Abstract
Background: Modeling with methods based on machine learning and artificial intelligence can help to understand the complex relationships between ergonomic risk factors and employee health. The aim of this study is to use machine learning methods in estimating the effect of individual factors, ergonomic interventions, quality of work life and productivity on work related musculoskeletal disorders (WMSDs) in the neck area in office workers.
Study design: A quasi-randomized control trial.
Methods: To measure the impact of interventions, modeling with machine learning method has been done on the data of a quasi-randomized control trial. The data included the information of 311 office workers (age 32.04 ±5.34). To measure the effect of factors affecting WMSDs, method neighborhood component analysis was used, and then support vector machines and decision tree algorithm were used to classify the decrease or increase of disorders.
Results: Three classified models were designed according to the follow-up times of the field study with accuracies of 86.5%, 80.3%, and 69%, respectively. These models were able to estimate most influencer factors with acceptable sensitivity. The main factors include; Age, BMI, interventions, quality of work life some subscales and several psychological factors. Models predicted that relative absenteeism and presenteeism were not related to the outputs.
Conclusions: In this study, focus was on disorders in the neck, and the obtained models showed that individual and management interventions can be the main factor in reducing WMSDs in the neck. Modeling with machine learning methods can create a new understanding of the relationships between variables affecting WMSDs.