Signal Quality in Continuous Transcutaneous Bilirubinometry.

Publisher: MDPI Country of Publication: Switzerland NLM ID: 101204366 Publication Model: Electronic Cited Medium: Internet ISSN: 1424-8220 (Electronic) Linking ISSN: 14248220 NLM ISO Abbreviation: Sensors (Basel) Subsets: MEDLINE

Original Publication: Basel, Switzerland : MDPI, c2000-

Bilirubin*/blood ; Bilirubin*/analysis ; Skin*/chemistry ; Skin*/metabolism; Humans ; Infant, Newborn ; Adult ; Jaundice, Neonatal/blood ; Jaundice, Neonatal/diagnosis ; Monitoring, Physiologic/methods

Bilirubin is a product of the metabolism of hemoglobin from red blood cells. Higher levels of bilirubin are a sign that either there is an unusual breaking down rate of red blood cells or the liver is not able to eliminate bilirubin, through bile, into the gastrointestinal tract. For adults, bilirubin is occasionally monitored through urine or invasive blood sampling, whilst all newborns are routinely monitored visually, or non-invasively with transcutaneous measurements (TcBs), due to their biological immaturity to conjugate bilirubin. Neonatal jaundice is a common condition, with higher levels of unconjugated bilirubin concentration having neurotoxic effects. Actual devices used in TcBs are focused on newborn populations, are hand-held, and, in some cases, operate in only two wavelengths, which does not necessarily guarantee reliable results over all skin tones. The same occurs with visual inspections. Based on that, a continuous bilirubin monitoring device for newborns is being developed to overcome visual inspection errors and to reduce invasive procedures. This device, operating optically with a mini-spectrometer in the visible range, is susceptible to patient movements and, consequently, to situations with a lower signal quality for reliable bilirubin concentration estimates on different types of skin. Therefore, as an intermediate development step and, based on skin spectra measurements from adults, this work addresses the device's placement status prediction as a signal quality indication index. This was implemented by using machine learning (ML), with the best performances being achieved by support vector machine (SVM) models, based on the spectra acquired on the arm and forehead areas.

Sci Rep. 2022 Dec 10;12(1):21412. (PMID: 36496546)
Pediatr Res. 2020 May;87(6):1039-1044. (PMID: 31086285)
World J Hepatol. 2015 May 8;7(7):926-41. (PMID: 25954476)
Biosensors (Basel). 2023 Jan 10;13(1):. (PMID: 36671955)
Acta Paediatr. 2005 Jan;94(1):65-71. (PMID: 15858963)
Biosensors (Basel). 2017 Jun 21;7(2):. (PMID: 28635643)
Sci Adv. 2021 Mar 3;7(10):. (PMID: 33658197)
IEEE J Biomed Health Inform. 2017 Sep;21(5):1216-1223. (PMID: 28113529)
Dig Dis. 2022;40(3):362-369. (PMID: 34015787)
JMIR Med Inform. 2020 Oct 29;8(10):e21222. (PMID: 33118947)
Biosensors (Basel). 2022 Mar 06;12(3):. (PMID: 35323434)
Semin Perinatol. 2014 Nov;38(7):438-51. (PMID: 25282473)
Indian Pediatr. 2017 May 15;54(5):369-372. (PMID: 28368263)
Biosensors (Basel). 2023 Jan 18;13(2):. (PMID: 36831919)
Sensors (Basel). 2022 Mar 10;22(6):. (PMID: 35336338)
Clin Biochem. 2018 May;55:69-74. (PMID: 29601801)
J Biomed Inform. 2007 Dec;40(6):661-71. (PMID: 17531544)
NPJ Digit Med. 2020 Apr 14;3:55. (PMID: 32337371)
Pediatrics. 1999 Jan;103(1):6-14. (PMID: 9917432)
NPJ Digit Med. 2020 Feb 10;3:18. (PMID: 32047863)
Sensors (Basel). 2023 Feb 23;23(5):. (PMID: 36904682)
Sensors (Basel). 2022 Aug 04;22(15):. (PMID: 35957395)
Sensors (Basel). 2024 May 07;24(10):. (PMID: 38793825)
Adv Neonatal Care. 2018 Apr;18(2):144-153. (PMID: 29498944)
Sensors (Basel). 2019 Aug 26;19(17):. (PMID: 31454930)
World J Pediatr. 2020 Jun;16(3):247-250. (PMID: 32112336)
Semin Perinatol. 2011 Jun;35(3):185-91. (PMID: 21641493)

PD/BDE/142935/2018 Fundação para a Ciência e Tecnologia

Keywords: bilirubin; jaundice; machine learning; newborns; signal quality

RFM9X3LJ49 (Bilirubin)

Date Created: 20240928 Date Completed: 20240928 Latest Revision: 20240930

20240930

PMC11435595

10.3390/s24186154

39338900