AI-Powered Expert System for Musculoskeletal Diagnosis: Optimization, Quantitative Evaluation and Empirical Validation

Musculoskeletal diseases (MSDs) affect the musculoskeletal system, often causing pain, inflammation, and restricted mobility. The diagnostic challenge arises from symptom overlap with other disorders, necessitating advanced decision-support technologies. This study introduces an optimized AI-driven expert system tailored for Tendonitis diagnosis, designed to enhance clinical decision-making and improve diagnostic accuracy. Developed using the Waterfall methodology, the system integrates a rule-based algorithm with a Random Forest Classifier to generate precise diagnostic outcomes. Empirical validation against physician-confirmed cases yielded a diagnostic accuracy of 93%, alongside precision (91%), recall (97%), F1-score (94%), sensitivity (91%), specificity (94%), and negative predictive value (82%). Featuring an intuitive interface, the system ensures seamless adoption into clinical workflows. Grounded in expert system principles, this innovation synthesizes artificial intelligence, medical expertise, and health informatics to advance musculoskeletal disease diagnostics. The findings highlight the potential of AI-driven expert systems to enhance diagnostic efficiency, optimize medical workflows, and drive innovation in musculoskeletal healthcare.