Predicting extubation readiness in extreme preterm infants based on patterns of breathing

Onu, Charles C.; Kanbar, Lara J.; Shalish, Wissam; Brown, Karen; Sant’Anna, Guilherme M.; Kearney, Robert E.; Precup, Doina

doi:10.1109/ssci.2017.8285255

Cited by 2 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chaparro and Giraldo [16] proposed a new extubation index based on the power of respiratory flow signal. Other indices, such as cardiorespiratory behavior [20] and breathing patterns [21] have been used for preterm neonate patients.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Extubation Failure for Intensive Care Unit Patients Using Light Gradient Boosting Machine

Chen

Ying

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Extubation failure is a complex and ongoing problem in the intensive care unit (ICU). It refers to the patients who require re-intubation after extubation (namely disconnection from mechanical ventilation). In these patients, extubation failure leads to severe risks associated with re-intubation and is associated with increased mortalities, longer stay in ICU and also higher health care costs. Many studies have been proposed to analyze the problem of extubation failure and identify possible factors or indices that may predict extubation failure. However, these studies used a small number of patients for extubation failure and limited their features to several vital signs or main characteristics. We argue that these are insufficient and less accurate for the prediction of extubation failure. In this paper, we analyze 3636 adult patient records in the MIMIC-III clinical database and apply the Light Gradient Boosting Machine (LightGBM) to predict extubation failure. Also, we perform feature importance analysis according to the result of LightGBM and interpret these features using SHapley Additive exPlanations (SHAP). Experimental results show that our LightGBM method is effective in predicting extubation failure and outperform other machine learning methods such as artificial neural network (ANN), logistic regression (LR) and support vector machine (SVM). The results of feature importance and SHAP analysis are also proved effective and accurate.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of Extubation Failure for Intensive Care Unit Patients Using Light Gradient Boosting Machine

Chen

Ying

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The performance observed in current work may be a more realistic measure given the increased heterogeneity in the population. In this work, the [19] which used only clinical variables, and is better than results in [20] which used only respiratory patterns. Overall, this highlights the difficulty of predicting extubation readiness in such a highrisk population.…”

Section: Discussionmentioning

confidence: 96%

“…This enables us to use each 1 The concept of balanced accuracy is different from balanced random forest. See appendix in [20] for a motivation on why balanced accuracy is a preferred metric over accuracy. example at least once for both training and testing.…”

Section: F Performance Metrics and Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Undersampling and Bagging of Decision Trees in the Analysis of Cardiorespiratory Behavior for the Prediction of Extubation Readiness in Extremely Preterm Infants

Kanbar¹,

Onu²,

Shalish³

et al. 2018

2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

Self Cite

View full text Add to dashboard Cite

Extremely preterm infants often require endotracheal intubation and mechanical ventilation during the first days of life. Due to the detrimental effects of prolonged invasive mechanical ventilation (IMV), clinicians aim to extubate infants as soon as they deem them ready. Unfortunately, existing strategies for prediction of extubation readiness vary across clinicians and institutions, and lead to high reintubation rates. We present an approach using Random Forest classifiers for the analysis of cardiorespiratory variability to predict extubation readiness. We address the issue of data imbalance by employing random undersampling of examples from the majority class before training each Decision Tree in a bag. By incorporating clinical domain knowledge, we further demonstrate that our classifier could have identified 71% of infants who failed extubation, while maintaining a success detection rate of 78%.  Pause (PAU): cessation of breathing indicated by low RCG and ABD power in the breathing band (0.4-2Hz).  Movement Artifact (MVT): periods during which there is power in the movement artifact band (0-0.4Hz) due to infant movement or nurse handling.  Synchronous Breathing (SYB): periods during which RCG and ABD are in synchrony.  Asynchronous Breathing (ASB): periods during which RCG and ABD are out of synchrony.AUREA is objective, repeatable, and has been tuned for this population. Further details are given in [13]. The following patterns were also extracted from the ECG and PPG signals: Bradycardia (BDY): artifact-free periods during which and the heart rate was below 100 beats/min.

show abstract

Predicting extubation readiness in extreme preterm infants based on patterns of breathing

Cited by 2 publications

References 16 publications

Prediction of Extubation Failure for Intensive Care Unit Patients Using Light Gradient Boosting Machine

Prediction of Extubation Failure for Intensive Care Unit Patients Using Light Gradient Boosting Machine

Undersampling and Bagging of Decision Trees in the Analysis of Cardiorespiratory Behavior for the Prediction of Extubation Readiness in Extremely Preterm Infants

Contact Info

Product

Resources

About