Extubating Extremely Preterm Infants: Predictors of Success and Outcomes following Failure

AI models in clinical neonatology: a review of modeling approaches and a consensus proposal for standardized reporting of model performance

Artificial intelligence (AI) is a rapidly advancing area with growing clinical applications in healthcare. The neonatal intensive care unit (NICU) produces large amounts of multidimensional data allowing AI and machine learning (ML) new avenues to improve early diagnosis, enhance monitoring, and provide highly-targeted treatment approaches. In this article, we review recent clinical applications of AI to important neonatal problems, including sepsis, retinopathy of prematurity, bronchopulmonary dysplasia, and others. For each clinical area, we highlight a variety of ML models published in the literature and examine the future role they may play at the bedside. While the development of these models is rapidly expanding, a fundamental understanding of model selection, development, and performance evaluation is crucial for researchers and healthcare providers alike. As AI plays an increasing role in daily practice, understanding the implications of AI design and performance will enable more effective implementation. We provide a comprehensive explanation of the AI development process and recommendations for a standardized performance metric framework. Additionally, we address critical challenges, including model generalizability, ethical considerations, and the need for rigorous performance monitoring to avoid model drift. Finally, we outline future directions, emphasizing the importance of collaborative efforts and equitable access to AI innovations.

Timeline of Weaning in Pediatric Long-Term Mechanical Ventilator Dependent Children: A Longitudinal Cohort Study

BACKGROUND

Children with invasive long-term mechanical ventilation (LTMV) dependence are a complex, heterogeneous population with wide variability in respiratory outcomes. Limited data exist on their ventilator weaning trajectories and respiratory characteristics as they progress toward liberation from the ventilator.

OBJECTIVE

To describe a population of children with invasive LTMV dependence who have successfully liberated from ventilator support, focusing on ventilator parameters as potential early predictors of liberation.

METHODS

This was a retrospective study of children who initiated chronic ventilator support at < 12 months of age at our institution, received ventilator support through a tracheostomy tube, were followed through our outpatient clinic, and were fully liberated from mechanical ventilation. Our primary outcome was age at liberation from ventilator support. Multiple covariates were described, including baseline descriptors, health system utilization descriptors, disease markers, and care milestones.

RESULTS

Seventy-eight patients were identified. The median age of tracheostomy was 3.8 [IQR: 3.0-4.8] months. The median age of first hospital discharge to home care was 9.3 months [IQR: 7.5-12], with a median of 44 hospital encounters after initial discharge. These patients were liberated at a median age of 23.9 [18.3-32.2] months. Age at liberation from the ventilator was highly variable within our institution.

CONCLUSION

The most significant variation in outcome was introduced after hospital discharge and appears to be largely independent of lung disease severity as indicated by ventilatory support. No single covariate was strongly correlated with liberation outcome. Further studies are needed to identify underlying pathophysiology that may contribute to the varied weaning trajectories to better define objective weaning strategies.

Predictive model development for premature infant extubation outcomes: development and analysis

BACKGROUND

Given the knowledge of the damage caused by prolonged invasive mechanical ventilation in premature newborns, withdrawing this support as quickly as possible is important to minimize morbidity. The aim of this study was to analyze the variables associated with extubation outcomes and to develop a predictive model for successful extubation in premature newborns.

METHODS

Data were obtained from a multicenter study involving six public maternity hospitals. The variables with the highest correlation to the extubation outcome were used to construct the predictive model through data analysis and machine learning methods, followed by training and testing of algorithms.

RESULTS

Data were collected from 405 premature newborns. The predictive model with the best metrics was trained and tested using the variables of gestational age, birth weight, weight at extubation, congenital infections, and time on invasive mechanical ventilation, based on 393 samples according to the extubation outcome (12 were discarded due to irretrievable missing data in important attributes). The model exhibited an accuracy of 77.78%, sensitivity of 79.41%, and specificity of 60%.

CONCLUSION

These variables generated a predictive model capable of estimating the probability of successful extubation in premature newborns.

IMPACT

Prolonged use of invasive mechanical ventilation in preterm newborns increases morbidity/mortality rates, emphasizing the importance of early withdrawal from invasive ventilatory support. However, the decision to extubate lacks tools with higher extubation outcome precision. The use of artificial intelligence through the construction of a predictive model can assist in the decision-making process for extubating preterm newborns based on real-world data. The implementation of this tool can optimize the decision to extubate preterm newborns, promoting successful extubation and reducing preterm newborns exposure to adverse events associated with extubation failure.

Predicting extubation failure in preterm infants using lung ultrasound: a diagnostic accuracy study

OBJECTIVE

To determine the accuracy of pre-extubation lung ultrasound (LUS) to predict reintubation in preterm infants born <32 weeks' gestation.

DESIGN

Prospective diagnostic accuracy study.

SETTING

Two neonatal intensive care units.

METHODS

Anterior and lateral LUS was performed pre-extubation. The primary outcome was the accuracy of LUS scores (range 0-24) to predict reintubation within 72 hours. Secondary outcomes were accuracy in predicting (1) reintubation within 7 days, (2) reintubation stratified by postnatal age and (3) accuracy of lateral imaging only (range 0-12). Pre-specified subgroup analyses were performed in extremely preterm infants born <28 weeks' gestation. Cut-off scores, sensitivities and specificities were calculated using receiver operating characteristic analysis and reported as area under the curves (AUCs).

RESULTS

One hundred preterm infants with a mean (SD) gestational age of 27.4 (2.2) weeks and birth weight of 1059 (354) g were studied. Thirteen were subsequently reintubated. The AUC (95% CI) of the pre-extubation LUS score for predicting reintubation was 0.63 (0.45-0.80). Accuracy was greater in extremely preterm infants: AUC 0.70 (0.52-0.87) and excellent in infants who were <72 hours of age at the time of extubation: AUC 0.90 (0.77-1.00). Accuracy was poor in infants who were >7 days of age. Lateral imaging alone demonstrated similar accuracy to scanning anterior and lateral regions.

CONCLUSIONS

In contrast to previous studies, LUS was not a strong predictor of reintubation in preterm infants. Accuracy is increased in extremely preterm infants. Future research should focus on infants at highest risk of extubation failure and consider simpler imaging protocols.

TRIAL REGISTRATION NUMBER

Australian New Zealand Clinical Trials Registry: ACTRN12621001356853.

Predicting Extubation Readiness in Preterm Infants Utilizing Machine Learning: A Diagnostic Utility Study

OBJECTIVE

The objective of this study was to predict extubation readiness in preterm infants using machine learning analysis of bedside pulse oximeter and ventilator data.

STUDY DESIGN

This is an observational study with prospective recordings of oxygen saturation (SpO2) and ventilator data from infants <30 weeks of gestation age. Research pulse oximeters collected SpO2 (1 Hz sampling rate) to quantify intermittent hypoxemia (IH). Continuous ventilator metrics were collected (4-5-minute sampling) from bedside ventilators. Data modeling was completed using unbiased machine learning algorithms. Three model sets were created using the following data source combinations: (1) IH and ventilator (IH + SIMV), (2) IH, and (3) ventilator (SIMV). Infants were also analyzed separated by postnatal age (infants <2 or ≥2 weeks of age). Models were compared by area under the receiver operating characteristic curve (AUC).

RESULTS

A total of 110 extubation events from 110 preterm infants were analyzed. Infants had a median gestation age and birth weight of 26 weeks and 825 g, respectively. Of the 3 models presented, the IH + SIMV model achieved the highest AUC of 0.77 for all infants. Separating infants by postnatal age increased accuracy further achieving AUC of 0.94 for <2 weeks of age group and AUC of 0.83 for ≥2 weeks group.

CONCLUSIONS

Machine learning analysis has the potential to enhance prediction accuracy of extubation readiness in preterm infants while utilizing readily available data streams from bedside pulse oximeters and ventilators.

Using machine-learning models to predict extubation failure in neonates with bronchopulmonary dysplasia

AIM

To develop a decision-support tool for predicting extubation failure (EF) in neonates with bronchopulmonary dysplasia (BPD) using a set of machine-learning algorithms.

METHODS

A dataset of 284 BPD neonates on mechanical ventilation was used to develop predictive models via machine-learning algorithms, including extreme gradient boosting (XGBoost), random forest, support vector machine, naïve Bayes, logistic regression, and k-nearest neighbor. The top three models were assessed by the area under the receiver operating characteristic curve (AUC), and their performance was tested by decision curve analysis (DCA). Confusion matrix was used to show the high performance of the best model. The importance matrix plot and SHapley Additive exPlanations values were calculated to evaluate the feature importance and visualize the results. The nomogram and clinical impact curves were used to validate the final model.

