Work-related musculoskeletal Disorders (WMSDs) are the most significant challenges in both developing and developed countries, affecting the majority of individuals throughout their lives. Considering the detrimental effects of musculoskeletal disorders on the productivity and general health of employees, this research utilizes the Cornell Musculoskeletal Disorder Questionnaire (CMDQ) to develop an intelligent model for assessing and predicting the levels of musculoskeletal disorders.

In this descriptive-analytical study, 810 employees from five organizations (in four occupational categories, including administrative, technical, production, and services) completed the CMDQ voluntarily. After collecting the questionnaire and performing relevant statistical analyses, data normalization and clustering based on the K-Means method were used to determine levels of musculoskeletal disorders. Finally, the multilayer perceptron artificial neural network was trained to predict the levels of musculoskeletal disorders; moreover,  the criteria of precision, accuracy, recall, and F1-score were used to evaluate the proposed model.

The performance of the proposed model in predicting the levels of musculoskeletal disorders is presented in two scenarios (use and non-use of the Synthetic Minority Oversampling Technique (SMOTE) method) based on the evaluation criteria provided. The accuracy, precision, recall, and F1-score values were 0.724, 0.709, 0.756, and 0.720, respectively. The appropriate accuracy and precision in the proposed model indicate its capability to identify the levels of musculoskeletal disorders in individuals and help healthcare professionals take necessary measures to prevent and predict them.

This study employs the CMDQ questionnaire and artificial intelligence to analyze musculoskeletal disorders in the workplace. The proposed model demonstrates significant accuracy and precision compared to similar studies. The results indicate that this model can be utilized to identify and predict musculoskeletal disorders in organizational employees, offering the potential to expedite the identification process and reduce costs.