Improvement in the Prediction of Ventilator Weaning Outcomes by an Artificial Neural Network in a Medical ICU
| العنوان: | Improvement in the Prediction of Ventilator Weaning Outcomes by an Artificial Neural Network in a Medical ICU |
|---|---|
| المؤلفون: | Chih Cheng Chang, Hung Wen Chiu, Tzu Tao Chen, Mauo Ying Bien, Hung Ju Kuo, Chun Nin Lee |
| المصدر: | Respiratory Care. 60:1560-1569 |
| بيانات النشر: | Daedalus Enterprises, 2015. |
| سنة النشر: | 2015 |
| مصطلحات موضوعية: | Male, Pulmonary and Respiratory Medicine, Respiratory rate, medicine.medical_treatment, Pressure support ventilation, Airway Extubation, Critical Care and Intensive Care Medicine, Models, Biological, Spontaneous breathing trial, Random Allocation, Predictive Value of Tests, Humans, Medicine, Intubation, Lung, Aged, Aged, 80 and over, Mechanical ventilation, Receiver operating characteristic, business.industry, Respiration, General Medicine, Middle Aged, Respiration, Artificial, Respiratory Function Tests, Intensive Care Units, ROC Curve, Anesthesia, Rapid shallow breathing index, Female, Neural Networks, Computer, business, Ventilator Weaning, Forecasting |
| الوصف: | Twenty-five to 40% of patients pass a spontaneous breathing trial (SBT) but fail to wean from mechanical ventilation. There is no single appropriate and convenient predictor or method that can help clinicians to accurately predict weaning outcomes. This study designed an artificial neural network (ANN) model for predicting successful extubation in mechanically ventilated patients.Ready-to-wean subjects (N = 121) hospitalized in medical ICUs were recruited and randomly divided into training (n = 76) and test (n = 45) sets. Eight variables consisting of age, reasons for intubation, duration of mechanical ventilation, Acute Physiology and Chronic Health Evaluation II score, mean inspiratory and expiratory times, mean breathing frequency, and mean expiratory tidal volume in a 30-min SBT (pressure support ventilation of 5 cm H2O and PEEP of 5 cm H2O) were selected as the ANN input variables. The prediction performance of the ANN model was compared with the rapid shallow breathing index (RSBI), maximum inspiratory pressure, RSBI at 1 min (RSBI1) and 30 min (RSBI30) in an SBT, and absolute percentage change in RSBI from 1 to 30 min in an SBT (ΔRSBI30) using a confusion matrix and receiver operating characteristic curves.The area under the receiver operating characteristic curves in the test set of the ANN model was 0.83 (95% CI 0.69-0.92, P.001), which is better than any one of the following predictors: 0.66 (95% CI 0.50-0.80, P = .04) for RSBI, 0.52 (95% CI 0.37-0.67, P = .86) for maximum inspiratory pressure, 0.53 (95% CI 0.37-0.68, P = .79) for RSBI1, 0.60 (95% CI 0.44-0.74, P = .34) for RSBI30, and 0.51 (95% CI 0.36-0.66, P = .91) for ΔRSBI30. Predicting successful extubation based on the ANN model of the test set had a sensitivity of 82%, a specificity of 73%, and an accuracy rate of 80%, with an optimal threshold of ≥ 0.5 selected from the training set.The ANN model improved the accuracy of predicting successful extubation. By applying it clinically, clinicians can select the earliest appropriate weaning time. |
| تدمد: | 1943-3654 0020-1324 |
| DOI: | 10.4187/respcare.03648 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6421189c6ae5d649bf306acb64b36ab4 https://doi.org/10.4187/respcare.03648 |
| Rights: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....6421189c6ae5d649bf306acb64b36ab4 |
| قاعدة البيانات: | OpenAIRE |
كن أول من يترك تعليقا!