Optimization and Quantitative Evaluation of an AI-Powered Expert System for Musculoskeletal Disease Diagnosis
Keywords:
Artificial Intelligence (AI), Clinical Decision Support Systems (CDSS), Diagnostic accuracy, Expert system, Musculoskeletal disease diagnosisAbstract
Musculoskeletal Diseases (MSDs) affect the body's musculoskeletal system, frequently leading to discomfort, inflammation, and restricted movement. Diagnosing these conditions is often complex due to symptom similarities with other medical issues, emphasizing the need for sophisticated decision-support systems. In order to help clinicians make accurate diagnoses, this study presents an improved AI-based expert system specifically intended for tendinitis. Built using the Waterfall development model, the system integrates a rule-based approach with a Random Forest Classifier to enhance diagnostic precision. Using physician-verified data, performance evaluation demonstrated high effectiveness, with 93% accuracy, 91% precision, 97% recall, 94% F1-score, 91% sensitivity, 94% specificity, and 82% negative predictive value. In order to facilitate adoption in clinical settings, the platform also has an easy-to-use user interface. This approach, which is based on expert system concepts, strengthens musculoskeletal diagnostic procedures by utilizing artificial intelligence, domain expertise, and health informatics. The findings highlight the promise of AI-driven tools in improving diagnostic speed and accuracy, optimizing healthcare workflows, and advancing the treatment of musculoskeletal conditions.
References
S. H. Alruwaili, A. Thirunavukkarasu, R. M. Alanazi, A. Y. Alsharari, D. K. Alruwaili, H. A. Alenzi, A. N. Alruwaili, and G. Q. Alruwaili, "Prevalence, patterns, and associated factors for musculoskeletal disorders among the healthcare workers of northern Saudi Arabia: A multicenter cross-sectional study," J. Pain Res., vol. 16, pp. 3735–3746, 2023. https://doi.org/10.2147/JPR.S415919
C. M. Espirito Santo, V. S. Santos, S. J. Kamper, C. M. Williams, G. C. Miyamoto, and T. P. Yamato, "Overview of the economic burden of musculoskeletal pain in children and adolescents: A systematic review with meta-analysis," Pain, vol. 165, no. 2, pp. 296–323, 2024. https://doi.org/10.1097/j.pain.0000000000003037
World Health Organization, “Musculoskeletal health,” World Health Organization, Jul. 14, 2022. https://www.who.int/news-room/fact-sheets/detail/musculoskeletal-conditions
M. Farzandipour, E. Nabovati, S. Saeedi, and E. Fakharian, "Fuzzy decision support systems to diagnose musculoskeletal disorders: A systematic literature review," Comput. Methods Programs Biomed., vol. 163, pp. 101–109, Sep. 2018. https://doi.org/10.1016/j.cmpb.2018.06.002
D. Mahajan, M. K. Gupta, N. Mantri, N. K. Joshi, S. Gnanasekar, A. D. Goel, S. Srinivasan, N. M. Gonade, S. K. Sharma, M. K. Garg, and P. Bhardwaj, "Musculoskeletal disorders among doctors and nursing officers: An occupational hazard of overstrained healthcare delivery system in western Rajasthan, India," BMC Musculoskeletal Disorders, vol. 24, no. 1, p. 349, 2023. https://doi.org/10.1186/s12891-023-06457-z
F. M. Amiri and A. Khadivar, "A fuzzy expert system for diagnosis and treatment of musculoskeletal disorders in wrist," Tehnički Vjesnik - Technical Gazette, vol. 24, pp. 147–155, Mar. 2017. https://hrcak.srce.hr/file/267127
M. A. Ibrahim, O. A. Ojo, and P. A. Oluwafisoye, "Design and implementation of an expert system for medical diagnosis and prescription," Trans. Niger. Assoc. Math. Phys., vol. 20, pp. 83–92, Mar. 2024. https://doi.org/10.60787/tnamp.v20.380
J. M. Román-Belmonte, H. De la Corte-Rodríguez, B. A. Rodríguez-Damiani, and E. C. Rodríguez-Merchán, Artificial intelligence in musculoskeletal conditions, in Artificial Intelligence in Medicine and Surgery. An Exploration of Current Trends, Potential Opportunities, and Evolving Threats, Frontiers in Bioscience-Landmark ,vol. 1, Mar. 25, 2023. https://doi.org/10.5772/intechopen.110696
National Health Service (NHS), "AI tools approved for detecting bone fractures in X-rays," The Guardian, Oct. 22, 2024. Available: https://www.theguardian.com/society/2024/oct/22/nhs-ai-artificial-intelligence-tools-scans-broken-bones-fractures-x-rays
S. A. Khan, D. Mistry, A. Stephens, and J. Dalrymple, “An artificial intelligence based approach to musculoskeletal acute knee injury triage,” 2025 ISAKOS Congress Abstract, 2025. Available from https://www.isakos.com/2025/Abstract/18891
Y. Gu, Y. Otake, K. Uemura, M. Takao, M. Soufi, Y. Hiasa, H. Talbot, S. Okada, N. Sugano, and Y. Sato, "MSKdeX: musculoskeletal (MSK) decomposition from an X-ray image for fine-grained estimation of lean muscle mass and muscle volume," in Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Interv., Cham, Switzerland: Springer Nature, Oct. 2023, pp. 497–507. https://doi.org/10.48550/arXiv.2305.19920
S. Amirian, L. A. Carlson, M. F. Gong, I. Lohse, K. R. Weiss, J. F. Plate, and A. P. Tafti, "Explainable AI in orthopedics: challenges, opportunities, and prospects," in Proc. 2023 Congress in Computer Science, Computer Engineering, & Applied Computing (CSCE), Jul. 2023, pp. 1374–1380. https://doi.org/10.1109/CSCE60160.2023.00230
Y. X. Teoh, A. Othmani, S. L. Goh, J. Usman, and K. W. Lai, "Deciphering knee osteoarthritis diagnostic features with explainable artificial intelligence: A systematic review," IEEE Access, Aug. 5, 2024. https://doi.org/10.1109/access.2024.3439096
S. K. Egereonu, N. Ekedebe, A. I. Otuonye, C. Etus, E. C. Amadi, and U. U. Egereonu, "Development of an expert system for diagnosing musculoskeletal disease," Int. J. Intell. Inf. Syst., vol. 13, no. 4, pp. 78–93, Sep. 2024. https://doi.org/10.11648/j.ijiis.20241304.12
