Background: Work-related musculoskeletal disorders (WRMSDs) remain a major cause of occupational disability and productivity loss worldwide. Traditional statistical methods have identified numerous associated factors; however, they often struggle to capture complex non-linear relationships and interactions across multiple domains of risk. Machine learning (ML) offers an alternative analytical approach for modelling such multidimensional relationships. Methods: Following the PRISMA 2020 guidelines (PROSPERO: CRD420250605234), literature searches were conducted in Web of Science, Scopus, and PubMed for studies published between 2020 and 2025. Eligible studies applied ML methods to identify factors associated with WRMSDs using cross-sectional study designs. Included studies were appraised using the Joanna Briggs Institute Critical Appraisal Checklist for analytical cross-sectional studies. Results: Ten studies met the inclusion criteria, representing workers from healthcare, transport, manufacturing, and service sectors across Asia, Africa, and Europe. Frequently applied ML algorithms included random forest, support vector machine, and artificial neural networks, demonstrating strong internal discriminative performance (area under the receiver operating characteristic curve: 0.80–0.99), although the absence of external validation in several studies suggests a potential risk of overfitting. Commonly identified factors included age, sex, awkward posture, vibration exposure, prolonged working hours, stress, and burnout. Psychosocial factors, including post-traumatic stress disorder, job stress, and depression, were ranked among the most influential predictors within ML models. Conclusions ML models demonstrate strong capability in discriminating WRMSDs risk and identifying multidimensional risk factors compared with traditional statistical approaches. These models highlight complex interrelationships between ergonomic and psychosocial exposures. Future research should incorporate external validation, objective exposure measurements, and standardized ML reporting frameworks to enhance methodological transparency and generalizability.

Purpose::To investigate the orthopedic injuries sustained while driving and using social media on cellular phones from an orthopedic resident's perspective.Methods::A total of 118 patients who presented with a history of road traffic accident secondary to social media usage and suffered from fractures were included in this cross-sectional study. These patients were reported from October 2018 to April 2019. We collected the data including the type of collision, type of social media usage during driving, location of injury, wearing of safety equipment's such as helmet and seat belt during driving.Results::The mean age of patients was (34.86 ± 12.73) (range 15-71) years. The common types of accident on the basis of collision of vehicles were: car versus motorbike 45 (38.1%), motorbike versus motorbike 28 (23.7%), and motorbike versus pedestrian 22 (18.6%). Most of the accidents (61, 51.7%) occurred due to mistake of motor-bikers. Out of them, 44 (37.3%) occurred on traffic signals, followed by 29 (24.6%) while driving on main roads. The common timing of accident was normal hours with frequency of 44 (37.3%), followed by 39 (33.1%) at late night. According to fracture type, closed injuries were 98 (83.1%) and open fractures were 20 (16.9%). The most common fracture was clavicular fracture (21, 22.5%) followed by soft tissue injury in 19 (16.1%) patients. The most common social media application usage during driving was Facebook 43 (36.4%), followed by Whatsapp 24 (20.3%), Google 19 (16.1%), and Instagram 15 (12.7%).Conclusion::This study provides evidence that social media usage while driving put the drivers and other road users' lives at high risk. The most common social media addiction while driving is Facebook and Whatsapp. So there is a need to make strict rules and penalties for using cell phone during driving so as to save the lives of drivers and other people using road.