Neonatal mortality risk assessment using SNAPPE- II score in a neonatal intensive care unit

Neonatal death prediction scores: a systematic review and meta-analysis

OBJECTIVE

To compare, through a systematic review and meta-analysis of observational accuracy studies, the main existing neonatal death prediction scores.

METHOD

Systematic review and meta-analysis of observational accuracy studies. The databases accessed were MEDLINE, ELSEVIER, LILACS, SciELO, OpenGrey, Open Access Thesis and Dissertations, EMBASE, Web of Science, SCOPUS and Cochrane Library. For qualitative analysis, Quality Assessment of Diagnostic Accuracy Studies 2 was used. For the quantitative analysis, the area under the curve and the SE were used, as well as the inverse of the variance as a weight measure, DerSimonian and Laird as a measure of random effects, Higgins' I² as an estimate of heterogeneity, Z as a final measure with a 95% confidence level.

RESULTS

55 studies were analysed, 8 scores were compared in a total of 193 849 newborns included. The most accurate neonatal death prediction score was Score for Neonatal Acute Physiology Perinatal Extension II (SNAPPE II) (0.89 (95% CI 0.86 to 0.92)) and the least accurate was gestational age (0.75 (95% CI 0.71 to 0.79)).

CONCLUSION

SNAPPE II was the most accurate score found in this study. Despite this, the choice of score depends on the situation and setting in which the newborn is inserted, and it is up to the researcher to analyse and decide which one to use based on practicality and the possibility of local implementation. Given this, it is interesting to carry out new prospective studies to improve the prediction of neonatal deaths around the world.

PROSPERO REGISTRATION NUMBER

CRD42023462425.

Predictors of mortality and severe illness from Escherichia coli sepsis in neonates

Neonatal Escherichia coli (E. coli) sepsis is increasing. There is limited data on the factors contributing to increased mortality and severity of illness in neonatal E. coli sepsis. A retrospective review of neonates (<30 days) admitted to a Level IV NICU in the United States from 2008 to 2022 diagnosed with E. coli bloodstream or cerebrospinal fluid infection was conducted. Primary outcome was defined as mortality from or severe illness during E. coli infection (defined as a need for inotropic support or metabolic acidosis). E. coli neonatal sepsis rate increased from 2008 to 2022 (average of 1.12 per 1000 live births). The primary outcome, which occurred in 57.4% of cases, was independently associated with prematurity, neutropenia, and thrombocytopenia. Ampicillin resistance was not associated with the primary outcome. GA, neutropenia, and thrombocytopenia but not ampicillin resistance, are associated with mortality or severe illness from E. coli sepsis.

The Effect of a Light-Dark Cycle on Premature Infants in the Neonatal Intensive Care Unit: A Randomized Controlled Study

PURPOSE

To investigate potential differences in discharge time, feeding methods and amounts, daily weight gain, vital signs, pain, and comfort levels among preterm infants born at 28-32 weeks' gestation who were hospitalized in the neonatal intensive care unit during long-term follow-up while implementing a light-dark cycle.

DESIGN AND METHODS

This is a randomized controlled study conducted with the support of a day-night cycle in premature infants born at 28-32 weeks' gestation and admitted to the neonatal intensive care unit of a teaching and research hospital affiliated with the Ministry of Health. The study compared the follow-up results from hospitalization to discharge over a period of 8 weeks.

RESULTS

50% of premature infants admitted to the unit are multiple pregnancies. There was no significant difference in discharge weight, comfort level, pain level, vital signs of the infants included in the study (p > 0.05). The optimal development of infant feeding patterns was examinedand it was observed that the study group had significantly improved before the control group in terms of the time to switch to full enteral feeding and oral feeding (p < 0,05). The daily weight gain of the babies was examined, it was seen that the weight gain was higher in the study group compared to the control group (p < 0,05). The mean duration of hospitalization was compared, it was seen that the babies in the study group were discharged significantly earlier (p < 0,05).

CONCLUSION

The study compared the long-term outcomes of premature babies hospitalized in neonatal intensive care and babies exposed to a light-dark cycle and regularly monitored in standard care. The results showed that the babies in the study group had higher daily weight gain and were discharged earlier than the control group. There were also no statistically significant differences in comfort and pain scores, vital signs or oxygen saturation between the study and control groups.

PRACTICE IMPLICATIONS

A light-dark cycle was found to be a feasible and promising intervention for infants at 28-32 weeks' gestation. It was a nurse-led management of care that could be integrated into the usual care of 28-32-week-old babies in neonatal units.

