Development and Validation of Unplanned Extubation Prediction Models Using Intensive Care Unit Data: Retrospective, Comparative, Machine Learning Study.
Sujeong HurJi Young MinJunsang YooKyunga KimChi Rayng ChungPatricia C DykesWon Chul ChaPublished in: Journal of medical Internet research (2021)
We successfully developed and validated machine learning-based prediction models to predict UE in ICU patients using electronic health record data. The best AUROC was 0.787 and the sensitivity was 0.949, which was obtained using the RF algorithm. The RF model was well-calibrated, and the Brier score and ICI were 0.129 and 0.048, respectively. The proposed prediction model uses widely available variables to limit the additional workload on the clinician. Further, this evaluation suggests that the model holds potential for clinical usefulness.
Keyphrases
- electronic health record
- machine learning
- intensive care unit
- big data
- mechanical ventilation
- clinical decision support
- end stage renal disease
- artificial intelligence
- ejection fraction
- newly diagnosed
- deep learning
- adverse drug
- chronic kidney disease
- cross sectional
- prognostic factors
- peritoneal dialysis
- cardiac surgery
- risk assessment
- respiratory failure
- data analysis
- acute respiratory distress syndrome