Match!

Data Science for Extubation Prediction and Value of Information in Surgical Intensive Care Unit.

Published on Oct 17, 2019in Journal of Clinical Medicine5.688
· DOI :10.3390/JCM8101709
Tsung-Lun Tsai (NCKU: National Cheng Kung University), Min-Hsin Huang (NCKU: National Cheng Kung University)+ 1 AuthorsWu-Wei Lai (NCKU: National Cheng Kung University)
Abstract
Besides the traditional indices such as biochemistry, arterial blood gas, rapid shallow breathing index (RSBI), acute physiology and chronic health evaluation (APACHE) II score, this study suggests a data science framework for extubation prediction in the surgical intensive care unit (SICU) and investigates the value of the information our prediction model provides. A data science framework including variable selection (e.g., multivariate adaptive regression splines, stepwise logistic regression and random forest), prediction models (e.g., support vector machine, boosting logistic regression and backpropagation neural network (BPN)) and decision analysis (e.g., Bayesian method) is proposed to identify the important variables and support the extubation decision. An empirical study of a leading hospital in Taiwan in 2015–2016 is conducted to validate the proposed framework. The results show that APACHE II and white blood cells (WBC) are the two most critical variables, and then the priority sequence is eye opening, heart rate, glucose, sodium and hematocrit. BPN with selected variables shows better prediction performance (sensitivity: 0.830; specificity: 0.890; accuracy 0.860) than that with APACHE II or RSBI. The value of information is further investigated and shows that the expected value of experimentation (EVE), 0.652 days (patient staying in the ICU), is saved when comparing with current clinical experience. Furthermore, the maximal value of information occurs in a failure rate around 7.1% and it reveals the “best applicable condition” of the proposed prediction model. The results validate the decision quality and useful information provided by our predicted model.
  • References (27)
  • Citations (0)
📖 Papers frequently viewed together
2009
2 Citations
78% of Scinapse members use related papers. After signing in, all features are FREE.
References27
Newest
#1Sonja Suntrup-Krueger (WWU: University of Münster)H-Index: 7
#2Sarah Schmidt (WWU: University of Münster)H-Index: 1
Last. Rainer Dziewas (WWU: University of Münster)H-Index: 35
view all 9 authors...
Background and Purpose— Predicting safe extubation represents a clinical challenge in acute stroke patients. Classical respiratory weaning criteria have not proven reliable. Concerning the paramoun...
4 CitationsSource
#2Antonella CotoiaH-Index: 6
Last. Janneke HornH-Index: 35
view all 6 authors...
INTRODUCTION: Extubation failure (EF) refers to the inability to maintain spontaneous breathing after removal of endotracheal tube. The aim of this review is to identify the best parameter to predict EF in adult intensive care patients. EVIDENCE ACQUISITION: We searched for publications in PubMed (2000-2016). Studies of patients intubated and mechanically ventilated for more than 24 hours were included and divided in groups basing on the extubation method. 2x2 tables were performed to evaluate t...
Source
#1Chia-Yen Lee (NCKU: National Cheng Kung University)H-Index: 12
#2Tsung Lun Tsai (NCKU: National Cheng Kung University)H-Index: 2
Abstract TFT-LCD panel manufacturers rely on experimental design and engineering experience for process monitoring and quality control throughout the production line. To shorten production and reduce the cost of labor resources, this study proposes a three-phase data science framework embedded with several data mining and machine learning techniques, which can identify the variables affecting yield, predict the metrology result of photo spacer process, and suggest the process control in the colo...
4 CitationsSource
#1Meng-Hsuen HsiehH-Index: 2
#2Meng-Ju HsiehH-Index: 3
Last. Chih-Cheng LaiH-Index: 3
view all 6 authors...
Background: Successful weaning from mechanical ventilation is important for patients in intensive care units (ICUs). The aim was to construct neural networks to predict successful extubation in ventilated patients in ICUs. Methods: Data from 1 December 2009 through 31 December 2011 of 3602 patients with planned extubation in Chi-Mei Medical Center’s ICUs was used to train and test an artificial neural network (ANN). The input was 37 clinical risk factors, and the output was a failed extubation p...
6 CitationsSource
#1Shamim NematiH-Index: 21
#2Andre HolderH-Index: 4
Last. Timothy G. BuchmanH-Index: 16
view all 6 authors...
Objectives:Sepsis is among the leading causes of morbidity, mortality, and cost overruns in critically ill patients. Early intervention with antibiotics improves survival in septic patients. However, no clinically validated system exists for real-time prediction of sepsis onset. We aimed to develop
60 CitationsSource
#1Chia-Yen Lee (NCKU: National Cheng Kung University)H-Index: 12
#2Bo Syun Chen (NCKU: National Cheng Kung University)H-Index: 1
Abstract In the fields of machine learning and data mining, feature selection methods are used to identify the most cost-effective predictors and to give a deeper understanding of pattern recognition and extraction. This study proposes a novel mutually-exclusive-and-collectively-exhaustive (MECE) feature selection scheme. Based on the MECE principle in decision science, the scheme, which has three stages including evaluation of independence, evaluation of importance and evaluation of completenes...
10 CitationsSource
#1Ronald R. Henriquez (UNC: University of North Carolina at Chapel Hill)H-Index: 1
#2Nichole L. Korpi-Steiner (UNC: University of North Carolina at Chapel Hill)H-Index: 6
The struggle with uncertainty among healthcare professionals about how to apply test results for risk stratification and diagnosis of patients was recently highlighted as a serious risk factor for diagnostic and medical decision-making errors in the 2015 Institute of Medicine (IOM) report Improving Diagnosis in Health Care (1). The Bayes theorem is well recognized by trainees and caregivers as a statistical key for updating the probability of a patient event (e.g., disease) occurring as test res...
2 CitationsSource
#1Chia-Yen Lee (NCKU: National Cheng Kung University)H-Index: 12
#2Ming-Chien Chiang (NCKU: National Cheng Kung University)H-Index: 1
A two-phase research framework considers demand forecast and capacity decision.A virtual data generation process used for small data extension for demand forecast.Demand forecast models with small data generate different demand scenarios.Stochastic programming suggests a robust capacity decision in aggregate planning.An empirical study of a TFT-LCD firm justifies the proposed framework. This study proposes a two-phase research framework to address the problem of capacity-demand mismatch in the h...
8 CitationsSource
Most patients staying in the intensive care unit (ICU) require respiratory support through a ventilator. Since prolonged mechanical ventilation and weaning from the ventilator without criteria or at the inappropriate time can result in many complications, it is required that patients be weaned off the ventilator as soon as possible. This study was conducted to investigate a few standard tools that predict successful and timely weaning of patients from the ventilator. In the literature, SOFA and ...
2 CitationsSource
#1Hung Ju KuoH-Index: 1
#2Hung Wen ChiuH-Index: 15
Last. Mauo Ying Bien (TMU: Taipei Medical University)H-Index: 1
view all 6 authors...
BACKGROUND: 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. METHODS: Ready-to-wean subjects ( N = 121) hospitalized in medical ICUs were recruited and randomly divi...
14 CitationsSource
Cited By0
Newest