Dataset Information

Predicting weaning difficulty for planned extubation patients with an artificial neural network.

ABSTRACT: This study aims to construct a neural network to predict weaning difficulty among planned extubation patients in intensive care units.This observational cohort study was conducted in eight adult ICUs in a medical center about adult patients experiencing planned extubation.The data of 3602 patients with planned extubation in ICUs of Chi-Mei Medical Center (from Dec. 2009 through Dec. 2011) was used to train and test an artificial neural network (ANN) model. The input features contain 47 clinical risk factors and the outputs are classified into three categories: simple, difficult, and prolonged weaning. A deep ANN model with four hidden layers of 30 neurons each was developed. The accuracy is 0.769 and the area under receiver operating characteristic curve for simple weaning, prolonged weaning, and difficult weaning are 0.910, 0.849, and 0.942 respectively.The results revealed that the ANN model achieved a good performance in prediction the weaning difficulty in planned extubation patients. Such a model will be helpful for predicting ICU patients' successful planned extubation.

SUBMITTER: Hsieh MH

PROVIDER: S-EPMC6783239 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting weaning difficulty for planned extubation patients with an artificial neural network.

Hsieh Meng Hsuen MH Hsieh Meng Ju MJ Cheng Ai-Chin AC Chen Chin-Ming CM Hsieh Chia-Chang CC Chao Chien-Ming CM Lai Chih-Cheng CC Cheng Kuo-Chen KC Chou Willy W

Medicine 20191001 40

This study aims to construct a neural network to predict weaning difficulty among planned extubation patients in intensive care units.This observational cohort study was conducted in eight adult ICUs in a medical center about adult patients experiencing planned extubation.The data of 3602 patients with planned extubation in ICUs of Chi-Mei Medical Center (from Dec. 2009 through Dec. 2011) was used to train and test an artificial neural network (ANN) model. The input features contain 47 clinical ...[more]

PMID: 31577746

Similar Datasets

Project description:BackgroundExtubation failure is common in critically ill patients, especially those with high-risk factors, and is associated with poor prognosis. Prophylactic use of oxygen therapy after extubation has been gradually introduced. However, the best respiratory support method is still unclear.PurposeThis study aimed to evaluate the efficacy of four post-extubation respiratory support approaches in reducing reintubation and respiratory failure in patients at high-risk of extubation failure.MethodsA comprehensive search was performed in Cochrane Central Register of Controlled Trials, PubMed, EMBASE, and Web of Science from inception to June 2022. Randomized controlled trials (RCTs) comparing post-extubation preventive use of respiratory management strategies, including conventional oxygen therapy (COT), non-invasive ventilation (NIV), and high-flow nasal catheter (HFNC) in high-risk patients with extubation failure were reviewed. Primary outcomes were reintubation rate and respiratory failure. Secondary outcomes included intensive care unit (ICU) mortality, ICU stay and length of hospital stay (LOS).ResultsSeventeen RCTs comprising 2813 participants were enrolled. Compared with COT, the three respiratory support methods (NIV, HFNC, NIV + HFNC) were all effective in preventing reintubation [odds ratio (OR) 0.46, 95% confidence interval (CI) 0.32-0.67; OR 0.26, 95% CI 0.14-0.48; OR 0.62, 95% CI 0.39-0.97, respectively] and respiratory failure (OR 0.23, 95% CI 0.10-0.52; OR 0.15, 95% CI 0.04-0.60; OR 0.26, 95% CI 0.10-0.72, respectively). NIV and NIV + HFNC also reduced ICU mortality (OR 0.40, 95% CI 0.22-0.74; OR 0.32, 95% CI 0.12-0.85). NIV + HFNC ranked best in terms of reintubation rate, respiratory failure and ICU mortality based on the surface under the cumulative ranking curve (SUCRA) (99.3, 87.1, 88.2, respectively). Although there was no significant difference in shortening ICU stay and LOS among the four methods, HFNC ranked first based on the SUCRA.ConclusionPreventive use of NIV + HFNC after scheduled extubation is probably the most effective respiratory support method for preventing reintubation, respiratory failure and ICU death in high-risk patients with extubation failure. HFNC alone seems to be the best method to shorten ICU stay and LOS.Systematic review registration[https://www.crd.york.ac.uk/prospero/], identifier [CRD42022340623].

Dataset Information

Predicting weaning difficulty for planned extubation patients with an artificial neural network.

Publications

Predicting weaning difficulty for planned extubation patients with an artificial neural network.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets