AI-Driven Diagnostics: Comparative Analysis of Machine Learning and Deep Learning Approaches in Multiple Sclerosis Diagnostics

Multiple Sclerosis (MS) is a chronic autoimmune disorder that targets the central nervous system, resulting in considerable physical and cognitive disabilities. Timely and precise diagnosis is essential for the effective management and treatment of Multiple Sclerosis (MS). Predicting MS involves using various types of data to assess the risk and diagnose the disease. The data commonly used are clinical, imaging, speech and gene data. This work presents a review of machine learning and deep learning methods, encompassing a broad spectrum of algorithms such as Support Vector Machines (SVM), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Convolutional Neural Networks (CNNs), and Artificial Neural Networks (ANNs). Furthermore, the survey gives a comparative analysis of the dataset used, algorithms employed and the performance metrics. The survey also compares the implemented results with DL using the gene data. It also identifies current challenges in MS prediction, such as heterogeneity of MS, integration of multimodal data, validation and clinical implementation. Our goal is to offer a valuable resource for researchers and practitioners.