Machine Learning to Improve Accuracy of Transcutaneous Bilirubinometry
Neonatology · 2024
DOI: 10.1159/000535970 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neonatology, 2024. Verfasst von Daisaku Morimoto und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatrics, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama, Japan, daisaku_morimoto@ya…. Hauptthemen laut MEDLINE: Bilirubin, Machine Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 28 Literaturangaben.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Pediatrics, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama, Japan, daisaku_morimoto@yahoo.co.jp.
- Department of Pediatrics, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama, Japan.
- Clinical AI Human Resources Development Program, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama, Japan.
Zitieren
APA
Morimoto, D., Washio, Y., Fukuda, K., Sato, T., Okamura, T., Watanabe, H., Yoshimoto, J., Tanioka, M., & Tsukahara, H. (2024). Machine Learning to Improve Accuracy of Transcutaneous Bilirubinometry. Neonatology. https://doi.org/10.1159/000535970
Vancouver
Morimoto D, Washio Y, Fukuda K, Sato T, Okamura T, Watanabe H, et al. Machine Learning to Improve Accuracy of Transcutaneous Bilirubinometry. Neonatology. 2024. doi:10.1159/000535970
BibTeX
@article{Morimoto2024,
author = {Morimoto, Daisaku and Washio, Yosuke and Fukuda, Kana and Sato, Takeshi and Okamura, Tomoka and Watanabe, Hirokazu and Yoshimoto, Junko and Tanioka, Maki and Tsukahara, Hirokazu},
title = {Machine Learning to Improve Accuracy of Transcutaneous Bilirubinometry},
journal = {Neonatology},
year = {2024},
doi = {10.1159/000535970}
}
EUVIMED