An artificial intelligence system to predict the optimal timing for mechanical ventilation weaning for intensive care unit patients: A two-stage prediction approach

Abstract

BackgroundFor the intensivists, accurate assessment of the ideal timing for successful weaning from the mechanical ventilation (MV) in the intensive care unit (ICU) is very challenging.PurposeUsing artificial intelligence (AI) approach to build two-stage predictive models, namely, the try-weaning stage and weaning MV stage to determine the optimal timing of weaning from MV for ICU intubated patients, and implement into practice for assisting clinical decision making.MethodsAI and machine learning (ML) technologies were used to establish the predictive models in the stages. Each stage comprised 11 prediction time points with 11 prediction models. Twenty-five features were used for the first-stage models while 20 features were used for the second-stage models. The optimal models for each time point were selected for further practical implementation in a digital dashboard style. Seven machine learning algorithms including Logistic Regression (LR), Random Forest (RF), Support Vector Machines (SVM), K Nearest Neighbor (KNN), lightGBM, XGBoost, and Multilayer Perception (MLP) were used. The electronic medical records of the intubated ICU patients of Chi Mei Medical Center (CMMC) from 2016 to 2019 were included for modeling. Models with the highest area under the receiver operating characteristic curve (AUC) were regarded as optimal models and used to develop the prediction system accordingly.ResultsA total of 5,873 cases were included in machine learning modeling for Stage 1 with the AUCs of optimal models ranging from 0.843 to 0.953. Further, 4,172 cases were included for Stage 2 with the AUCs of optimal models ranging from 0.889 to 0.944. A prediction system (dashboard) with the optimal models of the two stages was developed and deployed in the ICU setting. Respiratory care members expressed high recognition of the AI dashboard assisting ventilator weaning decisions. Also, the impact analysis of with- and without-AI assistance revealed that our AI models could shorten the patients’ intubation time by 21 hours, besides gaining the benefit of substantial consistency between these two decision-making strategies.ConclusionWe noticed that the two-stage AI prediction models could effectively and precisely predict the optimal timing to wean intubated patients in the ICU from ventilator use. This could reduce patient discomfort, improve medical quality, and lower medical costs. This AI-assisted prediction system is beneficial for clinicians to cope with a high demand for ventilators during the COVID-19 pandemic.

Predicting Successful Weaning from Mechanical Ventilation by Reduction in Positive End-expiratory Pressure Level Using Machine Learning

“…Most related work relies on the data from a single local hospital to define its patient collective [ 11 , 12 , 14 , 18 , 19 ]. The resulting models may be used as a basis to provide local ICU weaning dashboards.…”

“…al. [ 18 ], usually achieves lower scores than directly predicting the full weaning. There is only little work done on multi-stage weaning.…”

“…al. [ 18 ] used 25 features (+5 features) and achieved an slightly higher AUROC of 0.85 for the first stage and for the second stage they achieved an AUROC of 0.90. Similarly, Cheng et.…”

“…al. [ 18 ] described a two-stage weaning prediction algorithm based on XGBoost and other algorithms; first they successfully predict the switch of the ventilator from control to support mode, and from this stage they predict successful weaning. Similarly, Cheng et.…”

The intervention of artificial intelligence to improve the weaning outcomes of patients with mechanical ventilation: Practical applications in the medical intensive care unit and the COVID-19 intensive care unit: A retrospective study

“…We proposed a 2-phase weaning approach for building the predictive models: try-weaning phase and extubation phase (weaning MV). [ 11 ] 25 and 24 input variables were identified for the machine learning model in the try-weaning and extubation phases, respectively. These variables included age, Acute Physiology and Chronic Health Evaluation II (APACHE II) score, Therapeutic Intervention Scoring System (TISS) score, inspired oxygen fraction, positive end-expiratory pressure, respiratory rate, minute ventilation (Mv), peak inspiratory pressure, mean airway pressure, peripheral oxygen saturation, expiratory tidal volume, heart rate, systolic blood pressure, and diastolic blood pressure.…”