Publishing type：Research paper (scientific journal)  

DOI： 10.1016/j.pedneo.2023.08.006

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

INTRODUCTION: This study aimed to develop models for predicting total serum bilirubin by correcting errors of transcutaneous bilirubin using machine learning based on neonatal biomarkers that could affect spectrophotometric measurements of tissue bilirubin. METHODS: This retrospective study included infants born at our hospital (≥36 weeks old, ≥2,000 g) between January 2020 and December 2022. Infants without a phototherapy history were included. Robust linear regression, gradient boosting tree, and neural networks were used for machine learning models. A neural network, inspired by the structure of the human brain, was designed comprising three layers: input, intermediate, and output. RESULTS: Totally, 683 infants were included. The mean (minimum-maximum) gestational age, birth weight, participant age, total serum bilirubin, and transcutaneous bilirubin were 39.0 (36.0-42.0) weeks, 3,004 (2,004-4,484) g, 2.8 (1-6) days of age, 8.50 (2.67-18.12) mg/dL, and 7.8 (1.1-18.1) mg/dL, respectively. The neural network model had a root mean square error of 1.03 mg/dL and a mean absolute error of 0.80 mg/dL in cross-validation data. These values were 0.37 mg/dL and 0.28 mg/dL, smaller compared to transcutaneous bilirubin, respectively. The 95% limit of agreement between the neural network estimation and total serum bilirubin was -2.01 to 2.01 mg/dL. Unnecessary blood draws could be reduced by up to 78%. CONCLUSION: Using machine learning with transcutaneous bilirubin, total serum bilirubin estimation error was reduced by 25%. This integration could increase accuracy, lessen infant discomfort, and simplify procedures, offering a smart alternative to blood draws by accurately estimating phototherapy thresholds.

DOI： 10.1159/000535970

PubMed

researchmap

Language：Japanese   Publisher：(公社)日本超音波医学会  

researchmap

Language：Japanese   Publisher：(公社)日本新生児成育医学会  

researchmap

Language：Japanese   Publisher：(公社)日本新生児成育医学会  

researchmap

Language：Japanese   Publisher：(一社)日本周産期・新生児医学会  

researchmap

Language：Japanese   Publisher：(一社)日本周産期・新生児医学会  

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

Histidine-rich glycoprotein (HRG) has been reported to inhibit signaling leading to the release of high mobility group box 1 protein, a damage-associated molecular pattern. The present study aimed to determine the longitudinal change in HRG levels in extremely preterm infants and assess whether complications such as bronchopulmonary dysplasia (BPD) were associated with differences in HRG levels. In this multicenter, prospective, observational study, we measured serum HRG levels every 2 weeks from birth to 8 weeks of age. Serum HRG was measured using an enzyme-linked immunosorbent assay. We included 19 extremely preterm infants in the study and 74 samples were analyzed. The median gestational age was 26.0 weeks, and the median birth weight was 858 g. Serum HRG levels showed a significant upward trend after birth (p < 0.001); median HRG concentrations at birth and at 2, 4, 6, and 8 weeks of age were 1.07, 1.11, 2.86, 6.05, and 7.49 µg/mL, respectively. Onset of BPD was not associated with differences in serum HRG levels. Further, the serum HRG levels increased significantly after birth in extremely preterm infants.

DOI： 10.3390/biomedicines11010212

PubMed

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

BACKGROUND: Neonatal abstinence syndrome (NAS) induced by opiate use is common worldwide. While psychiatric drugs are a more common cause of NAS in Japan, infants of mothers taking psychiatric medications do not always develop NAS. The purpose of this study was to develop a practical model for predicting the onset of nonopiate-induced NAS using variables available at birth. METHODS: In this diagnostic study, prediction models were developed using multivariable logistic regression with retrospective data collected at our hospital between 2010 and 2019. NAS diagnosis was based on the Isobe score, and maternal medications were converted to dose equivalents. RESULTS: A total of 164 maternal and infant dyads met the inclusion criteria; 91 were included in the analysis, of whom 29 infants (32%) were diagnosed with NAS. Final models were created with and without the drug indices. The model without the drug indices consisted of neonatal head circumference in z-score and Apgar score at 5 minutes < 9, and the model with the drug indices included these, as well as antipsychotics and hypnotics indices. The C-statistics were 0.747 (95% CI: 0.638-0.856), and 0.795 (95% CI: 0.683-0.907), respectively, indicating good predictive accuracy of NAS onset for the models. CONCLUSIONS: This study developed models that predicted nonopiate-induced NAS with good accuracy, which may be further improved through the use of drug indices.

DOI： 10.1111/ped.15435

PubMed

researchmap

Language：Japanese   Publisher：(公社)日本新生児成育医学会  

researchmap

Language：Japanese   Publisher：(公社)日本小児科学会  

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Cambridge University Press ({CUP})  

BACKGROUND: No relationship has been reported between nonopiate neonatal abstinence syndrome (NAS) and anthropometric indices, including head circumference (HC). The purpose of this study was to determine the relationship between maternal nonopioid drug use and HC at birth in neonates with NAS. METHODS: This retrospective observational study included neonates born between January 1, 2010 and March 31, 2019, whose mothers had been taking antipsychotic, antidepressant, sedative, or anticonvulsant medications. The outcome measures were HCs of NAS infants and controls. RESULTS: Of 159 infants, 33 (21%) were diagnosed with NAS. There was no maternal opioid use among mothers during pregnancy. The HCs in the NAS group were significantly smaller than those in the control group. The median z-scores for HC at birth were -0.20 and 0.29 in the NAS group and the control group, respectively (P = .011). The median HCs at birth were 33.0 and 33.5 cm in the NAS group and the control group, respectively. Multivariate analysis revealed that maternal antipsychotic drug use and selective serotonin reuptake inhibitors were independently associated with NAS (P < .001 and P = .004, respectively). Notably, benzodiazepine use and smoking were not independent risk factors. CONCLUSIONS: The results suggest an association between maternal antipsychotic drug use and NAS, which was further associated with decreased HC. Careful monitoring of maternal drug use should be considered to improve fetal outcomes.

DOI： 10.1017/S1092852920001522

PubMed

researchmap

Language：Japanese   Publisher：(公社)日本小児科学会  

researchmap

Language：Japanese   Publisher：(公社)日本小児科学会  

researchmap

Language：Japanese   Publisher：(公社)日本小児科学会  

researchmap

Language：Japanese   Publisher：(一社)日本小児感染症学会  

researchmap

Language：Japanese   Publisher：(公社)日本小児科学会  

researchmap