Apnea in acute bilirubin encephalopathy

Detecting acute bilirubin encephalopathy in neonates based on multimodal MRI with deep learning

BACKGROUND

Differentiating acute bilirubin encephalopathy (ABE) from non-ABE in neonates with hyperbilirubinemia (HB) from routine magnetic resonance imaging (MRI) is extremely challenging since both conditions demonstrate similar T1 hyperintensities. To this end, we investigated whether the integration of multimodal MRI from routine clinical scans with deep-learning approaches could improve diagnostic performance.

METHODS

A total of 75 neonates with ABE and 75 neonates with HB (non-ABE) were included in the study. Each patient had three types of multimodal images taken, i.e., a T1-weighted image (T1WI), a T2-weighted image (T2WI), and an apparent diffusion coefficient (ADC) map. The three types of MRI contrasts and their combination were fed into two deep convolutional neural networks (CNNs), i.e., ResNet18 and DenseNet201. The performance of CNNs was compared with a traditional statistical method named logistic regression.

RESULTS

We demonstrated that diagnostic methods with the multimodal data were better than any of the single-modal data. Both CNN models outperformed the logistic regression method. The best performance was achieved by DenseNet201 with the combination of three modalities of T1WI, T2WI, and ADC, with an accuracy of 0.929 ± 0.042 and an area under the curve (AUC) of 0.991 ± 0.007.

CONCLUSIONS

Our study demonstrated that CNN models with multimodal MRI significantly improve the accuracy of diagnosing ABE.

IMPACT

We proposed an efficient strategy of detecting ABE in neonates based on multimodal MRI with deep learning, which achieved an accuracy of 0.929 ± 0.042 and an AUC of 0.991 ± 0.007. We demonstrated the advantage of integrating multimodal MRI in detecting ABE in neonates with HB, using deep-learning models. Our strategy of diagnosing ABE using deep-learning techniques with multimodal MRI from routine clinical scans is potentially applicable to clinical practice.

Magnetic Resonance Image of Neonatal Acute Bilirubin Encephalopathy: A Diffusion Kurtosis Imaging Study

Background and Objective: The abnormal T1-weighted imaging of MRI can be used to characterize neonatal acute bilirubin encephalopathy (ABE) in newborns, but has limited use in evaluating the severity and prognosis of ABE. This study aims to assess the value of diffusion kurtosis imaging (DKI) in detecting ABE and understanding its pathogenesis.

Method: Seventy-six newborns with hyperbilirubinemia were grouped into three groups (mild group, moderate group, and severe group) based on serum bilirubin levels. All the patients underwent conventional MRI and DKI serial, as well as 40 healthy full-term infants (control group). The regions of interest (ROIs) were the bilateral globus pallidus, dorsal thalamus, frontal lobe, auditory radiation, superior temporal gyrus, substantia nigra, hippocampus, putamen, and inferior olivary nucleus. The values of mean diffusivity (MD), axial kurtosis (AK), radial kurtosis (RK), and mean kurtosis (MK), and fractional anisotropy (FA), radial diffusivity (RD), and axis diffusivity (AD) of the ROIs were evaluated. All newborns were followed up and evaluated using the Denver Development Screening Test (DDST). According to the follow-up results, the patients were divided into the normal group, the suspicious abnormal group, and the abnormal group.

Result: Compared with the control group, significant differences were observed with the increased MK of dorsal thalamus, AD of globus pallidus in the moderate group, and increased RD, MK, AK, and RK value of globus pallidus, dorsal thalamus, auditory radiation, superior temporal gyrus, and hippocampus in the severe group. The peak value of total serum bilirubin was moderately correlated with the MK of globus pallidus, dorsal thalamus, and auditory radiation and was positively correlated with the other kurtosis value. Out of 76 patients, 40 finished the DDST, and only 9 patients showed an abnormality. Compared with the normal group, the AK value of inferior olivary nucleus showed significant differences (p < 0.05) in the suspicious abnormal group, and the MK of globus pallidus, temporal gyrus, and auditory radiation; RK of globus pallidus, dorsal thalamus, and auditory radiation; and MD of globus pallidus showed significant differences (p < 0.05) in the abnormal group.

Conclusion: DKI can reflect the subtle structural changes of neonatal ABE, and MK is a sensitive indicator to indicate the severity of brain damage.

