Machine-Learning Prediction of Pregnancy Outcomes After Assisted Reproductive Treatments

NCT07855783 | Recruiting

• 1 other identifier: PK 1.1.12.0074
• Study Type: observational
• Target: 2,200
• Locations: 1 country
• Sites: 2

Brief Summary

The goal of this observational study is to develop and validate a machine-learning model to predict pregnancy outcomes in women who have a positive pregnancy test following assisted reproductive treatment (ART), with the primary analysis focusing on in vitro fertilization (IVF) and frozen embryo transfer (FET). The study will also include an exploratory analysis of pregnancies following intrauterine insemination (IUI). The main questions it aims to answer are: Can early blood levels of beta-human chorionic gonadotropin (beta-hCG) predict the likelihood of live birth in an IVF or FET cycle? Can early beta-hCG levels help identify pregnancies at increased risk of biochemical pregnancy or early pregnancy loss? Participants will have clinical and treatment information, including beta-hCG measurements and pregnancy outcomes, collected from medical records or during prospective follow-up. No changes to participants' medical treatment will be made as part of the study.

Conditions

IVF Outcomes; Prediction Models; Infertility Assisted Reproductive Technology; Live Birth

Keywords

Prediction model; Machine learning; Biochemical pregnancy; Early pregnancy loss; Pregnancy outcome; Beta-hCG; Assisted reproductive technology

Outcome Measures

Primary Outcomes (1)

• Live birth following ART

  Delivery of a live infant at ≥24 weeks of gestation.

  From positive pregnancy test until delivery.

Secondary Outcomes (2)

• Biochemical pregnancy following ART

  From the first positive serum beta-hCG measurement until biochemical pregnancy resolution.

• Early Pregnancy Loss following ART

  From clinical pregnancy confirmation until 12 weeks of gestation.

Study Arms (1)

ART pregnancies with positive beta-hCG

Patients with a positive serum beta-hCG measurement following assisted reproductive treatment (ART), including in vitro fertilization (IVF), frozen embryo transfer (FET), and intrauterine insemination (IUI). Participants will be followed to assess pregnancy outcomes, including live birth, biochemical pregnancy, and early pregnancy loss.

Other: Machine-Learning Model for Prediction of Pregnancy Outcomes

Interventions

Machine-Learning Model for Prediction of Pregnancy Outcomes OTHER

A machine-learning prognostic model using early serum beta-hCG measurements and patient, embryo, and treatment characteristics to predict live birth and early adverse pregnancy outcomes following assisted reproductive treatment.

ART pregnancies with positive beta-hCG

Eligibility Criteria

• Age: 18 Years - 45 Years
• Sex: female
• Healthy Volunteers: No
• Age Groups: Adult (18-64)
• Sampling Method: Non-Probability Sample

Study Population

Participants will be women undergoing assisted reproductive treatment at the BetaPlus Center and, during the prospective validation phase, at the Clinical University Hospital in Rijeka, Croatia. The study population will include patients undergoing IVF/ICSI, frozen embryo transfer (FET), or intrauterine insemination (IUI).

You may qualify if:

• Women who underwent ART procedures (IUI, IVF/ICSI, or FET) using homologous oocytes.
• Availability of at least one positive early serum beta-HCG measurement after aspiration, FET, or insemination (beta-HCG \>10 mIU/mL).
• Availability of the pregnancy outcome.
• Availability of relevant patient characteristics and clinical variables required for predictive modeling.
• For embryo-transfer cycles, availability of information on embryo developmental stage and number of embryos transferred where applicable.
• For the prospective validation cohort, written informed consent.

You may not qualify if:

• Missing beta-HCG measurements critical for model input.
• Missing key demographic or clinical variables required for predictive modeling.
• Missing ART treatment protocol where required for the model.
• Missing pregnancy outcomes.
• Multiple pregnancy, hydatidiform mole, heterotopic pregnancy, and ectopic pregnancy will be excluded from the primary live-birth analysis but will be described separately and, where sample size permits, evaluated as secondary adverse pregnancy outcomes.
• Non-consent for prospective participation in validation.

Sponsors & Collaborators

• BetaPlus Center for Reproductive Medicine: lead
• Clinical Hospital Center Rijeka: collaborator

Study Sites (2)

Clinical Hospital Center

Rijeka, Croatia

RECRUITING

BetaPlus Center for Reproductive Medicine

Zagreb, 10000, Croatia

RECRUITING

Related Publications (15)

• Clarke EA, Jones C, Reckhow J, Flannagan K, Shaari D, Baird M, Lee JA, Sekhon L, Copperman AB, Romanski PA. Prognostic utility of serum beta human chorionic gonadotropin level following single euploid embryo transfer for live birth. Fertil Steril. 2026 Aug;126(2):371-378. doi: 10.1016/j.fertnstert.2026.04.025. Epub 2026 May 4.

  PMID: 42092529 BACKGROUND

• Papageorgiou TC, Leondires MP, Miller BT, Chang AS, Armstrong AB, Scott LA, Segars JH. Human chorionic gonadotropin levels after blastocyst transfer are highly predictive of pregnancy outcome. Fertil Steril. 2001 Nov;76(5):981-7. doi: 10.1016/s0015-0282(01)02840-0.

  PMID: 11704121 BACKGROUND

• Mourad A, Antaki R, Rowen M, Levesque E, Lapensee L. The POPI-Plus tool: prediction model of outcome of pregnancy in in vitro fertilization from a large retrospective cohort. Fertil Steril. 2024 Mar;121(3):489-496. doi: 10.1016/j.fertnstert.2023.11.035. Epub 2023 Dec 1.

