Prediction of implantation after blastocyst transfer in in vitro fertilization: a machine-learning perspective

Celine Blank (Corresponding author), Rogier Rudolf Wildeboer, Ilse DeCroo, Kelly Tilleman, Basiel Weyers, Petra de Sutter, Massimo Mischi, Benedictus Christiaan Schoot

Research output: Contribution to journalArticleAcademicpeer-review

3 Citations (Scopus)

Abstract

Objective: To develop a random forest model (RFM) to predict implantation potential of a transferred embryo and compare it with a multivariate logistic regression model (MvLRM), based on data from a large cohort including in vitro fertilization (IVF) patients treated with the use of single-embryo transfer (SET) of blastocyst-stage embryos. Design: Retrospective study of a 2-year single-center cohort of women undergoing IVF or intracytoplasmatic sperm injection (ICSI). Setting: Department of assisted reproductive medicine of an academic hospital. Patient(s): Data from 1,052 women who underwent fresh SET in IVF or ICSI cycles were included. Intervention(s): None. Main Outcome Measure(s): The performance of both RFM and MvLRM to predict pregnancy was quantified in terms of the area under the receiver operating characteristic (ROC) curve (AUC), classification accuracy, specificity, and sensitivity. Result(s): ROC analysis resulted in an AUC of 0.74 ± 0.03 for the proposed RFM and 0.66 ± 0.05 for the MvLRM for the prediction of ongoing pregnancies of ≥11 weeks. This RFM approach and the MvLRM yielded, respectively, sensitivities of 0.84 ± 0.07 and 0.66 ± 0.08 and specificities of 0.48 ± 0.07 and 0.58 ± 0.08. Conclusion(s): The performance to predict ongoing implantation will significantly improve with the use of an RFM approach compared with MvLRM.

LanguageEnglish
Pages318-326
JournalFertility and Sterility
Volume111
Issue number2
DOIs
StatePublished - 1 Feb 2019

Fingerprint

Embryo Transfer
Fertilization in Vitro
Logistic Models
Single Embryo Transfer
ROC Curve
Area Under Curve
Spermatozoa
Embryonic Structures
Machine Learning
Reproductive Medicine
Pregnancy
Injections
Blastocyst
Retrospective Studies
Outcome Assessment (Health Care)
Sensitivity and Specificity

Bibliographical note

doi: 10.1016/j.fertnstert.2018.10.030

Keywords

  • Blastocyst transfer
  • IVF
  • machine learning
  • prediction model
  • random forest

Cite this

@article{ca46c91b67bf4f0a9e31134a1736ca25,
title = "Prediction of implantation after blastocyst transfer in in vitro fertilization: a machine-learning perspective",
abstract = "Objective: To develop a random forest model (RFM) to predict implantation potential of a transferred embryo and compare it with a multivariate logistic regression model (MvLRM), based on data from a large cohort including in vitro fertilization (IVF) patients treated with the use of single-embryo transfer (SET) of blastocyst-stage embryos. Design: Retrospective study of a 2-year single-center cohort of women undergoing IVF or intracytoplasmatic sperm injection (ICSI). Setting: Department of assisted reproductive medicine of an academic hospital. Patient(s): Data from 1,052 women who underwent fresh SET in IVF or ICSI cycles were included. Intervention(s): None. Main Outcome Measure(s): The performance of both RFM and MvLRM to predict pregnancy was quantified in terms of the area under the receiver operating characteristic (ROC) curve (AUC), classification accuracy, specificity, and sensitivity. Result(s): ROC analysis resulted in an AUC of 0.74 ± 0.03 for the proposed RFM and 0.66 ± 0.05 for the MvLRM for the prediction of ongoing pregnancies of ≥11 weeks. This RFM approach and the MvLRM yielded, respectively, sensitivities of 0.84 ± 0.07 and 0.66 ± 0.08 and specificities of 0.48 ± 0.07 and 0.58 ± 0.08. Conclusion(s): The performance to predict ongoing implantation will significantly improve with the use of an RFM approach compared with MvLRM.",
keywords = "Blastocyst transfer, IVF, machine learning, prediction model, random forest",
author = "Celine Blank and Wildeboer, {Rogier Rudolf} and Ilse DeCroo and Kelly Tilleman and Basiel Weyers and {de Sutter}, Petra and Massimo Mischi and Schoot, {Benedictus Christiaan}",
note = "doi: 10.1016/j.fertnstert.2018.10.030",
year = "2019",
month = "2",
day = "1",
doi = "10.1016/j.fertnstert.2018.10.030",
language = "English",
volume = "111",
pages = "318--326",
journal = "Fertility and Sterility",
issn = "0015-0282",
publisher = "Agon Elsevier",
number = "2",

}

Prediction of implantation after blastocyst transfer in in vitro fertilization : a machine-learning perspective. / Blank, Celine (Corresponding author); Wildeboer, Rogier Rudolf; DeCroo, Ilse; Tilleman, Kelly; Weyers, Basiel; de Sutter, Petra; Mischi, Massimo; Schoot, Benedictus Christiaan.

