This study, conducted by Wang et al., examines the potential use of machine learning models for predicting factors associated with depression and anxiety in healthcare workers (HCWs) during ominous health crises, such as pandemics. 349 HCWs from a Tertiary Grade-A hospital in Shenyang, Liaoning province, China participated in this study, and depression and anxiety were measured using the PHQ-9 and GAD-7, respectively. Influencing factors were assessed at three levels - individual, interpersonal, and institutional. Data were fed into a random forest classifier, and the predictive ability of the model was assessed. For depression, the AUC, sensitivity (true positive), and specificity (true negative) scores for prediction were 0.88, 0.84, and 0.83, respectively, while for anxiety, the AUC, sensitivity, and specificity scores for prediction were 0.72, 0.88, and 0.51. The top 3 predictors for depression among HCWs were burnout, resilience, and emotional labor, and the top 3 predictors for anxiety were burnout, adaptability, and emotional labor. From the results, factors from the individual, interpersonal, and institutional levels were shown to all be significantly associated with depression and anxiety, and contrary to previous studies, the status of an HCW as a frontline worker did not significantly impact prediction results.