RESULTS

According to the AUC values and DCA results, the XGboost model performed best (AUC = 0.873, sensitivity = 0.896, specificity = 0.838). The nomogram and clinical impact curve verified that the XGBoost model possessed a significant predictive value. The following were predictive factors for EF: pO2, hemoglobin, mechanical ventilation (MV) rate, pH, Apgar score at 5 min, FiO2, C-reactive protein, Apgar score at 1 min, red blood cell count, PIP, gestational age, highest FiO2 at the first 24 h, heart rate, birth weight, pCO2. Further, pO2, hemoglobin, and MV rate were the three most important factors for predicting EF.

CONCLUSIONS

The present study indicated that the XGBoost model was significant in predicting EF in BPD neonates with mechanical ventilation, which is helpful in determining the right extubation time among neonates with BPD to reduce the occurrence of complications.

Airway management may influence postoperative ventilation need in preterm infants after laser eye treatment

BACKGROUND

Retinopathy of prematurity is treated with laser photocoagulation under general anaesthesia with intubation using endotracheal tube (ETT), which carries a risk for postoperative mechanical ventilation (MV). Laryngeal mask airway (LMA) may provide a safe alternative. We assessed the need for postoperative MV in preterm infants who received LMA versus ETT.

METHODS

In this single-centre, retrospective cohort study, preterm infants who underwent laser photocoagulation between 2014-2021 were enroled. For airway management, patients received either LMA (n = 224) or ETT (n = 47). The outcome was the rate of postoperative MV.

RESULTS

Patients' age were 37 [35;39] weeks of postmenstrual age, median bodyweight of Group LMA was higher than Group ETT's (2110 [1800;2780] g versus 1350 [1230;1610] g, respectively, p < 0.0001). After laser photocoagulation, 8% of Group LMA and 74% of Group ETT left the operating theatre requiring MV. Multiple logistic regression revealed that the use of LMA and every 100 g increase in bodyweight significantly decreased the odds of mechanical ventilation (OR 0.21 [95% CI 0.07-0.60], and 0.73 [95% CI 0.63-0.84], respectively). Propensity score matching confirmed that LMA decreased the odds of postoperative MV (OR 0.30 [95% CI 0.11-0.70]).

CONCLUSION

The use of LMA is associated with a reduced need for postoperative MV.

IMPACT

Using laryngeal mask airway instead of endotracheal tube for airway management in preterm infants undergoing general anaesthesia for laser photocoagulation for treating retinopathy of prematurity could significantly decrease the postoperative need for mechanical ventilation. According to our current understanding, this has been the largest study investigating the effect of laryngeal mask airway during general anaesthesia in preterm infants. Our study suggests that the use of laryngeal mask airway is a viable alternative to intubation in the vulnerable population of preterm infants in need of laser treatment.

Effectiveness of corticosteroids and epinephrine use in neonates for the first extubation attempt: A retrospective study

BACKGROUND

This study aimed to analyze the use of corticosteroids and epinephrine in neonates for the first extubation attempt and compared clinical characteristics of infants with successful and failed extubation events.

METHODS

This was a retrospective cohort study conducted at a single level III neonatal intensive care unit in Taiwan. The study included 215 infants born between 2020 and 2021 who had been intubated for more than 48 h before their first extubation attempt. We compared perinatal and peri-extubation characteristics and outcomes between the two groups. Successful extubation was defined as freedom from invasive ventilatory support 72 h after extubation. The relationship between corticosteroids, local epinephrine, and successful extubation was determined using multivariate logistic regression analysis.

RESULTS

In the univariate analysis, the failed extubation group received a significantly higher proportion of intravenous dexamethasone (p = 0.006) than the successful extubation group. Furthermore, the failed extubation group had a longer duration of nebulized epinephrine (p = 0.034) and more episodes of local application of epinephrine to the superior larynx (p = 0.003) than the successful extubation group. Multivariate analysis revealed that the absence of lung atelectasis, tachycardia 72 h after extubation, and lower post-extubation PCO2 were the key factors associated with successful extubation.

CONCLUSIONS

There were trends toward systemic dexamethasone, local application of epinephrine to the superior larynx, and longer duration of nebulized epinephrine in the reintubation group. However, corticosteroid or local epinephrine use was not significantly associated with successful extubation. Lung atelectasis, elevated levels of carbon dioxide, and tachycardia were identified as risk factors for extubation failure.

Characteristics and Outcomes in Preterm Infants with Extubation Failure in the First Week of Life

OBJECTIVE

This study aimed to evaluate characteristics and outcomes in preterm infants with extubation failures in their first week of life.

STUDY DESIGN

Retrospective chart review of infants born between 24 and 27 weeks' gestational age at the Sharp Mary Birch Hospital for Women and Newborns between January 2014 and December 2020 who had an extubation attempt within the first 7 days of life. Infants that were successfully extubated were compared with those who required reintubation in the first 7 days. Maternal and neonatal outcome measures were analyzed.

RESULTS

A total of 215 extremely preterm infants had an extubation attempt in the first 7 days of life. Forty-six infants (21.4%) failed extubation and were reintubated within the first 7 days. Infants who failed extubation had a lower pH (p < 0.01), increased base deficit (p < 0.01), and more surfactant doses prior to first extubation (p < 0.01). Birth weight, Apgar scores, antenatal steroid doses, and maternal risk factors such as preeclampsia, chorioamnionitis, and duration of ruptured membranes were not different between success and failure groups. Rates of moderate to large patent ductus arteriosus (p < 0.01), severe intraventricular hemorrhage (p < 0.01), posthemorrhagic hydrocephalus (p < 0.05), periventricular leukomalacia (p < 0.01), and retinopathy of prematurity stage 3 or greater (p < 0.05) were higher in the failure group.

CONCLUSION

In this cohort of extremely preterm infants that failed extubation in the first week of life, there were as increased risk of multiple morbidities. Base deficit, pH, and number of surfactant doses prior to first extubation may be useful tools in predicting which infants are likely to have early extubation success, but this needs prospective study.

KEY POINTS

· Predicting extubation readiness in preterm infants remains challenging.. · Extubation failure is associated with multiple neonatal morbidities.. · Infant clinical characteristics may help predict extubation failure..

Peri-extubation settings in preterm neonates: a systematic review and meta-analysis

OBJECTIVE

To systematically review: 1) peri-extubation settings; and 2) association between peri-extubation settings and outcomes in preterm neonates.

STUDY DESIGN

In this systematic review, studies were eligible if they reported patient-data on peri-extubation settings (objective 1) and/or evaluated peri-extubation levels in relation to clinical outcomes (objective 2). Data were meta-analyzed when appropriate using random-effects model.

RESULTS

Of 9681 titles, 376 full-texts were reviewed and 101 included. The pooled means of peri-extubation settings were summarized. For objective 2, three experimental studies were identified comparing post-extubation CPAP levels. Meta-analyses revealed lower odds for treatment failure [pooled OR 0.46 (95% CI 0.27-0.76); 3 studies, 255 participants] but not for re-intubation [pooled OR 0.66 (0.22-1.97); 3 studies, 255 participants] with higher vs. lower CPAP.

CONCLUSIONS

Summary of peri-extubation settings may guide clinicians in their own practices. Higher CPAP levels may reduce extubation failure, but more data on peri-extubation settings that optimize outcomes are needed.

Predictors of successful extubation from volume-targeted ventilation in extremely preterm neonates

OBJECTIVE

To identify variables associated with extubation success in extremely preterm neonates extubated from invasive volume-targeted ventilation.

STUDY DESIGN

We retrospectively evaluated 84 neonates ≤28 weeks' gestational age, on their first elective extubation. The primary outcome of successful extubation was defined as non-reintubation within seven days. We used multivariate logistic regression analysis.

RESULTS

We identified 58 (69%) neonates (mean gestational age of 26.5 ± 1.4 weeks, birthweight 921 ± 217 g) who met the primary outcome. Female sex (OR 1.15, 95% CI 1.01-9.10), higher pre-extubation weight (OR 1.29, 95% CI 1.05-1.59), and pH (OR 2.54, 95% CI 1.54-4.19), and lower pre-extubation mean airway pressure (MAP) (OR 0.49, 95% CI 0.33-0.73) were associated with successful extubation.

CONCLUSIONS

In preterm neonates, female sex, higher pre-extubation weight and pH, and lower pre-extubation MAP were predictors of successful extubation from volume-targeted ventilation. Evaluation of these variables will likely assist clinicians in selecting the optimal time for extubation in such vulnerable neonates.

