Enhanced fuzzy joint mutual information with Cuckoo Search Algorithm and genetic algorithm for diagnostics of chronic kidney disease prediction

2026-07-16 · Source: Machine learning : nature.com subject feeds · Field: Science & Research — Health & Medical Research, Mathematics & Computational Sciences, Artificial Intelligence & Machine Learning · Depth: Expert, quick

Summary

A new Feature Selection Model (FSM), the Enhanced Fuzzy Joint Mutual Information-Cuckoo Search Algorithm-Genetic Algorithm (EFJMI + CSA-GA), has been developed to improve Chronic Kidney Disease (CKD) prediction. This model addresses challenges in high-dimensional healthcare data, such as overfitting from the Curse of Dimensionality and inherent data fuzziness. The EFJMI + CSA-GA integrates fuzzy data processing from EFJMI with Cuckoo Search Algorithm-Genetic Algorithm (CSA-GA) optimization. Applied to the University of California Repository's CKD data, the model successfully minimized the complete feature set by 62%. Experimental results, validated with multiple classification algorithms, demonstrate that the FSM-recommended Recurrent Neural Network (RNN) classifier achieves high performance, including 99.71% Classification Accuracy, 99.81% sensitivity, and 99.58% specificity, outperforming conventional methods in handling complex medical data.

Key takeaway

For Data Scientists developing diagnostic models for complex medical conditions like CKD, you should consider integrating advanced feature selection methods. The EFJMI + CSA-GA approach demonstrates how combining fuzzy data processing with hybrid optimization can drastically reduce feature sets by 62% while achieving 99.71% accuracy. This suggests prioritizing robust feature engineering to overcome the Curse of Dimensionality and improve model reliability in high-dimensional healthcare datasets.

Key insights

The EFJMI + CSA-GA model significantly enhances CKD prediction by optimizing feature selection in fuzzy, high-dimensional healthcare data, achieving high accuracy.

Principles

• High-dimensional data requires robust feature selection.
• Fuzzy logic improves handling of healthcare data uncertainty.
• Hybrid optimization enhances diagnostic model accuracy.

Method

The EFJMI + CSA-GA integrates Enhanced Fuzzy Joint Mutual Information for fuzzy data processing with Cuckoo Search Algorithm-Genetic Algorithm optimization to reduce feature sets and improve classification accuracy for CKD prediction.

In practice

• Apply EFJMI + CSA-GA for medical diagnostics.
• Use RNN classifiers with optimized feature sets.
• Reduce feature dimensions in complex datasets.

Topics

• Chronic Kidney Disease Prediction
• Feature Selection
• Fuzzy Joint Mutual Information
• Cuckoo Search Algorithm
• Genetic Algorithm
• Recurrent Neural Networks

Best for: AI Scientist, Research Scientist, Data Scientist

Related on AIssential

• Soft Computing, Volume 30, Issue 1, January 2026 — This volume showcases diverse applications of soft computing, fuzzy logic, and AI across medical, financial, and logistical domains.
• Multi-population Diversity-guided Genetic Algorithm for Feature Selection in Network Intrusion Detection — MPDGGA improves NIDS feature selection by combining multi-population evolution with diversity-guided operators for better accuracy and feature compactness.
• Angular Gaussian Supervised Contrastive Learning for Long-Tailed Electrocardiogram Arrhythmia Diagnosis — AG-SCL enhances long-tailed ECG diagnosis by combining prior calibration with anisotropic representation learning for rare arrhythmias.
• Beyond Cross-Validation: Adaptive Parameter Selection for Kernel-Based Gradient Descents — This paper proposes a novel Hybrid Selection Strategy (HSS) for Kernel-Based Gradient Descent (KGD) algorithms, which integrates bias-variance analysis with the splitting method for adaptive parameter selection.
• A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction — Reproducible, log-driven AutoML reveals healthcare risk prediction pipeline component importance and search space redundancy.
• Federated learning with swarm intelligence for efficient and secure medical image analysis — Swarm intelligence-enhanced federated learning improves medical image analysis accuracy and efficiency while preserving privacy.

See Counsel's argued verdicts on the open AI decisions leaders are weighing →

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Machine learning : nature.com subject feeds.