Prediction of severe adverse neonatal outcomes at the second stage of labour using machine learning: a retrospective cohort study.
Adult
Delivery, Obstetric
/ statistics & numerical data
Female
Gravidity
Humans
Labor Presentation
Labor Stage, First
Labor Stage, Second
Machine Learning
Obstetric Labor Complications
/ diagnosis
Parity
Patient Admission
/ statistics & numerical data
Predictive Value of Tests
Pregnancy
Pregnancy Outcome
ROC Curve
Retrospective Studies
Machine learning
neonatal outcomes
obstetrics
personalised medicine
second stage of labour
Journal
BJOG : an international journal of obstetrics and gynaecology
ISSN: 1471-0528
Titre abrégé: BJOG
Pays: England
ID NLM: 100935741
Informations de publication
Date de publication:
10 2021
10 2021
Historique:
revised:
19
02
2021
received:
22
10
2020
accepted:
03
03
2021
pubmed:
14
3
2021
medline:
29
9
2021
entrez:
13
3
2021
Statut:
ppublish
Résumé
To create a personalised machine learning model for prediction of severe adverse neonatal outcomes (SANO) during the second stage of labour. Retrospective Electronic-Medical-Record (EMR) -based study. A cohort of 73 868 singleton, term deliveries that reached the second stage of labour, including 1346 (1.8%) deliveries with SANO. A gradient boosting model was created, analysing 21 million data points from antepartum features (e.g. gravidity and parity) gathered at admission to the delivery unit, and intrapartum data (e.g. cervical dilatation and effacement) gathered during the first stage of labour. Deliveries were allocated to high-risk and low-risk groups based on the Youden index to maximise sensitivity and specificity. SANO was defined as either umbilical cord pH levels ≤7.1 or 1-minute or 5-minute Apgar score ≤7. The model for prediction of SANO yielded an area under the receiver operating curve (AUC) of 0.761 (95% CI 0.748-0.774). A third of the cohort (33.5%, n = 24 721) were allocated to a high-risk group for SANO, which captured up to 72.1% of these cases (odds ratio 5.3, 95% CI 4.7-6.0; high-risk versus low-risk groups). Data acquired throughout the first stage of labour can be used to predict SANO during the second stage of labour using a machine learning model. Stratifying parturients at the beginning of the second stage of labour in a 'time out' session, can direct a personalised approach to management of this challenging aspect of labour, as well as improve allocation of staff and resources. Personalised prediction score for severe adverse neonatal outcomes in labour using machine learning model.
Identifiants
pubmed: 33713380
doi: 10.1111/1471-0528.16700
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
1824-1832Informations de copyright
© 2021 John Wiley & Sons Ltd.
Références
Clark SL, Hamilton EF, Garite TJ, Timmins A, Warrick PA, Smith S. The limits of electronic fetal heart rate monitoring in the prevention of neonatal metabolic acidemia. Am J Obstet Gynecol 2017;216:163.e161-e166.
Monitoring during labour. Intrapartum Care: Care of Healthy Women and Their Babies during Childbirth. London: National Institute for Health and Care Excellence, 2014.
Sabol BA, Caughey AB. Acidemia in neonates with a 5-minute Apgar score of 7 or greater - what are the outcomes? Am J Obstet Gynecol 2016;215:486.e481-486.
Royal College of Obstetricians and Gynaecologists. Each Baby Counts: 2015 Summary Report. London: RCOG, 2017.
Evans MI, Eden RD, Britt DW, Evans SM, Schifrin BS. Re-engineering the interpretation of electronic fetal monitoring to identify reversible risk for cerebral palsy: a case control series. J Matern Fetal Neonatal Med 2019;32:2561-9.
Bewley S, Braillon A. Electronic fetal heart rate monitoring: we need new research approaches. BMJ 2018;360:k658.
Cahill AG, Tuuli MG, Stout MJ, Lopez JD, Macones GA. A prospective cohort study of fetal heart rate monitoring: deceleration area is predictive of fetal acidemia. Am J Obstet Gynecol 2018;218:523.e521-e512.
Alfirevic Z, Devane D, Gyte GM, Cuthbert A. Continuous cardiotocography (CTG) as a form of electronic fetal monitoring (EFM) for fetal assessment during labour. Cochrane Database Syst Rev 2017;2:CD006066.
Vintzileos AM, Smulian JC. Decelerations, tachycardia, and decreased variability: have we overlooked the significance of longitudinal fetal heart rate changes for detecting intrapartum fetal hypoxia? Am J Obstet Gynecol 2016;215:261-4.
Clark SL, Nageotte MP, Garite TJ, Freeman RK, Miller DA, Simpson KR, et al. Intrapartum management of category II fetal heart rate tracings: towards standardization of care. Am J Obstet Gynecol 2013;209:89-97.
Balayla J, Shrem G. Use of artificial intelligence (AI) in the interpretation of intrapartum fetal heart rate (FHR) tracings: a systematic review and meta-analysis. Arch Gynecol Obstet 2019;300:7-14.
Steer PJ, Kovar I, McKenzie C, Griffin M, Linsell L. Computerised analysis of intrapartum fetal heart rate patterns and adverse outcomes in the INFANT trial. BJOG 2019;126:1354-61.
Nunes I, Ayres-de-Campos D, Ugwumadu A, Amin P, Banfield P, Nicoll A, et al. Central fetal monitoring with and without computer analysis: a randomized controlled trial. Obstet Gynecol 2017;129:83-90.
