Background
The process of childbirth is one of the most crucial events in the future health and
development of the offspring. The vulnerability of parturients and fetuses during
the delivery process led to the development of intrapartum monitoring methods and
to the emergence of alternative methods of delivery. However, current monitoring methods
fail to accurately discriminate between cases in which intervention is unnecessary,
partly contributing to the high rates of cesarean deliveries worldwide.
Machine learning methods are applied in various medical fields to create personalized
prediction models. These methods are used to analyze abundant, complex data with intricate
associations to aid in decision making. Initial attempts to predict vaginal delivery
vs cesarean deliveries using machine learning tools did not utilize the vast amount
of data recorded during labor. The data recorded during labor represent the dynamic
process of labor and therefore may be invaluable for dynamic prediction of vaginal
delivery.
Objective
We aimed to create a personalized machine learning–based prediction model to predict
successful vaginal deliveries using real-time data acquired during the first stage
of labor.
Study Design
Electronic medical records of labor occurring during a 12-year period in a tertiary
referral center were explored and labeled. Four different models were created using
input from multiple maternal and fetal parameters. Initial risk assessments for vaginal
delivery were calculated using data available at the time of admission to the delivery
unit, followed by models incorporating cervical examination data and fetal heart rate
data, and finally, a model that integrates additional data available during the first
stage of labor was created.
Results
A total of 94,480 cases in which a trial of labor was attempted were identified. Based
on approximately 180 million data points from the first stage of labor, machine learning
models were developed to predict successful vaginal deliveries. A model using data
available at the time of admission to the delivery unit yielded an area under the
curve of 0.817 (95% confidence interval, 0.811–0.823). Models that used real-time
data increased prediction accuracy. A model that includes real-time cervical examination
data had an initial area under the curve of 0.819 (95% confidence interval, 0.813–0.825)
at first examination, which increased to an area under the curve of 0.917 (95% confidence
interval, 0.913–0.921) by the end of the first stage. Adding the real-time fetal heart
monitor data provided an area under the curve of 0.824 (95% confidence interval, 0.818–0.830)
at first examination, which increased to an area under the curve of 0.928 (95% confidence
interval, 0.924–0.932) by the end of the first stage. Finally, adding additional real-time
data increased the area under the curve initially to 0.833 (95% confidence interval,
0.827–0.838) at the first cervical examination and up to 0.932 (95% confidence interval,
0.928–0.935) by the end of the first stage.
Conclusion
Real-time data acquired throughout the process of labor significantly increased the
prediction accuracy for vaginal delivery using machine learning models. These models
enable translation and quantification of the data gathered in the delivery unit into
a clinical tool that yields a reliable personalized risk score and helps avoid unnecessary
interventions.
Key words
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to American Journal of Obstetrics & GynecologyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Primary and repeat cesarean deliveries: a population-based study in the United States, 1979–2010.Epidemiology. 2017; 28: 567-574
- Cesarean delivery in the United States 2005 through 2014: a population-based analysis using the Robson 10-Group Classification System.Am J Obstet Gynecol. 2018; 219: 105.e1-105.e11
- Interventions to reduce unnecessary caesarean sections in healthy women and babies.Lancet. 2018; 392: 1358-1368
- Surgical speed and risk for maternal operative morbidity in emergent repeat cesarean delivery.Am J Obstet Gynecol. 2015; 213: 584.e1-584.e6
- “Doing something” about the caesarean delivery rate.Am J Obstet Gynecol. 2018; 219: 267-271
- WHO Statement on caesarean section rates.Reprod Health Matters. 2015; 23: 149-150
- Global epidemiology of use of and disparities in caesarean sections.Lancet. 2019; 394: 23-24
- Stemming the global caesarean section epidemic.Lancet. 2018; 392: 1279
- Births — method of delivery. 2017.(Available at:)https://www.cdc.gov/nchs/fastats/delivery.htmDate accessed: February 11, 2019
- Birth after previous caesarean birth (Green-top guideline no. 45). United Kingdom of Great Britain and Northern Ireland.Royal College of Obstetricians and Gynaecologists, 2015
- Health at a glance 2017: OECD indicators.OECD Publishing, Paris: Organization for Economic Co-operation and Development2017
- Evidence-based labor and delivery management.Am J Obstet Gynecol. 2008; 199: 445-454
- Chestnut’s obstetric anesthesia: principles and practice.Elsevier, Philadelphia2019
- Vacuum extraction failure is associated with a large head circumference.J Matern Fetal Neonatal Med. 2019; 32: 3325-3330
