{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:20:05Z","timestamp":1792790405030,"version":"4.5.0"},"posted":{"date-parts":[[2026,9,26]]},"group-title":"Obstetrics and Gynecology","reference-count":40,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T00:00:00Z","timestamp":1790380800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD), National Institutes of Health","award":["R01HD119210"],"award-info":[{"award-number":["R01HD119210"]}],"id":[{"id":"https:\/\/ror.org\/04byxyr05","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,26]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Timely detection of fetal distress during labor is a central pursuit of modern obstetric care. The primary measure used in this regard is fetal heart rate and contraction monitoring (echocardiotocography or CTG), which provides a continuous signal during labor. The vast majority of machine learning applications to CTG assume access to a 30 to 60 minute window just prior to delivery, which makes an untenable assumption that the timing of delivery is known. In this work, we reframe the problem as a time-to-event prediction task. We develop deep time-to-event models to predict the joint probability of imminent delivery and fetal acidosis, a biomarker of fetal hypoxia collected from umbilical cord gas after delivery. We develop a framework for this problem, drawing on deep discrete-time survival methods and marked point processes, adapting each to this particular setting (i.e., continuous physiological signals, fully observed events, partially observed labels). One approach dubbed Marked DeepHit accurately estimates delivery within one hour at multiple elapsed-time landmarks, with test-set AUROC of 0.837 [95% CI 0.692\u20130.970] and 0.935 [0.858\u20130.964] at 6 and 12 hours into labor, respectively. We find that these models also achieve competitive performance near delivery time compared to prior models trained specifically on the end of tracing, and outperform other clinical feature-based proposals, both on internal and external validation at a second site. These results give a proof-of-principle to support future prospective deployment of AI-EFM during labor.<\/jats:p>","DOI":"10.64898\/2026.09.21.26363416","type":"posted-content","created":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T17:30:16Z","timestamp":1790443816000},"source":"Crossref","is-referenced-by-count":0,"title":["Deep Time-to-Event Models for Intrapartum Fetal Monitoring"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0102-4958","authenticated-orcid":false,"given":"Guilherme S.","family":"Imai Aldeia","sequence":"first","affiliation":[{"name":"Computational Health Informatics Program, Boston Children\u2019s Hospital, Boston, MA, USA"},{"name":"Department of Pediatrics, Harvard Medical School, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7798-9318","authenticated-orcid":false,"given":"Helena","family":"Coggan","sequence":"additional","affiliation":[{"name":"Computational Health Informatics Program, Boston Children\u2019s Hospital, Boston, MA, USA"},{"name":"Department of Pediatrics, Harvard Medical School, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7750-2418","authenticated-orcid":false,"given":"Yuting","family":"Yang","sequence":"additional","affiliation":[{"name":"Computational Health Informatics Program, Boston Children\u2019s Hospital, Boston, MA, USA"},{"name":"Department of Pediatrics, Harvard Medical School, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6811-7980","authenticated-orcid":false,"given":"Lisa","family":"Levine","sequence":"additional","affiliation":[{"name":"Pregnancy and Perinatal Research Center, Department of Obstetrics and Gynecology, University of Pennsylvania, Perelman School of Medicine, Philadelphia, PA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3057-7500","authenticated-orcid":false,"given":"Jennifer A.","family":"McCoy","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, Geisel School of Medicine, Dartmouth Hitchcock Medical Center, Hanover, NH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1332-2960","authenticated-orcid":false,"given":"William","family":"La Cava","sequence":"additional","affiliation":[{"name":"Computational Health Informatics Program, Boston Children\u2019s Hospital, Boston, MA, USA"},{"name":"Department of Pediatrics, Harvard Medical School, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026093003300585000_2026.09.21.26363416v1.1","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD006066.pub3"},{"key":"2026093003300585000_2026.09.21.26363416v1.2","doi-asserted-by":"publisher","DOI":"10.1093\/ije\/dyr213"},{"key":"2026093003300585000_2026.09.21.26363416v1.3","doi-asserted-by":"publisher","DOI":"10.1002\/sim.2427"},{"key":"2026093003300585000_2026.09.21.26363416v1.