Am J Perinatol
DOI: 10.1055/a-1885-1697
Original Article

Applying Automated Machine Learning to Predict Mode of Delivery Using Ongoing Intrapartum Data in Laboring Patients

1   Department of Obstetrics and Gynecology, Cedars-Sinai Medical Center, Los Angeles, California
2   Division of Informatics, Department of Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California
,
Matthew Wells
3   Enterprise Data Intelligence, Cedars-Sinai Medical Center, Los Angeles, California
,
Davina Zamanzadeh
4   Medical and Imaging Informatics (MII) Group, Department of Radiological Sciences, University of California Los Angeles, Los Angeles, California
,
Samir Akre
4   Medical and Imaging Informatics (MII) Group, Department of Radiological Sciences, University of California Los Angeles, Los Angeles, California
,
Joshua M. Pevnick
2   Division of Informatics, Department of Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California
5   Division of General Internal Medicine, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, California
,
Alex A.T. Bui
4   Medical and Imaging Informatics (MII) Group, Department of Radiological Sciences, University of California Los Angeles, Los Angeles, California
6   Department of Bioengineering, University of California Los Angeles, Los Angeles, California
,
Kimberly D. Gregory
1   Department of Obstetrics and Gynecology, Cedars-Sinai Medical Center, Los Angeles, California
7   Department of Obstetrics and Gynecology, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, California
8   Department of Community Health Sciences, Los Angeles, California Fielding School of Public Health, Los Angeles, California
› Author Affiliations

Abstract

Objective This study aimed to develop and validate a machine learning (ML) model to predict the probability of a vaginal delivery (Partometer) using data iteratively obtained during labor from the electronic health record.

Study Design A retrospective cohort study of deliveries at an academic, tertiary care hospital was conducted from 2013 to 2019 who had at least two cervical examinations. The population was divided into those delivered by physicians with nulliparous term singleton vertex (NTSV) cesarean delivery rates <23.9% (Partometer cohort) and the remainder (control cohort). The cesarean rate among this population of lower risk patients is a standard metric by which to compare provider rates; <23.9% was the Healthy People 2020 goal. A supervised automated ML approach was applied to generate a model for each population. The primary outcome was accuracy of the model developed on the Partometer cohort at 4 hours from admission to labor and delivery. Secondary outcomes included discrimination ability (receiver operating characteristics–area under the curve [ROC-AUC]), precision-recall AUC, and calibration of the Partometer. To assess generalizability, we compared the performance and clinical predictors identified by the Partometer to the control model.

Results There were 37,932 deliveries during the study period; after exclusions, 9,385 deliveries were included in the Partometer cohort and 19,683 in the control cohort. Accuracy of predicting vaginal delivery at 4 hours was 87.1% for the Partometer (ROC-AUC: 0.82). Clinical predictors of greatest importance in the stacked Intrapartum Partometer Model included the Admission Model prediction and ongoing measures of dilatation and station which mirrored those found in the control population.

Conclusion Using automated ML and intrapartum factors improved the accuracy of prediction of probability of a vaginal delivery over both previously published models based on logistic regression. Harnessing real-time data and ML could represent the bridge to generating a truly prescriptive tool to augment clinical decision-making, predict labor outcomes, and reduce maternal and neonatal morbidity.

Key Points

  • Our ML-based model yielded accurate predictions of mode of delivery early in labor.

  • Predictors for models created on populations with high and low cesarean rates were the same.

  • A ML-based model may provide meaningful guidance to clinicians managing labor.

Supplementary Material



Publication History

Received: 28 April 2022

Accepted: 21 June 2022

Accepted Manuscript online:
25 June 2022

Article published online:
29 December 2022

© 2022. Thieme. All rights reserved.

