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

TL;DR

This study developed and evaluated machine learning models, especially LSTM with transfer learning, to predict failure of high-flow nasal cannula therapy in pediatric ICU patients using retrospective EMR data, achieving promising early prediction accuracy.

Contribution

The paper introduces a novel LSTM-based predictive model with transfer learning and input data perseveration for early detection of HFNC failure in critically ill children.

Findings

LSTM models outperformed logistic regression in predicting HFNC failure.

Best LSTM model achieved an AUROC of 0.78 two hours after HFNC initiation.

Models can predict HFNC failure within 24 hours, aiding timely clinical decisions.

Abstract

High Flow Nasal Cannula (HFNC) provides non-invasive respiratory support for critically ill children who may tolerate it more readily than other Non-Invasive (NIV) techniques. Timely prediction of HFNC failure can provide an indication for increasing respiratory support. This work developed and compared machine learning models to predict HFNC failure. A retrospective study was conducted using EMR of patients admitted to a tertiary pediatric ICU from January 2010 to February 2020. A Long Short-Term Memory (LSTM) model was trained to generate a continuous prediction of HFNC failure. Performance was assessed using the area under the receiver operating curve (AUROC) at various times following HFNC initiation. The sensitivity, specificity, positive and negative predictive values (PPV, NPV) of predictions at two hours after HFNC initiation were also evaluated. These metrics were also computed in a cohort with primarily respiratory diagnoses. 834 HFNC trials [455 training, 173 validation, 206 test] met the inclusion criteria, of which 175 [103, 30, 42] (21.0%) escalated to NIV or intubation. 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. Machine learning models trained using EMR data were able to identify children at risk for failing HFNC within 24 hours of initiation. LSTM models that incorporated transfer learning, input data perseveration and ensembling showed improved performance than the LR and standard LSTM models.