  PMID: 38043845 BACKGROUND

• Kidera N, Ishikawa T, Kawamura T, Miyasaka N. Serum human chorionic gonadotropin can predict live birth 7 days after frozen-thawed blastocyst transfer. F S Rep. 2025 Oct 23;6(4):455-461. doi: 10.1016/j.xfre.2025.10.002. eCollection 2025 Dec.

  PMID: 41473560 BACKGROUND

• Kalafat E, Ata B, Del Gallego R, Freedman A, Hoyos LR, Elkhatib I, Miller KA, Fatemi H, Lawrenz B. Predicting live birth following single euploid frozen-embryo transfer via beta-hCG dynamics: iHOPE prognostic model with external validation. Ultrasound Obstet Gynecol. 2026 Jun;67(6):824-835. doi: 10.1002/uog.70238. Epub 2026 May 24.

  PMID: 42177810 BACKGROUND

• Schmidt LL, Asch RH, Frederick JL, Rojas FJ, Stone SC, Balmaceda JP. The predictive value of a single beta human chorionic gonadotropin in pregnancies achieved by assisted reproductive technology. Fertil Steril. 1994 Aug;62(2):333-8. doi: 10.1016/s0015-0282(16)56887-3.

  PMID: 8034081 BACKGROUND

• Hughes LM, Schuler A, Sharmuk M, Schauer JM, Pavone ME, Bernardi LA. Early beta-hCG levels predict live birth after single embryo transfer. J Assist Reprod Genet. 2022 Oct;39(10):2355-2364. doi: 10.1007/s10815-022-02606-w. Epub 2022 Sep 8.

  PMID: 36074224 BACKGROUND

• Trautner PS, Oppelt P, Resch S, Enzelsberger SH, Ebner T, Shebl OJ. Single day 14 serum hCG values allow prediction of viable pregnancy and are significantly higher in frozen as compared to fresh single blastocyst transfer. J Assist Reprod Genet. 2024 Aug;41(8):2193-2200. doi: 10.1007/s10815-024-03164-z. Epub 2024 Jun 13.

  PMID: 38867095 BACKGROUND

• Al Mamari N, Al Zawawi N, Khayat S, Badeghiesh A, Son WY, Dahan MH. Revisiting serum beta-hCG cut-off levels and pregnancy outcomes using single embryo transfer. J Assist Reprod Genet. 2019 Nov;36(11):2307-2313. doi: 10.1007/s10815-019-01583-x. Epub 2019 Oct 12.

  PMID: 31605261 BACKGROUND

• Sarret Y, Reano A, Nicolas JF, Su H, Thivolet J. Bullous pemphigoid and cicatricial pemphigoid: immunoblotting detection of involved autoantigens. Autoimmunity. 1989;2(2):145-53. doi: 10.3109/08916938909019951.

  PMID: 2491598 BACKGROUND

• Hobeika E, Singh S, Malik S, Knochenhauer ES, Traub ML. Initial maternal serum human chorionic gonadotropin levels in pregnancies achieved after assisted reproductive technology are higher after preimplantation genetic screening and after frozen embryo transfer: a retrospective cohort. J Assist Reprod Genet. 2017 Oct;34(10):1333-1340. doi: 10.1007/s10815-017-0987-2. Epub 2017 Jun 21.

  PMID: 28639180 BACKGROUND

• Kathiresan AS, Cruz-Almeida Y, Barrionuevo MJ, Maxson WS, Hoffman DI, Weitzman VN, Christie DR, Manko GF, Ory SJ. Prognostic value of beta-human chorionic gonadotropin is dependent on day of embryo transfer during in vitro fertilization. Fertil Steril. 2011 Dec;96(6):1362-6. doi: 10.1016/j.fertnstert.2011.09.042. Epub 2011 Nov 1.

  PMID: 22047663 BACKGROUND

• Oron G, Shavit T, Esh-Broder E, Weon-Young S, Tulandi T, Holzer H. Predictive value of serum HCG concentrations in pregnancies achieved after single fresh or vitrified-warmed blastocyst transfer. Reprod Biomed Online. 2017 Sep;35(3):272-278. doi: 10.1016/j.rbmo.2017.05.011. Epub 2017 May 30.

  PMID: 28625759 BACKGROUND

• Oron G, Esh-Broder E, Son WY, Holzer H, Tulandi T. Predictive value of maternal serum human chorionic gonadotropin levels in pregnancies achieved by in vitro fertilization with single cleavage and single blastocyst embryo transfers. Fertil Steril. 2015 Jun;103(6):1526-31.e1-2. doi: 10.1016/j.fertnstert.2015.02.028. Epub 2015 Apr 22.

  PMID: 25910571 BACKGROUND

• Ozer G. Initial beta-hCG levels and 2-day-later increase rates effectively predict pregnancy outcomes in single blastocyst transfer in frozen-thawed or fresh cycles: A retrospective cohort study. Medicine (Baltimore). 2023 Oct 20;102(42):e35605. doi: 10.1097/MD.0000000000035605.

  PMID: 37861533 BACKGROUND

MeSH Terms

Conditions

Abortion, Spontaneous

Condition Hierarchy (Ancestors)

Pregnancy Complications; Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases

Study Officials

• Romana Dmitrovic

  BetaPlus Center for Reproductive Medicine

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Romana Dmitrovic

CONTACT

+385981983563; romana@betaplus.hr

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: OTHER
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: September 28, 2026
• First Posted: October 2, 2026
• Study Start: January 1, 2026
• Primary Completion (Estimated): December 31, 2026
• Study Completion (Estimated): September 30, 2027
• Last Updated: October 2, 2026

Record last verified: 2026-09

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP
• Time Frame: After publication and for 5 years thereafter
• Access Criteria: Data will be available to qualified researchers, subject to applicable ethical, legal, and institutional requirements

Locations

CR (2)