Higher versus lower nasal continuous positive airway pressure for extubation of extremely preterm infants in Australia (ÉCLAT): a multicentre, randomised, superiority trial

BACKGROUND

Extremely preterm infants often require invasive mechanical ventilation, and clinicians aim to extubate these infants as soon as possible. However, extubation failure occurs in up to 60% of extremely preterm infants and is associated with increased mortality and morbidity. Nasal continuous positive airway pressure (nCPAP) is the most common post-extubation respiratory support, but there is no consensus on the optimal nCPAP level to safely avoid extubation failure in extremely preterm infants. We aimed to determine if higher nCPAP levels compared with standard nCPAP levels would decrease rates of extubation failure in extremely preterm infants within 7 days of their first extubation.

METHODS

In this multicentre, randomised, open-label controlled trial done at three tertiary perinatal centres in Australia, we assigned extremely preterm infants to extubation to either higher nCPAP (10 cmH2O) or standard nCPAP (7 cmH2O). Infants were eligible if they were born at less than 28 weeks' gestation, were receiving mechanical ventilation via an endotracheal tube, and were being extubated for the first time to nCPAP. Eligible infants must have received previous treatment with exogenous surfactant and caffeine. Infants were ineligible if they were planned to be extubated to a mode of respiratory support other than nCPAP, if they had a known major congenital anomaly that might affect breathing, or if ongoing intensive care was not being provided. Parents or guardians provided prospective, written, informed consent. Infants were maintained within an assigned nCPAP range for a minimum of 24 h after extubation (higher nCPAP group 9-11 cmH2O and standard nCPAP group 6-8 cmH2O). Randomisation was stratified by both gestation (22-25 completed weeks or 26-27 completed weeks) and recruiting centre. The primary outcome was extubation failure within 7 days and analysis was by intention to treat. This trial was prospectively registered with the Australian New Zealand Clinical Trials Registry, number ACTRN12618001638224.

FINDINGS

Between March 3, 2019, and July 31, 2022, 483 infants were born at less than 28 weeks and admitted to the recruiting centres. 92 infants were not eligible, 172 were not approached, 65 families declined to participate, and 15 consented but were not randomly assigned. 139 infants were enrolled and randomly assigned, 70 to the higher nCPAP group and 69 to the standard nCPAP group. One infant in the higher nCPAP group was excluded from the analysis because consent was withdrawn after randomisation. 104 (75%) of 138 mothers were White. The mean gestation was 25·7 weeks (SD 1·3) and the mean birthweight was 777 grams (201). 70 (51%) of 138 infants were female. Extubation failure occurred in 24 (35%) of 69 infants in the higher nCPAP group and in 39 (57%) of 69 infants in the standard nCPAP group (risk difference -21·7%, 95% CI -38·5% to -3·7%). There were no significant differences in rates of adverse events between groups during the primary outcome period. Three patients died (two in the higher nCPAP group and one in the standard nCPAP group), pneumothorax occurred in one patient from each group, spontaneous intestinal perforation in three patients (two in the higher nCPAP group and one in the standard nCPAP group) and there were no events of pulmonary interstitial emphysema.

INTERPRETATION

Extubation of extremely preterm infants to higher nCPAP significantly reduced extubation failure compared with extubation to standard nCPAP, without increasing rates of adverse effects. Future larger trials are essential to confirm these findings in terms of both efficacy and safety.

FUNDING

National Health and Medical Research Council Centre for Research Excellence in Newborn Medicine, number 1153176.

Effect of different courses and durations of invasive mechanical ventilation on respiratory outcomes in very low birth weight infants

This multicenter retrospective study was conducted to explore the effects of different courses and durations of invasive mechanical ventilation (MV) on the respiratory outcomes of very low birth weight infants (VLBWI) in China. The population for this study consisted of infants with birth weight less than 1500 g needing at least 1 course of invasive MV and admitted to the neonatal intensive care units affiliated with the Chinese Neonatal Network within 6 h of life from January 1st, 2019 to December 31st, 2020. Univariate and multivariate logistic regression analyses were performed to evaluate associations between invasive MV and respiratory outcomes. Adjusted odds ratios (ORs) were computed with the effects of potential confounders. (1) Among the 3183 VLBWs with a history of at least one course of invasive MV, 3155 (99.1%) met inclusion criteria and were assessed for the primary outcome. Most infants received one course (76.8%) and a shorter duration of invasive MV (62.16% with ventilation for 7 days or less). (2) In terms of the incidence of all bronchopulmonary dysplasia (BPD) (mild, moderate, and severe BPD), there were no significant differences between different invasive MV courses [For 2 courses, adjusted OR = 1.11 (0.88, 1.39); For 3 courses or more, adjusted OR = 1.07 (0.72, 1.60)]. But, with the duration of invasive MV prolonging, the OR of BPD increased [8-21 days, adjusted OR = 1.98 (1.59, 2.45); 22-35 days, adjusted OR = 4.37 (3.17, 6.03); ≥ 36 days, adjusted OR = 18.44 (10.98, 30.99)]. Concerning severe BPD, the OR increased not only with the course of invasive MV but also with the duration of invasive MV [For 2 courses, adjusted OR = 2.17 (1.07, 4.40); For 3 courses or more, adjusted OR = 2.59 (1.02, 6.61). 8-21 days, adjusted OR = 8.42 (3.22, 22.01); 22-35 days, adjusted OR = 27.82 (9.08, 85.22); ≥ 36 days, adjusted OR = 616.45 (195.79, > 999.999)]. (3) When the interaction effect between invasive MV duration and invasive MV course was considered, it was found that there were no interactive effects in BPD and severe BPD. Greater than or equal to three courses would increase the chance of severe BPD, death, and the requirement of home oxygen therapy. Compared with distinct courses of invasive MV, a longer duration of invasive MV (> 7 days) has a greater effect on the risk of BPD, severe BPD, death, and the requirement of home oxygen therapy.

Predictors of extubation failure in newborns: a systematic review and meta-analysis

Extubation failure (EF) is a significant concern in mechanically ventilated newborns, and predicting its occurrence is an ongoing area of research. To investigate the predictors of EF in newborns undergoing planned extubation, we conducted a systematic review and meta-analysis. A systematic literature search was conducted in PubMed, Web of Science, Embase, and Cochrane Library for studies published in English from the inception of each database to March 2023. The PRISMA guidelines were followed in all phases of this systematic review. The Risk of Bias Assessment for Nonrandomized Studies tool was used to assess methodological quality. Thirty-four studies were included, 10 of which were overall low risk of bias, 15 of moderate risk of bias, and 9 of high risk of bias. The studies reported 43 possible predictors in six broad categories (intrinsic factors; maternal factors; diseases and adverse conditions of the newborn; treatment of the newborn; characteristics before and after extubation; and clinical scores and composite indicators). Through a qualitative synthesis of 43 predictors and a quantitative meta-analysis of 19 factors, we identified five definite factors, eight possible factors, and 22 unclear factors related to EF. Definite factors included gestational age, sepsis, pre-extubation pH, pre-extubation FiO2, and respiratory severity score. Possible factors included age at extubation, anemia, inotropic use, mean airway pressure, pre-extubation PCO2, mechanical ventilation duration, Apgar score, and spontaneous breathing trial. With only a few high-quality studies currently available, well-designed and more extensive prospective studies investigating the predictors affecting EF are still needed. In the future, it will be important to explore the possibility of combining multiple predictors or assessment tools to enhance the accuracy of predicting extubation outcomes in clinical practice.

Development and validation of a prediction model for evaluating extubation readiness in preterm infants

Successful early extubation has advantages not only in terms of short-term respiratory morbidities and survival but also in terms of long-term neurodevelopmental outcomes in preterm infants. However, no consensus exists regarding the optimal protocol or guidelines for extubation readiness in preterm infants. Therefore, the decision to extubate preterm infants was almost entirely at the attending physician's discretion. We identified robust and quantitative predictors of success or failure of the first planned extubation attempt before 36 weeks of post-menstrual age in preterm infants (<32 weeks gestational age) and developed a prediction model for evaluating extubation readiness using these predictors. Extubation success was defined as the absence of reintubation within 72 h after extubation. This observational cohort study used data from preterm infants admitted to the neonatal intensive care unit of Seoul National University Bundang Hospital in South Korea between July 2003 and June 2019 to identify predictors and develop and test a predictive model for extubation readiness. Data from preterm infants included in the Medical Informative Medicine for Intensive Care (MIMIC-III) database between 2001 and 2008 were used for external validation. From a machine learning model using predictors such as demographics, periodic vital signs, ventilator settings, and respiratory indices, the area under the receiver operating characteristic curve and average precision of our model were 0.805 (95% confidence interval [CI], 0.802-0.809) and 0.917, respectively in the internal validation and 0.715 (95% CI, 0.713-0.717) and 0.838, respectively in the external validation. Our prediction model (NExt-Predictor) demonstrated high performance in assessing extubation readiness in both internal and external validations.

