Dataset Information

Interpretable recurrent neural network models for dynamic prediction of the extubation failure risk in patients with invasive mechanical ventilation in the intensive care unit.

ABSTRACT:

Background

Clinical decision of extubation is a challenge in the treatment of patient with invasive mechanical ventilation (IMV), since existing extubation protocols are not capable of precisely predicting extubation failure (EF). This study aims to develop and validate interpretable recurrent neural network (RNN) models for dynamically predicting EF risk.

Methods

A retrospective cohort study was conducted on IMV patients from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Time series with a 4-h resolution were built for all included patients. Two types of RNN models, the long short-term memory (LSTM) and the gated recurrent unit (GRU), were developed. A stepwise logistic regression model was used to select key features for developing light-version RNN models. The RNN models were compared to other five non-temporal machine learning models. The Shapley additive explanations (SHAP) value was applied to explain the influence of the features on model prediction.

Results

Of 8,599 included patients, 2,609 had EF (30.3%). The area under receiver operating characteristic curve (AUROC) of LSTM and GRU showed no statistical difference on the test set (0.828 vs. 0.829). The light-version RNN models based on the 26 features selected out of a total of 89 features showed comparable performance as their corresponding full-version models. Among the non-temporal models, only the random forest (RF) (AUROC: 0.820) and the extreme gradient boosting (XGB) model (AUROC: 0.823) were comparable to the RNN models, but their calibration was deviated.

Conclusions

The RNN models have excellent predictive performance for predicting EF risk and have potential to become real-time assistant decision-making systems for extubation.

SUBMITTER: Zeng Z

PROVIDER: S-EPMC9513908 | biostudies-literature | 2022 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Interpretable recurrent neural network models for dynamic prediction of the extubation failure risk in patients with invasive mechanical ventilation in the intensive care unit.

Zeng Zhixuan Z Tang Xianming X Liu Yang Y He Zhengkun Z Gong Xun X

BioData mining 20220927 1

<h4>Background</h4>Clinical decision of extubation is a challenge in the treatment of patient with invasive mechanical ventilation (IMV), since existing extubation protocols are not capable of precisely predicting extubation failure (EF). This study aims to develop and validate interpretable recurrent neural network (RNN) models for dynamically predicting EF risk.<h4>Methods</h4>A retrospective cohort study was conducted on IMV patients from the Medical Information Mart for Intensive Care IV (MI ...[more]

PMID: 36163063

Similar Datasets

Project description:BackgroundThis study aimed to develop prognostic models for predicting the need for invasive mechanical ventilation (IMV) in intensive care unit (ICU) patients with COVID-19 and compare their performance with the Respiratory rate-OXygenation (ROX) index.MethodsA retrospective cohort study was conducted using data collected between March 2020 and August 2021 at three hospitals in Rio de Janeiro, Brazil. ICU patients aged 18 years and older with a diagnosis of COVID-19 were screened. The exclusion criteria were patients who received IMV within the first 24 h of ICU admission, pregnancy, clinical decision for minimal end-of-life care and missing primary outcome data. Clinical and laboratory variables were collected. Multiple logistic regression analysis was performed to select predictor variables. Models were based on the lowest Akaike Information Criteria (AIC) and lowest AIC with significant p values. Assessment of predictive performance was done for discrimination and calibration. Areas under the curves (AUC)s were compared using DeLong's algorithm. Models were validated externally using an international database.ResultsOf 656 patients screened, 346 patients were included; 155 required IMV (44.8%), 191 did not (55.2%), and 207 patients were male (59.8%). According to the lowest AIC, arterial hypertension, diabetes mellitus, obesity, Sequential Organ Failure Assessment (SOFA) score, heart rate, respiratory rate, peripheral oxygen saturation (SpO2), temperature, respiratory effort signals, and leukocytes were identified as predictors of IMV at hospital admission. According to AIC with significant p values, SOFA score, SpO2, and respiratory effort signals were the best predictors of IMV; odds ratios (95% confidence interval): 1.46 (1.07-2.05), 0.81 (0.72-0.90), 9.13 (3.29-28.67), respectively. The ROX index at admission was lower in the IMV group than in the non-IMV group (7.3 [5.2-9.8] versus 9.6 [6.8-12.9], p < 0.001, respectively). In the external validation population, the area under the curve (AUC) of the ROX index was 0.683 (accuracy 63%), the AIC model showed an AUC of 0.703 (accuracy 69%), and the lowest AIC model with significant p values had an AUC of 0.725 (accuracy 79%).ConclusionsIn the development population of ICU patients with COVID-19, SOFA score, SpO2, and respiratory effort signals predicted the need for IMV better than the ROX index. In the external validation population, although the AUCs did not differ significantly, the accuracy was higher when using SOFA score, SpO2, and respiratory effort signals compared to the ROX index. This suggests that these variables may be more useful in predicting the need for IMV in ICU patients with COVID-19.ClinicaltrialsGov identifierNCT05663528.

