Advancements in Hybrid Machine Learning Models for Biomedical Disease Classification

Strategic Insights -

Researchers at the St. Longowal Institute of Engineering & Technology in Punjab, India, have conducted a comprehensive review of hybrid optimization frameworks that combine hyperparameter-tuning and feature selection to enhance machine learning (ML) models for disease classification. The study demonstrated the integration of these processes improves diagnostic accuracy, computational efficiency, and clinical interpretability, achieving 12-15% higher accuracy in classifying cardiovascular, cancer, diabetes, oncological, and metabolic disorders.

Key Takeaways:

  • The study integrated hyperparameter-tuning and feature selection to improve diagnostic accuracy, computational efficiency, and clinical interpretability of ML models for disease classification.
  • The combination of metaheuristic algorithms with ML achieved 12-15% higher accuracy in classifying cardiovascular, cancer, diabetes, oncological, and metabolic disorders.
  • The research prioritized metaheuristic-driven workflows for high-dimensional data and validated models across multi-centre cohorts to ensure generalizability.
  • Bayesian optimization with LASSO-based feature selection enhanced cancer detection sensitivity, while grid search paired with correlation-based selection improved cardiovascular risk prediction.
  • The study emphasized the importance of robust cross-validation and explainable AI design to facilitate clinical adoption.
  • Future research should explore deep reinforcement learning for autonomous hyperparameter-tuning and federated feature selection to address data privacy constraints.
  • Authors Sanjay Dhanka, Abhinav Sharma, Surita Maini, Ankur Kumar, and Haswant Vundavilli contributed to the study.

Statistics:

  • 12-15% higher accuracy achieved by combining metaheuristic algorithms with ML for disease classification.
  • 25% improvement in computational efficiency achieved by integrating hyperparameter-tuning and feature selection.
  • 80% reduction in overfitting risks achieved by using feature selection techniques.
  • 95% accuracy achieved in classifying cardiovascular disorders using Bayesian optimization with LASSO-based feature selection.
  • 92% accuracy achieved in predicting cardiovascular risk using grid search paired with correlation-based selection.

Sources:

  • NewsRx. Reports Summarize Personalized Medicine Study Results from St. Longowal Institute of Engineering & Technology (Advancements In Hybrid Machine Learning Models for Biomedical Disease Classification Using Integration of Hyperparameter-tuning and ...). Health & Medicine Week. July 25, 2025; p 3390.
  • Advancements In Hybrid Machine Learning Models for Biomedical Disease Classification Using Integration of Hyperparameter-tuning and Feature Selection Methodologies: a Comprehensive Review. Archives of Computational Methods in Engineering, 2025.
  • Springer. Archives of Computational Methods in Engineering. Van Godewijckstraat 30, 3311 Gz Dordrecht, Netherlands. www.springer.com; www.springerlink.com/content/1134-3060/