Machine Learning-Based Pattern Recognition of Risk Factors for Low Back Pain among Adolescent Cricket Players in Dhaka City

Low back pain (LBP) is common among adolescent cricketers, often due to repetitive lumbar stress. This study investigated LBP among 450 adolescent cricketers in Dhaka City in Bangladesh, considering a range of factors, including sociodemographic characteristics, game-related activities, preventive practices, and LBP-related history. Several machine learning (ML) algorithms were applied to classify LBP severity, including K-Nearest Neighbors, Random Forest, Logistic Regression, and Support Vector Machine (SVM). The severity of LBP was categorized into three classes such as no pain, mild pain, and moderate pain owing to insufficient data in the severe pain category. Among the tested models, SVM with a sigmoid kernel demonstrated the best performance, achieving the highest performance metrics of test accuracy (87.6%), precision (90%), recall (87.6%), and F1-score (87.1%). In addition, regression analysis was performed to identify the contributing factors associated with LBP. Significant statistical correlations were evident between LBP and variables such as gender, educational background, family income, duration of practice, warm-up and cool-down protocol, and past history of LBP. These findings emphasize the importance of early preventive measures in lessening LBP risk among young cricket players. Overall, this study demonstrates the utility of ML and regression models in identifying sports injury risk patterns, supporting data-driven prevention and management strategies, and providing a baseline for future research in this field.