Machine learning approach identifies meconium metabolites as potential biomarkers of neonatal hyperbilirubinemia

Zeng, Shujuan; Wang, Zhangxing; Zhang, Peng; Zhen, Yin; Huang, Xun-Bin; Tang, Xisheng; Shi, Lindong; Guo, Kaiping; Liu, Ting; Wang, Mingbang; Qiu, Huixian

doi:10.1016/j.csbj.2022.03.039

Cited by 6 publications

(2 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The supernatants were transferred to a fresh glass vial for metabolomics analysis. A quality control (QC) sample was prepared by mixing an equal aliquot of the supernatants derived from test specimens to evaluate the reproducibility and reliability of the metabolomics analytical system ( Xie et al, 2021 ; Zeng et al, 2022 ).…”

Section: Methodsmentioning

confidence: 99%

Diagnostic and predictive values of serum metabolic profiles in sudden sensorineural hearing loss patients

Wang

Gao

Jiang

2022

Front. Mol. Biosci.

View full text Add to dashboard Cite

Sudden sensorineural hearing loss (SSNHL) is an otologic emergency, and metabolic disturbance is involved in its pathogenesis. This study recruited 20 SSNHL patients and 20 healthy controls (HCs) and collected their serum samples. Serum metabolites were detected by liquid chromatography-mass spectrometry, and metabolic profiles were analyzed. All patients were followed up for 3 months and categorized into recovery and non-recovery groups. The distinctive metabolites were assessed between two groups, and their predictive values for hearing recovery were evaluated. Analysis results revealed that SSNHL patients exhibited significantly characteristic metabolite signatures compared to HCs. The top 10 differential metabolites were further analyzed, and most of them showed potential diagnostic values based on receiver operator characteristic (ROC) curves. Finally, 14 SSNHL patients were divided into the recovery group, and six patients were included in the non-recovery group. Twelve distinctive metabolites were observed between the two groups, and ROC curves demonstrated that N4-acetylcytidine, p-phenylenediamine, sphingosine, glycero-3-phosphocholine, and nonadecanoic acid presented good predictabilities in the hearing recovery. Multivariate analysis results demonstrated that serum N4-Acetylcytidine, sphingosine and nonadecanoic acid levels were associated with hearing recovery in SSNHL patients. Our results identified that SSNHL patients exhibited distinctive serum metabolomics signatures, and several serum biomarkers were proved to be potential in predicting hearing recovery. The discriminative metabolites might contribute to illustrating the mechanisms of SSNHL and provide possible clues for its treatments.

show abstract

Section: Methodsmentioning

confidence: 99%

Diagnostic and predictive values of serum metabolic profiles in sudden sensorineural hearing loss patients

Wang

Gao

Jiang

2022

Front. Mol. Biosci.

View full text Add to dashboard Cite

show abstract

“…Metabolic disorders themselves may decrease bilirubin clearance in neonatal hyperbilirubinemia, and be regarded as potential biomarkers in the diagnosis of hyperbilirubinemia. Gut metabolites such as gut branched-chain amino acid (including valine, leucine, and isoleucine), proline, methionine, and phenylalanine were elevated in hyperbilirubinemia ( 16 ). Serum metabolites including valine, myo-inositol, lysine, leucine, lactate, isoleucine, alanine, creatine, and glycine were increased in neonatal hyperbilirubinemia compared to healthy controls ( 17 ).…”

Section: Introductionmentioning

confidence: 99%

A metabolomic-based biomarker discovery study for predicting phototherapy duration for neonatal hyperbilirubinemia

Zhu¹,

Wang²,

Zhang³

et al. 2022

Transl Pediatr

View full text Add to dashboard Cite

Background: Phototherapy is a recommended method for the treatment of neonatal hyperbilirubinemia.However, biomarkers for predicting the more effective duration of phototherapy prior to treatment are lacking. Therefore, we aimed to determine novel predictors for the timing of phototherapy from the perspective of metabolomics.Methods: A total of 12 newborns with neonatal hyperbilirubinemia were recruited on the day of admission.The infants were divided into a short-duration (<30 hours) phototherapy group and a long-duration (≥30 hours) phototherapy group based on the length of phototherapy treatment. Metabolites in serum samples were then explored using an untargeted metabolomics strategy.Results: In total, 59 of 1,073 significantly different metabolites were identified between the shortduration and long-duration phototherapy groups, including 18 upregulated and 41 downregulated metabolites. The results of metabolomic analysis showed that the differentially expressed metabolites were enriched in glycerophospholipid metabolism, which is closely associated with the excretion of bilirubin.Moreover, the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis revealed that the metabolites were also enriched in alpha-Linolenic acid metabolism and fatty acid elongation. Spearman correlation hierarchical clustering analysis demonstrated that 9 metabolites were negatively correlated with the duration of phototherapy. Metabolites, especially phosphatidylethanolamine (PE) (22:1(13Z)/15:0), phosphatidylcholine (PC) (18:1(9Z)/18:1(9Z)), phosphatidylserine (PS) (22:0/15:0), 5,6-dihydrouridine, and PE (MonoMe(11,3)/MonoMe(13,5)), had better predictability for the duration of phototherapy [area under curve (AUC): 1; 95% confidence interval (CI): 1-1] than total serum total bilirubin and direct bilirubin (AUC: 0.806; 95% CI: 0.55-1), as revealed by receiver operating characteristic analysis.Conclusions: Our research found that the differential metabolites were associated with the duration of neonatal jaundice and that glycerophospholipid metabolism might have played a role in this biological process. Moreover, metabolites such as PE (22:1(13Z)/15:0), PC (18:1(9Z)/18:1(9Z)), PS (22:0/15:0), 5,6-dihydrouridine, and PE (MonoMe(11,3)/MonoMe(13,5)) could be used as predictors for phototherapy duration in neonatal hyperbilirubinemia and assist with decision-making.

show abstract

Integration of pharmacodynamics, network pharmacology and metabolomics to elucidate effect and mechanism of Artemisia capillaris Thunb. in the treatment of jaundice

Yang

Pan

et al. 2023

Journal of Ethnopharmacology

View full text Add to dashboard Cite

Machine learning approach identifies meconium metabolites as potential biomarkers of neonatal hyperbilirubinemia

Cited by 6 publications

References 46 publications

Diagnostic and predictive values of serum metabolic profiles in sudden sensorineural hearing loss patients

Diagnostic and predictive values of serum metabolic profiles in sudden sensorineural hearing loss patients

A metabolomic-based biomarker discovery study for predicting phototherapy duration for neonatal hyperbilirubinemia

Integration of pharmacodynamics, network pharmacology and metabolomics to elucidate effect and mechanism of Artemisia capillaris Thunb. in the treatment of jaundice

Contact Info

Product

Resources

About