Thieme Medical Publishers, Inc.
333 Seventh Avenue, 18th Floor, New York, NY 10001, USA

 
  • References

  • 1 Caughey AB, Cahill AG, Guise J-M, Rouse DJ. American College of Obstetricians and Gynecologists (College), Society for Maternal-Fetal Medicine. Safe prevention of the primary cesarean delivery. Am J Obstet Gynecol 2014; 210 (03) 179-193
  • 2 Towner D, Castro MA, Eby-Wilkens E, Gilbert WM. Effect of mode of delivery in nulliparous women on neonatal intracranial injury. N Engl J Med 1999; 341 (23) 1709-1714
  • 3 Sebastião YV, Womack L, Vamos CA. et al. Hospital variation in cesarean delivery rates: contribution of individual and hospital factors in Florida. Am J Obstet Gynecol 2016; 214 (01) 123.e1-123.e18
  • 4 Grobman WA, Bailit JL, Rice MM. et al; Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD) Maternal-Fetal Medicine Units (MFMU) Network. Racial and ethnic disparities in maternal morbidity and obstetric care. Obstet Gynecol 2015; 125 (06) 1460-1467
  • 5 Yee LM, Costantine MM, Rice MM. et al; Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD) Maternal-Fetal Medicine Units (MFMU) Network. Racial and ethnic differences in utilization of labor management strategies intended to reduce cesarean delivery rates. Obstet Gynecol 2017; 130 (06) 1285-1294
  • 6 McDonald JA, Amatya A, Gard CC, Sigala J. Trends in Hispanic and non-Hispanic white cesarean delivery rates on the US-Mexico border, 2000-2015. PLoS One 2018; 13 (09) e0203550
  • 7 Valdes EG. Examining cesarean delivery rates by race: a population-based analysis using the robson ten-group classification system. J Racial Ethn Health Disparities 2021; 8 (04) 844-851
  • 8 Burke N, Burke G, Breathnach F. et al; Perinatal Ireland Research Consortium. Prediction of cesarean delivery in the term nulliparous woman: results from the prospective, multicenter Genesis study. Am J Obstet Gynecol 2017; 216 (06) 598.e1-598.e11
  • 9 Kawakita T, Reddy UM, Huang CC, Auguste TC, Bauer D, Overcash RT. Predicting vaginal delivery in nulliparous women undergoing induction of labor at term. Am J Perinatol 2018; 35 (07) 660-668
  • 10 Yang M, Liu C, Wang X. et al. An explainable artificial intelligence predictor for early detection of sepsis. Crit Care Med 2020; 48 (11) e1091-e1096
  • 11 Baltruschat I, Steinmeister L, Nickisch H. et al. Smart chest X-ray worklist prioritization using artificial intelligence: a clinical workflow simulation. Eur Radiol 2021; 31 (06) 3837-3845
  • 12 U.S. Department of Health and Human Services. DC Healthy People 2020. Accessed July 6, 2022, at: https://dchealth.dc.gov/page/dc-healthy-people-2020#:~:text=DC%20Healthy%20People%202020%20(DC,for%20important%20population%20health%20outcomes
  • 13 de Souza HCC, Perdoná GSC, Marcolin AC. et al. Development of caesarean section prediction models: secondary analysis of a prospective cohort study in two sub-Saharan African countries. Reprod Health 2019; 16 (01) 165
  • 14 Lipschuetz M, Guedalia J, Rottenstreich A. et al. Prediction of vaginal birth after cesarean deliveries using machine learning. Am J Obstet Gynecol 2020; 222 (06) 613.e1-613.e12
  • 15 Grobman WA, Lai Y, Landon MB. et al; National Institute of Child Health and Human Development (NICHD) Maternal-Fetal Medicine Units Network (MFMU). Development of a nomogram for prediction of vaginal birth after cesarean delivery. Obstet Gynecol 2007; 109 (04) 806-812
  • 16 Aron DC, Gordon HS, DiGiuseppe DL, Harper DL, Rosenthal GE. Variations in risk-adjusted cesarean delivery rates according to race and health insurance. Med Care 2000; 38 (01) 35-44