SHENG-NAN CHANGHu, Nian-ZeNian-ZeHuWu, Jo-HsuanJo-HsuanWuCheng, Hsun-MaoHsun-MaoChengCaffrey, James LJames LCaffreyHSI-YU YUYIH-SHARNG CHENHsu, JiunJiunHsuJOU-WEI LIN2023-10-192023-10-192023-09-1509492321https://pubmed.ncbi.nlm.nih.gov/37715216/https://scholars.lib.ntu.edu.tw/handle/123456789/636221Background: It is common to support cardiovascular function in critically ill patients with extracorporeal membrane oxygenation (ECMO). The purpose of this study was to identify patients receiving ECMO with a considerable risk of dying in hospital using machine learning algorithms. Methods: A total of 1342 adult patients on ECMO support were randomly assigned to the training and test groups. The discriminatory power (DP) for predicting in-hospital mortality was tested using both random forest (RF) and logistic regression (LR) algorithms. Results: Urine output on the first day of ECMO implantation was found to be one of the most predictive features that were related to in-hospital death in both RF and LR models. For those with oliguria, the hazard ratio for 1 year mortality was 1.445 (p < 0.001, 95% CI 1.265-1.650). Conclusions: Oliguria within the first 24 h was deemed especially significant in differentiating in-hospital death and 1 year mortality.enExtracorporeal membrane oxygenationMachine learning algorithmOliguriaRandom forestjournal article10.1186/s40001-023-01294-1377152162-s2.0-85171357298https://api.elsevier.com/content/abstract/scopus_id/85171357298