Optimising success of neonatal extubation: Respiratory support

In this review, we examine lung physiology before, during and after neonatal extubation and propose a three-phase model for the extubation procedure. We perform meta-analyses to compare different modes of non-invasive respiratory support after neonatal extubation and based on the findings, the following clinical recommendations are made.

Predictive factors for extubation success in very low and extremely low birth weight preterm infants

Background

Although invasive mechanical ventilation (IMV) has contributed to the survival of preterm infants with extremely low birth weight (ELBW), it is also associated with unsatisfactory clinical outcomes when used for prolonged periods. This study aimed to identify factors that may be decisive for extubation success in very low birth weight (VLBW) and extremely low birth weight (ELBW) preterm infants.

Methods

The cohort study included preterm infants with gestational age (GA) <36 weeks, birth weight (BW) <1500 grams who underwent IMV, born between 2015 and 2018. The infants were allocated into two groups: extubation success (SG) or failure (FG). A stepwise logistic regression model was created to determine variables associated with successful extubation.

Results

Eighty-three preterm infants were included. GA and post-extubation arterial partial pressure of carbon dioxide (PaCO2) were predictive of extubation success. Infants from FG had lower GA and BW, while those from SG had higher weight at extubation and lower post-extubation PaCO2.

Discussion

Although we found post-extubation PaCO2 as an extubation success predictor, which is a variable representative of the moment after the primary outcome, this does not diminish its clinical relevance since extubation does not implicate in ET removal only; it also involves all the aspects that take place within a specified period (72 hours) after the planned event.

Conclusion

GA and post-extubation PaCO2 were predictors for extubation success in VLBW and ELBW preterm infants. Infants who experienced extubation failure had lower birth weight and higher FiO2 prior to extubation.

A Nomogram for Predicting Extubation Failure in Preterm Infants with Gestational Age Less than 29 Weeks

INTRODUCTION

How to avoid reintubations in prematurity remains a hard nut. This study aimed to develop and validate a nomogram for predicting extubation failure in preterm infants who received different modes of noninvasive ventilation as post-extubation support.

METHODS

This was a secondary analysis of pre-existing data from a large multicenter RCT combined with a multicenter retrospective investigation in three tertiary referral NICUs in China. The training cohort consisted of extubated infants from the RCT and the validation cohort included neonates admitted to the three NICUs in the last 5 years. The nomogram was developed through univariate and multivariate logistic regression analyses of peri-extubation clinical variables.

RESULTS

A total of 432 and 183 preterm infants (25 weeks ≤ gestational age [GA] <29 weeks) were, respectively, included in the training cohort and the validation cohort. Lower birth weight, lower Apgar 5-min score, lower postmenstrual age at extubation, lower PO2 and higher PCO2 before extubation, and continuous positive airway pressure rather than nasal intermittent positive pressure ventilation or noninvasive high-frequency oscillatory ventilation after extubation were associated with higher risks of extubation failure (p < 0.05), on which the nomogram was established. In both the training cohort and the validation cohort, the nomogram demonstrated good predictive accuracy (area under the receiver operating characteristic curve = 0.744 and 0.826); the Hosmer-Lemeshow test (p = 0.192 and 0.401) and the calibration curve (R2 = 0.195 and 0.307) proved a good fitness and conformity; and the decision curve analysis showed significant net benefit at the best threshold (p = 0.201).

CONCLUSION

This nomogram could serve as a good decision-support tool when predicting extubation failure in preterm infants with GA less than 29 weeks.

Oxygen saturation histogram classification system to evaluate response to doxapram treatment in preterm infants

BACKGROUND

An oxygen saturation (SpO₂) histogram classification system has been shown to enable quantification of SpO₂ instability into five types, based on histogram distribution and time spent at SpO₂ ≤ 80%. We aimed to investigate this classification system as a tool to describe response to doxapram treatment in infants with severe apnea of prematurity.

METHODS

This retrospective study included 61 very-low-birth-weight infants who received doxapram. SpO₂ histograms were generated over the 24-h before and after doxapram start. Therapy response was defined as a decrease of ≥1 histogram types after therapy start.

RESULTS

The median (IQR) histogram type decreased from 4 (3-4) before to 3 (2-3) after therapy start (p < 0.001). The median (IQR) FiO₂ remained constant before (27% [24-35%]) and after (26% [22-35%]) therapy. Thirty-six infants (59%) responded to therapy within 24 h. In 34/36 (94%) of the responders, invasive mechanical ventilation (IMV) was not required during the first 72 h of therapy, compared to 15/25 (60%) of non-responders (p = 0.002). Positive and negative predictive values of the 24-h response for no IMV requirement within 72 h were 0.46 and 0.94, respectively.

CONCLUSIONS

Classification of SpO₂ histograms provides an objective bedside measure to assess response to doxapram therapy and can serve as a tool to detect changes in oxygenation status around respiratory interventions.

IMPACT

The SpO₂ histogram classification system provides a tool for quantifying response to doxapram therapy. The classification system allowed estimation of the probability of invasive mechanical ventilation requirement, already within a few hours of treatment. The SpO₂ histogram classification system allows an objective bedside assessment of the oxygenation status of the preterm infant, making it possible to assess the changes in oxygenation status in response to respiratory interventions.

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.

Risk factors and clinical outcomes of extubation failure in very early preterm infants: a single-center cohort study

BACKGROUND

Early extubation success (ES) in preterm infants may reduce various mechanical ventilation-associated complications; however, extubation failure (EF) can cause adverse short- and long-term outcomes. Therefore, the present study aimed to identify differences in risk factors and clinical outcomes between ES and EF in very early preterm infants.

METHODS

This retrospective study was conducted between January 2017 and December 2021. Premature infants born at 32 weeks' gestational age in whom extubation had failed at least once were assigned to the EF group. Successfully extubated patients with a similar gestational age and birth weight as those in the EF group were assigned to the ES group. EF was defined as the need for re-intubation within 120 h of extubation. Various variables were compared between groups.

RESULTS

The EF rate in this study was 18.6% (24/129), and approximately 80% of patients with EF required re-intubation within 90.17 h. In the ES group, there was less use of inotropes within 7 days of life (12 [63.2%] vs. 22 [91.7%], p = 0.022), a lower respiratory severity score (RSS) at 1 and 4 weeks (1.72 vs. 2.5, p = 0.026; 1.73 vs. 2.92, p = 0.010), and a faster time to reach full feeding (18.7 vs. 29.7, p = 0.020). There was a higher severity of bronchopulmonary dysplasia BPD (3 [15.8%] vs. 14 [58.3%], p = 0.018), longer duration of oxygen supply (66.5 vs. 92.9, p = 0.042), and higher corrected age at discharge (39.6 vs. 42.5, p = 0.043) in the EF group. The cutoff value, sensitivity, and specificity of the respiratory severity score (RSS) at 1 week were 1.98, 0.71, and 0.42, respectively, and the cutoff value, sensitivity, and specificity of RSS at 4 weeks were 2.22, 0.67, and 0.47, respectively.

CONCLUSIONS

EF caused adverse short-term outcomes such as a higher BPD severity and longer hospital stay. Therefore, extubation in very early preterm infants should be carefully evaluated. Using inotropes, feeding, and RSS at 1 week of age can help predict extubation success.

Age at First Extubation Attempt and Death or Respiratory Morbidities in Extremely Preterm Infants

OBJECTIVE

To describe the timing of first extubation in extremely preterm infants and explore the relationship between age at first extubation, extubation outcome, and death or respiratory morbidities.

STUDY DESIGN

In this subanalysis of a multicenter observational study, infants with birth weights of 1250 g or less and intubated within 24 hours of birth were included. After describing the timing of first extubation, age at extubation was divided into early (within 7 days from birth) vs late (days of life 8-35), and extubation outcome was divided into success vs failure (reintubation within 7 days after extubation), to create 4 extubation groups: early success, early failure, late success, and late failure. Logistic regression analyses were performed to evaluate associations between the 4 groups and death or bronchopulmonary dysplasia, bronchopulmonary dysplasia among survivors, and durations of respiratory support and oxygen therapy.

RESULTS

Of the 250 infants included, 129 (52%) were extubated within 7 days, 93 (37%) between 8 and 35 days, and 28 (11%) beyond 35 days of life. There were 93, 36, 59, and 34 infants with early success, early failure, late success, and late failure, respectively. Although early success was associated with the lowest rates of respiratory morbidities, early failure was not associated with significantly different respiratory outcomes compared with late success or late failure in unadjusted and adjusted analyses.

CONCLUSIONS

In a contemporary cohort of extremely preterm infants, early extubation occurred in 52% of infants, and only early and successful extubation was associated with decreased respiratory morbidities. Predictors capable of promptly identifying infants with a high likelihood of early extubation success or failure are needed.

