Development of a predictive model for work-relatedness of MSDs among semiconductor back-end workers

Abstract

Objective. Limited models are available to predict work-relatedness of musculoskeletal disorders (MSDs) among semiconductor back-end workers. This study aims to develop a model to predict the MSDs development among back-end workers. Method. Potential MSD risk factors were extracted from 277 work compensation investigation reports conducted between 2011–2019. Binary logistic regression approach was used to determine significant predictors. Results. Significant predictors (p < 0.05) include poor posture (odds ratio [OR] = 1.822; 95% confidence interval [CI] [1.261, 2.632]), forceful exertion (OR = 1.741; 95% CI [1.281, 2.367]), static posture (OR = 1.796; 95% CI [1.367, 2.378]), lifting and lowering (OR = 1.438; 95% CI [0.966, 1.880]), transferring (OR = 1.533; 95% CI [1.101, 2.136]), pushing and pulling (OR = 0.990; 95% CI [0.744, 1.317]), repairing machines (OR = 0.845; 95% CI 76 [0.616, 1.159]), preventive maintenance (OR = 1.061; 95% CI [0.765, 1.471]) and quality inspection (OR = 0.982; 95% CI [0.729, 1.322]). Confounding factors and employment duration played crucial roles in the model. Cross-validation of predictive model was 86.2%, while face validation among 30 experts was 7.9/10 (SD 1.9). Conclusion. The model allows practitioners to predict potential MSD cases among semiconductor back-end workers and proactively plan appropriate mitigation measures.