Early prediction of need for invasive mechanical ventilation in the neonatal intensive care unit using artificial intelligence and electronic health records: a clinical study

BACKGROUND

Respiratory support is crucial for newborns with underdeveloped lung. The clinical outcomes of patients depend on the clinician's ability to recognize the status underlying the presented symptoms and signs. With the increasing number of high-risk infants, artificial intelligence (AI) should be considered as a tool for personalized neonatal care. Continuous monitoring of vital signs is essential in cardiorespiratory care. In this study, we developed deep learning (DL) prediction models for rapid and accurate detection of mechanical ventilation requirements in neonates using electronic health records (EHR).

METHODS

We utilized data from the neonatal intensive care unit in a single center, collected between March 3, 2012, and March 4, 2022, including 1,394 patient records used for model development, consisting of 505 and 889 patients with and without invasive mechanical ventilation (IMV) support, respectively. The proposed model architecture includes feature embedding using feature-wise fully connected (FC) layers, followed by three bidirectional long short-term memory (LSTM) layers.

RESULTS

A mean gestational age (GA) was 36.61 ± 3.25 weeks, and the mean birth weight was 2,734.01 ± 784.98 g. The IMV group had lower GA, birth weight, and longer hospitalization duration than the non-IMV group (P < 0.05). Our proposed model, tested on a dataset from March 4, 2019, to March 4, 2022. The mean AUROC of our proposed model for IMV support prediction performance demonstrated 0.861 (95%CI, 0.853-0.869). It is superior to conventional approaches, such as newborn early warning score systems (NEWS), Random Forest, and eXtreme gradient boosting (XGBoost) with 0.611 (95%CI, 0.600-0.622), 0.837 (95%CI, 0.828-0.845), and 0.0.831 (95%CI, 0.821-0.845), respectively. The highest AUPRC value is shown in the proposed model at 0.327 (95%CI, 0.308-0.347). The proposed model performed more accurate predictions as gestational age decreased. Additionally, the model exhibited the lowest alarm rate while maintaining the same sensitivity level.

CONCLUSION

Deep learning approaches can help accurately standardize the prediction of invasive mechanical ventilation for neonatal patients and facilitate advanced neonatal care. The results of predictive, recall, and alarm performances of the proposed model outperformed the other models.

Outcomes of neonates born through meconium-stained amniotic fluid pre and post 2015 NRP guideline implementation

A shift in the Neonatal Resuscitation Program (NRP) guidelines occurred in 2015 from routine intubation and endotracheal suctioning of all meconium-stained non-vigorous infants towards less aggressive interventions based on response to initial resuscitation. This study aims to examine the impact of this change on outcomes of non-vigorous infants born through meconium-stained amniotic fluid at a level III academic NICU encompassing years before and after the change in guideline. This single-center retrospective study compared NICU therapies and clinical outcomes of 117 non-vigorous newborns pre-guideline implementation to 106 non-vigorous newborns post-guideline implementation. Nearly two thirds of infants in the pre-guideline cohort received endotracheal suctioning with recovery of meconium compared to less than a third of infants in the post-guideline cohort (p<0.01). Though a higher proportion of the pre-guideline cohort were admitted to the NICU for respiratory issues compared to the post-guideline cohort, the two groups did not differ significantly with regard to morbidity and therapies. Despite a marked reduction in rates of intubation and endotracheal suctioning, there is no difference in outcomes between pre-guideline implementation vs post-guideline implementation in non-vigorous meconium-stained infants, supporting the recent NRP guideline change and highlighting the benefit of expectant management.

Comparison of STOPS and SNAPPE-II in Predicting Neonatal Survival at Hospital Discharge: A Prospective, Multicentric, Observational Study

OBJECTIVE

To compare SNAPPE-II and STOPS admission severity scores in neonates admitted to neonatal intensive care unit (NICU) with a gestational age of ≥ 33 wk.

METHODS

In this multicenter, prospective, observational study, the sickness scoring was done on all the neonates at 12 h after admission to the NICUs. The scoring systems were compared by the area under the curve (AUC) on the receiver operating characteristics (ROC) curve.

RESULTS

A total of 669 neonates with gestational age ≥ 33 wk (mortality rate: 2.4%), who were admitted to five participating NICUs within 24 h of birth, were included. Both SNAPPE-II and STOPS had the good discriminatory and predictive ability for mortality with AUCs of 0.965 [95% confidence interval (CI): 0.94-0.98] and 0.92 (95% CI: 0.87-0.99), respectively. The STOPS scoring system with a cutoff score ≥ 4 on the ROC curve had 85% accuracy, whereas the SNAPPE-II cutoff score ≥ 33 on the ROC curve had 94% accuracy in predicting mortality.

CONCLUSION

In infants with the gestational age of ≥ 33 wk, SNAPPE-II and STOPS showed similar predictive ability, but the STOPS score, being a simpler clinical tool, might be more useful in resource-limited settings.

