Hybrid Supervised Machine Learning Models for Enhanced Alzheimer’s Disease Classification
DOI:
https://doi.org/10.53560/PPASA(62-4)696Keywords:
Predictive Modeling, Biomedical Data Analysis, Feature Engineering, Gradient Boosting, Clinical Decision Support, Cross-Validation, Diagnostic AccuracyAbstract
This research aims to facilitate the early and precise identification of Alzheimer's disease (AD), which remains one of the most prevalent neurodegenerative diseases impacting people's health and quality of life around the world. Employing machine learning algorithms, this study aims to develop reliable and effective models that support clinical workflows and streamline processes, thereby reducing the burden on patients and their families and ultimately enhancing patient-centric diagnostic frameworks. An approach to data cleaning, involving data imputation, encoding categorical variables, normalization of certain features, and stratified training and testing data splitting with hyperparameter tuning, was employed. This approach utilized both grid search and stratified k-fold cross-validation. Traditional models, ensemble techniques, and hybrid models were tested, including Lasso + LightGBM, XGBoost + SVM, and blended models such as LightGBM, CatBoost, Logistic Regression, and XGBoost. Lasso + LightGBM outperformed others in hybrid models. Lasso + LightGBM achieved an accuracy of 0.961240, precision of 0.943231, recall of 0.947368, and F1score of 0.945295, Cohen's Kappa of 0.915284, Hamming Loss of 0.038760, and Jaccard Index with the value of 0.896266. This research contributes to UNSDG 3, “Good Health and Well-being”, by enhancing data-driven health education and resources, and an efficient diagnostic and management system for Alzheimer's. It also promotes healthy aging globally among the population.
References
1. D. Jadhav, N. Saraswat, N. Vyawahare, and D. Shirode. Targeting the molecular web of Alzheimer's disease: unveiling pathways for effective pharmacotherapy. The Egyptian Journal of Neurology, Psychiatry and Neurosurgery 60(1): 7 (2024).
2. M. Wang, Y. Lin, F. Gu, W. Xing, B. Li, X. Jian, C. Liu, D. Li, Y. Li, T. Wu, and D. Ta. Diagnosis of cognitive and motor disorder levels in stroke patients through explainable machine learning based on MRI. Medical Physics 51(3):1763-1774 (2024).
3. F. Öhman, J. Hassenstab, D. Berron, M. Schöll, and K. Papp. Current Advances in Digital Cognitive Assessment for Preclinical Alzheimer's Disease. Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring 13(1): 1-19 (2021).
4. P. El Kafrawy, H. Fathi, M. Qaraad, A.K. Kelany, and X. Chen. An efficient SVM-based feature selection model for cancer classification using high-dimensional microarray data. IEEE Access 9:155353-69 (2021).
5. Q.U. Hamza, M.A. Baloch, M.A. Rajwana, A. Raza, and Z.U. Zia. Hybrid ensemble learning approaches for high-accuracy dementia detection: integrating deep learning models. Kashf Journal of Multidisciplinary Research 2(05): 66-83 (2025).
6. N. Rane, S.P. Choudhary, and J. Rane. Ensemble Deep Learning and Machine Learning: Applications, Opportunities, Challenges, and Future Directions. Studies in Medical and Health Science 1(2): 18-41 (2024).
7. H.T. Hoc, R. Silhavy, Z. Prokopova, and P. Silhavy. Comparing stacking ensemble and deep learning for software project effort estimation. IEEE Access (11): 60590-60604 (2023).
8. M.J. Iqbal, Z. Javed, H. Sadia, I.A. Qureshi, A. Irshad, R. Ahmed, K. Malik, S. Raza, A. Abbas, R. Pezzani, and J. Sharifi-Rad. Clinical applications of artificial intelligence and machine learning in cancer diagnosis: Looking into the future. Cancer Cell International 21(1): 270-280 (2021).
9. S. Asif, Y. Wenhui, S. Ur-Rehman, Q. Ul-Ain, K. Amjad, Y. Yueyang, S. Jinhai, and M. Awais. Advancements and prospects of machine learning in medical diagnostics: unveiling the future of diagnostic precision. Archives of Computational Methods in Engineering 32(2): 853-883 (2024).
10. Y. Jin, Z. Ren, W. Wang, Y. Zhang, L. Zhou, X. Yao, and T. Wu. Classification of Alzheimer's disease using robust TabNet neural networks on genetic data. Mathematical Biosciences and Engineering MBE 20(5): 8358-8374 (2023).
