1
|
Morimoto D, Washio Y, Fukuda K, Sato T, Okamura T, Watanabe H, Yoshimoto J, Tanioka M, Tsukahara H. Machine Learning to Improve Accuracy of Transcutaneous Bilirubinometry. Neonatology 2024:1-8. [PMID: 38684146 DOI: 10.1159/000535970] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/20/2023] [Accepted: 12/15/2023] [Indexed: 05/02/2024]
Abstract
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.
Collapse
Affiliation(s)
- Daisaku Morimoto
- Department of Pediatrics, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama, Japan,
| | - Yosuke Washio
- Department of Pediatrics, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama, Japan
| | - Kana Fukuda
- Department of Pediatrics, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama, Japan
| | - Takeshi Sato
- Department of Pediatrics, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama, Japan
| | - Tomoka Okamura
- Department of Pediatrics, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama, Japan
| | - Hirokazu Watanabe
- Department of Pediatrics, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama, Japan
| | - Junko Yoshimoto
- Department of Pediatrics, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama, Japan
| | - Maki Tanioka
- Clinical AI Human Resources Development Program, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama, Japan
| | - Hirokazu Tsukahara
- Department of Pediatrics, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama, Japan
| |
Collapse
|
2
|
Abiha U, Banerjee DS, Mandal S. Demystifying non-invasive approaches for screening jaundice in low resource settings: a review. Front Pediatr 2023; 11:1292678. [PMID: 38054187 PMCID: PMC10694303 DOI: 10.3389/fped.2023.1292678] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/12/2023] [Accepted: 10/18/2023] [Indexed: 12/07/2023] Open
Abstract
All national and international pediatric guidelines universally prescribe meticulous bilirubin screening for neonates as a critical measure to mitigate the incidence of acute bilirubin encephalopathy (ABE) and Kernicterus. The prevailing gold standard for jaundice detection in neonates necessitates invasive blood collection, followed by subsequent biochemical testing. While the invasive procedure provides dependable bilirubin measurements and continues to be the sole gold standard diagnostic method for assessing bilirubin concentration. There exists a pressing need to innovate non-invasive screening tools that alleviate the sampling stress endured by newborns, mitigate iatrogenic anemia, and expedite the turnaround time for obtaining results. The exploration of non-invasive modalities for bilirubin measurements is gaining momentum, driven by the overarching goal of minimizing the number of pricks inflicted upon neonates, thereby rendering screening a swift, efficient, comfortable, and dependable process. This comprehensive review article delves extensively into the array of non-invasive approaches and digital solutions that have been proposed, implemented, and utilized for neonatal bilirubin screening, with a particular emphasis on their application in low-resource settings. Within this context, the review sheds light on the existing methodologies and their practical applications, with a specific focus on transcutaneous bilirubin meters. Moreover, it underscores the prevailing open challenges in this domain and outlines potential directions for future research endeavors. Notably, the review underscores the imperative need for robust educational programs targeted at both families and healthcare personnel to expedite the process of seeking timely care for neonatal jaundice. Additionally, it underscores the necessity for the development of enhanced screening and diagnostic tools that can offer greater accuracy in clinical practice.
