Alzheimer Hastalığının Tahmininde Makine Öğrenmesi Yaklaşımları

Year 2024, Volume: 4 Issue: 2, 110 - 118, 27.12.2024

Kadriye Filiz Balbal

Abstract

Alzheimer Hastalığı (AD), bir bireyin davranışını, hafızasını ve bilişsel işlevlerini önemli ölçüde etkileyen ve nihayetinde bağımsızlık kaybına yol açan bir hastalıktır. AD'nin erken ve doğru teşhisi, özellikle şu anda kesin bir tedavi bulunmadığından, ilerlemesini hafifletmek ve hasta sonuçlarını iyileştirmek için kritik öneme sahiptir. Bu çalışma, hasta semptomlarına ve klinik verilere dayanarak AD'yi tahmin etmek ve teşhis etmek için makine öğrenimi algoritmalarının uygulamasını araştırmaktadır. Bu araştırmada kullanılan veri seti, demografik, yaşam tarzı ve tıbbi faktörleri kapsayan 35 özellik ve eksik değer içermeyen 2.149 hastadan kapsamlı sağlık bilgilerini içerir. Hastalık tahminindeki etkinliklerini belirlemek için yaygın olarak tanınan yedi makine öğrenimi algoritması - KNN, GNB, SVM, DT, RF, AdaBoost ve XGBoost - değerlendirildi. Performans, her modelin sağlam bir değerlendirmesini sağlayan geri çağırma, kesinlik, doğruluk ve F1 puanı ölçümleri kullanılarak değerlendirildi. XGBoost, üstün tahmin yeteneğini vurgulayan %95,35'lik en yüksek doğruluk oranına ulaşırken, KNN %75,54 ile en düşük doğruluğu kaydetti. Sonuçlar, Alzheimer Hastalığının erken teşhisi için karmaşık klinik verileri analiz etmede makine öğrenimi algoritmalarının, özellikle XGBoost gibi topluluk yöntemlerinin gücünü göstermektedir. Bu bulgular, Alzheimer Hastalığı riski taşıyan bireylerin yaşam kalitesini iyileştirmek için gerekli olan tanı doğruluğunu artırma ve zamanında müdahaleleri mümkün kılmada makine öğreniminin kritik rolünü vurgulamaktadır.

Keywords

makine öğrenmesi, sınıflandırma, hastalık tahmini, Alzheimer Hastalığı

Machine Learning Approaches for Prediction of Alzheimer’s Disease

Abstract

Alzheimer's Disease (AD) is a disorder that significantly impacts an individual’s behavior, memory, and cognitive functions, ultimately leading to a loss of independence. Early and accurate diagnosis of AD is critical to mitigating its progression and improving patient outcomes, especially as no definitive cure is currently available. This study investigates the application of machine learning algorithms to predict and diagnose AD based on patient symptoms and clinical data. The dataset used in this research includes comprehensive health information from 2,149 patients, with 35 features covering demographic, lifestyle, and medical factors, and no missing values. Seven widely recognized machine learning algorithms—KNN, GNB, SVM, DT, RF, AdaBoost, and XGBoost—were evaluated to determine their effectiveness in disease prediction. Performance was assessed using recall, precision, accuracy, and F1-score metrics, providing a robust evaluation of each model. XGBoost achieved the highest accuracy rate of 95.35%, highlighting its superior predictive capability, while KNN recorded the lowest accuracy at 75.54%. The results demonstrate the strength of machine learning algorithms, particularly ensemble methods like XGBoost, in analyzing complex clinical data for the early detection of Alzheimer’s Disease. These findings underscore the critical role of machine learning in enhancing diagnostic accuracy and enabling timely interventions, which are essential for improving the quality of life for individuals at risk of Alzheimer’s Disease.

