Abstract
BACKGROUND: Noninvasive respiratory support (NRS) is increasingly used to support patients with acute respiratory failure. However, noninvasive support failure may worsen outcomes compared to primary support with invasive mechanical ventilation. Therefore, there is a need to identify patients where NRS is failing so that treatment can be reassessed and adjusted. The objective of this study was to develop and evaluate 3 recurrent neural network (RNN) models to predict NRS failure. METHODS: This was a cross-sectional observational study to evaluate the ability of deep RNN models (long short-term memory [LSTM], gated recurrent unit [GRU]), and GRU with trainable decay) to predict failure of NRS. Data were extracted from electronic health records from all adult (≥ 18 y) patient records requiring any type of oxygen therapy or mechanical ventilation between November 1, 2013-September 30, 2020, across 46 ICUs in the Southwest United States in a single health care network. Input variables for each model included serum chloride, creatinine, albumin, breathing frequency, heart rate, S(pO(2)) , F(IO(2)) , arterial oxygen saturation (S(aO(2)) ), and 2 measurements each (point-of-care and laboratory measurement) of P(aO(2)) and partial pressure of arterial oxygen from an arterial blood gas. RESULTS: Time series data from electronic health records were available for 22,075 subjects. The highest accuracy and area under the receiver operating characteristic curve were for the LSTM model (94.04% and 0.9636, respectively). Accurate predictions were made 12 h after ICU admission, and performance remained high well in advance of NRS failure. CONCLUSIONS: RNN models using routinely collected time series data can accurately predict NRS failure well before intubation. This lead time may provide an opportunity to intervene to optimize patient outcomes.