Advertisement

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

      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

      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.
      Predicción de implantación después de transferencia de blastocitos en fecundación in vitro: una perspectiva desde el aprendizaje automatizado

      Objetivo

      Desarrollar un modelo de bosque aleatorio (RFM) para predecir el potencial de implantación de un embrión transferido y compararlo con un modelo de regresión logística multivariante (MvLRM), basado en datos de una gran cohorte que incluye pacientes de fecundación in vitro (IVF) sometidas a transferencia de un solo blastocisto (SET).

      Diseño

      Estudio retrospectivo de cohortes unicéntrico de 2 años de mujeres sometidas a IVF o inyección intracitoplasmática de espermatozoides (ICSI).

      Entorno

      Departamento de medicina reproductiva asistida de un hospital académico.

      Paciente(s)

      Se incluyeron datos de 1052 mujeres que se sometieron a SET en fresco en FIV o ciclos ICSI.

      Intervención(es)

      Ninguna

      Principales medidas de resultado

      El rendimiento de RFM y MvLRM para predecir el embarazo se cuantificó en términos del área bajo la curva (AUC) de la característica operativa del receptor (ROC), la precisión de clasificación, la especificidad y la sensibilidad.

      Resultados

      El análisis de ROC resultó en un AUC de 0.74 ± 0.03 para el RFM propuesto y 0.66± 0.05 para el MvLRM para la predicción de embarazos evolutivos de ≥11 semanas. Este enfoque RFM y el MvLRM produjeron, respectivamente, sensibilidades de 0.84 ± 0.07 y 0.66 ± 0.08 y especificidades de 0.48 ± 0.07 y 0.58 ± 0.08.

      Conclusión

      El rendimiento para predecir la implantación evolutiva mejorará significativamente con el uso de un enfoque RFM en comparación con MvLRM.

      Key Words

      To read this article in full you will need to make a payment

      Subscribe:

