Identification of gender differences in the factors influencing shoulders, neck and upper limb MSD by means of multivariate adaptive regression splines (MARS)

Abstract In the present research, models based on multivariate adaptive regression splines (MARS) are proposed to study the influence of gender in the factors affecting the development of shoulders, neck and upper limb MSD. Two different MARS models, corresponding to men and women, are constructed to identify variables with the strongest effect on the target MSD. Both models are capable to predict successfully the occurrence of the studied disorders. Men seem to be more vulnerable to physical risk factors and some other working conditions, whereas women appear to be more affected by psychosocial risk factors and activities carried out outside their working hours. According to the results, gender needs to be considered to ensure the success and effectiveness of ergonomic interventions on the whole working population.