A Clinical Prediction Rule for Rebound Hyperbilirubinemia Following Inpatient Phototherapy

Chang, Pearl W.; Kuzniewicz, Michael W.; McCulloch, Charles E.; Newman, Thomas B.

doi:10.1542/peds.2016-2896

Cited by 45 publications

(36 citation statements)

References 15 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recent risk stratification approaches include additional clinical factors for the prediction of neonatal hyperbilirubinemia shortly after birth, 13 before discharge, 14 or following inpatient phototherapy. 15 Even though approaches for risk stratification provide clinicians with a guideline for their assessment, these methods are overly general, as they do not consider whether or not an individual actually received a phototherapy treatment-a decision that often depends on further practical considerations. For instance, a clinician's assessment of visible jaundice or of the medical history of a neonate are important factors that flow into the treatment decision; therefore, we define a case of clinically relevant hyperbilirubinemia if a phototherapy treatment was delivered.…”

Section: Introductionmentioning

confidence: 99%

Enhanced early prediction of clinically relevant neonatal hyperbilirubinemia with machine learning

et al. 2019

View full text Add to dashboard Cite

BACKGROUND: Machine learning models may enhance the early detection of clinically relevant hyperbilirubinemia based on patient information available in every hospital. METHODS: We conducted a longitudinal study on preterm and term born neonates with serial measurements of total serum bilirubin in the first two weeks of life. An ensemble, that combines a logistic regression with a random forest classifier, was trained to discriminate between the two classes phototherapy treatment vs. no treatment. RESULTS: Of 362 neonates included in this study, 98 had a phototherapy treatment, which our model was able to predict up to 48 h in advance with an area under the ROC-curve of 95.20%. From a set of 44 variables, including potential laboratory and clinical confounders, a subset of just four (bilirubin, weight, gestational age, hours since birth) suffices for a strong predictive performance. The resulting early phototherapy prediction tool (EPPT) is provided as an open web application. CONCLUSION: Early detection of clinically relevant hyperbilirubinemia can be enhanced by the application of machine learning. Existing guidelines can be further improved to optimize timing of bilirubin measurements to avoid toxic hyperbilirubinemia in highrisk patients while minimizing unneeded measurements in neonates who are at low risk.

show abstract

Section: Introductionmentioning

confidence: 99%

Enhanced early prediction of clinically relevant neonatal hyperbilirubinemia with machine learning

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In recent studies, the occurrence of RHB was reported to be between 0.7%-19.6% (7,19). The wide range of the reported frequencies could be (19) found a higher rate (19.6%) and this increased rate was attributed to the discontinuation of phototherapy in cases with higher STB levels (18). In another study, the rebound frequency was recorded as 0.7% and the exclusion of risk groups was held accountable for this low prevalence (7).…”

Section: Discussionmentioning

confidence: 99%

“…Waiting for a rebound STB level measurement prolongs hospital stay; therefore, AAP recommends rebound measurements only in babies with certain risk factors (2). In one study, gestational and postnatal age, and STB levels at the time of cessation of phototherapy were reported as the three most important risk factors for RHB (18). It has been reported in many studies that late-preterm infants, who have the highest risk for newborn jaundice, also have a high "rebound" rate (5,10).…”

Section: Discussionmentioning

confidence: 99%

“…The "early treatment group" consisted of the infants who received phototherapy before the 72 nd hour of life and the "late treatment group" consisted of the infants who received phototherapy after the 72 nd hour of life. Phototherapy was discontinued when STB levels dropped below 13-14 mg/dL in the late treatment group and 3 mg/dL or more below the phototherapy threshold level according to postnatal age in the early treatment group (17,18). RHB was defined as the return of TSB to the phototherapy threshold within 72 hours of phototherapy.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Do We Have to Obtain Rebound Bilirubin Levels and What is the Optimal Time?

Özdemir¹,

Bilgen²,

Memişoğlu³

et al. 2019

jpr

View full text Add to dashboard Cite

Aim:We aimed to determine the frequency of rebound hyperbilirubinemia (RHB) needing treatment and therefrom, to clarify the clinical importance of routinely checking serum total bilirubin (STB) levels after the cessation of phototherapy and to define an optimal time to check STB levels for the detection of RHB.Materials and Methods: Term and late preterm babies who received phototherapy were included in this study. The demographic and clinical features, time of onset of jaundice, phototherapy time and results to determine the etiology of jaundice were recorded for all babies. Serum "rebound" bilirubin measurements were performed two times at 12 and at 24 hours after the cessation of phototherapy. The re-initiation of phototherapy according to the 12 th and 24 th hour STB levels was accepted as "early rebound" and "late rebound", respectively. IBM SPSS 22 was used for statistical analyses.Results: Data was available for 110 infants. The rebound rate requiring phototherapy was 9.1% (n=10) and all had a risk factor. Most of the babies (9/10) rebounded at the 12 th hour after the termination of phototherapy. Hemolysis and prematurity were found to be statistically significant for RHB (p=0.008; p=0.048). Conclusion:Post-phototherapy bilirubin follow-up may be incorporated using a combined approach of individualization, evaluation of risk factors, and application of common sense before discharge. Our study showed that STB levels could be measured after the cessation of phototherapy, especially in patients with a risk factor, at the 12 th hour before discharge. Randomized controlled studies with larger sample sizes are still needed for definitive recommendations.

show abstract

“…Numerous previous studies have analyzed the bilirubin rebound after phototherapy, 10 -15 but none have approached the sample size studied by Chang et al 9 In addition, comparisons with these studies are difficult because of differences in the populations studied, the bilirubin levels chosen for phototherapy termination, and the criteria used to define rebound. In some institutions, about half of the infants receiving phototherapy for the first time are those who are readmitted, 10 a population in whom the primary cause for hyperbilirubinemia is much less likely to be active hemolysis and in whom the risk of rebound is much lower.…”

mentioning

confidence: 99%

Can I Stop Phototherapy for This Baby?

Paul

Maisels

2017

Pediatrics

View full text Add to dashboard Cite

A Clinical Prediction Rule for Rebound Hyperbilirubinemia Following Inpatient Phototherapy

Abstract: The risk of rebound hyperbilirubinemia can be quantified according to an infant's gestational age, age at phototherapy initiation, and TSB relative to the treatment threshold at phototherapy termination.

Cited by 45 publications

References 15 publications

Enhanced early prediction of clinically relevant neonatal hyperbilirubinemia with machine learning

Enhanced early prediction of clinically relevant neonatal hyperbilirubinemia with machine learning

Do We Have to Obtain Rebound Bilirubin Levels and What is the Optimal Time?

Can I Stop Phototherapy for This Baby?

Contact Info

Product

Resources

About