Determining resuscitation threshold for extremely preterm infants based on the survival rates without severe neurological injury

Background

Published guidelines on decision-making and resuscitation of extremely preterm infants primarily focus on high-income countries. For rapidly industrializing ones like China, there is a lack of population-based data for informing prenatal management and practice guidelines.

Methods

The Sino-northern Neonatal Network conducted a prospective multi-centre cohort study between 1 January 2018 and 31 December 2021. Infants with a gestational age (GA) between 22 (postnatal age in days = 0) and 28 (postnatal age in days = 6) admitted to 40 tertiary NICUs in northern China were included and evaluated for death or severe neurological injury before discharge.

Results

For all extremely preterm infants (n = 5838), the proportion of admission to the neonatal was 4.1% at 22-24 weeks, 27.2% at 25-26 weeks, and 75.2% at 27 and 28 weeks. Among 2228 infants admitted to the NICU, 216 (11.1%) were still elected for withdrawal of care (WIC) due to non-medical factors. Survival rates without severe neurological injury were 6.7% for infants at 22-23 weeks, 28.0% at 24 weeks, 56.7% at 24 weeks, 61.7% at 25 weeks, 79.9% at 26 weeks, and 84.5% at 27 and 28 weeks. Compared with traditional criterion at 28 weeks, the relative risk for death or severe neurological injury were 1.53 (95% confidence interval (CI) = 1.26-1.86) at 27 weeks, 2.32 (95% CI = 1.73-3.11) at 26 weeks, 3.62 (95% CI = 2.43-5.40) at 25 weeks, and 8.91 (95% CI = 4.69-16.96) at 24 weeks. The NICUs with higher proportion of WIC also had a higher rate of death or severe neurological injury after maximal intensive care (MIC).

Conclusions

Compared to the traditional threshold of 28 weeks, more infants received MIC after 25 weeks, leading to significant increases in survival rates without severe neurological injury. Therefore, the resuscitation threshold should be gradually adjusted from 28 to 25 weeks based on reliable capacity.

Registration

China Clinical Trials Registry. ID: ChiCTR1900025234.

A Study of the Prediction of Mortality in a Tertiary Care Hospital Using the Modified Sick Neonatal Score (MSNS): An Observational Cross-Sectional Study

PURPOSE

India is a major contributor to neonatal deaths worldwide. There is a paucity of amenities for the management of neonatal health issues in rural areas of our country. Hence, there is a need to invent a reliable scoring system for the analysis of neonatal mortality.

AIM

The aim of the study is to evaluate the Modified Sick Neonatal Score (MSNS) as a predictor of mortality in neonatal care units in resource-limited settings.

MATERIALS AND METHODS

This cross-sectional observational study was performed in the intensive care unit of our hospital. All the data were collected and analyzed using IBM Corp.'s Statistical Package for Social Sciences (SPSS) software.

RESULTS

Overall, 71 participants were considered for the present study. The common clinical diagnoses noticed in our participants were meconium aspiration, malformation, and jaundice. The MSNS score compared between expired and discharged participants is found to be statistically significant with p<0.05.

CONCLUSION

The MSNS scoring system is considered an ideal scoring system for detecting early mortality in neonates.

Post-transport TOPS score as a predictive marker of mortality among transported neonates and its comparative analysis with SNAP-II PE

Aim

Multiple parameters are available to predict the outcome of critically sick neonates admitted in neonatal intensive care unit (NICU). Main aim of the study is to validate the role of TOPS, especially the post-transport TOPS score as a simplified assessment of neonatal acute physiology in predicting mortality among transported neonates admitted at level III NICU. Also, to compare the efficiency of post transport TOPS score with SNAP II PE in predicting mortality.

Methods

A prospective study carried out with 85 neonates transported from various primary health care centres to level III NICU. Physiological status of the neonates was assessed with the help of pre and post transport TOPS scores. Post-transport TOPS score was recorded immediately after the admission and SNAP II PE within 24 h of admission at level III NICU. Receiver operating characteristics analysis was performed to observe the mortality prediction efficiency of TOPS score and was compared with SNAP II PE.

Results

64 neonates were died due to asphyxia and preterm birth (32%) related complications. Strong significant association with the mortality rate was found between the total post transport TOPS score (0.001) and SNAP II PE (0.003). The AUC, sensitivity and specificity of post transport TOPS score for a cut-off value ≤7 were 0.900, 87.5% and 80% and significant (<0.001) and for SNAP II PE for a cut-off value >12 were 0.913, 75.5% and 100% and is significant (<0.001).

