%0 Journal Article
%T Machine Learning from Veno-Venous Extracorporeal Membrane Oxygenation Identifies Factors Associated with Neurological Outcomes.
%A Leng A
%A Shou B
%A Liu O
%A Bachina P
%A Kalra A
%A Bush EL
%A Whitman GJR
%A Cho SM
%J Lung
%V 202
%N 4
%D 2024 Aug 30
%M 38814448
%F 3.777
%R 10.1007/s00408-024-00708-z
%X <B>BACKGROUND: </B>Neurological complications are common in patients receiving veno-venous extracorporeal membrane oxygenation (VV-ECMO) support. We used machine learning (ML) algorithms to identify predictors for neurological outcomes for these patients.<BR><B>METHODS: </B>All demographic, clinical, and circuit-related variables were extracted for adults with VV-ECMO support at a tertiary care center from 2016 to 2022. The primary outcome was good neurological outcome (GNO) at discharge defined as a modified Rankin Scale of 0-3.<BR><B>RESULTS: </B>Of 99 total VV-ECMO patients (median age = 48 years; 65% male), 37% had a GNO. The best performing ML model achieved an area under the receiver operating characteristic curve of 0.87. Feature importance analysis identified down-trending gas/sweep/blender flow, FiO2, and pump speed as the most salient features for predicting GNO.<BR><B>CONCLUSIONS: </B>Utilizing pre- as well as post-initiation variables, ML identified on-ECMO physiologic and pulmonary conditions that best predicted neurological outcomes.