- A large head circumference is more strongly associated with unplanned cesarean or instrumental delivery and neonatal complications than high birthweight.Am J Obstet Gynecol. 2015; 213: 833.e1-833.e12
- Sonographic large fetal head circumference and risk of cesarean delivery.Am J Obstet Gynecol. 2018; 218: 339.e1-339.e7
- Evolution of the human pelvis and obstructed labor: new explanations of an old obstetrical dilemma.Am J Obstet Gynecol. 2020; 222: 3-16
- Fetal head circumference and length of second stage of labor are risk factors for levator ani muscle injury, diagnosed by 3-dimensional transperineal ultrasound in primiparous women.Am J Obstet Gynecol. 2009; 201: 91.e1-91.e7
- Higher rates of operative delivery and maternal and neonatal complications in persistent occiput posterior position with a large head circumference: a retrospective cohort study.Fetal Diagn Ther. 2018; 44: 51-58
- Changing trends in operative delivery performed at full dilatation over a 10-year period.J Obstet Gynaecol. 2010; 30: 370-375
- Comparison of nulliparas undergoing cesarean section in first and second stages of labour: a prospective study in a tertiary teaching hospital.Obstet Gynecol Int. 2011; 2011: 986506
- Differences in outcomes between cesarean section in the second versus the first stages of labor.J Matern Fetal Neonatal Med. 2019; 32: 2539-2542
- Caesarean section at full dilatation: incidence, impact and current management.Obstet Gynaecol. 2014; 16: 199-205
- Assessing first-stage labor progression and its relationship to complications.Am J Obstet Gynecol. 2016; 214: 358.e1-358.e8
- New labor management guidelines and changes in cesarean delivery patterns.Am J Obstet Gynecol. 2017; 217: 689.e1-689.e8
- Comparison of maternal and infant outcomes from primary cesarean delivery during the second compared with first stage of labor.Obstet Gynecol. 2007; 109: 917-921
- Association between time of day and performance, indications, and outcomes of obstetric interventions among nulliparous women delivering at term.J Perinatol. 2019; 39: 808-813
- Uterine contractions in spontaneous labor. A quantitative study.Am J Obstet Gynecol. 1970; 106: 378-387
- Dysfunctional labor. VII. A comprehensive program for diagnosis, evaluation, and management.Obstet Gynecol. 1965; 25: 844-847
- Contemporary patterns of spontaneous labor with normal neonatal outcomes.Obstet Gynecol. 2010; 116: 1281-1287
- Contemporary patterns of labor in nulliparous and multiparous women.Am J Obstet Gynecol. 2020; 222: 267.e1-267.e9
- Machine learning in medicine.Circulation. 2015; 132: 1920-1930
- Predicting the future — big data, machine learning, and clinical medicine.N Engl J Med. 2016; 375: 1216-1219
- Clinical applications of machine learning algorithms: beyond the black box.BMJ. 2019; 364: l886
- Machine learning in medicine.N Engl J Med. 2019; 380: 1347-1358
- Classification of caesarean section and normal vaginal deliveries using foetal heart rate signals and advanced machine learning algorithms.Biomed Eng Online. 2017; 16: 89
- Implementation of classification algorithms to predict mode of delivery.Int J Comput Sci Inf Technol. 2015; 6: 4531-4534
- Prediction of vaginal birth after cesarean deliveries using machine learning.Am J Obstet Gynecol. 2020; ([Epub ahead of print])
- Machine learning ensemble modelling to classify caesarean section and vaginal delivery types using cardiotocography traces.Comput Biol Med. 2018; 93: 7-16
- Prediction of risk for cesarean delivery in term nulliparas: a comparison of neural network and multiple logistic regression models.Am J Obstet Gynecol. 2009; 201: 113.e1-113.e6
- CatBoost: unbiased boosting with categorical features.Adv Neural Inf Process Syst. 2018; 31: 6639-6649
- Index for rating diagnostic tests.Cancer. 1950; 3: 32-35
- Verification of forecasts expressed in terms of probability.Mon Weather Rev. 1950; 78: 1-3
- Fast implementation of DeLong’s algorithm for comparing the areas under correlated receiver operating characteristic curves.IEEE Signal Process Lett. 2014; 21: 1389-1393
- From local explanations to global understanding with explainable AI for trees.Nat Mach Intell. 2020; 2: 56-67
- An analysis of four missing data treatment methods for supervised learning.Appl Artif Intell. 2003; 17: 519-533
- Computer modeling to predict cesarean delivery in term nulliparas [28N].Obstet Gynecol. 2016; 127: 122S
- Deep learning and alternative learning strategies for retrospective real-world clinical data.NPJ Digit Med. 2019; 2: 43
Article Info
Publication History
Published online: May 16, 2020
Accepted:
May 12,
2020
Received in revised form:
April 28,
2020
Received:
February 3,
2020
Footnotes
This research was funded by the Israel Ministry of Science and Technology (M.L.)
The authors report no conflict of interest.
Cite this article as: Guedalia J, Lipschuetz M, Novoselsky Persky M, et al. Real-time data analysis using a machine learning model significantly improves prediction of successful vaginal deliveries. Am J Obstet Gynecol 2020;223:437.e1-15.
Identification
Copyright
© 2020 Elsevier Inc. All rights reserved.