Pathogenesis and Management of Indirect Hyperbilirubinemia in Preterm Neonates Less Than 35 Weeks: Moving Toward a Standardized Approach

Premature infants have a higher incidence of indirect hyperbilirubinemia than term infants. Management of neonatal indirect hyperbilirubinemia in late preterm and term neonates has been well addressed by recognized, consensus-based guidelines. However, the extension of these guidelines to the preterm population has been an area of uncertainty because of limited evidence. This leads to variation in clinical practice and lack of recognition of the spectrum of bilirubin-induced neurologic dysfunction (BIND) in this population. Preterm infants are metabolically immature and at higher risk for BIND at lower bilirubin levels than their term counterparts. Early use of phototherapy to eliminate BIND and minimize the need for exchange transfusion is the goal of treatment in premature neonates. Although considered relatively safe, phototherapy does have side effects, and some NICUs tend to overuse phototherapy. In this review, we describe the epidemiology and pathophysiology of BIND in preterm neonates, and discuss our approach to standardized management of indirect hyperbilirubinemia in the vulnerable preterm population. The proposed treatment charts suggest early use of phototherapy in preterm neonates with the aim of reducing exposure to high irradiance levels, minimizing the need for exchange transfusions, and preventing BIND. The charts are pragmatic and have additional curves for stopping phototherapy and escalating its intensity. Having a standardized approach would support future research and quality improvement initiatives that examine dose and duration of phototherapy exposure with relation to outcomes.

Diagnosis of Bilirubin Encephalopathy in Preterm Infants with Dyskinetic Cerebral Palsy

INTRODUCTION

Very preterm infants are susceptible to bilirubin neurotoxicity, the signs of which are unclear during early infancy. We investigated children born preterm and later diagnosed with bilirubin encephalopathy (BE) to gain insights into accurate early diagnosis.

METHODS

We identified 93 children born preterm and clinically diagnosed with BE who visited our hospital between 2006 and 2018. Perinatal history, findings of auditory brainstem response (ABR), brain magnetic resonance imaging (MRI), and functional outcomes were investigated retrospectively based on chart review.

RESULTS

The mean gestational age and birth weights were 27.2 weeks and 991 g, respectively. During the neonatal period, only 3% (2/71) had exchange transfusions, and none were diagnosed with acute BE. ABR was abnormal in 64% (51/80), but the majority (34/51) required no hearing aids. Brain MRI taken between 6 and 18 months of age revealed bilateral T2 hyperintensity of the globi pallidi in 91% (60/66); subsequently, the rate decreased with age. Functional communication outcomes were markedly superior to gross motor and hand function outcomes.

CONCLUSION

For early diagnosis of BE, brain MRI is recommended at a corrected age of between 6 and 18 months, especially for those with abnormal ABR during early infancy, and even with no apparent history of marked neonatal hyperbilirubinemia.

Influence of Moderate Hyperbilirubinemia on Cardiorespiratory Control in Preterm Lambs

Hyperbilirubinemia (HB) is responsible for neonatal jaundice in 60% of term newborns and 90% of preterm infants. Neonatal HB can induce neurological damage (acute HB encephalopathy) and has been associated with persistent apneas. The objective of the present study was to investigate the immediate and delayed effects of moderate, clinically-relevant HB on cardiorespiratory control in preterm lambs. Two groups of five preterm lambs, namely control and HB, were studied. At day five of life, moderate HB (150-250 μmol/L) was induced and maintained during 17 h in the HB group while control lambs received a placebo solution. Six hours after HB onset, 7-h polysomnographic recordings with electrocardiogram (ECG) and respiratory (RESP) signals were performed to assess the immediate effects of HB on heart rate variability (HRV), respiratory rate variability (RRV), and cardiorespiratory interrelations. Identical recordings were repeated 72 h after HB induction to examine the delayed effects of HB on HRV, RRV and cardiorespiratory interrelations. Our results demonstrate a higher HRV and vagal activity immediately after induction of moderate HB. Meanwhile, a decrease in respiratory rate with an increase in both long- and short-term RRV was also noted, as well as a higher amplitude of the respiratory sinus arrhythmia and cardiorespiratory coupling. Seventy-two hours later, the alterations in HRV, RRV, and cardiorespiratory interrelations were attenuated, although a number of them were still present, suggesting a lasting influence of HB on the basal control of the cardiorespiratory system. Our results pave the way for studies in human preterms to assess the relevance of monitoring HRV, RRV, and cardiorespiratory interrelations to detect the acute neurological effects of HB and consequently adapt the treatment of neonatal jaundice.

