Comparing Random Forest and ANN In Early Detection of Alzheimer

Abstract

Alzheimer’s disease is a progressive disorder that affects memory, cognitive abilities, and behavior, and is one of the leading causes of dementia worldwide. Early detection is essential to slow disease progression and improve patient care. However, conventional diagnostic methods such as brain imaging and clinical evaluations are often expensive, time-consuming, and not easily accessible. This study investigates the use of artificial intelligence (AI) as an alternative approach for detecting Alzheimer’s disease using simple and non-invasive data. Two AI models are compared: Random Forest and Artificial Neural Network (ANN). The dataset consists of basic clinical features, including age, memory test scores, and family history. Experimental results show that the Random Forest model achieves an accuracy of 94%, outperforming the ANN model, which reaches an accuracy of 82%. These findings indicate that Random Forest is more effective for structured clinical data and suggest that traditional machine learning techniques can outperform deep learning models in certain healthcare applications. The results support the development of practical, data-driven tools to assist healthcare professionals in faster and more accessible diagnosis.