Makine Öğrenmesi ve Yenilikçi Özellik Mühendisliği Kullanılarak Alzheimer Tanısının Tahmini

Year 2025, Volume: 27 Issue: 81, 457 - 465, 29.09.2025

Murat Emeç , Gamze Gezgin

https://doi.org/10.21205/deufmd.2025278113

Abstract

Alzheimer hastalığı, dünya çapında sağlık sistemleri için büyük sorunlar yaratır ve demansın önde gelen nedenlerindendir. Erken teşhis edilmesi, etkili yönetim ve müdahaleyi mümkün kılar. Bununla birlikte geleneksel tanı yöntemleri zaman alıcı, invaziv ve maliyetlidir Bu çalışma Alzheimer hastalığının erken tanısı için Recursive Feature Elimination(RFE) gibi özellik seçim teknikleri ve hiperparametre optimizasyonunun rolünü vurgulayarak, gelişmiş makine öğrenmesini modellerinin uygulanmasını araştırmaktadır. Değerlendirmeler sonucunda, RFE ile beraber kullanılan CatBoost modeli, %95,81 doğruluk ve %94,00 F1-skora ulaşarak sağlamlığı ve güvenilirliğiyle öne çıkan model olmuştur. Random Forest ve XGBoost modelleri de, özellik önemi ve RFE ile birleştirildiğinde güçlü sonuçlar elde edebilmiştir. Araştırma, doğruluk, duyarlılık, kesinlik ve F1-skor gibi temel metriklerde model performansını artırmada özellik mühendisliği ve hiperparametre ayarlarının öne çıkan etkisini vurgulamaktadır. Bu araştırma, tıbbi tanılarda makine öğrenimi tekniklerinin entegre edilmesi sonucunda invaziv olmayan, maliyet etkin ve verimli bir yaklaşım sunulabildiğini ortaya koymaktadır. Çalışma sonucunda elde edilen bilgiler, erken tanı yöntemlerini ve hasta sonuçlarını iyileştirmeyi hedefleyen teşhis modellerinde gelecekteki ilerlemelere zemin hazırlamaktadır. Bununla beraber alzheimer hastalığının bireyler ve toplum üzerindeki etkisini düşürmeye yönelik küresel çalışmalara katkıda bulunmaktadır.

Keywords

Alzheimer hastalığı , Erken Tanı , Makine Öğrenmesi , Özellik Mühendisliği

Prediction of Alzheimer's Diagnosis with Machine Learning and Innovative Feature Engineering

Abstract

Alzheimer's disease is a leading cause of dementia, presenting significant challenges to healthcare systems globally. Early diagnosis is essential for effective management and intervention, yet traditional diagnostic methods remain invasive, time-consuming, and costly. This study investigates the application of advanced machine learning models, emphasising the role of feature selection techniques, such as RFE (Recursive Feature Elimination) and hyperparameter optimisation, to enhance the early detection of Alzheimer's disease. Among the evaluated models, CatBoost with RFE achieved the highest performance, with an accuracy of 95.81% and an F1-score of 94.00%, demonstrating its robustness and reliability as a diagnostic tool. Random Forest and XGBoost models also showed strong results, particularly when combined with feature importance and RFE. The findings highlight the significant impact of feature engineering and hyperparameter tuning in improving model performance across key metrics, including accuracy, recall, precision, and F1-score. This research underscores the potential of integrating machine learning techniques into medical diagnostics, offering a non-invasive, cost-effective, and efficient approach to Alzheimer's disease prediction. The insights gained from this study lay the groundwork for future advancements in diagnostic models, aiming to improve early detection strategies and patient outcomes, ultimately contributing to the global effort to mitigate the impact of Alzheimer's disease on individuals and society.