Clinicopathological Spectrum of Bilirubin Encephalopathy/Kernicterus

Bilirubin encephalopathy/kernicterus is relatively rare, but continues to occur despite universal newborn screening. What is more interesting is the spectrum of clinical and even neuropathological findings that have been reported in the literature to be associated with bilirubin encephalopathy and kernicterus. In this review, the authors discuss the array of clinicopathological findings reported in the context of bilirubin encephalopathy and kernicterus, as well as the types of diagnostic testing used in patients suspected of having bilirubin encephalopathy or kernicterus. The authors aim to raise the awareness of these features among both pediatric neurologists and neuropathologists.

Prevalence and burden of illness of treated hemolytic neonatal hyperbilirubinemia in a privately insured population in the United States

Background

Prevalence of hemolytic neonatal hyperbilirubinemia (NHB) is not well characterized, and economic burden at the population level is poorly understood. This study evaluated the prevalence, clinical characteristics, and economic burden of hemolytic NHB newborns receiving treatment in U.S. real-world settings.

Methods

This cohort study used administrative claims from 01/01/2011 to 08/31/2017. The treated cohort had hemolytic NHB diagnosis and received phototherapy, intravenous immunoglobulin, and/or exchange transfusions. They were matched with non-NHB newborns who had neither NHB nor related treatments on the following: delivery hospital/area, gender, delivery route, estimated gestational age (GA), health plan eligibility, and closest date of birth within 5 years. Inferential statistics were reported.

Results

The annual NHB prevalence was 29.6 to 31.7%; hemolytic NHB, 1.8 to 2.4%; treated hemolytic NHB, 0.46 to 0.55%, between 2011 and 2016. The matched analysis included 1373 pairs ≥35 weeks GA. The treated hemolytic NHB cohort had significantly more birth trauma and hemorrhage (4.5% vs. 2.4%, p = 0.003), vacuum extractor affecting newborn (1.9% vs. 0.8%, p = 0.014), and polycythemia neonatorum (0.8% vs. 0%, p = 0.001) than the matched non-NHB cohort. The treated hemolytic NHB cohort also had significantly longer mean birth hospital stays (4.5 vs. 3.0 days, p < 0.001), higher level 2–4 neonatal intensive care admissions (15.7% vs. 2.4, 15.9% vs. 2.8 and 10.6% vs. 2.5%, respectively, all p < 0.001) and higher 30-day readmission (8.7% vs. 1.7%, p < 0.001).

One-month and one-year average total costs of care were significantly higher for the treated hemolytic NHB cohort vs. the matched non-NHB cohort, $14,405 vs. $5527 (p < 0.001) and $21,556 vs. $12,986 (p < 0.001), respectively. The average costs for 30-day readmission among newborns who readmitted were $13,593 for the treated hemolytic NHB cohort and $3638 for the matched non-NHB cohort, p < 0.001. The authors extrapolated GA-adjusted prevalence of treated hemolytic NHB in the U.S. newborn population ≥ 35 weeks GA and estimated an incremental healthcare expenditure of $177.0 million during the first month after birth in 2016.

Conclusions

The prevalence of treated hemolytic NHB was 4.6–5.5 patients per 1000 newborns. This high-risk hemolytic NHB imposed substantial burdens of healthcare resource utilization and incremental costs on newborns, their caregivers, and the healthcare system.

Moderate Hyperbilirubinemia Alters Neonatal Cardiorespiratory Control and Induces Inflammation in the Nucleus Tractus Solitarius

