Investigating Psychological Differences Between Nurses and Other Health Care Workers From the Asia-Pacific Region During the Early Phase of COVID-19: Machine Learning Approach (Preprint)

Abstract

BACKGROUND As the pandemic evolves, frontline work challenges continue to impose significant psychological impact on nurses. However, there is a lack of data how nurses fared compared to other healthcare workers in Asia-Pacific region. OBJECTIVE This study aims to investigate 1) psychological differences between nurses, doctor and non-medical healthcare workers, and 2) psychological outcome characteristics of nurses from different Asia-Pacific countries. METHODS Decision-tree type machine learning models (LIghtGBM, Gradientboost, and RandomForest) were adopted to predict psychological impact on nurses. The SHAP (SHapley Additive exPlanations) values of these models were extracted to identify the distinctive psychological distress characteristic. RESULTS Nurses had relatively higher percentages of normal or no-change in psychological distress symptoms relative to other healthcare workers (86.3% - 96.8% vs 80.7% - 92.3%). Among those without psychological symptoms, nurses constituted a higher proportion than doctors and non-medical healthcare workers (40.8%, 25.8%, and 33.4%, respectively). CONCLUSIONS Different contexts, cultures, and points in pandemic curve may have contributed to differing patterns of psychological outcomes amongst nurses in various Asia-Pacific countries. It is important that all healthcare workers practise self-care and render peer support to bolster psychological resilience for effective coping. CLINICALTRIAL Not applicable