Solving the Extubation Equation: Successfully Weaning Infants Born Extremely Preterm from Mechanical Ventilation

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.

Factors associated with extubation failure in very low birth weight infants: a cohort study in the northeast Brazil

OBJECTIVES

Identifying and understanding the main risk factors associated with extubation failure of very low birthweight (VLBW) infants in different populations can subsequently help in establishing better criteria while taking decision of extubation. The aim of the study was to identify factors associated with extubation failure in VLBW infants.

METHODS

A cohort study of VLBW infants who underwent their first extubation between April 2018 and December 2019 in a Neonatal Intensive Care Unit, Alagoas, Brazil, were included in this study. Extubation failure was defined as reintubation within seven days of extubation. Relative risks of predictive variables different between the extubation success group (ES) and extubation failure group (EF) were estimated with a robust Poisson regression model.

RESULTS

Out of the 112 infants included, 26 (23%) cases exhibited extubation failure. Extremely low birth weight (RR 2.55, 95% CI 1.07, 6.06), mechanical ventilation duration for first extubation greater than seven days (RR 2.66, 95% CI 1.10, 6.45), vaginal delivery (RR 2.07, 95% CI 1.03, 4.18) and maternal chorioamnionitis (RR 4.89, 95% CI 1.26-18.98) remained independently associated with extubation failure. EF had a significant greater need for respiratory support, longer oxygen therapy duration, more bronchopulmonary dysplasia (BPD) and longer length of hospital stay, even when adjusted for confounding variables.

CONCLUSIONS

Extremely low birth weight infants needing mechanical ventilation, wherein the duration for first extubation was longer than seven days, with vaginal delivery and maternal chorioamnionitis failed more frequently at the first attempt of extubation. And this failure increased the risk of BPD and the length of hospital stay.

Accuracy of a spontaneous breathing trial for extubation of neonates

BACKGROUND

Prevalence of extubation failure in neonates may be up to 80%, but evidence to determine if a neonate is ready for extubation remains unclear. We aim to evaluate a spontaneous breathing trial accuracy with minimum pressure support to predict success in neonates' extubation and identify variables related to failures.

METHODS

This is a diagnostic accuracy study based on a cohort study in an intensive care unit with all eligible newborn infants subjected to invasive mechanical ventilation for at least 24 hours submitted to the trial for 10 minutes before extubations. The outcome was failures of extubations, considered if reintubation was needed until 72 hours.

RESULTS

The incidence of failure was 14.7%among 170 extubations. There were 145 successful extubations; of these, 140 also passed the trial with a sensitivity of 96.5%(95%CI: 92.1-98.9). Of the 25 extubations that eventually failed, 16 failed the test with a specificity of 64.0%(95%CI: 42.5-82.0). The negative predictive value was 76.2%, and the positive predictive value was 94%. In stratifying by weight, the accuracy was >98.7%for neonates weighting >2500 g, but 72.5%for those weighing <1250 g. Extubation failures occurred more frequently in smaller (p = 0.01), preterm infants (p = 0.17), with longer ventilation time (p = 0.05), and having a hemodynamically significant persistent arterial duct (p = 0.01), compared with infants whose extubation was successful.

CONCLUSION

The spontaneous breathing trial with minimum pressure support ventilation seems to predict extubation success with great accuracy in full-term and larger neonates.

Patterns of reintubation in extremely preterm infants: a longitudinal cohort study

BackgroundThe optimal approach for reporting reintubation rates in extremely preterm infants is unknown. This study aims to longitudinally describe patterns of reintubation in this population over a broad range of observation windows following extubation.MethodsTiming and reasons for reintubation following a first planned extubation were collected from infants with birth weight ≤1,250 g. An algorithm was generated to discriminate between reintubations attributable to respiratory and non-respiratory causes. Frequency and cumulative distribution curves were constructed for each category using 24 h intervals. The ability of observation windows to capture respiratory-related reintubations while limiting non-respiratory reasons was assessed using a receiver operating characteristic curve.ResultsOut of 194 infants, 91 (47%) were reintubated during hospitalization; 68% for respiratory and 32% for non-respiratory reasons. Respiratory-related reintubation rates steadily increased from 0 to 14 days post-extubation before reaching a plateau. In contrast, non-respiratory reintubations were negligible in the first post-extubation week, but became predominant after 14 days. An observation window of 7 days captured 77% of respiratory-related reintubations while only including 14% of non-respiratory cases.ConclusionReintubation patterns are highly variable and affected by the reasons for reintubation and observation window used. Ideally, reintubation rates should be reported using a cumulative distribution curve over time.