A survey on Ankylosing spondylitis (AS) detection and prediction using machine learning and deep learning- review

Ankylosing spondylitis (AS) is a chronic inflammatory illness caused by sacroiliitis that primarily affects men. X-rays, computed tomography (CT), magnetic resonance imaging (MRI), and digital imaging and communications in medicine (DICOM) images all play significant functions in AS detection. The goal of this research is to investigate the knowledge of AS and present a comprehensive assessment of artificial intelligence (AI) techniques. In this paper, potential of AI, machine learning (ML), and deep learning (DL) to aid in the early identification of AS and the forecasting of more successful patient-specific treatment. For AS diagnosis, ML (K Nearest Neighbor (KNN), Support Vector Machine (SVM), Naïve Bayes (NB), Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), and Artificial Neural Network (ANN)) and DL (Recurrent Neural Network (RNN), Deep Neural Network (DNN), Convolutional Neural Network (CNN), pretrained CNNs, and transformer models) trained models have created. The extensive healthcare systems require the timely and efficient support of ML and DL techniques. Benefits are mainly higher in lacking person specialists and investigative resources. The review describes the many types of methodologies, dataset descriptions, and limits of earlier efforts to identify gaps. It offers comprehensive details of the most recent improvements at various stages of AS identification and therapy. Overall, this work supports future research in this area and offers a thorough analysis of AS diagnosis.