Hyperbilirubinemia (HB) occurs in 90% of preterm newborns. Moderate HB can induce acute neurological disorders while severe HB has been linked to a higher incidence of apneas of prematurity. The present study aimed to test the hypothesis that even moderate HB disrupts cardiorespiratory control in preterm lambs. Two groups of preterm lambs (born 14 days prior to term), namely control (n = 6) and HB (n = 5), were studied. At day 5 of life, moderate HB (150–250 μmol/L) was induced during 17 h in the HB group after which cardiorespiratory control as well as laryngeal and pulmonary chemoreflexes were assessed during baseline recordings and during hypoxia. Recordings were repeated 72 h after HB induction, just before euthanasia. In addition, neuropathological studies were performed to investigate for cerebral bilirubin deposition as well as for signs of glial reactivity in brainstem structures involved in cardiorespiratory control. Results revealed that sustained and moderate HB: (i) decreased baseline respiratory rate and increased the time spent in apnea; (ii) blunted the cardiorespiratory inhibition normally observed during both laryngeal and pulmonary chemoreflexes; and (iii) increased heart rate in response to acute hypoxia. These acute physiological changes were concurrent with an activation of Alzheimer type II astrocytes throughout the brain, including the brainstem. Concomitantly, bilirubin deposits were observed in the leptomeninges, but not in brain parenchyma. While most cardiorespiratory alterations returned to normal 72 h after HB normalization, the expression of glial fibrillary acid protein (GFAP) and ionized calcium binding adaptor molecule 1 (Iba1) was still increased within the nucleus tractus solitarius. In conclusion, moderate and sustained HB in preterm lambs induced cardiorespiratory alterations, the latter of which were associated with neurohistopathological changes. These changes are indicative of an inflammatory response in the brainstem neuroanatomical substrates involved in cardiorespiratory control.

Bilirubin Binding Capacity in the Preterm Neonate

Total serum/plasma bilirubin (TB), the biochemical measure currently used to evaluate and manage hyperbilirubinemia, is not a useful predictor of bilirubin-induced neurotoxicity in premature infants. Altered bilirubin-albumin binding in premature infants limits the usefulness of TB in premature infants. In this article, bilirubin-albumin binding, a modifying factor for bilirubin-induced neurotoxicity, in premature infants is reviewed.

Hyperbilirubinemia in Preterm Neonates

Preterm neonates with increased bilirubin production loads are more likely to sustain adverse outcomes due to either neurotoxicity or overtreatment with phototherapy and/or exchange transfusion. Clinicians should rely on expert consensus opinions to guide timely and effective interventions until there is better evidence to refine bilirubin-induced neurologic dysfunction or benefits of bilirubin. In this article, we review the evolving evidence for bilirubin-induced brain injury in preterm infants and highlight the clinical approaches that minimize the risk of bilirubin neurotoxicity.

Bilirubin-Induced Neurotoxicity in the Preterm Neonate

Bilirubin-induced neurotoxicity in preterm neonates remains a clinical concern. Multiple cellular and molecular cascades likely underlie bilirubin-induced neuronal injury, including plasma membrane perturbations, excitotoxicity, neuroinflammation, oxidative stress, and cell cycle arrest. Preterm newborns are particularly vulnerable secondary to central nervous system immaturity and concurrent adverse clinical conditions that may potentiate bilirubin toxicity. Acute bilirubin encephalopathy in preterm neonates may be subtle and manifest primarily as recurrent symptomatic apneic events. Low-bilirubin kernicterus continues to be reported in preterm neonates, and although multifactorial in nature, is often associated with marked hypoalbuminemia.

The clinical syndrome of bilirubin-induced neurologic dysfunction

Clinicians have hypothesized a spectrum of minor neurologic manifestations, consistent with neuroanatomical reports and collectively termed as a "syndrome of bilirubin-induced neurologic dysfunction (BIND)," which can occur in the absence of classical kernicterus. The current review builds on these initial reports with a focus on clinical signs and symptoms that are assessed by standardized tools and manifest from neonatal age to childhood. These clinical manifestations are characterized by the following domains: (i) neuromotor signs; (ii) muscle tone abnormalities; (iii) hyperexcitable neonatal reflexes; (iv) variety of neurobehavior manifestations; (v) speech and language abnormalities; and (vi) evolving array of central processing abnormalities, such as sensorineural audiology and visuomotor dysfunctions. Concerns remain that the most vulnerable infants are likely to acquire BIND, either because their exposure to bilirubin is not identified as severe enough to need treatment or is prolonged but slightly below current threshold levels for intervention. Knowing that a total serum/plasma bilirubin (TB) level is not the most precise indicator of neurotoxicity, the role of expanded biomarkers or a "bilirubin panel" has yet to be validated in prospective studies. Future studies that correlate early "toxic" bilirubin exposure to long-term academic potential of children are needed to explore new insights into bilirubin's effect on the structural and functional maturation of an infant's neural network topology.