A continuous demand for assistance and an overcrowded emergency department (ED) require early and safe discharge of low-risk severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-infected patients. We developed (n = 128) and validated (n = 330) the acute PNeumonia early assessment (aPNea) score in a tertiary hospital and preliminarily tested the score on an external secondary hospital (n = 97). The score’s performance was compared to that of the National Early Warning Score 2 (NEWS2). The composite outcome of either death or oral intubation within 30 days from admission occurred in 101 and 28 patients in the two hospitals, respectively. The area under the receiver operating characteristic (AUROC) curve of the aPNea model was 0.86 (95% confidence interval (CI), 0.78–0.93) and 0.79 (95% CI, 0.73–0.89) for the development and validation cohorts, respectively. The aPNea score discriminated low-risk patients better than NEWS2 at a 10% outcome probability, corresponding to five cut-off points and one cut-off point, respectively. aPNea’s cut-off reduced the number of unnecessary hospitalizations without missing outcomes by 27% (95% CI, 9–41) in the validation cohort. NEWS2 was not significant. In the external cohort, aPNea’s cut-off had 93% sensitivity (95% CI, 83–102) and a 94% negative predictive value (95% CI, 87–102). In conclusion, the aPNea score appears to be appropriate for discharging low-risk SARS-CoV-2-infected patients from the ED.

Background and aim: There is a need to determine which clinical variables predict the severity of COVID-19. We analyzed a series of critically ill COVID-19 patients to see if any of our dataset's clinical variables were associated with patient outcomes. Methods: We retrospectively analyzed the data of COVID-19 patients admitted to the ICU of the Hospital in Pordenone from March 11, 2020, to April 17, 2020. Patients' characteristics of survivors and deceased groups were compared. The variables with a different distribution between the two groups were implemented in a generalized linear regression model (LM) and in an Artificial Neural Network (NN) model to verify the "robustness" of the association with mortality. Results: In the considered period, we reviewed the data of 22 consecutive patients: 8 died. The causes of death were a severe respiratory failure (3), multi-organ failure (1), septic shock (1), pulmonary thromboembolism (2), severe hemorrhage (1). Lymphocyte and the platelet count were significantly lower in the group of deceased patients (p-value 0.043 and 0.020, respectively; cut-off values: 660/mm3; 280,000/mm3, respectively). Prothrombin time showed a statistically significant trend (p-value= 0.065; cut-off point: 16.8/sec). The LM model (AIC= 19.032), compared to the NN model (Mean Absolute Error, MAE = 0.02), was substantially alike (MSE 0.159 vs. 0.136). Conclusions: In the context of critically ill COVID-19 patients admitted to ICU, lymphocytopenia, thrombocytopenia, and lengthening of prothrombin time were strictly correlated with higher mortality. Additional clinical data are needed to be able to validate this prognostic score.