1Research Scholar, Department of Computer Science, RVS College of Arts and Science (Autonomous), Sulur, Coimbatore, India
Email: veeruabi93@gmail.com
2Faculty Associate, Department of Computer Science - UG, PSGR Krishnammal College for Women, Coimbatore, India
Email: v_abinaya@psgrkcw.ac.in
3Associate Professor & Head, MSc Data Science, KPR College of Arts Science and Research, Coimbatore, India
Email: chitra.k@kprcas.ac.in
Diabetes has become a primary global health concern, leading to severe complications such as cardiovascular disease, kidney failure, and vision loss. Deep learning algorithms have shown significant potential in medical applications, enabling precise disease detection and treatment while reducing the burden on healthcare professionals. Recent advancements in diabetes forecasting have paved the way for early intervention and patient empowerment. This research proposes a novel diabetes prediction model that integrates an Enhanced LSTM classifier with feature selection using Grey Wolf Optimization (GWO) and Particle Swarm Optimization (PSO). A lightweight adaptive sampling approach is introduced to enhance data efficiency, ensuring optimal data collection while reducing redundancy. To further improve prediction accuracy and computational efficiency, we implement an enhanced Ant Colony Optimization (ACO) clustering technique for data grouping. The proposed model is rigorously evaluated using key performance metrics, including accuracy, precision, recall, and F1 score, demonstrating its effectiveness in diabetes prediction.
Keywords: Diabetes Prediction, Deep Learning, LSTM Classifier, Feature Selection, Adaptive Sampling, Enhanced Ant Colony Optimization.
How to cite this article: Abinaya V, Chitra K. A Novel Approach to Diabetes Forecasting Using Enhanced Ant Colony Optimization and LSTM Classifier. Int J Drug Deliv Technol. 2026;16(6s): 634-641; DOI: 10.25258/ijddt.16.6s.89
Source of support: None
Conflict of interest: None