Predicting High-Flow Nasal Cannula Failure in an ICU Using a Recurrent Neural Network with Transfer Learning and Input Data Perseveration: A Retrospective Analysis

no code implementations • 20 Nov 2021 • George A. Pappy, Melissa D. Aczon, Randall C. Wetzel, David R. Ledbetter

The LSTM models trained with transfer learning generally performed better than the LR models, with the best LSTM model achieving an AUROC of 0. 78, vs 0. 66 for the LR, two hours after initiation.

Specificity Transfer Learning

Interpreting a Recurrent Neural Network's Predictions of ICU Mortality Risk

no code implementations • 23 May 2019 • Long V. Ho, Melissa D. Aczon, David Ledbetter, Randall Wetzel

Deep learning has demonstrated success in many applications; however, their use in healthcare has been limited due to the lack of transparency into how they generate predictions.

Feature Importance ICU Mortality +1