Optimised Healthcare Data Classification Using MI-PSO-ANFIS-GA: A Hybrid Machine Learning Approach

View at publisher Summarise with VIRAT
Authors: Tanvir Habib Sardar, Devipriya VS, P. Naresh, Nivetha R, Mubeen Ahmed Khan, Nur Alom Talukdar
Cited by: 0
References: 18

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The exponential growth of healthcare data necessitates advanced machine-learning approaches for accurate and efficient disease classification. Traditional feature selection and classification techniques face difficulty while dealing with high-dimensional medical data, leading to computational inefficiencies and overfitting. This paper introduces MI-PSO-ANFIS-GA, a hybrid framework integrating Mutual Information (MI) and Particle Swarm Optimization (PSO) for optimal feature selection, Adaptive Neuro-Fuzzy Inference System (ANFIS) for classification, and Genetic Algorithm (GA) for hyperparameter optimization. The proposed approach is validated on a 750,000-record cardiovascular disease dataset, demonstrating superior accuracy (97.4 %), precision (96.8 %), recall (98.1 %), and computational efficiency compared to traditional classifiers. Extensive evaluations highlight its robustness, including training ratio performance, loss convergence, and ROC analysis. The results confirm that MI-PSO-ANFIS-GA effectively reduces dimensionality, enhances classification reliability, and optimises computational efficiency, making it a viable solution for real-time healthcare analytics.

Fields of Study & Subjects

Artificial Intelligence in Healthcare Metaheuristic Optimization Algorithms Research Data Mining and Machine Learning Applications

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
848–853
Publication date
21 January 2026
Language
EN