Conclusion

TOPS score, especially the post transport TOPS score has an equally good prediction capacity of mortality similar like SNAP II PE among mobilised critically ill neonates. Hence, the TOPS score can be used as a simple and effective method to predict mortality risk among transported neonates immediately after admission at level III NICU.

The role of skin-to-skin contact in exclusive breastfeeding: a cohort study

OBJETIVE

To understand the role of exposure to skin-to-skin contact and its minimum duration in determining exclusive breastfeeding at hospital discharge in infants weighing up to 1,800g at birth.

METHODS

A multicenter cohort study was carried out in five Brazilian neonatal units. Infants weighing ≤ 1,800g at birth were eligible. Skin-to-skin contact time was recorded by the health care team and parents on an individual chart. Maternal and infant data was obtained from maternal questionnaires and medical records. The Classification Tree, a machine learning method, was used for data analysis; the tree growth algorithm, using statistical tests, partitions the dataset into mutually exclusive subsets that best describe the response variable and calculates appropriate cut-off points for continuous variables, thus generating an efficient explanatory model for the outcome under study.

RESULTS

A total of 388 infants participated in the study, with a median of 31.6 (IQR = 29–31.8) weeks of gestation age and birth weight of 1,429g (IQR = 1,202–1,610). The exclusive breastfeeding rate at discharge was 61.6%. For infant’s weighting between 1,125g and 1,655g, exposed to skin-to-skin contact was strongly associated with exclusive breastfeeding. Moreover, infants who made an average > 149.6 min/day of skin-to-skin contact had higher chances in this outcome (74% versus 46%). In this group, those who received a severity score (SNAPPE-II) equal to zero increased their chances of breastfeeding (83% versus 63%).

CONCLUSION

Skin-to-skin contact proved to be of great relevance in maintaining exclusive breastfeeding at hospital discharge for preterm infants weighing 1,125g–1,655g at birth, especially in those with lower severity scores.

Skin-to-skin contact and deaths in newborns weighing up to 1800 grams: a cohort study

OBJECTIVE

To evaluate the association between dose of skin-to-skin contact (SSC) per day and initiation time with the occurrence of deaths in newborns with weight up to 1800g.

METHOD

Multicentric cohort in five Brazilian neonatal units, including newborns with a birth weight of ≤1800g. The time of SSC was registered in individual file, by the team or family during the hospitalization. Maternal and newborn data were obtained through questionnaires applied to mothers and in medical records. Classification Tree was used for data analysis.

RESULTS

The performance of the first SSC after 206h was significantly associated with death (p = 0.02). Although there was no association between SSC/day and death (p = 0.09), the number of deaths among those who performed more than 146.9 minutes/day was lower (3;1.5%) than among those who performed this practice for a shorter time (13;6.4%), a fact considered of great clinical importance. Early and late infections present statistically significant associations with the outcome. The chance of death was equal to zero when there was no early infection in the group with the longest duration of SSC. This probability was also equal to zero in the absence of late sepsis for the group with less than 146.9 minutes/day of SSC.

CONCLUSIONS

The first SSC before 206 hours of life is recommended in order to observe a reduction in the risk of neonatal death. Staying in SSC for more than 146.9 min/day seems to be clinically beneficial for these neonates mostly when it was associated with the absence of infection.

Comparison of CRIB-II with SNAPPE-II for predicting survival and morbidities before hospital discharge in neonates with gestation ≤ 32 weeks: a prospective multicentric observational study

Various studies validated and compared Score for Neonatal Acute Physiology with Perinatal extension-II (SNAPPE-II) and Clinical Risk Index for Babies-II (CRIB-II) admission sickness severity scores for predicting survival, but very few studies compared them for predicting the morbidities in preterm infants. In this multicenter prospective observational study, SNAPPE-II and CRIB-II newborn illness severity scores were compared for predicting mortality and morbidities in infants with gestational age of ≤ 32 weeks. Major morbidities were classified as bronchopulmonary dysplasia, abnormal cranial ultrasound (presence of intraventricular hemorrhage grade III or more or periventricular leukomalacia grade II to IV), and retinopathy of prematurity requiring treatment. Combined adverse outcome was defined as death or any major morbidity. Comparison of the scoring systems was done by area under the curve (AUC) on receiver operating characteristics curve (ROC curve) analysis. A total of 419 neonates who were admitted to 5 participating NICUs were studied. The mortality rate in the study population was 8.8%. Both CRIB-II (AUC: 0.795) and SNAPPE-II (AUC: 0.78) had good predictive ability for in-hospital mortality. For predicting any one of the major morbidities and combined adverse outcome, CRIB-II had better predictive ability than SNAPPE-II with AUC of 0.83 vs. 0.70 and 0.85 vs. 0.74, respectively.

CONCLUSION

In infants with gestational age of ≤ 32 weeks, both CRIB-II and SNAPPE-II are good scoring systems for predicting mortality. CRIB-II, being a simpler scoring system and having better predictive ability for major morbidities and combined adverse outcome, is preferable over SNAPPE-II.

WHAT IS KNOWN

• SNAPPE-II and CRIB-II scores have good predictive ability on in-hospital mortality in preterm neonates.

WHAT IS NEW

• SNAPPE-II and CRIB-II both have good predictive ability for mortality, but CRIB-II has better ability for short-term morbidities related to the prematurity.

Neonatal brain injury influences structural connectivity and childhood functional outcomes

Neonatal brain injury may impact brain development and lead to lifelong functional impairments. Hypoxic-ischemic encephalopathy (HIE) and congenital heart disease (CHD) are two common causes of neonatal brain injury differing in timing and mechanism. Maturation of whole-brain neural networks can be quantified during development using diffusion magnetic resonance imaging (dMRI) in combination with graph theory metrics. DMRI of 35 subjects with CHD and 62 subjects with HIE were compared to understand differences in the effects of HIE and CHD on the development of network topological parameters and functional outcomes. CHD newborns had worse 12–18 month language (P<0.01) and 30 month cognitive (P<0.01), language (P = 0.05), motor outcomes (P = 0.01). Global efficiency, a metric of brain integration, was lower in CHD (P = 0.03) than in HIE, but transitivity, modularity and small-worldness were similar. After controlling for clinical factors known to affect neurodevelopmental outcomes, we observed that global efficiency was highly associated with 30 month motor outcomes (P = 0.02) in both groups. To explore neural correlates of adverse language outcomes in CHD, we used hypothesis-based and data-driven approaches to identify pathways with altered structural connectivity. We found that connectivity strength in the superior longitudinal fasciculus (SLF) tract 2 was inversely associated with expressive language. After false discovery rate correction, a whole connectome edge analysis identified 18 pathways that were hypoconnected in the CHD cohort as compared to HIE. In sum, our study shows that neonatal structural connectivity predicts early motor development after HIE or in subjects with CHD, and regional SLF connectivity is associated with language outcomes. Further research is needed to determine if and how brain networks change over time and whether those changes represent recovery or ongoing dysfunction. This knowledge will directly inform strategies to optimize neurologic functional outcomes after neonatal brain injury.

SNAPPE II Score as a Predictor of Neonatal Mortality in NICU at a Tertiary Care Hospital in Pakistan

Introduction

The concept of illness severity scoring has been around for long and is currently being utilized in many neonatal intensive care unit (NICU). Scoring systems that help to quantify mortality risks on the basis of clinical conditions not only help in estimating prognosis, but also help clinicians in making decisions particularly in situations presenting with dilemmas. This study aims to determine SNAPPE-II (Score for Neonatal Acute Physiology-Perinatal Extension) score as a predictor of neonatal mortality in NICU at a tertiary care hospital in Pakistan.

Methodology

It was a longitudinal cohort study. The study was conducted at a neonatal intensive care unit (NICU) of Aga Khan University Hospital (AKUH) Karachi, Pakistan. All neonates were included who were born in AKUH and who needed respiratory support in NICU.

Results

A total of 333 newborns were enrolled for this study. Out of those 30 (9.1%) neonates expired while 298 (90.9%) survived. Area Under the Receiver operative curve was calculated to obtain the SNAPPE-II score’s diagnostic discrimination ability. Area under the curve (AUC) was 80.2±4.6% which corresponds to a moderate diagnostic accuracy for the prediction of neonatal mortality. The 95% CI for this was between 71.1-89.2%. SNAPPE-II category III (>40) was found to be the strongest predictor of mortality, with a sensitivity of 40% and a specificity of 98.7%.

Conclusion

The SNAPPE-II scoring system, we conclude, might be a valuable technique for predicting newborn death in resource-constrained NICUs.

Machine Learning Algorithms to Predict Mortality of Neonates on Mechanical Intubation for Respiratory Failure

BACKGROUND

Early identification of critically ill neonates with poor outcomes can optimize therapeutic strategies. We aimed to examine whether machine learning (ML) methods can improve mortality prediction for neonatal intensive care unit (NICU) patients on intubation for respiratory failure.

METHODS

A total of 1734 neonates with respiratory failure were randomly divided into training (70%, n = 1214) and test (30%, n = 520) sets. The primary outcome was the probability of NICU mortality. The areas under the receiver operating characteristic curves (AUCs) of several ML algorithms were compared with those of the conventional neonatal illness severity scoring systems including the NTISS and SNAPPE-II.

