Integrating Machine Learning and Deep Learning Techniques for Advanced Alzheimer’s Disease Detection through Gait Analysis
Malay Sarkar
Abstract
Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that severely affects cognitive and motor functions, necessitating early detection for timely intervention and improved patient outcomes. Subtle changes in gait, including stride length and cadence, have been identified as potential early indicators of cognitive decline associated with AD (Del Din et al., 2019). This study leverages advanced deep learning methodologies to enhance the diagnostic capability of gait analysis. Using datasets collected from wearable sensors and motion capture systems, Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) were implemented to classify individuals as healthy or at risk for AD. Evaluation metrics, including accuracy, precision, and recall, demonstrated superior performance of deep learning models compared to traditional diagnostic approaches, achieving over 90% classification accuracy in detecting early-stage AD (Esser et al., 2021). These results highlight the transformative potential of AI in healthcare, particularly in non-invasive diagnostic tools for neurodegenerative diseases.