Project description:RationaleAcute respiratory failure is a life-threatening clinical outcome in critically ill pediatric patients. In severe cases, patients can require mechanical ventilation (MV) for survival. Early recognition of these patients can potentially help clinicians alter the clinical course and lead to improved outcomes.ObjectivesTo build a data-driven model for early prediction of the need for mechanical ventilation in pediatric intensive care unit (PICU) patients.MethodsThe study consists of a single-center retrospective observational study on a cohort of 13,651 PICU patients admitted between 1/01/2010 and 5/15/2018 with a prevalence of 8.06% for MV due to respiratory failure. XGBoost (extreme gradient boosting) and a convolutional neural network (CNN) using medication history were used to develop a prediction model that could yield a time-varying "risk-score"-a continuous probability of whether a patient will receive MV-and an ideal global threshold was calculated from the receiver operating characteristics (ROC) curve. The early prediction point (EPP) was the first time the risk-score surpassed the optimal threshold, and the interval between the EPP and the start of the MV was the early warning period (EWT). Spectral clustering identified patient groups based on risk-score trajectories after EPP.ResultsA clinical and medication history-based model achieved a 0.89 area under the ROC curve (AUROC), 0.6 sensitivity, 0.95 specificity, 0.55 positive predictive value (PPV), and 0.95 negative predictive value (NPV). Early warning time (EWT) median [inter-quartile range] of this model was 9.9[4.2-69.2] hours. Clustering risk-score trajectories within a six-hour window after the early prediction point (EPP) established three patient groups, with the highest risk group's PPV being 0.92.ConclusionsThis study uses a unique method to extract and apply medication history information, such as time-varying variables, to identify patients who may need mechanical ventilation for respiratory failure and provide an early warning period to avert it.

Project description:ImportanceIn adults in whom weaning from invasive mechanical ventilation is difficult, noninvasive ventilation may facilitate early liberation, but there is uncertainty about its effectiveness in a general intensive care patient population.ObjectiveTo investigate among patients with difficulty weaning the effects of protocolized weaning with early extubation to noninvasive ventilation on time to liberation from ventilation compared with protocolized invasive weaning.Design, setting, and participantsRandomized, allocation-concealed, open-label, multicenter clinical trial enrolling patients between March 2013 and October 2016 from 41 intensive care units in the UK National Health Service. Follow-up continued until April 2017. Adults who received invasive mechanical ventilation for more than 48 hours and in whom a spontaneous breathing trial failed were enrolled.InterventionsPatients were randomized to receive either protocolized weaning via early extubation to noninvasive ventilation (n = 182) or protocolized standard weaning (continued invasive ventilation until successful spontaneous breathing trial, followed by extubation) (n = 182).Main outcomes and measuresPrimary outcome was time from randomization to successful liberation from all forms of mechanical ventilation among survivors, measured in days, with the minimal clinically important difference defined as 1 day. Secondary outcomes were duration of invasive and total ventilation (days), reintubation or tracheostomy rates, and survival.ResultsAmong 364 randomized patients (mean age, 63.1 [SD, 14.8] years; 50.5% male), 319 were evaluable for the primary effectiveness outcome (41 died before liberation, 2 withdrew, and 2 were discharged with ongoing ventilation). The median time to liberation was 4.3 days in the noninvasive group vs 4.5 days in the invasive group (adjusted hazard ratio, 1.1; 95% CI, 0.89-1.40). Competing risk analysis accounting for deaths had a similar result (adjusted hazard ratio, 1.1; 95% CI, 0.86-1.34). The noninvasive group received less invasive ventilation (median, 1 day vs 4 days; incidence rate ratio, 0.6; 95% CI, 0.47-0.87) and fewer total ventilator days (median, 3 days vs 4 days; incidence rate ratio, 0.8; 95% CI, 0.62-1.0). There was no significant difference in reintubation, tracheostomy rates, or survival. Adverse events occurred in 45 patients (24.7%) in the noninvasive group compared with 47 (25.8%) in the invasive group.Conclusions and relevanceAmong patients requiring mechanical ventilation in whom a spontaneous breathing trial had failed, early extubation to noninvasive ventilation did not shorten time to liberation from any ventilation.Trial registrationISRCTN Identifier: ISRCTN15635197.

Dataset Information

Interpretable recurrent neural network models for dynamic prediction of the extubation failure risk in patients with invasive mechanical ventilation in the intensive care unit.

Background

Methods

Results

Conclusions

Publications

Interpretable recurrent neural network models for dynamic prediction of the extubation failure risk in patients with invasive mechanical ventilation in the intensive care unit.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets