integrated with the SO algorithm.
• The CKD-SO framework was developed for predicting kidney and liver diseases.

Main Results:

• The developed CKD-SO model achieved a highly accurate prediction rate of 99.7% for CKD detection.
• The SO algorithm effectively identified the most relevant features for disease prediction.
• The study demonstrated the potential of SO in optimizing ML models for medical data.

Conclusions:

• The CKD-SO framework represents a significant advancement in automated CKD detection.
• Early and accurate CKD detection using this method can facilitate timely interventions.
• This approach has the potential to reduce the global burden of CKD-related mortality and morbidity.