Impact analysis and predictive modeling in emergency care： Evaluating the effects of immediately post-COVID-19 lockdown at a top Chinese teaching hospital

Background Coronavirus disease of 2019 (COVID-19) has caused a global pandemic. Emergency department (ED) suffered a significant impact due to COVID-19 spread after policy adjustments at the end of 2022 in China. Methods This study analyzed the impact of post-COVID-19 lock-down on ED visits and critically ill patients at Peking University People's Hospital from December 2022 to January 2023. Machine learning was employed to identify key predictors of mortality in critically ill ED patients. A Graphical User Interface (GUI) was developed to estimate the prognostic predictors. Results We have observed a significant rise in ED visits and admissions of critical patient, particularly with COVID-19 pneumonia. A total of 25413 patients visited ED, of who 631 patients were critically ill. Our analysis of 581 critical patients revealed distinct clinical and demographic characteristics like hypertension and diabetes, with a notable prevalence of complications such as acute respiratory distress syndrome, acute kidney injury and respiratory failure. We further studied the variables with high contribution to model prediction to observe the characteristic differences between the variables in the non-survival group and the survival group. Age, hypoxic state and ventilator support, white blood cell, platelets, and coagulation indicators were identified as key risk factors for mortality using a Random Forest model. The study's predictive model demonstrated high accuracy, with its area under the receiver-operator curve as 0·8385, which incorporated into a user-friendly GUI for clinical application and could enhance the management of critical COVID-19 cases in emergency settings. Conclusion The pandemic spread rapidly in China after the quarantine was lifted. The predictive score and GUI for estimating prognostic risk factors in ED critical patients can be used to aid in the proper treatment and optimizing medical resources.