English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

High Flow Nasal Cannula (HFNC) provides non-invasive respiratory support forcritically ill children who may tolerate it more readily than otherNon-Invasive (NIV) techniques. Timely prediction of HFNC failure can provide anindication for increasing respiratory support. This work developed and comparedmachine learning models to predict HFNC failure. A retrospective study wasconducted using EMR of patients admitted to a tertiary pediatric ICU fromJanuary 2010 to February 2020. A Long Short-Term Memory (LSTM) model wastrained to generate a continuous prediction of HFNC failure. Performance wasassessed using the area under the receiver operating curve (AUROC) at varioustimes following HFNC initiation. The sensitivity, specificity, positive andnegative predictive values (PPV, NPV) of predictions at two hours after HFNCinitiation were also evaluated. These metrics were also computed in a cohortwith primarily respiratory diagnoses. 834 HFNC trials [455 training, 173validation, 206 test] met the inclusion criteria, of which 175 [103, 30, 42](21.0%) escalated to NIV or intubation. The LSTM models trained with transferlearning generally performed better than the LR models, with the best LSTMmodel achieving an AUROC of 0.78, vs 0.66 for the LR, two hours afterinitiation. Machine learning models trained using EMR data were able toidentify children at risk for failing HFNC within 24 hours of initiation. LSTMmodels that incorporated transfer learning, input data perseveration andensembling showed improved performance than the LR and standard LSTM models.

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