An artificial intelligence system to predict the optimal timing for mechanical ventilation weaning for intensive care unit patients: A two-stage prediction approach

Background

For the intensivists, accurate assessment of the ideal timing for successful weaning from the mechanical ventilation (MV) in the intensive care unit (ICU) is very challenging.

Purpose

Using artificial intelligence (AI) approach to build two-stage predictive models, namely, the try-weaning stage and weaning MV stage to determine the optimal timing of weaning from MV for ICU intubated patients, and implement into practice for assisting clinical decision making.

Methods

AI and machine learning (ML) technologies were used to establish the predictive models in the stages. Each stage comprised 11 prediction time points with 11 prediction models. Twenty-five features were used for the first-stage models while 20 features were used for the second-stage models. The optimal models for each time point were selected for further practical implementation in a digital dashboard style. Seven machine learning algorithms including Logistic Regression (LR), Random Forest (RF), Support Vector Machines (SVM), K Nearest Neighbor (KNN), lightGBM, XGBoost, and Multilayer Perception (MLP) were used. The electronic medical records of the intubated ICU patients of Chi Mei Medical Center (CMMC) from 2016 to 2019 were included for modeling. Models with the highest area under the receiver operating characteristic curve (AUC) were regarded as optimal models and used to develop the prediction system accordingly.

Results

A total of 5,873 cases were included in machine learning modeling for Stage 1 with the AUCs of optimal models ranging from 0.843 to 0.953. Further, 4,172 cases were included for Stage 2 with the AUCs of optimal models ranging from 0.889 to 0.944. A prediction system (dashboard) with the optimal models of the two stages was developed and deployed in the ICU setting. Respiratory care members expressed high recognition of the AI dashboard assisting ventilator weaning decisions. Also, the impact analysis of with- and without-AI assistance revealed that our AI models could shorten the patients' intubation time by 21 hours, besides gaining the benefit of substantial consistency between these two decision-making strategies.

Conclusion

We noticed that the two-stage AI prediction models could effectively and precisely predict the optimal timing to wean intubated patients in the ICU from ventilator use. This could reduce patient discomfort, improve medical quality, and lower medical costs. This AI-assisted prediction system is beneficial for clinicians to cope with a high demand for ventilators during the COVID-19 pandemic.

Weaning and extubation from neonatal mechanical ventilation: an evidenced-based review

Mechanical ventilation is a lifesaving treatment used to treat critical neonatal patients. It facilitates gas exchange, oxygenation, and CO2 removal. Despite advances in non-invasive ventilatory support methods in neonates, invasive ventilation (i.e., ventilation via an endotracheal tube) is still a standard treatment in NICUs. This ventilation approach may cause injury despite its advantages, especially in preterm neonates. Therefore, it is recommended that neonatologists consider weaning neonates from invasive mechanical ventilation as soon as possible. This review examines the steps required for the neonate's appropriate weaning and safe extubation from mechanical ventilation.

The Outcome- or Cost-Effectiveness Analysis of LUS-Based Care or CXR-Based Care of Neonatal Lung Diseases: The Clinical Practice Evidence from a Level Ⅲ NICU in China

OBJECTIVE

To compare the effect of managing neonatal lung disease with lung ultrasound (LUS) or chest X-ray (CXR) monitoring on health outcomes and cost-effectiveness.

METHODS

The data obtained from the NICU of the Beijing Chaoyang District Maternal and Child Healthcare Hospital were used as the study group, as LUS has completely replaced CXR in managing newborn lung disease in the hospital for the past 5 years. The primary outcomes of this study were the misdiagnosis rate of respiratory distress syndrome (RDS), the using status of mechanical ventilation, the incidence rate of bronchopulmonary dysplasia (BPD) and the survival rate in hospitalized infants. The secondary outcomes included the use pulmonary surfactant (PS), and the mortality rate of severe diseases (such as pneumothorax, pulmonary hemorrhage and RDS, etc.).

RESULTS

Managing neonatal lung disease with LUS monitoring may enable the following effects: The frequency of ventilator use reducing by 40.2%; the duration of mechanical ventilation reducing by 67.5%; and the frequency of ventilator weaning failure being totally avoided. A misdiagnosis rate of 30% for RDS was also avoided. The dosage of PS was significantly reduced by 50% to 75%. No BPD occurred in the LUS-based care group for 5 years. The fatality rates of RDS, pneumothorax and pulmonary hemorrhage decreased by 100%. The poor prognosis rate of VLBW infants decreased by 85%, and the total mortality rate of hospitalized infants decreased by 90%. Therefore, the cost of LUS-based care was inevitably saved.

CONCLUSIONS

Diagnosing and managing neonatal lung diseases with LUS monitoring have significant benefits, and this technology should be widely promoted and applied around the world.

Predictors of extubation outcomes among extremely and very preterm infants: a retrospective cohort study

OBJECTIVE

To explore the clinical or sociodemographic predictors for both successful and failed extubation among Chinese extremely and very preterm infants METHODS: A retrospective cohort study was carried out among extremely and very preterm infants born at less than 32 weeks of gestational age (GA).

RESULTS

Compared with the infants who experienced extubation failure, the successful infants had higher birth weight (OR 0.997; CI 0.996-0.998), higher GA (OR 0.582; 95% CI 0.499-0.678), a caesarean section delivery (OR 0.598; 95% CI 0.380-0.939), a higher five-minute Apgar score (OR 0.501; 95% CI 0.257-0.977), and a higher pH prior to extubation (OR 0.008; 95% CI 0.001-0.058). Failed extubation was associated with older mothers (OR 1.055; 95% CI 1.013-1.099), infants intubated in the delivery room (OR 2.820; 95% CI 1.742-4.563), a higher fraction of inspired oxygen (FiO₂) prior to extubation (OR 5.246; 95% CI 2.540-10.835), higher partial pressure of carbon dioxide (PCO₂) prior to extubation (OR 7.820; 95% CI 3.725-16.420), and higher amounts of lactic acid (OR 1.478;95% CI 1.063-2.056).

CONCLUSIONS

Higher GA, higher pre-extubation pH, lower pre-extubation FiO₂ and PCO, and lower age at extubation are significant predictors of successful extubation among extremely and very preterm infants.

Machine learning for prediction of bronchopulmonary dysplasia-free survival among very preterm infants

Background

Bronchopulmonary dysplasia (BPD) is one of the most common and serious sequelae of prematurity. Prompt diagnosis using prediction tools is crucial for early intervention and prevention of further adverse effects. This study aims to develop a BPD-free survival prediction tool based on the concept of the developmental origin of BPD with machine learning.

Methods

Datasets comprising perinatal factors and early postnatal respiratory support were used for initial model development, followed by combining the two models into a final ensemble model using logistic regression. Simulation of clinical scenarios was performed.

Results

Data from 689 infants were included in the study. We randomly selected data from 80% of infants for model development and used the remaining 20% for validation. The performance of the final model was assessed by receiver operating characteristics which showed 0.921 (95% CI: 0.899–0.943) and 0.899 (95% CI: 0.848–0.949) for the training and the validation datasets, respectively. Simulation data suggests that extubating to CPAP is superior to NIPPV in BPD-free survival. Additionally, successful extubation may be defined as no reintubation for 9 days following initial extubation.

Conclusions

Machine learning-based BPD prediction based on perinatal features and respiratory data may have clinical applicability to promote early targeted intervention in high-risk infants.

Noninvasive Neurally Adjusted Ventilation in Postextubation Stabilization of Preterm Infants: A Randomized Controlled Study

OBJECTIVE

To compare the effects of noninvasive neurally adjusted ventilatory assist (NIV-NAVA) to nasal continuous positive airway pressure (NCPAP) in achieving successful extubation in preterm infants.

STUDY DESIGN

This prospective, single-center, randomized controlled trial enrolled preterm infants born at <30 weeks of gestation who received invasive ventilation. Participants were assigned at random to either NIV-NAVA or NCPAP after their first extubation from invasive ventilation. The primary outcome of the study was extubation failure within 72 hours of extubation. Electrical activity of the diaphragm (Edi) values were collected before extubation and at 1, 4, 12, and 24 hours after extubation.

RESULTS

A total of 78 infants were enrolled, including 35 infants in the NIV-NAVA group and 35 infants in the NCPAP group. Extubation failure within 72 hours of extubation was higher in the NCPAP group than in the NIV-NAVA group (28.6% vs 8.6%; P = .031). The duration of respiratory support and incidence of severe bronchopulmonary dysplasia were similar in the 2 groups. Peak and swing Edi values were comparable before and at 1 hour after extubation, but values at 4, 12, and 24 hours after extubation were lower in the NIV-NAVA group compared with the NCPAP group.