11. M. Chakraborty, N. Naoal, S. Momen, and N. Mohammed. ANALYZE-AD: A Comparative Analysis of Novel AI Approaches for Early Alzheimer’s Detection. Array. 22: 100352 (2024).
12. A.S. Alatrany, W. Khan, A. Hussain, H. Kolivand, and D. Al-Jumeily. An Explainable Machine Learning Approach for Alzheimer's Disease Classification. Scientific Reports 14(1): 2637-2654 (2024).
13. E. Mahamud, M. Assaduzzaman, J. Islam, N. Fahad, M.J. Hossen, and T.T. Ramanathan. Enhancing Alzheimer's disease detection: An explainable machine learning approach with ensemble techniques. Intelligence-Based Medicine 11(11): 100240 (2025).
14. T. Emmanuel, T. Maupong, D. Mpoeleng, T. Semong, B. Mphago, and O. Tabona. A survey on missing data in machine learning. Journal of Big Data 8(1): 140 (2021).
15. M.K. Dahouda and I. Joe. A deep-learning embedding technique for categorical features encoding. IEEE Access 9: 114381-114391 (2021).
16. V. Sharma. A study on data scaling methods for machine learning. International Journal for Global Academic & Scientific Research 1(1): 31-42 (2022).
17. R.K. Halder, M.N. Uddin, M.A. Uddin, S. Aryal, and A. Khraisat. Enhancing K-nearest neighbor algorithm: A comprehensive review and performance analysis of modifications. Journal of Big Data 11(1): 113-125 (2024).
18. A.A. Amer, S.D. Ravana, and R.A. Habeeb. Effective k-nearest neighbor models for data classification enhancement. Journal of Big Data 12(1): 86 (2025).
19. C.K. Reddy, P.A. Reddy, P.S. Reddy, M. Shuaib, S. Alam, S. Ahmad, and A. Rajaram. Twined ensemble framework for network security: integrating Random Forest, AdaBoost, and Gradient Boosting for enhanced intrusion detection. Discover Internet of Things 5(1): 107 (2025).
20. H. Şevgin. A comparative study of ensemble methods in the field of education: Bagging and boosting algorithms. International Journal of Assessment Tools in Education 10(3): 544-562 (2023).
21. J.C. Timoneda. Estimating group fixed effects in panel data with a binary dependent variable: How the LPM outperforms logistic Regression in rare events data. Social Science Research 93(1): 102486 (2021).
22. A. Demircioğlu. Applying oversampling before cross-validation will lead to high bias in radiomics. Scientific Reports 14(1): 11563 (2024).
23. N.S. Nafis and S. Awang. An enhanced hybrid feature selection technique using term frequency-inverse document frequency and support vector machine-recursive feature elimination for sentiment classification. IEEE Access 9: 52177-52192 (2021).
24. T. Mahmood, A. Rehman, T. Saba, T.J. Alahmadi, M. Tufail, S.A. Bahaj, and Z. Ahmad. Enhancing Prognosis of Coronary Artery Disease: A Novel Dual-Class Boosted Decision Trees Strategy for Robust Optimization. IEEE Access 12: 107119-107143 (2024).
25. R. Vishraj, S. Gupta, and S. Singh. Evaluation of feature selection methods utilizing random forest and logistic regression for lung tissue categorization using HRCT images. Expert Systems 40(8): e13320 (2023).
26. K.A. Ahmed, I. Humaira, A.R. Khan, M.S. Hasan, M. Islam, A. Roy, M. Karim, M. Uddin, A. Mohammad, and M.D. Xames. Advancing breast cancer prediction: Comparative analysis of ML models and deep learning-based multi-model ensembles on original and synthetic datasets. PLoS One 20(6):e0326221 (2025).
27. I. Malashin, V. Tynchenko, A. Gantimurov, V. Nelyub, and A. Borodulin. Boosting-based machine learning applications in polymer science: A review. Polymers 17(4): 499 (2025).
28. H. Alshamlan, A. Alwassel, A. Banafa, and L Alsaleem. Improving Alzheimer’s Disease Prediction with different Machine Learning Approaches and Feature Selection Techniques. Diagnostics 14(19): 2237 (2024).
29. R.A. Gad and A. Abdelhafeez. Alzheimer’s Disease Prediction using Hybrid Machine Learning Techniques. SciNexuses 1: 174-83 (2024).
