The need to make biomechanical-based musculoskeletal disorders (MSDs) predictions arises from the desire to prevent work-related injuries and risks, improve workers’ well-being, and related economic expenses. MSDs prediction models have a significant impact on the early detection and treatments of MSDs that improve overall health, identify risk factors, and leverage them proactively. This literature review aimed to assess the current state of the art on biomechanical-based MSDs prediction and to map the application of sensor-based devices and other recent techniques. Based on the inclusion/exclusion, out of the 183 studies originally retrieved, 14 articles were selected for further analysis. The results of the study show that the most applicable smart wearable sensors are inertial wearable units. The study also found that the majority of the research was conducted in a laboratory setup. Even though, some studies provide possible reasons for lack of research in real occupational environments, a comprehensive future study is required to explain the limitations. Moreover, the study has shown that supervised machine learning (ML) algorithms are commonly used to make predictions based on the output of wearable sensors with an accuracy of more than 90%. Generally, wearable sensors and learning algorithms have made remarkable strides and have promising future applications in real world; however, finer technical details still require improvements.