*Result*: Exploring Computational Techniques in Preprocessing Neonatal Physiological Signals for Detecting Adverse Outcomes: Scoping Review.

Title:
Exploring Computational Techniques in Preprocessing Neonatal Physiological Signals for Detecting Adverse Outcomes: Scoping Review.
Authors:
Rahman J; Commonwealth Scientific and Industrial Research Organisation (CSIRO) Australian e-Health Research Centre, Australia, Sydney, Australia., Brankovic A; Commonwealth Scientific and Industrial Research Organisation (CSIRO) Australian e-Health Research Centre, Australia, Brisbane, Australia., Tracy M; Neonatal Intensive Care Unit, Westmead, Sydney, Australia., Khanna S; Commonwealth Scientific and Industrial Research Organisation (CSIRO) Australian e-Health Research Centre, Australia, Brisbane, Australia.
Source:
Interactive journal of medical research [Interact J Med Res] 2024 Aug 20; Vol. 13, pp. e46946. Date of Electronic Publication: 2024 Aug 20.
Publication Type:
Journal Article; Scoping Review
Language:
English
Journal Info:
Publisher: JMIR Publications Country of Publication: Canada NLM ID: 101598421 Publication Model: Electronic Cited Medium: Print ISSN: 1929-073X (Print) Linking ISSN: 1929073X NLM ISO Abbreviation: Interact J Med Res Subsets: PubMed not MEDLINE
Imprint Name(s):
Original Publication: Toronto : JMIR Publications, 2012-
References:
Annu Int Conf IEEE Eng Med Biol Soc. 2008;2008:165-8. (PMID: 19162619)
Annu Rev Biomed Eng. 2017 Jun 21;19:221-248. (PMID: 28301734)
Front Neurosci. 2020 Nov 19;14:594880. (PMID: 33328866)
IEEE J Biomed Health Inform. 2014 Sep;18(5):1560-70. (PMID: 25192568)
IEEE Trans Biomed Eng. 2017 Sep;64(9):2300-2308. (PMID: 27898379)
Sci Rep. 2021 Mar 31;11(1):7308. (PMID: 33790395)
IEEE J Biomed Health Inform. 2021 Apr;25(4):1006-1017. (PMID: 32881699)
Paediatr Child Health. 2006 Apr;11(4):211-5. (PMID: 19030273)
Physiol Meas. 2012 Jul;33(7):1135-50. (PMID: 22735075)
CEUR Workshop Proc. 2019 Aug;2429:15-22. (PMID: 33867901)
Circulation. 2000 Jun 13;101(23):E215-20. (PMID: 10851218)
Physiol Meas. 2015 Sep;36(9):1763-83. (PMID: 26235524)
Healthc Inform Res. 2018 Jul;24(3):198-206. (PMID: 30109153)
JMIR Med Inform. 2020 Jul 31;8(7):e15965. (PMID: 32735230)
IEEE Trans Biomed Eng. 1986 Dec;33(12):1157-65. (PMID: 3817849)
Annu Int Conf IEEE Eng Med Biol Soc. 2014;2014:262-5. (PMID: 25569947)
Annu Int Conf IEEE Eng Med Biol Soc. 2021 Nov;2021:5463-5468. (PMID: 34892362)
BMJ. 2021 Mar 29;372:n71. (PMID: 33782057)
BMJ Qual Saf. 2019 Mar;28(3):238-241. (PMID: 30291179)
J Neonatal Perinatal Med. 2021;14(4):553-561. (PMID: 33523025)
Comput Biol Med. 2015 Aug;63:169-77. (PMID: 26093065)
Acta Paediatr. 2023 Apr;112(4):686-696. (PMID: 36607251)
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:4001-4004. (PMID: 28269162)
Pediatr Res. 2016 Sep;80(3):382-8. (PMID: 27089498)
BMC Med. 2015 Jan 06;13:1. (PMID: 25563062)
Comput Methods Programs Biomed. 2021 Sep;209:106321. (PMID: 34380078)
IEEE Trans Biomed Eng. 2006 Mar;53(3):485-96. (PMID: 16532775)
Eur Heart J. 1996 Mar;17(3):354-81. (PMID: 8737210)
Ann Intern Med. 2012 Jul 3;157(1):29-43. (PMID: 22751758)
Physiol Meas. 2012 Jan;33(1):1-17. (PMID: 22156193)
Sci Rep. 2021 May 18;11(1):10486. (PMID: 34006917)
J Neurosci Methods. 2016 Sep 1;270:76-84. (PMID: 27291356)
J Med Internet Res. 2021 Sep 30;23(9):e28209. (PMID: 34591017)
