Computational approaches for early disease detection of diabetes using machine learning and intelligent systems
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
Early detection of diabetes is emerging as one of the most transformative avenues in modern healthcare, driven by rapid advances in machine learning, deep learning and intelligent systems. Computational models now analyze demographic, clinical, behavioral and sensor-generated data to identify subtle metabolic patterns long before conventional diagnostics register abnormalities. Classical algorithms such as logistic regression, SVM and random forests have demonstrated strong predictive power, while deep neural networks, CNN-based image analysis and LSTM models extend detection capabilities to retinal scans, ECG signals and temporal health records. Intelligent systems-including fuzzy expert systems, IoT-enabled monitoring and interpretable clinical decision-support platforms-further enhance real-world applicability. By integrating multi-modal data with explainable AI, these approaches create a foundation for proactive screening, timely intervention and reduced long-term disease burden.
Fields of Study & Subjects
Artificial Intelligence in Healthcare
Internet of Things and AI
Machine Learning in Healthcare
Publication details
- Journal / source
- International Journal of Cloud Computing and Database Management
- Volume
- 7
- Issue
- 1
- Pages
- 99–108
- Publication date
- 1 January 2026
- Language
- EN