INTEGRATING MACHINE LEARNING INTO ALZHEIMER’S RESEARCH: A CLINICAL DECISION SUPPORT SYSTEM APPROACH

Introduction: Alzheimer’s Disease is defined as a progressive brain disease that affects memory, thinking, and behavior. It accounts for 50-80% of all dementia cases. Diagnosis can be challenging, particularly in the early stages and notably in mild cognitive impairment. The growing number and diversity of health-related data have led to the widespread use of machine learning algorithms in the early detection of Alzheimer’s Disease. This study focuses on developing an Artificial Intelligence-based clinical decision support system that classifies individuals as individuals with Alzheimer’s Disease, Mild Cognitive Impairment, or healthy individuals. Materials and Method: The dataset used in the study was obtained from the Brain Aging and Dementia Unit of the Geriatrics Department. All patients aged between 45 and 96 years and followed up in the clinic were examined. Classification was performed using the Logistic Regression, Naive Bayes, K-Nearest Neighbor, Artificial Neural Networks, Support Vector Machines, Decision Trees, and ensemble methods. Results: The CatBoost algorithm outperformed the other models in terms of accuracy. Ensemble learning methods outperformed traditional methods for 176 samples in the Alzheimer class. Random Forest method exhibited the highest precision for Mild Cognitive Impairment classification. Conclusion: Machine learning techniques according to the purpose of the study can serve experts as a low-cost and non-invasive diagnostic tool. The clinical decision support system developed in this study has been designed as a tool to assist the clinicians. Keywords: Machine Learning; Alzheimer Disease; Clinical Decision Support Systems.