Keywords

Alzheimer , Early Diagnosis , Machine Learning , Feature Engineering

References

• Ünal, C., Gökşen, Y. 2024. Unlocking Neurological Mysteries: Machine Learning Approaches to Early Detection of Alzheimer's Disease, Güvenlik Bilimleri Dergisi, Vol. 13, no. 1, pp. 85-104.
• Jo, T., Nho, K., Saykin, A. 2019. Deep Learning in Alzheimer's Disease: Diagnostic Classification and Prognostic Prediction Using Neuroimaging Data, Frontiers in Ageing Neuroscience, Vol. 11, DOI: 10.3389/fnagi.2019.00220.
• Alatrany, A., Hussain, A., Mustafina, J., Al-Jumeily, D. 2022. Machine Learning Approaches and Applications in Genome-Wide Association Study for Alzheimer’s Disease: A Systematic Review, IEEE Access, DOI: 10.1109/ACCESS.2022.3182543.
• Venugopalan, J., Tong, L., Hassanzadeh, H., Wang, M. 2021. Multimodal Deep Learning Models for Early Detection of Alzheimer’s Disease Stage, Scientific Reports, Vol. 11, DOI: 10.1038/s41598-020-74399-w.
• Aqeel, A., Hassan, A., Khan, M., Rehman, S., Tariq, U., Kadry, S., Majumdar, A., Thinnukool, O. 2022. A Long Short-Term Memory Biomarker-Based Prediction Framework for Alzheimer’s Disease, Sensors, Vol. 22, DOI: 10.3390/s22041475.
• Bi, X., Li, S., Xiao, B., Li, Y., Wang, G., Ma, X. 2020. Computer-aided Alzheimer's disease diagnosis by an unsupervised deep learning technology, Neurocomputing, Vol. 392, pp. 296-304, DOI: 10.1016/J.NEUCOM.2018.11.111.
• Liu, S., Liu, S., Cai, W., Che, H., Pujol, S., Kikinis, R., Feng, D., Fulham, M. 2015. Multimodal Neuroimaging Feature Learning for Multiclass Diagnosis of Alzheimer's Disease, IEEE Transactions on Biomedical Engineering, Vol. 62, pp. 1132-1140, DOI: 10.1109/TBME.2014.2372011.
• Alsaeed, D., Omar, S. 2022. Brain MRI Analysis for Alzheimer’s Disease Diagnosis Using CNN-Based Feature Extraction and Machine Learning, Sensors, Vol. 22, DOI: 10.3390/s22082911.
• Irfan, M., Shahrestani, S., Elkhodr, M. 2023. Early Detection of Alzheimer's Disease Using Cognitive Features: A Voting-Based Ensemble Machine Learning Approach, IEEE Engineering Management Review, Vol. 51, pp. 16-25, DOI: 10.1109/EMR.2022.3230820.
• Kavitha, C., Mani, V., Srividhya, S., Khalaf, O., Romero, C. 2022. Early-Stage Alzheimer's Disease Prediction Using Machine Learning Models, Frontiers in Public Health, Vol. 10, DOI: 10.3389/fpubh.2022.853294.
• Meng, X., Wu, Y., Liu, W., Wang, Y., Xu, Z., Jiao, Z. 2022. Research on Voxel-Based Features Detection and Analysis of Alzheimer’s Disease Using Random Survey Support Vector Machine, Frontiers in Neuroinformatics, Vol. 16, DOI: 10.3389/fninf.2022.856295.
• Castellazzi, G., Cuzzoni, M.G., Cotta Ramusino, M., Martinelli, D. et al. 2020. A machine learning approach for the differential diagnosis of Alzheimer's and vascular dementia fed by MRI-selected features, Frontiers in Neuroinformatics, Vol. 14, p. 25.
• Jo, T., Nho, K., Saykin, A.J. 2019. Deep learning in Alzheimer's disease: diagnostic classification and prognostic prediction using neuroimaging data, Frontiers in Ageing Neuroscience, Vol. 11, p. 220.
• Raza, M., Awais, M., Ellahi, W., Aslam, N., Nguyen, H.X., Le Minh, H. 2019. Diagnosis and Monitoring of Alzheimer's Patients Using Classical and Deep Learning Techniques.
• Cochrane, C., Castineira, D., Shiban, N., Protopapas, P. 2020. Application of Machine Learning to Predict the Risk of Alzheimer's Disease: An Accurate and Practical Solution for Early Diagnostics.
• Chang, C.H., Lin, C.H., Lane, H.Y. 2021. Machine Learning and Novel Biomarkers for the Diagnosis of Alzheimer’s Disease.
• Battineni, G., Amran Hossain, M., Chintalapudi, N., Traini, E., Rao Dhulipalla, V., Ramasamy, M., Amenta, F. 2021. Improved Alzheimer’s Disease Detection by MRI Using Multimodal Machine Learning Algorithms.
• Li, X., Qiu, Y., Zhou, J., Xie, Z. 2021. Applications and Challenges of Machine Learning Methods in Alzheimer's Disease Multi-Source Data Analysis.
• Aqeel, A., Hassan, A., Attique Khan, M., Rehman, S., Tariq, U., Kadry, S., Majumdar, A., Thinnukool, O. 2022. A Long Short-Term Memory Biomarker-Based Prediction Framework for Alzheimer’s Disease.
• Singh, N.D.P., Soni, N., Kapoor, A. 2022. Automated Detection of Alzheimer’s Disease Using MRI Images and Deep Neural Networks - A Review.
• Bucholc, M., James, C., Al Khleifat, A., Badhwar, A.P. et al. 2023. Artificial Intelligence for Dementia Research Methods Optimisation.
• Kang, W., Li, B., Papma, J.M., Jiskoot, L.C. et al. 2023. An Interpretable Machine Learning Model with Deep Learning-Based Imaging Biomarkers for Diagnosis of Alzheimer's Disease.
• Abdelwahab, M.M., Al-Karawi, K.A., Semary, H.E. 2023. Deep Learning-Based Prediction of Alzheimer’s Disease Using Microarray Gene Expression Data.
• Ahmadi, M., Javaheri, D., Khajavi, M., Danesh, K., Hur, J. 2024. A Deeply Supervised Adaptable Neural Network for Diagnosis and Classification of Alzheimer’s Severity Using Multitask Feature Extraction.
• El Kharoua, R. 2024. Alzheimer’s Disease Dataset, Kaggle, DOI: 10.3470/KAGGLE/DSV/8668279.
• Klasan, A., Neri, T., Sommer, C., Leie, M.A., Dworschak, P., Schofer, M.D., Heyse, T.J. 2019. Analysis of acetabular version: Retroversion prevalence, age, side and gender correlations, Journal of Orthopaedic Translation, Vol. 18, pp. 7-12, DOI: 10.1016/j.jot.2018.12.002.