NPJ Digit Med. 2021 Jul 14;4(1):108. (PMID: 34262112)
Comput Biol Med. 2015 Aug;63:118-23. (PMID: 26073098)
BMJ Open. 2021 Dec 21;11(12):e055209. (PMID: 34933863)
IEEE Trans Biomed Eng. 2003 Jun;50(6):686-96. (PMID: 12814235)
Neonatology. 2021;118(4):394-405. (PMID: 34261070)
J Biomed Inform. 2022 Nov;135:104216. (PMID: 36208833)
IEEE J Biomed Health Inform. 2016 Mar;20(2):527-38. (PMID: 25706937)
Annu Int Conf IEEE Eng Med Biol Soc. 2015;2015:2355-8. (PMID: 26736766)
Arch Dis Child Fetal Neonatal Ed. 2019 Mar;104(2):F182-F186. (PMID: 29588296)
Clin Neurophysiol. 2017 Jan;128(1):14-15. (PMID: 27866114)
Crit Care Explor. 2021 Jan 27;3(1):e0302. (PMID: 33532727)
Physiol Meas. 2021 Sep 27;42(9):. (PMID: 34271562)
IEEE Trans Inf Technol Biomed. 2012 May;16(3):488-500. (PMID: 22361665)
Pediatr Res. 2023 Jun;93(7):1913-1921. (PMID: 36593281)
Am J Perinatol. 2018 Nov;35(13):1331-1338. (PMID: 29807371)
IEEE J Biomed Health Inform. 2020 Mar;24(3):681-692. (PMID: 31295130)
J Child Neurol. 2020 Jul;35(8):517-525. (PMID: 32306827)
Ann Biomed Eng. 2021 Sep;49(9):2159-2169. (PMID: 33638031)
Med Phys. 2020 Jun;47(5):e228-e235. (PMID: 32418341)
Comput Methods Programs Biomed. 2019 Oct;180:104996. (PMID: 31421605)
Womens Health (Lond). 2021 Jan-Dec;17:17455065211046132. (PMID: 34519596)
Am J Perinatol. 2014 Feb;31(2):157-62. (PMID: 23592319)
Comput Methods Programs Biomed. 2022 Nov;226:107155. (PMID: 36215858)
NPJ Digit Med. 2022 Jan 17;5(1):6. (PMID: 35039624)
Pediatr Res. 2020 Jan;87(2):210-220. (PMID: 31377752)
PLoS One. 2019 Oct 29;14(10):e0223785. (PMID: 31661497)
Sleep. 1997 Jul;20(7):553-60. (PMID: 9322271)
J Med Signals Sens. 2021 Jul 21;11(3):222-226. (PMID: 34466402)
ScientificWorldJournal. 2015;2015:727694. (PMID: 25734185)
Conf Proc IEEE Eng Med Biol Soc. 2004;2006:442-5. (PMID: 17271708)
JRSM Cardiovasc Dis. 2020 Aug 05;9:2048004020945142. (PMID: 33240492)
Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:5614-5517. (PMID: 30441609)
IEEE Trans Biomed Eng. 1985 Mar;32(3):230-6. (PMID: 3997178)
J Perinatol. 2022 Dec;42(12):1561-1575. (PMID: 35562414)
IEEE J Biomed Health Inform. 2023 Jan;27(1):550-561. (PMID: 36264730)
Syst Rev. 2016 Dec 5;5(1):210. (PMID: 27919275)
Med Biol Eng Comput. 2015 Jan;53(1):1-13. (PMID: 25300402)
Sci Data. 2016 May 24;3:160035. (PMID: 27219127)
Ann Biomed Eng. 2019 Feb;47(2):646-658. (PMID: 30255214)
Prog Biophys Mol Biol. 1995;64(2-3):237-78. (PMID: 8987386)
Comput Biol Med. 2021 Jul;134:104521. (PMID: 34111664)
Int J Nurs Stud. 2018 Jan;77:81-90. (PMID: 29055243)
Public Health. 2014 May;128(5):399-403. (PMID: 24794180)
J Pak Med Assoc. 2013 Feb;63(2):283-5. (PMID: 23894916)
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:920-923. (PMID: 28268474)
IEEE J Biomed Health Inform. 2015 Jul;19(4):1193-208. (PMID: 26173222)
J Appl Physiol (1985). 2015 Mar 1;118(5):558-68. (PMID: 25549762)
Artif Intell Med. 2019 Jul;98:59-76. (PMID: 31521253)
Contributed Indexing:
Keywords: adverse outcomes; morbidity; neonatal intensive care unit; physiological signals; predictive and diagnostic models; preterm; signal analysis; signal processing
Entry Date(s):
Date Created: 20240820 Latest Revision: 20250130
Update Code:
20260130
PubMed Central ID:
PMC11372324
DOI:
10.2196/46946
PMID:
39163610
Database:
MEDLINE

*Further Information*