CONCLUSIONS

In the present trial, NIV-NAVA was more effective than NCPAP in preventing extubation failure in preterm infants.

TRIAL REGISTRATION

ClinicalTrials.gov: NCT02590757.

Predictors of extubation success: a population-based study of neonates below a gestational age of 26 weeks

OBJECTIVE

The aim of the study was to investigate first extubation attempts among extremely premature (EP) infants and to explore factors that may increase the quality of clinical judgement of extubation readiness.

DESIGN AND METHOD

A population-based study was conducted to explore first extubation attempts for EP infants born before a gestational age (GA) of 26 weeks in Norway between 1 January 2013 and 31 December 2018. Eligible infants were identified via the Norwegian Neonatal Network database. The primary outcome was successful extubation, defined as no reintubation within 72 hours after extubation.

RESULTS

Among 482 eligible infants, 316 first extubation attempts were identified. Overall, 173 (55%) infants were successfully extubated, whereas the first attempt failed in 143 (45%) infants. A total of 261 (83%) infants were extubated from conventional ventilation (CV), and 55 (17%) infants were extubated from high-frequency oscillatory ventilation (HFOV). In extubation from CV, pre-extubation fraction of inspired oxygen (FiO₂) ≤0.35, higher Apgar score, higher GA, female sex and higher postnatal age were important predictors of successful extubation. In extubation from HFOV, a pre-extubation FiO₂ level ≤0.35 was a relevant predictor of successful extubation.

CONCLUSIONS

The correct timing of extubation in EP infants is important. In this national cohort, 55% of the first extubation attempts were successful. Our results suggest that additional emphasis on oxygen requirement, sex and general condition at birth may further increase extubation success when clinicians are about to extubate EP infants for the first time.

Respiratory management for extremely premature infants born at 22 to 23 weeks of gestation in proactive centers in Sweden, Japan, and USA

Survival of preterm newborn infants have increased steadily since the introduction of surfactant treatment and antenatal steroids. In the absence of randomized controlled trials on ventilatory strategies in extremely preterm infants, we present ventilatory strategies applied during the initial phase and the continued ventilatory care as applied in three centers with proactive prenatal and postnatal management and well documented good outcomes in terms of mortality and morbidity in this cohort of infants.

Can Fraction of Inspired Oxygen Predict Extubation Failure in Preterm Infants?

Background: Prolonged mechanical ventilation in preterm infants may cause complications. We aimed to analyze the variables affecting extubation outcomes in preterm infants at high risk of extubation failure. Methods: This was a single-center, observational, retrospective study. Extubation failure was defined as survival with the need for reintubation within 72 h. Successfully extubated neonates (group 1) were compared to those with failed extubation (group 2). Multivariate logistic regression analysis evaluated factors that predicted extubation outcomes. Results: Eighty infants with a birth weight under 1000 g and/or gestational age (GA) under 28 weeks were included. Extubation failure occurred in 29 (36.2%) and success in 51 (63.8%) neonates. Most failures (75.9%) occurred within 24 h. Pre-extubation inspired oxygen fraction (FiO₂) of 27% had a sensitivity of 58.6% and specificity of 64.7% for extubation failure. Post-extubation FiO₂ of 32% had a sensitivity of 65.5% and specificity of 62.8% for failure. Prolonged membrane rupture (PROM) and high GA were associated with extubation success in multivariate logistic regression analysis. Conclusions: High GA and PROM were associated with extubation success. Pre- and post-extubation FiO₂ values were not significantly predictive of extubation failure. Further studies should evaluate if overall assessment, including ventilatory parameters and clinical factors, can predict extubation success in neonates.

The Impact of Time Interval Between First Extubation and Reintubation on Bronchopulmonary Dysplasia or Death in Very Low Birth Weight Infants

OBJECTIVE

To explore the association between time from first extubation to reintubation and moderate-to-severe bronchopulmonary dysplasia (BPD) or death in very low birth weight infants.

STUDY DESIGN

Infants weighing <1,500 g at birth, requiring mechanical ventilation, and undergoing their initial extubation were retrospectively included from January 2014 to December 2021. They were divided into the moderate-to-severe BPD/death group and the comparison group according to the incidence of moderate-to-severe BPD or death. We defined time to reintubation as the time interval between first extubation and reintubation. In a stepwise multivariate logistic regression analysis, we examined the association between time to reintubation and moderate-to-severe BPD/death using different observation windows after initial extubation (24-h intervals).

RESULTS

A total of 244 infants were recruited, including 57 cases in the moderate-severe BPD/death group and 187 cases in the comparison group, and 93 (38.1%) cases were reintubated at least one time after their first extubation. Univariate analysis showed that reintubation rates within different observation windows in the moderate-to-severe BPD/death group were statistically significantly (p < 0.05) higher than those in the comparison group. Multivariate regression analysis showed that reintubation within observation windows 48 h or 72 h post-extubation was an independent risk factor in moderate-to-severe BPD/death and death, but not moderate-to-severe BPD. When the time window was 48 h, the probability of moderate-to-severe BPD/death [odds ratio (OR): 3.778, 95% confidence interval (CI): 1.293-11.039] or death (OR: 4.734, 95% CI: 1.158-19.354) was highest. While after extending the observation window to include reintubations after 72 h from initial extubation, reintubation was not associated with increased risk of moderate-to-severe BPD and/or death.

CONCLUSIONS

Not all reintubations conferred increased risks of BPD/death. Only reintubation within 72 h from initial extubation was independently associated with increased likelihood of moderate-to-severe BPD/death and death in very low birth weight infants, and reintubation within the first 48 h post-extubation posed the greatest risk.

Diaphragmatic electromyography during a spontaneous breathing trial to predict extubation failure in preterm infants

BACKGROUND

Premature attempts at extubation and prolonged episodes of ventilatory support in preterm infants have adverse outcomes. The aim of this study was to determine whether measuring the electrical activity of the diaphragm during a spontaneous breathing trial (SBT) could predict extubation failure in preterm infants.

METHODS

When infants were ready for extubation, the electrical activity of the diaphragm was measured by transcutaneous electromyography (EMG) before and during a SBT when the infants were on endotracheal continuous positive airway pressure.

RESULTS

Forty-eight infants were recruited (median (IQR) gestational age of 27.2 (25.6-30.4) weeks). Three infants did not pass the SBT and 13 failed extubation. The amplitude of the EMG increased during the SBT [2.3 (1.5-4.2) versus 3.5 (2.1-5.3) µV; p < 0.001]. In the whole cohort, postmenstrual age (PMA) was the strongest predictor for extubation failure (area under the curve (AUC) 0.77). In infants of gestational age <29 weeks, the percentage change of the EMG predicted extubation failure with an AUC of 0.74 while PMA was not associated with the outcome of extubation.

CONCLUSIONS

In all preterm infants, PMA was the strongest predictor of extubation failure; in those born <29 weeks of gestation, diaphragmatic electromyography during an SBT was the best predictor of extubation failure.

IMPACT

Composite assessments of readiness for extubation may be beneficial in the preterm population. Diaphragmatic electromyography measured by surface electrodes is a non-invasive technique to assess the electrical activity of the diaphragm. Postmenstrual age was the strongest predictor of extubation outcome in preterm infants. The change in diaphragmatic activity during a spontaneous breathing trial in extremely prematurely born infants can predict subsequent extubation failure with moderate sensitivity and specificity.

Decision to extubate extremely preterm infants: art, science or gamble?

In the modern era of neonatology, mechanical ventilation has been restricted to a smaller and more immature population of extremely preterm infants. Given the adverse outcomes associated with mechanical ventilation, every effort is made to extubate these infants as early as possible. However, the scientific basis for determining extubation readiness remains imprecise and primarily guided by clinical judgement, which is highly variable and subjective. In the absence of accurate tools to assess extubation readiness, many infants fail their extubation attempt and require reintubation, which also increases complications. Recent advances in the field have led to unravelling some of the complexities surrounding extubation in this population. This review aims to synthesise the available knowledge and provide a more evidence-based approach towards the reporting of extubation outcomes and assessment of extubation readiness in extremely preterm infants.

Impact of early respiratory care for extremely preterm infants

Despite advances in neonatal intensive care, more than half of surviving infants born extremely preterm (EP; < 28 weeks' gestation) develop bronchopulmonary dysplasia (BPD). Prevention of BPD is critical because of its associated mortality and morbidity, including adverse neurodevelopmental outcomes and respiratory health in later childhood and beyond. The respiratory care of EP infants begins before birth, then continues in the delivery room and throughout the primary hospitalization. This chapter will review the evidence for interventions after birth that might improve outcomes for infants born EP, including the timing of umbilical cord clamping, strategies to avoid or minimize exposure to mechanical ventilation, modes of mechanical ventilation and non-invasive respiratory support, oxygen saturation targets, postnatal corticosteroids and other adjunct therapies.

