Academic Journal
Προβολή σε EDS
Συνδεδεμένο Πλήρες Κείμενο

Predictive models of miscarriage on the basis of data from a preconception cohort study.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Predictive models of miscarriage on the basis of data from a preconception cohort study.
Συγγραφείς: Yland JJ; Department of Epidemiology, Boston University School of Public Health, Boston, Massachusetts. Electronic address: yland@bu.edu., Zad Z; Hariri Institute for Computing and Computational Science & Engineering, Boston University, Boston, Massachusetts; Division of Systems Engineering, Department of Electrical and Computer Engineering, Boston University, Boston, Massachusetts., Wang TR; Department of Epidemiology, Boston University School of Public Health, Boston, Massachusetts., Wesselink AK; Department of Epidemiology, Boston University School of Public Health, Boston, Massachusetts., Jiang T; Department of Epidemiology, Boston University School of Public Health, Boston, Massachusetts., Hatch EE; Department of Epidemiology, Boston University School of Public Health, Boston, Massachusetts., Paschalidis IC; Hariri Institute for Computing and Computational Science & Engineering, Boston University, Boston, Massachusetts; Division of Systems Engineering, Department of Electrical and Computer Engineering, Boston University, Boston, Massachusetts; Department of Biomedical Engineering, Boston University, Boston, Massachusetts., Wise LA; Department of Epidemiology, Boston University School of Public Health, Boston, Massachusetts.
Πηγή: Fertility and sterility [Fertil Steril] 2024 Jul; Vol. 122 (1), pp. 140-149. Date of Electronic Publication: 2024 Apr 10.
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: Elsevier for the American Society for Reproductive Medicine Country of Publication: United States NLM ID: 0372772 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1556-5653 (Electronic) Linking ISSN: 00150282 NLM ISO Abbreviation: Fertil Steril Subsets: MEDLINE
Imprint Name(s): Publication: New York. NY : Elsevier for the American Society for Reproductive Medicine
Original Publication: New York, Hoeber.
Ιατρικοί όροι (MeSH): Abortion, Spontaneous*/epidemiology, United States/epidemiology ; Canada/epidemiology ; Humans ; Female ; Adult ; Pregnancy ; Prospective Studies ; Young Adult ; Middle Aged ; Risk Factors ; Risk Assessment ; Predictive Value of Tests ; Cohort Studies ; Male ; Self Report
Περίληψη: Objective: To use self-reported preconception data to derive models that predict the risk of miscarriage.
Design: Prospective preconception cohort study.
Setting: Not applicable.
Patients: Study participants were female, aged 21-45 years, residents of the United States or Canada, and attempting spontaneous pregnancy at enrollment during 2013-2022. Participants were followed for up to 12 months of pregnancy attempts; those who conceived were followed through pregnancy and postpartum. We restricted analyses to participants who conceived during the study period.
Exposure: On baseline and follow-up questionnaires completed every 8 weeks until pregnancy, we collected self-reported data on sociodemographic factors, reproductive history, lifestyle, anthropometrics, diet, medical history, and male partner characteristics. We included 160 potential predictor variables in our models.
Main Outcome Measures: The primary outcome was a miscarriage, defined as pregnancy loss before 20 weeks of gestation. We followed participants from their first positive pregnancy test until miscarriage or a censoring event (induced abortion, ectopic pregnancy, loss of follow-up, or 20 weeks of gestation), whichever occurred first. We fit both survival and static models using Cox proportional hazards models, logistic regression, support vector machines, gradient-boosted trees, and random forest algorithms. We evaluated model performance using the concordance index (survival models) and the weighted F1 score (static models).
Results: Among the 8,720 participants who conceived, 20.4% reported miscarriage. In multivariable models, the strongest predictors of miscarriage were female age, history of miscarriage, and male partner age. The weighted F1 score ranged from 73%-89% for static models and the concordance index ranged from 53%-56% for survival models, indicating better discrimination for the static models compared with the survival models (i.e., the ability of the model to discriminate between individuals with and without miscarriage). No appreciable differences were observed across strata of miscarriage history or among models restricted to ≥8 weeks of gestation.
Conclusion: Our findings suggest that miscarriage is not easily predicted on the basis of preconception lifestyle characteristics and that advancing age and a history of miscarriage are the most important predictors of incident miscarriage.
(Copyright © 2024 American Society for Reproductive Medicine. Published by Elsevier Inc. All rights reserved.)
Competing Interests: Declaration of Interests J.J.Y. has nothing to disclose. Z.Z. reports funding from the National Institutes of Health (NIH) and the National Science Foundation (NSF) for the submitted work. T.R.W. reports funding from NIH and the NSF for the submitted work. A.K.W. reports funding from NIH outside the submitted work. T.J. has nothing to disclose. E.E.H. has nothing to disclose. I.C.P. reports funding from NIH and NSF for the submitted work; consulting for Gibson Dunn Law; payment for a monograph published with Now Publishers; advisory committee of the Alzheimer’s Disease Data Initiative, Director of the Hariri Institute at Boston University outside the submitted work. L.A.W. reports funding from NIH and NSF for the submitted work; consultant for AbbVie, Inc. and the Gates Foundation; honoraria for presentations at selected universities (Colorado University, University of Rochester, University of Modena & Reggio Emilia) and conferences (Society for Epidemiologic Research); member of the steering committee for AbbVie on Abnormal Uterine Bleeding and Fibroids; in-kind donations from Kindara.com (fertility apps) and Swiss Precision Diagnostics (home pregnancy tests) outside the submitted work.