Keywords

machine learning, classification, Alzheimer, disease prediction

References

• D.M. Khan, N. Yahya, N. Kamel, I. Faye, “Automated diagnosis of major depressive disorder using brain effective connectivity and 3D convolutional neural network,” IEEE Access, 9, pp. 8835-8846, 2021, 10.1109/ACCESS.2021.3049427
• M. Sudharsan and G. Thailambal. "Alzheimer's disease prediction using machine learning techniques and principal component analysis (PCA)," Materials Today: Proceedings 81, pp. 182-190, 2023.
• A. Association, “2019 Alzheimer's disease facts and figures”, Alzheimer's & Dementia, 15 (3), pp. 321-387, 2019.
• C.K. Gomathy and A. Rohith Naidu, "The Prediction Of Disease Using Machine Learning Techniques", International Journal of Scientific Research in Engineering and Management (IJSREM), vol. 5, no. 7, 2021.
• C. R. Mallela, L. R. Bhavani and B. Ankayarkanni, Disease Prediction Using Machine Learning Techniques, IEEE, pp. 962-966, 2021.
• T.V. Sriram, M.V. Rao, G.S. Narayana, D.S.V.G. Kaladhar and T.P.R. Vital, "Intelligent Parkinson Disease Prediction Using Machine Learning Algorithms", International Journal of Engineering and Innovative Technology (IJEIT), vol. 3, no. 3, September 2013.
• K. Gomathi and D. Shanmuga Priya, Multi Disease Prediction using Data Mining Techniques, 2016.
• A. Gavhane, G. Kokkula, I. Pandya and K. Devatkar, Prediction of Heart Disease Using Machine Learning Algorithms, 2018.
• S. Arunachalam, "Cardiovascular Disease Prediction Model using Machine Learning Algorithms", International Journal for Research in Applied Science & Engineering Technology, vol. 8, no. VI, June 2020, ISSN 2321-9653.
• A.D., Praveen, T.P., Vital, D., Jayaram and L.V. Satyanarayana, “Intelligent Liver Disease Prediction (ILDP) System Using Machine Learning Models”. Intelligent Computing in Control and Communication. Lecture Notes in Electrical Engineering, vol 702, 2021. Springer, Singapore. https://doi.org/10.1007/978-981-15-8439-8_50.
• R.E. Kharoua, “Alzheimer's Disease Dataset”, 2024. Kaggle. https://doi.org/10.34740/KAGGLE/DSV/8668279.
• K. Taunk, S. De, S. Verma and A. Swetapadma, "A Brief Review of Nearest Neighbor Algorithm for Learning and Classification," 2019 International Conference on Intelligent Computing and Control Systems (ICCS), Madurai, India, 2019, pp. 1255-1260, doi: 10.1109/ICCS45141.2019.9065747.
• I. Triguero, D. García‐Gil, J. Maillo, J. Luengo, S. García and F. Herrera, “Transforming big data into smart data: An insight on the use of the k‐nearest neighbors algorithm to obtain quality data”, Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 9(2), e1289, 2019.
• H. Kamel, A. Dhahir and J.M. Al-Tuwaijari. "Cancer classification using gaussian naive bayes algorithm." 2019 international engineering conference (IEC). IEEE, 2019.
• S. Suthaharan and S. Shan, "Support vector machine." Machine learning models and algorithms for big data classification: thinking with examples for effective learning, 207-235, 2016.
• K. Nong, H. Zhang and Z. Liu, “Comparative Study of Different Machine Learning Models for Heat Transfer Performance Prediction of Evaporators in Modular Refrigerated Display Cabinets”, Energies, 17, 6189, 2024. https://doi.org/10.3390/en17236189
• A. T. Azar, H. I. Elshazly, A. E. Hassanien and A. M. Elkorany, “A random forest classifier for lymph diseases.” Computer methods and programs in biomedicine, 113(2), 465-473, 2014.
• W. Wang and S. Dongchu, "The improved AdaBoost algorithms for imbalanced data classification." Information Sciences 563, 358-374, 2021.
• S. Li and Z. Xiaojing, "Research on orthopedic auxiliary classification and prediction model based on XGBoost algorithm." Neural Computing and Applications 32.7 ,1971-1979, 2020.
• P. Iacobescu, V. Marina, C. Anghel, and A-D. Anghele, “Evaluating Binary Classifiers for Cardiovascular Disease Prediction: Enhancing Early Diagnostic Capabilities. Journal of Cardiovascular Development and Disease”, 11(12):396, 2024. https://doi.org/10.3390/jcdd11120396.
• P. Pranjal, S. Mallick, A. Das, A. Negi and M.R. Panda, "Alzheimer's Disease Prediction Using Modern Machine Learning Techniques." 2024 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC). IEEE, 2024.