Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Dec:2019:381-385.
doi: 10.1109/CAMSAP45676.2019.9022670. Epub 2020 Mar 5.

EXTRACTING INTERPRETABLE FEATURES FOR FETAL HEART RATE RECORDINGS WITH GAUSSIAN PROCESSES

Guanchao Feng  1 , J Gerald Quirk  2 , Petar M Djurić  1
Affiliations

EXTRACTING INTERPRETABLE FEATURES FOR FETAL HEART RATE RECORDINGS WITH GAUSSIAN PROCESSES

Guanchao Feng et al. Int Workshop Comput Adv Multisens Adapt Process. 2019 Dec.

Abstract

During labor, fetal heart rate (FHR) and uterine activity (UA) are continuously monitored with Cardiotocography (CTG). The FHR and UA signals are visually inspected by obstetricians to assess the fetal well-being. However, due to the subjectivity of the visual inspection, the evaluations of CTG recordings performed by obstetricians have high inter- and intra-variability. The computerized analysis of FHR relies on features either hand-crafted by experts or automatically learned by machine learning methods. However, the popular interpretable FHR features, in general, have low correlation with the pH value of the umbilical cord blood at birth, which is the current gold standard for labeling FHRs in the computerized analysis of FHRs. The features found by machine learning methods, by contrast, usually have limited interpretability. In this paper, in a follow up of our previous work on FHR analysis using Gaussian processes (GPs), we explore the possibility of using the hyperparameters of GPs as interpretable features. Our results indicate that some GP features achieve high correlation with the pH values, while at the same time they are not highly correlated with other popular features.

Keywords: Cardiotocography; Gaussian processes; fetal heart rate; uterine activity.

PubMed Disclaimer

Figures

Fig. 1.
Fig. 1.
A segment of not-preprocessed (raw) FHR tracing and its corresponding UA signal.
Fig. 2.
Fig. 2.
Correlation matrix of GP features and pH value.
See this image and copyright information in PMC

References

    1. Nageotte MP, “Fetal heart rate monitoring,” in Seminars in Fetal and Neonatal Medicine, vol. 20, no. 3. Elsevier, 2015, pp. 144–148. - PubMed
    1. Freeman RK, Garite TJ, Nageotte MP, and Miller LA, Fetal Heart Rate Monitoring. Lippincott Williams & Wilkins, 2012.
    1. Ayres-de Campos D, Spong CY, Chandraharan E, and Panel FIFMEC, “FIGO consensus guidelines on intrapartum fetal monitoring: Cardiotocography,” International Journal of Gynecology & Obstetrics, vol. 131, no. 1, pp. 13–24, 2015. [Online]. Available: 10.1016/j.ijgo.2015.06.020 - DOI - PubMed
    1. Bernardes J, Moura C, de Sa JPM, and Leite LP, “The Porto system for automated cardiotocographic signal analysis,” Journal of Perinatal Medicine-Official Journal of the WAPM, vol. 19, no. 1–2, pp. 61–65, 1991. - PubMed
    1. Dawes G, Visser G, Goodman J, and Redman C, “Numerical analysis of the human fetal heart rate: The quality of ultrasound records,” American Journal of Obstetrics and Gynecology, vol. 141, no. 1, pp. 43–52, 1981. - PubMed

LinkOut - more resources