RESULTS

For NICU mortality, the random forest (RF) model showed the highest AUC (0.939 (0.921-0.958)) for the prediction of neonates with respiratory failure, and the bagged classification and regression tree model demonstrated the next best results (0.915 (0.891-0.939)). The AUCs of both models were significantly better than the traditional NTISS (0.836 (0.800-0.871)) and SNAPPE-II scores (0.805 (0.766-0.843)). The superior performances were confirmed by higher accuracy and F1 score and better calibration, and the superior and net benefit was confirmed by decision curve analysis. In addition, Shapley additive explanation (SHAP) values were utilized to explain the RF prediction model.

CONCLUSIONS

Machine learning algorithms increase the accuracy and predictive ability for mortality of neonates with respiratory failure compared with conventional neonatal illness severity scores. The RF model is suitable for clinical use in the NICU, and clinicians can gain insights and have better communication with families in advance.

Association between genetic variations in carbamoyl-phosphate synthetase gene and persistent neonatal pulmonary hypertension

Persistent pulmonary hypertension of the new-borns (PPHN) is one of the main etiologies of morbidity as well as mortality in neonates. Previous studies found that genetic polymorphisms in urea cycle enzymes are associated with PPHN. Few of the genetic polymorphisms in neonates have been recognized with PPHN. We aimed to find out the prevalence of the CPS-I gene polymorphism and to correlate the genotype with the serum nitric oxide (NO) levels in Egyptian neonates with idiopathic PPHN. We included neonates diagnosed with PPH (n = 150) while the control group included healthy neonates with matched age and sex (n = 100). The CPS-I gene polymorphism: A/C, trans-version substitution, rs4399666 genotype was identified using TaqMan-based quantitative PCR. The results revealed that the CPS-I A/C rs4399666 gene polymorphism and lower serum NO levels were significantly associated with idiopathic PPHN in neonates. In addition, serum NO level was significantly associated with an rs4366999 A/C variant gene in idiopathic PPHN (p = 0.001). Univariable regression analysis demonstrated that there was a significant association between CPS-I A/C rs4399666 CC and increased risk of PPHN (odd ratio, 95% CI of 1.8 (0.78 to 1.75), p-value = 0.04).Conclusion: We concluded that mutant CPS-I A/C rs4399666 minor variant especially the homozygous CC genotype is frequently distributed among the PPHN group. This demonstrates that the presence of mutant CPS-I rs4399666 does not necessarily predispose to the development of PPHN in neonates, but nonetheless, if the C allele is inherited in the homozygous CC genotype, it is associated with a higher risk of PPHN. What is Known: • Prior studies found that polymorphisms in urea cycle enzyme genes are associated with PPHN. • Association between CPS-1 gene polymorphisms is significantly associated with PPHN. What is New: • The prevalence of CPS-1, A/C trans-version substitution, rs4399666 gene polymorphism in Egyptian neonates presented with idiopathic PPHN. • Mutant CPS-I A/C rs4399666 especially the homozygous CC genotype is more frequently distributed among PPHN, and it is significantly associated with low serum nitric oxide level.

Clinician-family relationships may impact neonatal intensive care: clinicians' perspectives

OBJECTIVE

Collaborative clinician-family relationships are necessary for the delivery of successful patient- and family-centered care (PFCC) in the NICU. Challenging clinician-family relationships may undermine such collaboration and the potential impacts on patient care are unknown.

STUDY DESIGN

Consistent caregivers were surveyed to describe their relationships and collaboration with families of infants hospitalized ≥ 28 days. Medical record review collected infant and family characteristics hypothesized to impact relationships. Mixed methods analysis was performed.

RESULTS

Clinicians completed 243 surveys representing 77 families. Clinicians reported low collaboration with families who were not at the bedside and/or did not speak English. Clinicians perceived most clinician-family relationships impact the infant's hospital course. Negative impacts included communication challenges, mistrust or frustration with the team and disruptions to patient care.

CONCLUSION

This study identifies features of clinician-family relationships that may negatively impact an infant's NICU stay. Targeting supports for these families is necessary to achieve effective PFCC.

Development and Validation of a Clinical Prognostic Risk Score to Predict Early Neonatal Mortality, Ethiopia: A Receiver Operating Characteristic Curve Analysis

Background

Early neonatal death is the death of a live-born baby within the first seven days of life, which is 73% of all postnatal deaths in the globe. This study aimed to develop and validate a prognostic clinical risk tool for the prediction of early neonatal death.

