The biomechanical characteristics of an individual may provide information about their orthopedic health status. Disease prognosis can now be conducted automatically. Machine learning algorithms are frequently employed in healthcare research. Various algorithms are utilized to identify illnesses and classify individuals accurately. In this context, this study is distinctive in its aim to assist specialists in determining the type of orthopedic condition. In this article, we have employed several methods to quantify accuracy, which serves as a means of analyzing the efficacy of each machine learning algorithm in detecting and categorizing patients with orthopedic conditions. Six biomechanical variables derived from the areas and the shapes of the lumbar spine and pelvis are calculated for each subject in the dataset. Our two-stage process yielded a normal precision exceeding 90% for most of the calculations, except the Decision Tree (DT) technique, which achieved a remarkable accuracy of nearly 100%. Utilizing a dataset of patient biomechanical measurements, the study applies machine learning algorithms to identify patterns indicative of specific musculoskeletal disorders. The results demonstrate that machine learning (ML) may significantly increase diagnostic accuracy, reduce misdiagnosis, and provide suitable treatment recommendations.