Fig. 3

Panel a. Predictive performance (AUC and AUPRC) of our LSTM-based model versus Random Forrest (RF) and Logistic Regression (LR) for the overall patient dataset, including also variables related to kidney and liver function. Panel b. Predictive performance of our LSTM-based model versus Random Forrest (RF) and Logistic Regression (LR) for the subgroup of patients admitted with respiratory disorders, including also variables related to kidney and liver function. Confidence intervals are shown in grey for both panels