Methods

A prospective follow-up study was conducted among 393 neonates at Debre Tabor Referral hospital, Northwest Ethiopia. Multivariable logistic regression model was employed to identify potential prognostic determinants for early neonatal mortality. Area under receiver operating characteristics curve (AUROC) was used to check the model discrimination probability using ‘pROC’ R-package. Model calibration plot was checked using ‘givitiR’ R-package. Finally, a risk score prediction tool was developed for ease of applicability. Decision curve analysis was done for cost-benefit analysis and to check the clinical impact of the model.

Results

Overall, 15.27% (95% CI: 12.03–19.18) of neonates had the event of death during the follow-up period. Maternal undernutrition, antenatal follow-up less than four times, birth asphyxia, low birth weight, and not exclusive breastfeeding were the prognostic predictors of early neonatal mortality. The AUROC for the reduced model was 88.7% (95% CI: 83.8–93.6%), which had good discriminative probability. The AUROC of the simplified risk score algorithm was 87.8% (95% CI, 82.7–92.9%). The sensitivity and specificity of the risk score tool was 70% and 89%, respectively. The true prediction accuracy of the risk score tool to predict early neonatal mortality was 86%, and the false prediction probability was 13%.

Conclusion

We developed an early neonatal death prediction tool using easily available maternal and neonatal characteristics for resource-limited settings. This risk prediction using risk score is an easily applicable tool to identify neonates at a higher risk of having early neonatal mortality. This risk score tool would offer an opportunity to reduce early neonatal mortality, thus improving the overall early neonatal death in a resource-limited setting.

Machine Learning Approaches to Predict In-Hospital Mortality among Neonates with Clinically Suspected Sepsis in the Neonatal Intensive Care Unit

Background: preterm and critically ill neonates often experience clinically suspected sepsis during their prolonged hospitalization in the neonatal intensive care unit (NICU), which can be the initial sign of final adverse outcomes. Therefore, we aimed to utilize machine learning approaches to predict neonatal in-hospital mortality through data-driven learning. Methods: a total of 1095 neonates who experienced clinically suspected sepsis in a tertiary-level NICU in Taiwan between August 2017 and July 2020 were enrolled. Clinically suspected sepsis was defined based on clinical features and laboratory criteria and the administration of empiric antibiotics by clinicians. The variables used for analysis included patient demographics, clinical features, laboratory data, and medications. The machine learning methods used included deep neural network (DNN), k-nearest neighbors, support vector machine, random forest, and extreme gradient boost. The performance of these models was evaluated using the area under the receiver operating characteristic curve (AUC). Results: the final in-hospital mortality of this cohort was 8.2% (90 neonates died). A total of 765 (69.8%) and 330 (30.2%) patients were randomly assigned to the training and test sets, respectively. Regarding the efficacy of the single model that most accurately predicted the outcome, DNN exhibited the greatest AUC (0.923, 95% confidence interval [CI] 0.953–0.893) and the best accuracy (95.64%, 95% CI 96.76–94.52%), Cohen’s kappa coefficient value (0.74, 95% CI 0.79–0.69) and Matthews correlation coefficient value (0.75, 95% CI 0.80–0.70). The top three most influential variables in the DNN importance matrix plot were the requirement of ventilator support at the onset of suspected sepsis, the feeding conditions, and intravascular volume expansion. The model performance was indistinguishable between the training and test sets. Conclusions: the DNN model was successfully established to predict in-hospital mortality in neonates with clinically suspected sepsis, and the machine learning algorithm is applicable for clinicians to gain insights and have better communication with families in advance.

Therapeutic effects and outcomes of rescue high-frequency oscillatory ventilation for premature infants with severe refractory respiratory failure

Despite wide application of high frequency oscillatory ventilation (HFOV) in neonates with respiratory distress, little has been reported about its rescue use in preterm infants. We aimed to evaluate the therapeutic effects of HFOV in preterm neonates with refractory respiratory failure and investigate the independent risk factors of in-hospital mortality. We retrospectively analyzed data collected prospectively (January 2011–December 2018) in four neonatal intensive care units of two tertiary-level medical centers in Taiwan. All premature infants (gestational age 24–34 weeks) receiving HFOV as rescue therapy for refractory respiratory failure were included. A total of 668 preterm neonates with refractory respiratory failure were enrolled. The median (IQR) gestational age and birth weight were 27.3 (25.3–31.0) weeks and 915.0 (710.0–1380.0) g, respectively. Pre-HFOV use of cardiac inotropic agents and inhaled nitric oxide were 70.5% and 23.4%, respectively. The oxygenation index (OI), FiO₂, and AaDO₂ were markedly increased after HFOV initiation (all p < 0.001), and can be decreased within 24–48 h (all p < 0.001) after use of HFOV. 375 (56.1%) patients had a good response to HFOV within 3 days. The final in-hospital mortality rate was 34.7%. No association was found between specific primary pulmonary disease and survival in multivariate analysis. We found preterm neonates with gestational age < 28 weeks, occurrences of sepsis, severe hypotension, multiple organ dysfunctions, initial higher severity of respiratory failure and response to HFOV within the first 72 h were independently associated with final in-hospital mortality. The mortality rate of preterm neonates with severe respiratory failure remains high after rescue HFOV treatment. Aggressive therapeutic interventions to treat sepsis and prevent organ dysfunctions are the suggested strategies to optimize outcomes.