Ignatov PN, Lutomski JE. Quantitative cardiotocography to improve fetal assessment during labor: a preliminary randomized controlled trial. Eur J Obstet Gynecol Reprod Biol 2016;205:91-7.
Belfort MA, Saade GR, Thom E, Blackwell SC, Reddy UM, Thorp JM Jr, et al. A randomized trial of intrapartum fetal ECG ST-segment analysis. N Engl J Med 2015;373:632-41.
Devoe L, Golde S, Kilman Y, Morton D, Shea K, Waller J. 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 2000;183:361-6.
Flatley C, Gibbons K, Hurst C, Flenady V, Kumar S. Cross-validated prediction model for severe adverse neonatal outcomes in a term, non-anomalous, singleton cohort. BMJ Paediatr Open 2019;3:e000424.
Holmgren CM, Esplin MS, Jackson M, Porter TF, Henry E, Horne BD, et al. A risk stratification model to predict adverse neonatal outcome in labor. J Perinatol 2013;33:914-8.
Locatelli A, Incerti M, Paterlini G, Doria V, Consonni S, Provero C, et al. Antepartum and intrapartum risk factors for neonatal encephalopathy at term. Am J Perinatol 2010;27:649-54.
Cohen SM, Lipschuetz M, Yagel S. Is a prolonged second stage of labor too long? Ultrasound Obstet Gynecol 2017;50:423-6.
Quinones JN, Gomez D, Hoffman MK, Ananth CV, Smulian JC, Skupski DW, et al. Length of the second stage of labor and preterm delivery risk in the subsequent pregnancy. Am J Obstet Gynecol 2018;219:467.e461-e468.
Gimovsky AC, Berghella V. Randomized controlled trial of prolonged second stage: extending the time limit vs usual guidelines. Am J Obstet Gynecol 2016;214:361.e361-e366.
Leveno KJ, Nelson DB, McIntire DD. Second-stage labor: how long is too long? Am J Obstet Gynecol 2016;214:484-9.
Nelson DB, McIntire DD, Leveno KJ. Second-stage labor: consensus versus science. Am J Obstet Gynecol 2020;222:144-9.
Deo RC. Machine learning in medicine. Circulation 2015;132:1920-30.
Obermeyer Z, Emanuel EJ. Predicting the future - big data, machine learning, and clinical medicine. N Engl J Med 2016;375:1216-9.
Watson DS, Krutzinna J, Bruce IN, Griffiths CE, McInnes IB, Barnes MR, et al. Clinical applications of machine learning algorithms: beyond the black box. BMJ 2019;364:l886.
Rajkomar A, Dean J, Kohane I. Machine Learning in Medicine. N Engl J Med 2019;380:1347-58.
Fergus P, Hussain A, Al-Jumeily D, Huang DS, Bouguila N. Classification of caesarean section and normal vaginal deliveries using foetal heart rate signals and advanced machine learning algorithms. Biomed Eng Online 2017;16:89.
Kamat A, Oswal V, Datar M. Implementation of classification algorithms to predict mode of delivery. Int J Comput Sci Inf Technol 2015;6:4531-4.
Guedalia J, Lipschuetz M, Novoselsky Persky M, Cohen SM, Rottenstreich A, Levin G, 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-e15.
Lipschuetz M, Guedalia J, Rottenstreich A, Novoselsky Persky M, Cohen SM, Kabiri D, et al. Prediction of vaginal birth after cesarean deliveries using machine learning. Am J Obstet Gynecol 2020;222(6):613.e1-e12.
The American College of Obstetricians and Gynecologists, Society for Maternal-Fetal Medicine, Caughey AB, Cahill AG, Guise JM, Rouse DJ. Safe prevention of the primary cesarean delivery. Am J Obstet Gynecol 2014;210:179-93.
Zhang J, Landy HJ, Branch DW, Burkman R, Haberman S, Gregory KD, et al. Contemporary patterns of spontaneous labor with normal neonatal outcomes. Obstet Gynecol 2010;116:1281-7.
American College of Obstetrics and Gynecology Committee on Practice Bulletins-Obstetrics. ACOG Practice Bulletin Number 49, December 2003: dystocia and augmentation of labor. Obstet Gynecol 2003;102:1445-54.
Sun X, Xu W. Fast implementation of DeLong's algorithm for comparing the areas under correlated receiver operating characteristic curves. IEEE Signal Process Lett 2014;21:1389-93.
Prokhorenkova L, Gusev G, Vorobev A, Dorogush AV, Gulin A. CatBoost: unbiased boosting with categorical features. arXiv: 1706.09516.
Youden WJ. Index for rating diagnostic tests. Cancer 1950;3:32-5.
Vu K, Clark RA, Bellinger C, Erickson G, Osornio-Vargas A, Zaiane OR, et al. The index lift in data mining has a close relationship with the association measure relative risk in epidemiological studies. BMC Med Inform Decis Mak 2019;19:112.
Lundberg SM, Erion G, Chen H, DeGrave A, Prutkin JM, Nair B, et al. From local explanations to global understanding with explainable AI for trees. Nat Mach Intell 2020;2:56-67.
Shapley LS. A value for n-person games. In: Kuhn HW, Tucker AW, editors. Contributions to the Theory of Games, Vol. 2. Princeton, NJ: Princeton University Press, 1953. pp. 307-17.
Wiegerinck MM, Danhof NA, Van Kaam AH, Tamminga P, Mol BW. The validity of the variable "NICU admission" as an outcome measure for neonatal morbidity: a retrospective study. Acta Obstet Gynecol Scand 2014;93:603-9.