Relationship Between the Respiratory Severity Score and Extubation Failure in Very-Low-Birth-Weight Premature Infants

Objective:

The objective of the study is to investigate the utility of the respiratory severity score (RSS), an easy-to-use, non-invasive respiratory failure assessment tool that does not require arterial blood sampling, for predicting extubation failure in very-low-birth-weight premature infants.

Methods:

Demographic characteristics, clinical course, and neonatal morbidities were retrospectively analyzed. Data were obtained from the files of infants who were admitted to our unit between February 2016 and September 2020, were born before 30 weeks’ gestation, and had a birth weight <1250 g. Extubation success was defined as no need for reintubation for 72 h after extubation. RSS and RSS/kg values before each patient’s first planned extubation were calculated. RSS values before extubation and risk factors for extubation failure were compared between infants in the successful and failed extubation groups.

Results:

Our study enrolled 142 infants who met the inclusion criteria. The extubation failure rate was 30.2% (43/142). Early gestation, low birth weight, male sex, high RSS, grade ≥3 intraventricular hemorrhage, late-onset sepsis, low weight at the time of extubation, and postmenstrual age at the time of extubation were identified as risk factors for extubation failure. In the logistic regression analysis including these risk factors, RSS/kg remained a significant risk factor, along with late-onset sepsis (OR 25.7 [95% CI: 5.70–115.76]; p<0.001). In the receiver operating characteristic analysis of RSS values, at a cutoff value of 2.13 (area under the curve: 82.5%), RSS/kg had 77% sensitivity and 78% specificity (p<0.001). The duration of mechanical ventilation and hospital stay were prolonged in infants with extubation failure. The incidence rates of stage ≥3 retinopathy of prematurity and stage ≥2 necrotizing enterocolitis were also higher.

Conclusions:

High RSS and RSS/kg values were closely associated with extubation failure and can be used as a non-invasive assessment tool to support clinical decision-making, and thus reduce the rate of extubation failure.

Effects of heliox and non-invasive neurally adjusted ventilatory assist (NIV-NAVA) in preterm infants

Due to its unique properties, helium–oxygen (heliox) mixtures may provide benefits during non-invasive ventilation, however, knowledge regarding the effects of such therapy in premature infants is limited. This is the first report of heliox non-invasive neurally adjusted ventilatory assist (NIV-NAVA) ventilation applied in neonates born ≤ 32 weeks gestational age. After baseline NIV-NAVA ventilation with a standard mixture of air and oxygen, heliox was introduced for 3 h, followed by 3 h of air-oxygen. Heart rate, peripheral capillary oxygen saturation, cerebral oxygenation, electrical activity of the diaphragm (Edi) and selected ventilatory parameters (e.g., respiratory rate, peak inspiratory pressure) were continuously monitored. We found that application of heliox NIV-NAVA in preterm infants was feasible and associated with a prompt and significant decrease of Edi suggesting reduced respiratory effort, while all other parameters were stable throughout the study, and had similar values during heliox and air-oxygen ventilation. This therapy may potentially enhance the efficacy of non-invasive respiratory support in preterm neonates and reduce the number of infants progressing to ventilatory failure.

Clinical survey and predictors for the development of tracheobronchomalacia in preterm infants

BACKGROUND

Tracheobronchomalacia (TBM) contributes to the increased morbidity and mortality observed in preterm infants. Effective strategies for the prevention of TBM are necessary to achieve better outcomes. We sought to identify risk factors associated with the development of TBM in preterm infants. Optimal cut-off values for each risk factor were also determined.

METHODS

A total of 80 infants who were born at 36 week's gestation or earlier and underwent flexible bronchoscopy were included in our study sample. A comparison of demographic and clinical risk factors between those with TBM (n = 35, 44%) and those without TBM (n = 45, 56%) was conducted using multivariate logistic regression analysis. Receiver operating characteristic curve analysis was performed to determine the appropriate cut-off values for predicting the development of TBM.

RESULTS

In the multivariate analysis, only peak inspiratory pressure (PIP) and the number of intubation days remained significantly different between infants with and without TBM. Preterm infants with TBM received higher PIP (odds ratio: [OR], 1.067; 95% confidence interval [CI], 1.010-1.128; p = .020) and were intubated for longer (odds ratio [OR], 1.019; 95% CI, 1.003-1.035; p = .016) than those without TBM. Infants who received PIP > 19.5 cmH₂ O or were intubated for >79.5 days were associated with a significantly higher risk of presence of TBM.

CONCLUSION

High PIP and prolonged intubation were major risk factors for the development of TBM in premature infants. Those who require PIP > 19.5 cmH₂ O or intubation >79.5 days warrant bronchoscopy examination for early diagnosis and management of TBM.

Respiratory setback associated with extubation failure in extremely preterm infants

BACKGROUND AND OBJECTIVES

Extubation failure in preterm infants is associated with an increased risk of mortality and morbidity. There is limited evidence to suggest if the increased morbidities are due to inherent differences among infants who fail or succeed; or whether these are due to a true respiratory setback among those who fail extubation. The aim of this study was to evaluate the respiratory status of infants who fail extubation and to assess the time taken for these infants to achieve pre-extubation respiratory status.

METHODS

This was a retrospective study of infants with birth weight ≤ 1250 g who were born between January 2009 and December 2016. Infants were eligible if they failed first elective extubation. Extubation failure was defined as need for re-intubation within 5 days of extubation. Ventilator settings, blood gas parameters, respiratory severity score (RSS), and ventilation index (VI) were used to assess the respiratory status of infants.

RESULTS

Out of 384 infants, 76% were successful and 24% failed extubation. Among those who failed extubation 91%, 77%, and 56% infants remained intubated at 24 h, 72 h, and 7 days, respectively. Respiratory status was worse at 24 and 72 h after re-intubation when compared to pre-extubation levels. The median times for RSS and VI to reach pre-extubation levels were 4 and 7 days, respectively.

CONCLUSION

Among preterm infants, failed elective extubation is associated with a significant setback in the respiratory status. Infants who fail an extubation attempt may not achieve pre-extubation respiratory status for many days after reintubation.

Protocol for a randomised controlled trial comparing two CPAP levels to prevent extubation failure in extremely preterm infants

INTRODUCTION

Respiratory distress syndrome is a complication of prematurity and extremely preterm infants born before 28 weeks' gestation often require endotracheal intubation and mechanical ventilation. In this high-risk population, mechanical ventilation is associated with lung injury and contributes to bronchopulmonary dysplasia. Therefore, clinicians attempt to extubate infants as quickly and use non-invasive respiratory support such as nasal continuous positive airway pressure (CPAP) to facilitate the transition. However, approximately 60% of extremely preterm infants experience 'extubation failure' and require reintubation. While CPAP pressures of 5-8 cm H2O are commonly used, the optimal CPAP pressure is unknown, and higher pressures may be beneficial in avoiding extubation failure. Our trial is the Extubation CPAP Level Assessment Trial (ÉCLAT). The aim of this trial is to compare higher CPAP pressures 9-11 cm H2O with a current standard pressures of 6-8 cmH2O on extubation failure in extremely preterm infants.

METHODS AND ANALYSIS

200 extremely preterm infants will be recruited prior to their first extubation from mechanical ventilation to CPAP. This is a parallel group randomised controlled trial. Infants will be randomised to one of two set CPAP pressures: CPAP 10 cmH2O (intervention) or CPAP 7 cmH2O (control). The primary outcome will be extubation failure (reintubation) within 7 days. Statistical analysis will follow standard methods for randomised trials on an intention to treat basis. For the primary outcome, this will be by intention to treat, adjusted for the prerandomisation strata (GA and centre). We will use the appropriate parametric and non-parametric statistical tests.

ETHICS AND DISSEMINATION

Ethics approval has been granted by the Monash Health Human Research Ethics Committees. Amendments to the trial protocol will be submitted for approval. The findings of this study will be written into a clinical trial report manuscript and disseminated via peer-reviewed journals (on-line or in press) and presented at national and international conferences.Trial registration numberACTRN12618001638224; pre-results.

Reintubation rates after extubation to different non-invasive ventilation modes in preterm infants

INTRODUCTION

Respiratory Distress Syndrome (RDS) is a common cause of neonatal morbidity and mortality in premature newborns. In this study, we aim to compare the reintubation rate in preterm babies with RDS who were extubated to Nasal Continuous Positive Airway Pressure (NCPAP) versus those extubated to Nasal Intermittent Positive Pressure Ventilation (NIPPV).

