High Breath-by-Breath Variability Is Associated With Extubation Failure in Children

The Constrained Disorder Principle Accounts for the Variability That Characterizes Breathing: A Method for Treating Chronic Respiratory Diseases and Improving Mechanical Ventilation

Variability characterizes breathing, cellular respiration, and the underlying quantum effects. Variability serves as a mechanism for coping with changing environments; however, this hypothesis does not explain why many of the variable phenomena of respiration manifest randomness. According to the constrained disorder principle (CDP), living organisms are defined by their inherent disorder bounded by variable boundaries. The present paper describes the mechanisms of breathing and cellular respiration, focusing on their inherent variability. It defines how the CDP accounts for the variability and randomness in breathing and respiration. It also provides a scheme for the potential role of respiration variability in the energy balance in biological systems. The paper describes the option of using CDP-based artificial intelligence platforms to augment the respiratory process's efficiency, correct malfunctions, and treat disorders associated with the respiratory system.

Automated prediction of extubation success in extremely preterm infants: the APEX multicenter study

BACKGROUND

Extremely preterm infants are frequently subjected to mechanical ventilation. Current prediction tools of extubation success lacks accuracy.

METHODS

Multicenter study including infants with birth weight ≤1250 g undergoing their first extubation attempt. Clinical data and cardiorespiratory signals were acquired before extubation. Primary outcome was prediction of extubation success. Automated analysis of cardiorespiratory signals, development of clinical and cardiorespiratory features, and a 2-stage Clinical Decision-Balanced Random Forest classifier were used. A leave-one-out cross-validation was done. Performance was analyzed by ROC curves and determined by balanced accuracy. An exploratory analysis was performed for extubations before 7 days of age.

RESULTS

A total of 241 infants were included and 44 failed (18%) extubation. The classifier had a balanced accuracy of 73% (sensitivity 70% [95% CI: 63%, 76%], specificity 75% [95% CI: 62%, 88%]). As an additional clinical-decision tool, the classifier would have led to an increase in extubation success from 82% to 93% but misclassified 60 infants who would have been successfully extubated. In infants extubated before 7 days of age, the classifier identified 16/18 failures (specificity 89%) and 73/105 infants with success (sensitivity 70%).

CONCLUSIONS

Machine learning algorithms may improve a balanced prediction of extubation outcomes, but further refinement and validation is required.

IMPACT

A machine learning-derived predictive model combining clinical data with automated analyses of individual cardiorespiratory signals may improve the prediction of successful extubation and identify infants at higher risk of failure with a good balanced accuracy. Such multidisciplinary approach including medicine, biomedical engineering and computer science is a step forward as current tools investigated to predict extubation outcomes lack sufficient balanced accuracy to justify their use in future trials or clinical practice. Thus, this individualized assessment can optimize patient selection for future trials of extubation readiness by decreasing exposure of low-risk infants to interventions and maximize the benefits of those at high risk.

Comprehensive breathing variability indices enhance the prediction of extubation failure in patients on mechanical ventilation

BACKGROUND AND OBJECTIVE

Despite the numerous studies on extubation readiness assessment for patients who are invasively ventilated in the intensive care unit, a 10-15% extubation failure rate persists. Although breathing variability has been proposed as a potential predictor of extubation failure, it is mainly assessed using simple statistical metrics applied to basic respiratory parameters. Therefore, the complex pattern of breathing variability conveyed by continuous ventilation waveforms may be underexplored.

METHODS

Here, we aimed to develop novel breathing variability indices to predict extubation failure among invasively ventilated patients. First, breath-to-breath basic and comprehensive respiratory parameters were computed from continuous ventilation waveforms 1 h before extubation. Subsequently, the basic and advanced variability methods were applied to the respiratory parameter sequences to derive comprehensive breathing variability indices, and their role in predicting extubation failure was assessed. Finally, after reducing the feature dimensionality using the forward search method, the combined effect of the indices was evaluated by inputting them into the machine learning models, including logistic regression, random forest, support vector machine, and eXtreme Gradient Boosting (XGBoost).

RESULTS

The coefficient of variation of the dynamic mechanical power per breath (CV-MPd[J/breath]) exhibited the highest area under the receiver operating characteristic curve (AUC) of 0.777 among the individual indices. Furthermore, the XGBoost model obtained the best AUC (0.902) by combining multiple selected variability indices.

CONCLUSIONS

These results suggest that the proposed novel breathing variability indices can improve extubation failure prediction in invasively ventilated patients.

A 30-Minute Spontaneous Breathing Trial Misses Many Children Who Go On to Fail a 120-Minute Spontaneous Breathing Trial

BACKGROUND

The optimal length of spontaneous breathing trials (SBTs) in children is unknown.

RESEARCH QUESTIONS

What are the most common reasons for SBT failure in children, and when do they occur? Can clinical parameters at the 30-min mark of a 120-min SBT predict outcome?

STUDY DESIGN AND METHODS

We performed a secondary analysis of a clinical trial in pediatric ARDS, in which 2-h SBTs are conducted daily. SBT failure is based on objective criteria, including esophageal manometry for effort of breathing, categorized as passage, early failure (≤ 30 min), or late failure (30-120 min). Spirometry was used to calculate respiratory rate (RR), tidal volume (Vt), and rapid shallow breathing index (RSBI), in addition to pulse oximetry and capnography. Predictive models evaluated parameters at 30 min against SBT outcome, using receiver operating characteristic plots and area under the curve.

RESULTS

We included 100 children and 305 SBTs, with 42% of SBTs being successful, 32% failing within 30 min, and 25% failing between 30 and 120 min. Of the patients passing SBTs at 30 min, 40% went on to fail by 120 min. High respiratory effort (esophageal manometry) was present in > 80% of failed SBTs. At the 30-min mark, there were no clear thresholds for RR, Vt, RSBI, Fio2, oxygen saturation, or capnography that could reliably predict SBT outcome. Multivariable modeling identified RR (P < .001) and RSBI > 7 (P = .034) at 30 min, pre-SBT inspiratory pressure level (P = .009), and pre-SBT retractions (P = .042) as predictors for SBT failure, but this model performed poorly in an independent validation set with the receiver operating characteristic plot crossing the reference line (area under the curve, 0.67).

INTERPRETATION

A 30-min SBT may be too short in children recovering from pediatric ARDS because many go on to fail between 30 and 120 min. Reassuring values of Vt, RR, and gas exchange at 30 min do not reliably predict SBT passage at 2 h, likely because they do not capture the effort of breathing.

CLINICAL TRIAL REGISTRATION

ClinicalTrials.gov; No.: NCT03266016; URL: www.

CLINICALTRIALS

gov.