Ergonomic design for optimizing work-related strains and enhancing patient safety in the healthcare environment

Abstract

Background

Work-related musculoskeletal disorders (MSDs) pose a significant occupational health challenge for healthcare professionals, affecting both workforce efficiency and patient safety. The physical demands of healthcare roles, particularly post-COVID-19, have increased strain on workers, necessitating advanced ergonomic solutions. Traditional ergonomic assessment methods often fail to provide comprehensive, data-driven insights, highlighting the need for a more integrated approach.

Objective

This study aims to develop a novel Data Envelopment Analysis (DEA) and Random Forest (RF) modeling framework to enhance ergonomic risk assessment in healthcare environments. By integrating DEA's efficiency evaluation with RF's predictive modeling, the proposed methodology seeks to provide a more precise, scalable, and data-driven solution for optimizing ergonomic design and improving patient safety.

Methods

The DEA-RF framework systematically evaluates ergonomic effectiveness using DEA, while RF enhances prediction accuracy, enabling proactive risk mitigation. The model was tested on real-world ergonomic data, and its performance was assessed based on accuracy, precision, recall, F-measure, error rate, and computational efficiency.

Results

The model demonstrated superior performance, achieving 98.96% accuracy, 99.27% precision, 98.87% recall, and a 98.82% F-measure, with a low error rate of 1.07% and computational efficiency of 2.2 s. These findings validate the reliability and real-world applicability of the proposed framework in reducing MSD risks and improving patient safety.

Conclusions

The study presents a scalable and adaptable evidence-based ergonomic assessment approach for healthcare administrators, facility designers, and policymakers. By integrating efficiency evaluation with predictive analytics, the DEA-RF framework advances ergonomic assessment methodologies, setting a foundation for future intelligent, data-driven occupational health strategies.