OpenLB
Open Library of Bioscience
Advanced Search
Bioengineering (Basel, Switzerland)
Feb 15, 2023;10 (2):

Detection of Suspicious Cardiotocographic Recordings by Means of a Machine Learning Classifier.

Carlo Ricciardi, Francesco Amato, Annarita Tedesco, Donatella Dragone, Carlo Cosentino, Alfonso Maria Ponsiglione, Maria Romano
Author Information
  1. Carlo Ricciardi: Department of Electrical Engineering and Information Technology (DIETI), University of Naples "Federico II", 80125 Naples, Italy. ORCID
  2. Francesco Amato: Department of Electrical Engineering and Information Technology (DIETI), University of Naples "Federico II", 80125 Naples, Italy. ORCID
  3. Annarita Tedesco: Department of Engineering for Innovation, University of Salento, 73100 Lecce, Italy.
  4. Donatella Dragone: Department of Experimental and Clinical Medicine 'Gaetano Salvatore', University "Magna Graecia" of Catanzaro, 88100 Catanzaro, Italy. ORCID
  5. Carlo Cosentino: Department of Experimental and Clinical Medicine 'Gaetano Salvatore', University "Magna Graecia" of Catanzaro, 88100 Catanzaro, Italy. ORCID
  6. Alfonso Maria Ponsiglione: Department of Electrical Engineering and Information Technology (DIETI), University of Naples "Federico II", 80125 Naples, Italy. ORCID
  7. Maria Romano: Department of Electrical Engineering and Information Technology (DIETI), University of Naples "Federico II", 80125 Naples, Italy.
PMID: 36829746 DOI: 10.3390/bioengineering10020252

Abstract

Cardiotocography (CTG) is one of the fundamental prenatal diagnostic methods for both antepartum and intrapartum fetal surveillance. Although it has allowed a significant reduction in intrapartum and neonatal mortality and morbidity, its diagnostic accuracy is, however, still far from being fully satisfactory. In particular, the identification of uncertain and suspicious CTG traces remains a challenging task for gynecologists. The introduction of computerized analysis systems has enabled more objective evaluations, possibly leading to more accurate diagnoses. In this work, the problem of classifying suspicious CTG recordings was addressed through a machine learning approach. A machine-based labeling was proposed, and a binary classification was carried out using a support vector machine (SVM) classifier to distinguish between suspicious and normal CTG traces. The best classification metrics showed accuracy, sensitivity, and specificity values of 92%, 92%, and 90%, respectively. The main results were compared both with results obtained by considering a more unbalanced dataset and with relevant literature studies in the field. The use of the SVM proved to be promising in the field of CTG classification. However, appropriate feature selection and dataset balancing are crucial to achieve satisfactory performance of the classifier.

Keywords

cardiotocography fetal heart rate machine learning support vector machine

References

PLoS One. 2020 Aug 3;15(8):e0236982 [PMID: 32745099]
Antioxidants (Basel). 2020 Mar 25;9(4): [PMID: 32218124]
Eur J Obstet Gynecol Reprod Biol. 2019 Mar;234:179-184 [PMID: 30710764]
Comput Biol Med. 2007 May;37(5):663-9 [PMID: 16893537]
Biomed Eng Online. 2014 Jul 05;13:94 [PMID: 24998888]
Int J Gynaecol Obstet. 2015 Oct;131(1):13-24 [PMID: 26433401]
Bioengineering (Basel). 2021 Dec 28;9(1): [PMID: 35049717]
IEEE Trans Biomed Eng. 2006 May;53(5):875-84 [PMID: 16686410]
IEEE Trans Biomed Eng. 2023 Apr;70(4):1196-1207 [PMID: 36201421]
Diagnostics (Basel). 2023 Feb 23;13(5): [PMID: 36900002]
Comput Methods Programs Biomed. 2016 Feb;124:121-37 [PMID: 26638805]
Comput Biol Med. 2006 Jun;36(6):619-33 [PMID: 16005863]
Math Biosci Eng. 2021 Aug 23;18(5):6995-7009 [PMID: 34517568]
J Med Syst. 2001 Aug;25(4):269-76 [PMID: 11463203]
Biomed Eng Lett. 2018 Feb 6;8(1):1-3 [PMID: 30603186]
Baillieres Clin Obstet Gynaecol. 1994 Sep;8(3):643-61 [PMID: 7813133]
Sensors (Basel). 2021 Apr 07;21(8): [PMID: 33917206]
Eur J Obstet Gynecol Reprod Biol. 2016 Oct;205:27-31 [PMID: 27566218]
Entropy (Basel). 2020 Jan 16;22(1): [PMID: 33285878]
Sci Rep. 2021 Jun 28;11(1):13367 [PMID: 34183748]
Cochrane Database Syst Rev. 2015 Nov 24;(11):CD009433 [PMID: 26599471]
Sensors (Basel). 2021 Sep 13;21(18): [PMID: 34577342]
Comput Biol Med. 2009 Feb;39(2):106-18 [PMID: 19193367]
Conf Proc IEEE Eng Med Biol Soc. 2004;2006:462-5 [PMID: 17271713]
Comput Methods Programs Biomed. 2020 Nov;196:105712 [PMID: 32877811]
Int J Appl Basic Med Res. 2019 Oct-Dec;9(4):226-230 [PMID: 31681548]
Biomed Eng Online. 2011 Jan 19;10:6 [PMID: 21244712]
Journal Article

Word Cloud

Similar Articles

Cited By