Collapse
Affiliation(s)
- Umme Abiha
- Department of Smart Healthcare, Indian Institute of Technology, Jodhpur, India
- All India Institute of Medical Science, Jodhpur, India
| | - Dip Sankar Banerjee
- Computer Science and Engineering, Indian Institute of Technology, Jodhpur, India
| | - Saptarshi Mandal
- Transfusion Medicine and Blood Bank, All India Institute of Medical Science, Jodhpur, India
| |
Collapse
|
3
|
Okwundu CI, Olowoyeye A, Uthman OA, Smith J, Wiysonge CS, Bhutani VK, Fiander M, Gautham KS. Transcutaneous bilirubinometry versus total serum bilirubin measurement for newborns. Cochrane Database Syst Rev 2023; 5:CD012660. [PMID: 37158489 PMCID: PMC10167941 DOI: 10.1002/14651858.cd012660.pub2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 05/10/2023]
Abstract
BACKGROUND Jaundice is a very common condition in newborns, affecting up to 60% of term newborns and 80% of preterm newborns in the first week of life. Jaundice is caused by increased bilirubin in the blood from the breakdown of red blood cells. The gold standard for measuring bilirubin levels is obtaining a blood sample and processing it in a laboratory. However, noninvasive transcutaneous bilirubin (TcB) measurement devices are widely available and used in many settings to estimate total serum bilirubin (TSB) levels. OBJECTIVES To determine the diagnostic accuracy of transcutaneous bilirubin measurement for detecting hyperbilirubinaemia in newborns. SEARCH METHODS We searched CENTRAL, MEDLINE, Embase, CINAHL and trial registries up to 18 August 2022. We also checked the reference lists of all included studies and relevant systematic reviews for other potentially eligible studies. SELECTION CRITERIA We included cross-sectional and prospective cohort studies that evaluated the accuracy of any TcB device compared to TSB measurement in term or preterm newborn infants (0 to 28 days postnatal age). All included studies provided sufficient data and information to create a 2 × 2 table for the calculation of measures of diagnostic accuracy, including sensitivities and specificities. We excluded studies that only reported correlation coefficients. DATA COLLECTION AND ANALYSIS Two review authors independently applied the eligibility criteria to all citations from the search and extracted data from the included studies using a standard data extraction form. We summarised the available results narratively and, where possible, we combined study data in a meta-analysis. MAIN RESULTS We included 23 studies, involving 5058 participants. All studies had low risk of bias as measured by the QUADAS 2 tool. The studies were conducted in different countries and settings, included newborns of different gestational and postnatal ages, compared various TcB devices (including the JM 101, JM 102, JM 103, BiliChek, Bilitest and JH20-1C) and used different cutoff values for a positive result. In most studies, the TcB measurement was taken from the forehead, sternum, or both. The sensitivity of various TcB cutoff values to detect significant hyperbilirubinaemia ranged from 74% to 100%, and specificity ranged from 18% to 89%. AUTHORS' CONCLUSIONS The high sensitivity of TcB to detect hyperbilirubinaemia suggests that TcB devices are reliable screening tests for ruling out hyperbilirubinaemia in newborn infants. Positive test results would require confirmation through serum bilirubin measurement.
Collapse
Affiliation(s)
- Charles I Okwundu
- Centre for Evidence-based Health Care, Faculty of Medicine and Health Sciences, Stellenbosch University, Cape Town, South Africa
| | - Abiola Olowoyeye
- Phoenix Children's Hospital and University of Arizona College of Medicine, Phoenix, Arizona, USA
| | - Olalekan A Uthman
- Warwick Centre for Applied Health Research and Delivery (WCAHRD), Division of Health Sciences, Warwick Medical School, The University of Warwick, Coventry, UK
| | - Johan Smith
- Department of Paediatrics and Child Health, Stellenbosch University, Faculty of Health Sciences, Stellenbosch, South Africa
| | - Charles S Wiysonge
- Cochrane South Africa, South African Medical Research Council, Cape Town, South Africa
| | - Vinod K Bhutani
- Division of Neonatal and Developmental Medicine, Department of Pediatrics, Stanford School of Medicine, Lucile Packard Children's Hospital, Palo Alto, California, USA
| | | | - Kanekal S Gautham
- Chair of Pediatrics and Pediatrician-in-Chief, Nemours Children's Health System, University of Central Florida College of Medicine, Orlando, Florida, USA
| |
Collapse
|
4
|
Khurshid F, Rao SPN, Sauve C, Gupta S. Universal screening for hyperbilirubinemia in term healthy newborns at discharge: A systematic review and meta-analysis. J Glob Health 2022; 12:12007. [PMID: 36579719 PMCID: PMC9798347 DOI: 10.7189/jogh.12.12007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/30/2022] Open
Abstract