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijgo.2015.06.020"},{"key":"2026093003300585000_2026.09.21.26363416v1.5","doi-asserted-by":"publisher","DOI":"10.1111\/aogs.14498"},{"key":"2026093003300585000_2026.09.21.26363416v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2018.01.026"},{"key":"2026093003300585000_2026.09.21.26363416v1.7","doi-asserted-by":"publisher","DOI":"10.1080\/14767058.2018.1542676"},{"key":"2026093003300585000_2026.09.21.26363416v1.8","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2393-14-16"},{"key":"2026093003300585000_2026.09.21.26363416v1.9","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1972.tb00899.x"},{"key":"2026093003300585000_2026.09.21.26363416v1.10","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939875"},{"key":"2026093003300585000_2026.09.21.26363416v1.11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2022.11.1275"},{"key":"2026093003300585000_2026.09.21.26363416v1.12","doi-asserted-by":"publisher","DOI":"10.1097\/AOG.0000000000002106"},{"key":"2026093003300585000_2026.09.21.26363416v1.13","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1999.10474144"},{"key":"2026093003300585000_2026.09.21.26363416v1.14","doi-asserted-by":"publisher","DOI":"10.1111\/aogs.13639"},{"key":"2026093003300585000_2026.09.21.26363416v1.15","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-019-00619-1"},{"key":"2026093003300585000_2026.09.21.26363416v1.16","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-020-00710-y"},{"key":"2026093003300585000_2026.09.21.26363416v1.17","doi-asserted-by":"publisher","DOI":"10.1016\/j.mex.2024.102664"},{"issue":"129","key":"2026093003300585000_2026.09.21.26363416v1.18","first-page":"1","article-title":"Time-to-event prediction with neural networks and Cox regression","volume":"20","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"2026093003300585000_2026.09.21.26363416v1.19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11842"},{"key":"2026093003300585000_2026.09.21.26363416v1.20","unstructured":"Ilya Loshchilov and Frank Hutter . SGDR: Stochastic gradient descent with warm restarts. In International Conference on Learning Representations, 2017. URL https:\/\/openreview.net\/forum?id=Skq89Scxx."},{"key":"2026093003300585000_2026.09.21.26363416v1.21","doi-asserted-by":"publisher","DOI":"10.1097\/AOG.0b013e3181841395"},{"key":"2026093003300585000_2026.09.21.26363416v1.22","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.c1471"},{"issue":"10","key":"2026093003300585000_2026.09.21.26363416v1.23","first-page":"1","article-title":"Births: Final data for 2002","volume":"52","year":"2003","journal-title":"Natl Vital Stat Rep","ISSN":"https:\/\/id.crossref.org\/issn\/1551-8922","issn-type":"print"},{"key":"2026093003300585000_2026.09.21.26363416v1.24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2024.04.022"},{"key":"2026093003300585000_2026.09.21.26363416v1.25","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering10091007"},{"key":"2026093003300585000_2026.09.21.26363416v1.26","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-63108-6"},{"key":"2026093003300585000_2026.09.21.26363416v1.27","doi-asserted-by":"publisher","DOI":"10.1109\/JTEHM.2025.3548401"},{"key":"2026093003300585000_2026.09.21.26363416v1.28","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM199603073341001"},{"key":"2026093003300585000_2026.09.21.26363416v1.29","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-92805-9"},{"key":"2026093003300585000_2026.09.21.26363416v1.30","doi-asserted-by":"publisher","DOI":"10.1109\/embc.2018.8513625"},{"key":"2026093003300585000_2026.09.21.26363416v1.31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2933368"},{"key":"2026093003300585000_2026.09.21.26363416v1.32","doi-asserted-by":"publisher","DOI":"10.1002\/sim.2712"},{"key":"2026093003300585000_2026.09.21.26363416v1.33","doi-asserted-by":"publisher","DOI":"10.1214\/17-STS629"},{"key":"2026093003300585000_2026.09.21.26363416v1.34","doi-asserted-by":"publisher","DOI":"10.1055\/a-2099-4395"},{"key":"2026093003300585000_2026.09.21.26363416v1.35","doi-asserted-by":"crossref","unstructured":"Oleksandr Shchur , Ali Caner T\u00fcrkmen , Tim Januschowski , and Stephan G\u00fcnnemann . Neural temporal point processes: A review. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI), pages 4585\u20134593, 2021.","DOI":"10.24963\/ijcai.2021\/623"},{"key":"2026093003300585000_2026.09.21.26363416v1.36","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2016.2546312"},{"key":"2026093003300585000_2026.09.21.26363416v1.37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2022.10.003"},{"key":"2026093003300585000_2026.09.21.26363416v1.38","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9469.2006.00529.x"},{"key":"2026093003300585000_2026.09.21.26363416v1.39","unstructured":"Johann Vargas-Calixto , Michael W Kuzniewicz , Marie-Coralie Cornet , Yvonne W Wu , Aditi Lahiri , Lawrence Gerstley , John Parker , Philip A War-rick , and Robert E Kearney . Time-Surrogate Variables Enhance the Association Between Car-diotocographic Features and Intrapartum Hypoxic-Ischemic Encephalopathy."},{"key":"2026093003300585000_2026.09.21.26363416v1.40","doi-asserted-by":"publisher","DOI":"10.1111\/j.1541-0420.2005.00323.x"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.09.21.26363416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T10:30:17Z","timestamp":1790764217000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.09.21.26363416"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,26]]},"references-count":40,"URL":"https:\/\/doi.org\/10.64898\/2026.09.21.26363416","relation":{},"subject":[],"published":{"date-parts":[[2026,9,26]]},"subtype":"preprint"}}