References: Eur J Nutr. 2022 Sep;61(6):3255-3265. (PMID: 35461408)
Am J Epidemiol. 2004 Oct 1;160(7):661-7. (PMID: 15383410)
Ultrasound Obstet Gynecol. 2003 Dec;22(6):571-7. (PMID: 14689528)
Obstet Gynecol. 1993 Jul;82(1):132-8. (PMID: 8515913)
Fertil Steril. 2003 Feb;79(2):330-9. (PMID: 12568842)
J Acad Nutr Diet. 2013 Apr;113(4):569-80. (PMID: 23415502)
Am J Clin Nutr. 2014 Oct;100(4):1166-72. (PMID: 25240079)
Epidemiol Rev. 2002;24(2):91-101. (PMID: 12762085)
Paediatr Perinat Epidemiol. 2015 Jul;29(4):360-71. (PMID: 26111445)
Public Health Nutr. 2019 Dec;22(18):3385-3394. (PMID: 31131783)
BMJ. 2020 Nov 11;371:m3966. (PMID: 33177047)
Hum Reprod. 2012 Aug;27(8):2526-31. (PMID: 22593431)
J Obstet Gynaecol Res. 2022 Jul;48(7):1632-1640. (PMID: 35577316)
BJOG. 2014 Oct;121(11):1375-84. (PMID: 24548778)
Paediatr Perinat Epidemiol. 2018 Jan;32(1):19-29. (PMID: 29053188)
Reprod Biomed Online. 2008 Jul;17(1):101-13. (PMID: 18616898)
Paediatr Perinat Epidemiol. 2008 Jul;22(4):334-40. (PMID: 18578746)
N Engl J Med. 1977 Sep 1;297(9):468-71. (PMID: 887128)
J Stat Softw. 2010;33(1):1-22. (PMID: 20808728)
Am J Epidemiol. 1988 Aug;128(2):420-30. (PMID: 3273482)
Diagn Progn Res. 2017 Nov 16;1:18. (PMID: 31093547)
Ann Epidemiol. 2015 Dec;25(12):936-41.e1. (PMID: 26452607)
Epidemiology. 2008 Jan;19(1):55-62. (PMID: 18091004)
PLoS One. 2013 Aug 28;8(8):e72095. (PMID: 24015208)
Epidemiology. 2006 Sep;17(5):500-5. (PMID: 16837826)
Semin Reprod Med. 2000;18(4):331-9. (PMID: 11355791)
Am J Obstet Gynecol. 2020 Aug;223(2):242.e1-242.e22. (PMID: 32109464)
Am J Obstet Gynecol. 2019 Jun;220(6):567.e1-567.e18. (PMID: 30742825)
Int J Epidemiol. 2012 Apr;41(2):405-13. (PMID: 22253313)
J Obstet Gynaecol. 2022 Aug;42(6):2069-2074. (PMID: 35048758)
Comput Methods Programs Biomed. 2020 Nov;196:105624. (PMID: 32623348)
Paediatr Perinat Epidemiol. 2014 Sep;28(5):412-23. (PMID: 25225009)
Acta Obstet Gynecol Scand. 2006;85(9):1057-65. (PMID: 16929410)
Obstet Gynecol. 2013 Nov;122(5):1139-1140. (PMID: 24150030)
Am J Obstet Gynecol. 2008 Mar;198(3):279.e1-8. (PMID: 18221932)
Hum Reprod. 2018 Mar 1;33(3):494-502. (PMID: 29390148)
Am J Epidemiol. 2021 Sep 1;190(9):1830-1840. (PMID: 33517416)
Epidemiology. 1994 Jul;5(4):422-8. (PMID: 7918812)
J Biomed Inform. 2020 Aug;108:103496. (PMID: 32652236)
Am J Epidemiol. 2006 Feb 1;163(3):279-88. (PMID: 16339051)
Hum Reprod. 2015 May;30(5):1246-55. (PMID: 25788567)
Fertil Steril. 2022 Jan;117(1):144-152. (PMID: 34863518)
Sao Paulo Med J. 2006 Jul 6;124(4):181-5. (PMID: 17086297)
Am J Epidemiol. 2001 Dec 15;154(12):1089-99. (PMID: 11744511)
Am J Epidemiol. 2004 May 15;159(10):993-1001. (PMID: 15128612)
Reprod Biol Endocrinol. 2016 Mar 31;14:15. (PMID: 27036944)
Pharmacoepidemiol Drug Saf. 2020 Sep;29(9):1101-1110. (PMID: 32783283)
BMC Pregnancy Childbirth. 2022 Sep 9;22(1):697. (PMID: 36085038)
PLoS One. 2015 Mar 04;10(3):e0118432. (PMID: 25738806)
Eur J Nutr. 2022 Aug;61(5):2737-2748. (PMID: 35279733)
N Engl J Med. 1988 Jul 28;319(4):189-94. (PMID: 3393170)
Grant Information: R01 GM135930 United States GM NIGMS NIH HHS; R01 HD086742 United States HD NICHD NIH HHS; R21 HD072326 United States HD NICHD NIH HHS; UL1 TR001430 United States TR NCATS NIH HHS
Contributed Indexing: Keywords: Miscarriage; machine learning; predictive modeling; pregnancy; spontaneous abortion
Entry Date(s): Date Created: 20240411 Date Completed: 20240619 Latest Revision: 20250702
Update Code: 20260130
PubMed Central ID: PMC11651128
DOI: 10.1016/j.fertnstert.2024.04.007
PMID: 38604264
Βάση Δεδομένων: MEDLINE
Περιγραφή
ISSN:1556-5653
DOI:10.1016/j.fertnstert.2024.04.007