Background All term healthy neonates are screened for jaundice before hospital discharge as a standard clinical practice, but methods vary from clinical screening (visual inspection and/or risk factor assessment) to transcutaneous bilirubin (TcB) or total serum bilirubin (TSB) testing, depending on the setting. Methods This systematic review of randomized and non-randomized studies evaluated the effectiveness of universal TcB and universal TSB screening at discharge compared to clinical screening alone for term healthy neonates. The outcomes were neonatal mortality, readmission for jaundice, severe hyperbilirubinemia (>20 mg/dL), jaundice requiring exchange transfusion, and bilirubin-induced neurological dysfunction (BIND). We searched MEDLINE via Ovid, EBM reviews, Embase, CINAHL, clinical trials databases, and reference lists of retrieved articles. Two authors separately evaluated the risk of bias, extracted data, and synthesized effect estimates using relative risk (RR) for randomized and odds ratio (OR) for non-randomized studies. Results For universal TcB at discharge, we included one randomized trial enrolling 1858 participants and four non-randomized studies enrolling 375 956 participants. No study reported neonatal mortality. The randomized trial suggested that universal TcB at discharge may decrease readmission for jaundice (risk ratio (RR) = 0.24, 95% confidence interval (CI) = 0.13 to 0.46; low certainty evidence) and severe hyperbilirubinemia (RR = 0.27, 95% CI = 0.08 to 0.97; low certainty evidence), but the effect on jaundice requiring exchange transfusion (RR = 0.20, 95% CI = 0.01 to 41.6) and BIND (RR = 0.33, 95% CI = 0.01 to 8.17) was uncertain. Meta-analysis of non-randomized studies suggested that TcB may decrease severe hyperbilirubinemia (odds ratio (OR) = 0.25, 95% = CI 0.12 to 0.52; low certainty evidence) and jaundice requiring exchange transfusion (OR = 0.28, 95% CI = 0.19 to 0.42; low certainty evidence), but the effect on readmission for jaundice was uncertain (OR = 1.01, 95% CI = 0.38 to 2.7; very low certainty evidence). For universal TSB, we included three studies from the United States enrolling 490 426 participants. The effect on severe hyperbilirubinemia (OR = 0.37, 95% CI = 0.15 to 0.88), jaundice requiring exchange transfusion (OR = 0.53, 95% CI = 0.13 to 2.25) and readmission for jaundice (OR = 1.01, 95% CI = 0.62 to 1.67) was uncertain. Conclusions Universal TcB at discharge may improve clinical outcomes for term healthy neonates. Evidence for universal TSB is uncertain. Registration PROSPERO 2020 CRD42020187279.
Collapse
Affiliation(s)
- Faiza Khurshid
- Department of Pediatrics, Division of Neonatal-Perinatal Medicine, Queens University, Kingston, Ontario, Canada
| | - Suman PN Rao
- Department of Maternal, Newborn, Child, Adolescent Health and Aging, World Health Organization WHO
| | - Caroline Sauve
- Department of Education and Academy, Centre Hospitalier de l’Université de Montréal, Quebec, Canada
| | - Shuchita Gupta
- Department of Maternal, Newborn, Child, Adolescent Health and Aging, World Health Organization WHO
| |
Collapse
|
5
|
Paul HA, Adams BJ, Venner AA. Improving quality of transcutaneous bilirubin measurements: Value of in-house developed quality control. Pract Lab Med 2021; 24:e00206. [PMID: 33598521 PMCID: PMC7868991 DOI: 10.1016/j.plabm.2021.e00206] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2020] [Accepted: 01/24/2021] [Indexed: 11/28/2022] Open
Abstract
OBJECTIVES Quality assurance (QA) plays an integral role in Point of Care Testing (POCT) programs. Quality control (QC) is an important QA program component to ensure high quality results and enhanced patient care. The measurement of transcutaneous bilirubin (TcB) in the POCT setting is an essential part of newborn care in Alberta, Canada. However, there is currently no available commercial QC material for TcB meters. An in-house developed QC material has been in use within a single TcB POCT program within Alberta. The objective of this study was to determine the performance of this QC material by other POCT staff and clinical end-users to assess whether its use could be expanded. DESIGN AND METHODS Two levels of QC material were measured by POCT staff and clinical end-users across 12 different sites using the Dräger Jaundice Meter JM-103® and JM-105® meters. RESULTS The performance of the QC material was acceptable when tested by POCT staff, was stable and reliable over time, and had an acceptable CV (≤8%). However, the data does not support use of the QC material by clinical end-users. CONCLUSIONS The use of the QC material could be expanded into other TcB settings for use by POCT staff. Additional training and experience with the QC material by end-users is needed to facilitate QC use in the clinical setting.
Collapse
Affiliation(s)
- Heather Anne Paul
- Alberta Precision Laboratories, 3535, Research Rd NW, Calgary, AB, T2L 2K8, Canada
- Department of Pathology and Laboratory Medicine, Cumming School of Medicine, University of Calgary, 3330, Hospital Drive NW, Calgary, AB, T2N 4N1, Canada
| | - Brenda Joanne Adams
- Alberta Precision Laboratories, 3535, Research Rd NW, Calgary, AB, T2L 2K8, Canada
| | - Allison Anne Venner
- Alberta Precision Laboratories, 3535, Research Rd NW, Calgary, AB, T2L 2K8, Canada
- Department of Pathology and Laboratory Medicine, Cumming School of Medicine, University of Calgary, 3330, Hospital Drive NW, Calgary, AB, T2N 4N1, Canada
| |
Collapse
|