Archives of Gynecology and Obstetrics

, Volume 300, Issue 1, pp 7–14 | Cite as

Use of artificial intelligence (AI) in the interpretation of intrapartum fetal heart rate (FHR) tracings: a systematic review and meta-analysis

  • Jacques BalaylaEmail author
  • Guy Shrem



To determine the degree of inter-rater reliability (IRR) between human and artificial intelligence (AI) interpretation of fetal heart rate tracings (FHR), and to determine whether AI-assisted electronic fetal monitoring interpretation improves neonatal outcomes amongst laboring women.

Data sources

We searched Medline, EMBASE, Google Scholar, Scopus, ISI Web of Science and Cochrane database search, as well as PubMed ( and RCT registry ( until the end of October 2018 to conduct a systematic review and meta-analysis comparing visual and AI interpretation of EFM in labor. Similarly, we sought out all studies evaluating the IRR between AI and expert interpretation of EFM.

Tabulation, integration and results

Weighed mean Cohen’s Kappa was calculated to assess the global IRR. Risk of bias was assessed using the Cochrane Handbook for Systematic Reviews of Interventions. We used relative risks (RR) and a random effects (RE) model to calculate weighted estimates. Statistical homogeneity was checked by the χ2 test and I2 using Review Manager 5.3.5 (The Cochrane Collaboration, 2014.) We obtained 201 records, of which 9 met inclusion criteria. Three RCT’s were used to compare the neonatal outcomes and 6 cohort studies were used to establish the degree of IRR between both approaches of EFM evaluation. With regards to the neonatal outcomes, a total of 55,064 patients were included in the analysis. Relative to the use of clinical (visual) evaluation of the FHR, the use of AI did not change the incidence rates of neonatal acidosis, cord pH below < 7.20, 5-min APGAR scores < 7, mode of delivery, NICU admission, neonatal seizures, or perinatal death. With regards to the degrees of inter-rater reliability, a weighed mean Cohen’s Kappa of 0.49 [0.32–0.66] indicates moderate agreement between expert observers and computerized systems.


The use of AI and computer analysis for the interpretation of EFM during labor does not improve neonatal outcomes. Inter-rater reliability between experts and computer systems is moderate at best. Future studies should aim at further elucidating these findings.


Artificial intelligence Computer Fetal monitoring Fetal heart rate Inter-rater reliability Neonatal outcomes 


Author contributions

Both authors (JB, GS) accomplished all tasks equally: protocol/project development; data collection or management; data analysis; manuscript writing/editing.


This study was not funded.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants performed by any of the authors.


  1. 1.
    Verghese A, Shah NH, Harrington RA (2018) What this computer needs is a physician: humanism and artificial intelligence. JAMA 319(1):19–20CrossRefGoogle Scholar
  2. 2.
    Hamet P, Tremblay J (2017) Artificial intelligence in medicine. Metab Clin Exp 69S:S36–S40CrossRefGoogle Scholar
  3. 3.
    Macones GA et al (2008) The 2008 National Institute of Child Health and Human Development workshop report on electronic fetal monitoring: update on definitions, interpretation, and research guidelines. Obstet Gynecol 112(3):661–666CrossRefGoogle Scholar
  4. 4.
    Jauniaux E, Prefumo F (2016) Fetal heart monitoring in labour: from pinard to artificial intelligence. BJOG 123(6):870CrossRefGoogle Scholar
  5. 5.
    Lear CA et al (2016) The myths and physiology surrounding intrapartum decelerations: the critical role of the peripheral chemoreflex. J Physiol 594(17):4711–4725CrossRefGoogle Scholar
  6. 6.
    Liston R, Sawchuck D, Young D (2018) No. 197b-Fetal health surveillance: intrapartum consensus guideline. J Obstet Gynaecol Can 40(4):e298–e322CrossRefGoogle Scholar
  7. 7.
    Alfirevic Z et al (2017) Continuous cardiotocography (CTG) as a form of electronic fetal monitoring (EFM) for fetal assessment during labour. Cochrane Database Syst Rev 2:CD006066Google Scholar
  8. 8.
    Group, I.C. (2017) Computerised interpretation of fetal heart rate during labour (INFANT): a randomised controlled trial. Lancet 389(10080):1719–1729CrossRefGoogle Scholar
  9. 9.
    Ignatov PN, Lutomski JE (2016) Quantitative cardiotocography to improve fetal assessment during labor: a preliminary randomized controlled trial. Eur J Obstet Gynecol Reprod Biol 205:91–97CrossRefGoogle Scholar
  10. 10.
    Nunes I et al (2017) Central fetal monitoring with and without computer analysis: a randomized controlled trial. Obstet Gynecol 129(1):83–90CrossRefGoogle Scholar
  11. 11.
    Sun S (2011) Meta-analysis of Cohen’s kappa. Health Serv Outcomes Res Method 11(3–4):145–163CrossRefGoogle Scholar
  12. 12.
    Jackson M et al (2011) Frequency of fetal heart rate categories and short-term neonatal outcome. Obstet Gynecol 118(4):803–808CrossRefGoogle Scholar
  13. 13.
    Belfort MA et al (2015) A randomized trial of intrapartum Fetal ECG ST-segment analysis. N Engl J Med 373(7):632–641CrossRefGoogle Scholar
  14. 14.
    Fairley S, Lawson H, Morris K (2000) Inter-observer agreement in cardiotocogram interpretation: how reliable is Ontario? J SOGC 22(5):366–373CrossRefGoogle Scholar
  15. 15.
    Donker DK, van Geijn HP, Hasman A (1993) Interobserver variation in the assessment of fetal heart rate recordings. Eur J Obstet Gynecol 52(1):21–28CrossRefGoogle Scholar
  16. 16.
    Parer JT et al (2006) Fetal acidemia and electronic fetal heart rate patterns: is there evidence of an association? J Matern Fetal Neonatal Med 19(5):289–294CrossRefGoogle Scholar
  17. 17.
    Akselrod S et al (1981) Power spectrum analysis of heart rate fluctuation: a quantitative probe of beat-to-beat cardiovascular control. Science 213(4504):220–222CrossRefGoogle Scholar
  18. 18.
    Parer JT, Hamilton EF (2010) Comparison of 5 experts and computer analysis in rule-based fetal heart rate interpretation. Am J Obstet Gynecol 203(5):451 (e1-7) CrossRefGoogle Scholar
  19. 19.
    Devoe L et al (2000) A comparison of visual analyses of intrapartum fetal heart rate tracings according to the new national institute of child health and human development guidelines with computer analyses by an automated fetal heart rate monitoring system. Am J Obstet Gynecol 183(2):361–366CrossRefGoogle Scholar
  20. 20.
    Bracero LA, Roshanfekr D, Byrne DW (2000) Analysis of antepartum fetal heart rate tracing by physician and computer. J Maternal Fetal Med 9(3):181–185Google Scholar
  21. 21.
    Costa MA et al (2010) Comparison of a computer system evaluation of intrapartum cardiotocographic events and a consensus of clinicians. J Perinat Med 38(2):191–195CrossRefGoogle Scholar
  22. 22.
    Krupa N et al (2011) Antepartum fetal heart rate feature extraction and classification using empirical mode decomposition and support vector machine. Biomed Eng Online 10:6CrossRefGoogle Scholar
  23. 23.
    Chen CY et al (2014) Comparison of a novel computerized analysis program and visual interpretation of cardiotocography. PLoS ONE 9(12):e112296CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Obstetrics and GynecologyMcGill UniversityMontrealCanada

Personalised recommendations