Prediction of perinatal death using machine learning models: a birth registry-based cohort study in northern Tanzania

OBJECTIVE

We aimed to determine the key predictors of perinatal deaths using machine learning models compared with the logistic regression model.

DESIGN

A secondary data analysis using the Kilimanjaro Christian Medical Centre (KCMC) Medical Birth Registry cohort from 2000 to 2015. We assessed the discriminative ability of models using the area under the receiver operating characteristics curve (AUC) and the net benefit using decision curve analysis.

SETTING

The KCMC is a zonal referral hospital located in Moshi Municipality, Kilimanjaro region, Northern Tanzania. The Medical Birth Registry is within the hospital grounds at the Reproductive and Child Health Centre.

PARTICIPANTS

Singleton deliveries (n=42 319) with complete records from 2000 to 2015.

PRIMARY OUTCOME MEASURES

Perinatal death (composite of stillbirths and early neonatal deaths). These outcomes were only captured before mothers were discharged from the hospital.

RESULTS

The proportion of perinatal deaths was 3.7%. There were no statistically significant differences in the predictive performance of four machine learning models except for bagging, which had a significantly lower performance (AUC 0.76, 95% CI 0.74 to 0.79, p=0.006) compared with the logistic regression model (AUC 0.78, 95% CI 0.76 to 0.81). However, in the decision curve analysis, the machine learning models had a higher net benefit (ie, the correct classification of perinatal deaths considering a trade-off between false-negatives and false-positives)-over the logistic regression model across a range of threshold probability values.

CONCLUSIONS

In this cohort, there was no significant difference in the prediction of perinatal deaths between machine learning and logistic regression models, except for bagging. The machine learning models had a higher net benefit, as its predictive ability of perinatal death was considerably superior over the logistic regression model. The machine learning models, as demonstrated by our study, can be used to improve the prediction of perinatal deaths and triage for women at risk.

Plasma Oxidative Status in Preterm Infants Receiving LCPUFA Supplementation: A Pilot Study

After birth, preterm infants are deficient in arachidonic acid (ARA), docosahexaenoic acid (DHA), and antioxidants, increasing their risk of oxidative stress-related pathologies. The principal aim was to evaluate if supplementation with long-chain polyunsaturated fatty acids (LCPUFAs) improves antioxidant defenses. In total, 21 preterm infants were supplemented with ARA and DHA in a 2:1 ratio (ARA:DHA-S) or with medium-chain triglycerides (MCT-S). Plasma n-3 and n-6 LCPUFAs were measured at birth, postnatal day 28, and 36 weeks of postmenstrual age (36 WPA) by gas chromatography–mass spectroscopy. Plasma antioxidants (glutathione (GSH), catalase, and thiols) and oxidative damage biomarkers (malondialdehyde (MDA), carbonyls) were analyzed at the same time points by spectrophotometry, and scores of antioxidant status (Antiox-S) and oxidative damage (Proxy-S) were calculated. At 36 WPA, linoleic acid (LA) and dihomo-γ-linolenic acid (DGLA) were decreased in ARA:DHA-S compared to the MCT-S group (LA: ARA:DHA-S = 18.54 ± 1.68, MCT-S = 22.80 ± 1.41; p = 0.018; DGLA: ARA:DHA-S = 1.68 ± 0.38, MCT-S = 2.32 ± 0.58; p = 0.018). Furthermore, α-linolenic acid (ALA) was increased in ARA:DHA-S (ARA:DHA-S = 0.52 ± 0.33, MCT-S = 0.22 ± 0.10; p = 0.018). Additionally, LA:DHA ratio was decreased in the ARA:DHA-S compared to control group (ARA:DHA-S = 6.26 ± 2.35, MCT-S = 8.21 ± 2.65; p = 0.045). By the end of supplementation (36 WPA), catalase, thiol groups, and Antiox-S were significantly higher in neonates receiving ARA:DHA-S compared to those receiving MCT-S, with no differences in oxidative stress biomarkers. In conclusion, ARA:DHA supplementation in preterm neonates resulted in an overall improvement in antioxidant to oxidant balance and a decrease in early fatty acid precursors of the n-6 relative to the n-3 pathway. These effects may reduce oxidative stress and inflammation.