*Background: Computational signal preprocessing is a prerequisite for developing data-driven predictive models for clinical decision support. Thus, identifying the best practices that adhere to clinical principles is critical to ensure transparency and reproducibility to drive clinical adoption. It further fosters reproducible, ethical, and reliable conduct of studies. This procedure is also crucial for setting up a software quality management system to ensure regulatory compliance in developing software as a medical device aimed at early preclinical detection of clinical deterioration.
Objective: This scoping review focuses on the neonatal intensive care unit setting and summarizes the state-of-the-art computational methods used for preprocessing neonatal clinical physiological signals; these signals are used for the development of machine learning models to predict the risk of adverse outcomes.
Methods: Five databases (PubMed, Web of Science, Scopus, IEEE, and ACM Digital Library) were searched using a combination of keywords and MeSH (Medical Subject Headings) terms. A total of 3585 papers from 2013 to January 2023 were identified based on the defined search terms and inclusion criteria. After removing duplicates, 2994 (83.51%) papers were screened by title and abstract, and 81 (0.03%) were selected for full-text review. Of these, 52 (64%) were eligible for inclusion in the detailed analysis.
Results: Of the 52 articles reviewed, 24 (46%) studies focused on diagnostic models, while the remainder (n=28, 54%) focused on prognostic models. The analysis conducted in these studies involved various physiological signals, with electrocardiograms being the most prevalent. Different programming languages were used, with MATLAB and Python being notable. The monitoring and capturing of physiological data used diverse systems, impacting data quality and introducing study heterogeneity. Outcomes of interest included sepsis, apnea, bradycardia, mortality, necrotizing enterocolitis, and hypoxic-ischemic encephalopathy, with some studies analyzing combinations of adverse outcomes. We found a partial or complete lack of transparency in reporting the setting and the methods used for signal preprocessing. This includes reporting methods to handle missing data, segment size for considered analysis, and details regarding the modification of the state-of-the-art methods for physiological signal processing to align with the clinical principles for neonates. Only 7 (13%) of the 52 reviewed studies reported all the recommended preprocessing steps, which could have impacts on the downstream analysis.
Conclusions: The review found heterogeneity in the techniques used and inconsistent reporting of parameters and procedures used for preprocessing neonatal physiological signals, which is necessary to confirm adherence to clinical and software quality management system practices, usefulness, and choice of best practices. Enhancing transparency in reporting and standardizing procedures will boost study interpretation and reproducibility and expedite clinical adoption, instilling confidence in the research findings and streamlining the translation of research outcomes into clinical practice, ultimately contributing to the advancement of neonatal care and patient outcomes.
(©Jessica Rahman, Aida Brankovic, Mark Tracy, Sankalp Khanna. Originally published in the Interactive Journal of Medical Research (https://www.i-jmr.org/), 20.08.2024.)*