METHODS

This is a retrospective study conducted in the Neonatal Intensive Care Unit (NICU) of Women's Wellness and Research Center (WWRC), Doha, Qatar. The medical files (n = 220) of ventilated preterm infants with gestational age ranging between 28 weeks 0 days and 36 weeks + 6 days gestation and extubated to non-invasive respiratory support (whether NCPAP, NIPPV, or Nasal Cannula) during the period from January 2016 to December 2017 were reviewed.

RESULTS

From the study group of 220 babies, n = 97 (44%) babies were extubated to CPAP, n = 77 (35%) were extubated to NIPPV, and n = 46 (21%) babies were extubated to Nasal Cannula (NC). Out of the n = 220 babies, 18 (8.2%) were reintubated within 1 week after extubation. 14 of the 18 (77.8%) were reintubated within 48 h of extubation. Eleven babies needed reintubation after being extubated to NCPAP (11.2%) and seven were reintubated after extubation to NIPPV (9.2%), none of those who were extubated to NC required reintubation (P = 0.203). The reintubation rate was not affected by extubation to any form of non-invasive ventilation (P = 0.625). The mode of ventilation before extubation does not affect the reintubation rate (P = 0.877). The presence of PDA and NEC was strongly associated with reintubation which increased by two and four-folds respectively in those morbidities. There is an increased risk of reintubation with babies suffering from NEC and BPD and this was associated with an increased risk of hospital stay with a P-value ranging (from 0.02-0.003). Using multivariate logistic regression, NEC the NEC (OR = 5.52, 95% CI 1.26, 24.11, P = 0.023) and the vaginal delivery (OR = 0.23, 95% CI 0.07, 0.78, P = 0.018) remained significantly associated with reintubation.

CONCLUSION

Reintubation rates were less with NIPPV when compared with NCPAP, however, this difference was not statistically significant. This study highlights the need for further research studies with a larger number of neonates in different gestational ages birth weight categories. Ascertaining this information will provide valuable data for the factors that contribute to re-intubation rates and influence the decision-making and management of RDS patients in the future.

Short-term effects of synchronized vs. non-synchronized NIPPV in preterm infants: study protocol for an unmasked randomized crossover trial

BACKGROUND

Non-invasive ventilation (NIV) has been recommended as the best respiratory support for preterm infants with respiratory distress syndrome (RDS). However, the best NIV technique to be used as first intention in RDS management has not yet been established. Nasal intermittent positive pressure ventilation (NIPPV) may be synchronized (SNIPPV) or non-synchronized to the infant's breathing efforts. The aim of the study is to evaluate the short-term effects of SNIPPV vs. NIPPV on the cardiorespiratory events, trying to identify the best ventilation modality for preterm infants at their first approach to NIV ventilation support.

METHODS

An unmasked randomized crossover study with three treatment phases was designed. All newborn infants < 32 weeks of gestational age with RDS needing NIV ventilation as first intention or after extubation will be consecutively enrolled in the study and randomized to the NIPPV or SNIPPV arm. After stabilization, enrolled patients will be alternatively ventilated with two different techniques for two time frames of 4 h each. NIPPV and SNIPPV will be administered with the same ventilator and the same interface, maintaining continuous assisted ventilation without patient discomfort. During the whole duration of the study, the patient's cardiorespiratory data and data from the ventilator will be simultaneously recorded using a polygraph connected to a computer. The primary outcome is the frequency of episodes of oxygen desaturation. Secondary outcomes are the number of the cardiorespiratory events, FiO₂ necessity, newborn pain score evaluation, synchronization index, and thoracoabdominal asynchrony. The calculated sample size was of 30 patients.

DISCUSSION

It is known that NIPPV produces a percentage of ineffective acts due to asynchronies between the ventilator and the infant's breaths. On the other hand, an ineffective synchronization could increase work of breathing. Our hypothesis is that an efficient synchronization could reduce the respiratory work and increase the volume per minute exchanged without interfering with the natural respiratory rhythm of the patient with RDS. The results of this study will allow us to evaluate the effectiveness of the synchronization, demonstrating whether SNIPPV is the most effective non-invasive ventilation mode in preterm infants with RDS at their first approach to NIV ventilation.

TRIAL REGISTRATION

ClinicalTrials.gov NCT03289936 . Registered on September 21, 2017.

Predictors and outcomes of extubation failure in extremely preterm infants

AIM

To determine predictors and outcomes of extubation failure in extremely preterm (EP) infants born <28 weeks' gestational age (GA).

METHODS

Retrospective clinical audit across two tertiary-level neonatal intensive care units in Melbourne, Australia. Two-hundred and four EP infants who survived to their first extubation from mechanical ventilation. Extubation failure (re-intubation) within 7 days after the first extubation.

RESULTS

Lower GA (odds ratio [OR] 0.71, 95% confidence interval (CI), 0.61-0.89, P < 0.001) and higher pre-extubation measured mean airway pressure (MAP) on the mechanical ventilator (OR 1.9 [95% CI 1.41-2.51], P < 0.001) predicted extubation failure. The area under a receiver operating characteristic curve for GA and MAP was 0.77 (95% CI 0.70-0.82). After adjustment for GA, infants who experienced extubation failure had higher rates of bronchopulmonary dysplasia (P < 0.001), post-natal systemic corticosteroid treatment (P < 0.001), airway trauma (P < 0.003), longer durations of treatment with mechanical ventilation (P < 0.001), non-invasive respiratory support (P < 0.001), supplemental oxygen therapy (P = 0.05) and longer hospitalisation (P = 0.025).

CONCLUSIONS

Lower GA and higher pre-extubation measured MAP were predictive of extubation failure within 7 days in extremely preterm infants. Extubation failure was associated with increased morbidity and extended periods of respiratory support and hospitalisation.

Could myocardial function be predictive of successful extubation in newborns and infants?

OBJECTIVE

To investigate the relationship between cardiac function and extubation readiness in infants using speckle tracking echocardiography.

WORKING HYPOTHESIS

Cardiac function combined with established clinical parameters may better identify readiness for extubation.

STUDY DESIGN

Pilot prospective observational study.

PATIENT SELECTION

Mechanically ventilated infants were included.

METHODOLOGY

Cardiac function was assessed by echocardiography immediately before extubation. Systolic and diastolic function in the left (LV) and right ventricles (RV) were assessed by measurement of longitudinal strain (LS), and circumferential strain (CS) in the LV only. Pulmonary artery pressures were assessed using the velocity of tricuspid regurgitation jet (TR), septal position, and end-systolic eccentricity index (EI ES). Cases who extubated successfully (Group 1) were compared to cases who required reintubation (Group 2).

RESULTS

Twenty-five cases were included. LV CS and RV LS were significantly lower in those who required reintubation (Group 2) compared to those who were successfully extubated (Group 1) (LV CS, -21 (12)% vs. -33 (3)%, p = .001; RV LS -19 (2.7)% vs. -20 (2.5)%, p = .04). TR was absent in all cases. The septal shape was normal in 18 cases (72%), displaced to the left in 7 (28%) cases. No significant differences were found in LV EI ES between groups.

[Risk factors for the first ventilator weaning failure in preterm infants receiving invasive mechanical ventilation]

OBJECTIVE

To study the risk factors for the first ventilator weaning failure and the relationship between the weaning failure and prognosis in preterm infants receiving invasive mechanical ventilation.

METHODS

A retrospective analysis was performed for the preterm infants who were admitted to the Neonatal Intensive Care Unit of Peking University Third Hospital and received mechanical ventilation within 72 hours after birth. According to whether reintubation was required within 72 hours after the first weaning, the infants were divided into a successful weaning group and a failed weaning group.

RESULTS

A total of 282 preterm infants were enrolled, and there were 43 infants (15.2%) in the failed weaning group. Compared with the successful weaning group, the failed weaning group had significantly lower gestational age and birth weight (P < 0.05), a significantly higher rate of intubation in the delivery room (P < 0.05), and a significantly higher proportion of infants with patent ductus arteriosus (PDA; diameter ≥ 2.5 mm) (P < 0.05). Use of ≥ 2 vasoactive agents before ventilator weaning (OR=2.48, 95%CI:1.22-5.03, P < 0.05) and PDA (≥ 2.5 mm) (OR=4.54, 95%CI:2.02-10.24, P < 0.05) were risk factors for ventilator weaning failure. Compared with the successful weaning group, the failed weaning group had significantly higher incidence rates of ventilator-associated pneumonia, moderate-to-severe bronchopulmonary dysplasia, and sepsis (P < 0.05). The oxygen inhalation time and hospital stay in the failed weaning group were significantly longer than those in the successful weaning group (P < 0.05).

CONCLUSIONS

Use of ≥ 2 vasoactive agents before ventilator weaning and PDA (≥ 2.5 mm) are risk factors for ventilator weaning failure, and ventilator weaning failure may be associated with adverse outcomes in hospitalized preterm infants.