Privacy-Preserving Diabetes and Heart Disease Prediction via Federated Learning and WCO
Abstract Diabetes, afflicting 537 million worldwide, is a prevalent and lethal non-communicable ailment. Its onset, influenced by factors like obesity and family history, manifests symptoms such as frequent urination. Long-term complications encompass heart, kidney, and nerve ailments. Early predict...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-08-01
|
| Series: | International Journal of Computational Intelligence Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44196-025-00956-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract Diabetes, afflicting 537 million worldwide, is a prevalent and lethal non-communicable ailment. Its onset, influenced by factors like obesity and family history, manifests symptoms such as frequent urination. Long-term complications encompass heart, kidney, and nerve ailments. Early prediction mitigates risks. All these encompassing strategies are designed to improve prediction precision and facilitate proactive diabetes control. This research employed SMOTE methods to tackle imbalanced classes, utilizing various classification algorithms such as Random Forest, XGBoost, Multilayer Perceptron, Gradient Boost, and AdaBoost. Following extensive training and evaluation, the AdaBoost classifier delivered superior outcomes, achieving a 94.02% accuracy rate, an F1 score of 93.32%, and an AUC of 0.95. In the healthcare industry, accurately forecasting diabetes mellitus is crucial; however, privacy laws hinder the transfer of medical information from the Internet of Medical Things (IoMT), causing delays in diagnosis. This study introduces the Federated Learning with Weighted Conglomeration Optimization (FLWCO) model as a solution to these challenges. In Centralized Learning, AdaBoost with WCO achieves an accuracy of 95.32% when tested on a Kaggle dataset consisting of 96,146 instances. During the second stage, FLWCO achieves a superior 97.27% accuracy rate compared to other federated learning techniques. The method not only guarantees privacy conformity but also decreases communication expenses. FLWCO demonstrates superiority over existing federated learning algorithms in real-world heart illness prediction. Furthermore, the proposed model can be employed to estimate the likelihood of heart disease in individuals with diabetes. This highlights the potential of federated learning, especially FLWCO, in leveraging distributed data while preserving privacy, facilitating accurate diabetes mellitus diagnosis, and addressing challenges in sharing medical information securely and efficiently. |
|---|---|
| ISSN: | 1875-6883 |