Fig. 1: Machine learning (ML) models achieve high-performance in adjudicating the presence of bilateral infiltrates from chest imaging reports. | Nature Communications

Fig. 1: Machine learning (ML) models achieve high-performance in adjudicating the presence of bilateral infiltrates from chest imaging reports.

From: Open-source computational pipeline flags instances of acute respiratory distress syndrome in mechanically ventilated adult patients

Fig. 1

Error bars and bands show 95% confidence intervals for estimates of the mean obtained using bootstrapping (n = 10). a Receiver operating characteristic (ROC) curve for the eXtreme Gradient Boosting (XGBoost) model trained on chest imaging reports from the development set. b Bootstrapped mean area under the ROC (AUROC) shows that all four ML approaches yield accuracies greater or equal to 0.85. c Feature importances for the four different ML approaches considered. Features in bold are highly ranked in importance in all 4 approaches.

Back to article page