In: Fertility and Sterility, Vol. 111, No. 2, 01.02.2019, p. 318-326.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Prediction of implantation after blastocyst transfer in in vitro fertilization

T2 - Fertility and Sterility

AU - Blank,Celine

AU - Wildeboer,Rogier Rudolf

AU - DeCroo,Ilse

AU - Tilleman,Kelly

AU - Weyers,Basiel

AU - de Sutter,Petra

AU - Mischi,Massimo

AU - Schoot,Benedictus Christiaan

N1 - doi: 10.1016/j.fertnstert.2018.10.030

PY - 2019/2/1

Y1 - 2019/2/1

N2 - Objective: To develop a random forest model (RFM) to predict implantation potential of a transferred embryo and compare it with a multivariate logistic regression model (MvLRM), based on data from a large cohort including in vitro fertilization (IVF) patients treated with the use of single-embryo transfer (SET) of blastocyst-stage embryos. Design: Retrospective study of a 2-year single-center cohort of women undergoing IVF or intracytoplasmatic sperm injection (ICSI). Setting: Department of assisted reproductive medicine of an academic hospital. Patient(s): Data from 1,052 women who underwent fresh SET in IVF or ICSI cycles were included. Intervention(s): None. Main Outcome Measure(s): The performance of both RFM and MvLRM to predict pregnancy was quantified in terms of the area under the receiver operating characteristic (ROC) curve (AUC), classification accuracy, specificity, and sensitivity. Result(s): ROC analysis resulted in an AUC of 0.74 ± 0.03 for the proposed RFM and 0.66 ± 0.05 for the MvLRM for the prediction of ongoing pregnancies of ≥11 weeks. This RFM approach and the MvLRM yielded, respectively, sensitivities of 0.84 ± 0.07 and 0.66 ± 0.08 and specificities of 0.48 ± 0.07 and 0.58 ± 0.08. Conclusion(s): The performance to predict ongoing implantation will significantly improve with the use of an RFM approach compared with MvLRM.

AB - Objective: To develop a random forest model (RFM) to predict implantation potential of a transferred embryo and compare it with a multivariate logistic regression model (MvLRM), based on data from a large cohort including in vitro fertilization (IVF) patients treated with the use of single-embryo transfer (SET) of blastocyst-stage embryos. Design: Retrospective study of a 2-year single-center cohort of women undergoing IVF or intracytoplasmatic sperm injection (ICSI). Setting: Department of assisted reproductive medicine of an academic hospital. Patient(s): Data from 1,052 women who underwent fresh SET in IVF or ICSI cycles were included. Intervention(s): None. Main Outcome Measure(s): The performance of both RFM and MvLRM to predict pregnancy was quantified in terms of the area under the receiver operating characteristic (ROC) curve (AUC), classification accuracy, specificity, and sensitivity. Result(s): ROC analysis resulted in an AUC of 0.74 ± 0.03 for the proposed RFM and 0.66 ± 0.05 for the MvLRM for the prediction of ongoing pregnancies of ≥11 weeks. This RFM approach and the MvLRM yielded, respectively, sensitivities of 0.84 ± 0.07 and 0.66 ± 0.08 and specificities of 0.48 ± 0.07 and 0.58 ± 0.08. Conclusion(s): The performance to predict ongoing implantation will significantly improve with the use of an RFM approach compared with MvLRM.

KW - Blastocyst transfer

KW - IVF

KW - machine learning

KW - prediction model

KW - random forest

UR - http://www.scopus.com/inward/record.url?scp=85059339391&partnerID=8YFLogxK

U2 - 10.1016/j.fertnstert.2018.10.030

DO - 10.1016/j.fertnstert.2018.10.030

M3 - Article

VL - 111

SP - 318

EP - 326

JO - Fertility and Sterility

JF - Fertility and Sterility

SN - 0015-0282

IS - 2

ER -