Comparative Analysis of Hybrid Machine Learning Models for Early Stage Diabetes and Cardiovascular Disease Prediction
Description
Early detection of Type 2 Diabetes Mellitus (T2DM) and cardiovascular diseases (CVD) is critical for reducing global morbidity and mortality rates. This study presents a comprehensive comparative analysis of two advanced machine learning models designed for early-stage disease prediction. Model-1 employs a stacking
ensemble architecture combining logistic regression, naïve Bayes, AdaBoost, support vector machines (SVM), artificial neural networks (ANN), and k-nearest neighbors (k-NN), aggregated via a random forest meta-classifier for T2DM prediction. Model-2 integrates a long short-term memory (LSTM) network with a
quantum neural network (QNN), optimized using a self-improved aquila optimization (SIAO) algorithm for CVD prediction. The analysis evaluates performance metrics, computational efficiency, adaptability to diverse datasets, and practical implications for healthcare applications. Results demonstrate Model-1’s exceptional
accuracy (99.72%) and low false positive rate, while Model-2 achieves robust performance on imbalanced datasets (96.69% accuracy) despite higher resource demands. The study highlights trade-offs between model complexity, data requirements, and operational feasibility, offering actionable insights for medical
practitioners and researchers.
Files
IJRPR433391.pdf
Files
(473.8 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:36a6ff54c0e6c61c868ab7586b21f23e
|
473.8 kB | Preview Download |
Additional details
Dates
- Accepted
-
2025-04-27
References
- Abdollahi, Jafar, and Babak Nouri-Moghaddam. 2022. "Hybrid Stacked Ensemble Combined with Genetic Algorithms for Diabetes Prediction." Iran Journal of Computer Science 5(3):205–20. doi: 10.1007/s42044-022-00100-1.
- Abidi, Mustufa Haider, Usama Umer, Syed Hammad Mian, and Abdulrahman Al-Ahmari. 2023. "Big Data-Based Smart Health Monitoring System: Using Deep Ensemble Learning." IEEE Access 11:114880–903. doi: 10.1109/ACCESS.2023.3325323.
- Aman, and Rajender Singh Chhillar. 2020. "Disease Predictive Models for Healthcare by Using Data Mining Techniques: State of the Art." International Journal of Engineering Trends and Technology - IJETT 68(10):52-57,. doi: 10.14445/22315381/IJETT-V68I10P209.
- Aman, and Rajender Singh Chhillar. 2021. "Analyzing Predictive Algorithms in Data Mining for Cardiovascular Disease Using WEKA Tool." International Journal of Advanced Computer Science and Applications 12(8, Art. no. 8):31. doi: 10.14569/IJACSA.2021.0120817.
- Aman, and Rajender Singh Chhillar. 2023. "Optimized Stacking Ensemble for Early-Stage Diabetes Mellitus Prediction." International Journal of Electrical and Computer Engineering (IJECE) 13:7048–55. doi: 10.11591/ijece.v13i6.pp7048-7055.
- Andras Janosi, William Steinbrunn. 1989. "Heart Disease."
- Anon. 2020. "Early Stage Diabetes Risk Prediction."
- Anon. n.d.-a. "Pima Indians Diabetes Database." Retrieved November 15, 2022 (https://www.kaggle.com/datasets/uciml/pima-indians-diabetes database).
- Anon. n.d.-b. "Statlog (Heart)."
- Darolia, Aman, Rajender Singh Chhillar, Musaed Alhussein, Surjeet Dalal, Khursheed Aurangzeb, and Umesh Kumar Lilhore. 2024. "Enhanced Cardiovascular Disease Prediction through Self-Improved Aquila Optimized Feature Selection in Quantum Neural Network & LSTM Model." Frontiers in Medicine 11. doi: 10.3389/fmed.2024.1414637.
- Janiesch, Christian, Patrick Zschech, and Kai Heinrich. 2021. "Machine Learning and Deep Learning." Electronic Markets 31(3):685–95. doi: 10.1007/s12525-021-00475-2.
- Khan, Moien Abdul Basith, Muhammad Jawad Hashim, Jeffrey Kwan King, Romona Devi Govender, Halla Mustafa, and Juma Al Kaabi. 2020. "Epidemiology of Type 2 Diabetes – Global Burden of Disease and Forecasted Trends." Journal of Epidemiology and Global Health 10(1):107–11. doi: 10.2991/jegh.k.191028.001