      Subscribe to Fertility and Sterility
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • European Society for Human Reproduction and Embryology
        ART fact sheet. 2017.
        (Available at:)
        • European Society for Human Reproduction and Embryology
        ART fact sheet. 2016.
        (Available at:)
        • Luke B.
        • Brown M.B.
        • Wantman E.
        • Stern J.E.
        • Baker V.L.
        • Widra E.
        • et al.
        A prediction model for live birth and multiple births within the first three cycles of assisted reproductive technology.
        Fertil Steril. 2014; 102: 744-752
        • Choi B.
        • Bosch E.
        • Lannon B.M.
        • Leveille M.C.
        • Wong W.H.
        • Leader A.
        • et al.
        Personalized prediction of first-cycle in vitro fertilization success.
        Fertil Steril. 2013; 99: 1905-1911
        • Vaegter K.K.
        • Lakic T.G.
        • Olovsson M.
        • Berglund L.
        • Brodin T.
        • Holte J.
        Which factors are most predictive for live birth after in vitro fertilization and intracytoplasmic sperm injection (IVF/ICSI) treatments? Analysis of 100 prospectively recorded variables in 8,400 IVF/ICSI single-embryo transfers.
        Fertil Steril. 2017; 107: 641-648.e2
        • van Loendersloot L.L.
        • van Wely M.
        • Repping S.
        • Bossuyt P.M.M.
        • van der Veen F.
        Individualized decision-making in IVF: calculating the chances of pregnancy.
        Hum Reprod. 2013; 28: 2972-2980
        • Lintsen A.M.E.
        • Braat D.D.M.
        • Habbema J.D.F.
        • Kremer J.A.M.
        • Eijkemans M.J.C.
        Can differences in IVF success rates between centres be explained by patient characteristics and sample size?.
        Hum Reprod. 2010; 25: 110-117
        • Verberg M.F.G.
        • Eijkemans M.J.C.
        • Macklon N.S.
        • Heijnen E.M.E.W.
        • Fauser B.C.J.M.
        • Broekmans F.J.
        Predictors of ongoing pregnancy after single-embryo transfer following mild ovarian stimulation for IVF.
        Fertil Steril. 2008; 89: 1159-1165
        • Ottosen L.D.M.
        • Kesmodel U.
        • Hindkjær J.
        • Ingerslev H.J.
        Pregnancy prediction models and eSET criteria for IVF patients—do we need more information?.
        J Assist Reprod Genet. 2007; 24: 29-36
        • Hunault C.C.
        • Eijkemans M.J.C.
        • Pieters M.H.E.C.
        • te Velde E.R.
        • Habbema J.D.
        • Fauser B.C.J.M.
        • et al.
        A prediction model for selecting patients undergoing in vitro fertilization for elective single embryo transfer.
        Fertil Steril. 2002; 77: 725-732
        • Stolwijk A.M.
        • Zielhuis G.A.
        • Hamilton C.J.C.M.
        • Straatman H.
        • Hollanders J.M.G.
        • Goverde H.J.M.
        • et al.
        Prognostic models for the probability of achieving an ongoing pregnancy after in-vitro fertilization and the importance of testing their predictive value.
        Hum Reprod. 1996; 11: 2298-2303
        • Minaretzis D.
        • Harris D.
        • Alper M.M.
        • Mortola J.F.
        • Berger M.J.
        • Power D.
        Multivariate analysis of factors predictive of successful live births in in vitro fertilization (IVF) suggests strategies to improve IVF outcome.
        J Assist Reprod Genet. 1998; 15: 365-371
        • Commenges-Ducos M.
        • Tricaud S.
        • Papaxanthos-Roche A.
        • Dallay D.
        • Horovitz J.
        • Commenges D.
        Modelling of the probability of success of the stages of in-vitro fertilization and embryo transfer: stimulation, fertilization and implantation.
        Hum Reprod. 1998; 13: 78-83
        • Templeton A.
        • Morris J.K.
        • Parslow W.
        Factors that affect outcome of in-vitro fertilisation treatment.
        Lancet. 1996; 348: 1402-1406
        • McLernon D.J.
        • Steyerberg E.W.
        • te Velde E.R.
        • Lee A.J.
        • Bhattacharya S.
        Predicting the chances of a live birth after one or more complete cycles of in vitro fertilisation: population based study of linked cycle data from 113 873 women.
        BMJ. 2016; 355: i5735
        • Dhillon R.K.
        • McLernon D.J.
        • Smith P.P.
        • Fishel S.
        • Dowell K.
        • Deeks J.J.
        • et al.
        Predicting the chance of live birth for women undergoing IVF: a novel pretreatment counselling tool.
        Hum Reprod. 2016; 31: 84-92
        • Nelson S.M.
        • Lawlor D.A.
        Predicting live birth, preterm delivery, and low birth weight in infants born from in vitro fertilisation: a prospective study of 144,018 treatment cycles.
        PLoS Med. 2011; 8: e1000386
        • Chen F.
        • De Neubourg D.
        • Debrock S.
        • Peeraer K.
        • d’Hooghe T.
        • Spiessens C.
        Selecting the embryo with the highest implantation potential using a data mining based prediction model.
        Reprod Biol Endocrinol. 2016; 14: 10
        • Hafiz P.
        • Nematollahi M.
        • Boostani R.
        • Jahromi B.N.
        Predicting implantation outcome of in vitro fertilization and intracytoplasmic sperm injection using data mining techniques.
        Int J Fertil Steril. 2017; 11: 184-190
        • Sarais V.
        • Reschini M.
        • Busnelli A.
        • Biancardi R.
        • Paffoni A.
        • Somigliana E.
        Predicting the success of IVF: external validation of the van Loendersloot model.
        Hum Reprod. 2016; 31: 1245-1252
        • de Sutter P.
        • Delbaere I.
        • Gerris J.
        • Verstraelen H.
        • Goetgeluk S.
        • van der Elst J.
        • et al.
        Birthweight of singletons after assisted reproduction is higher after single- than after double-embryo transfer.
        Hum Reprod. 2006; 21: 2633-2637
        • Delbaere I.
        • Vansteelandt S.
        • Gerris J.
        • de Sutter P.
        • de Bacquer D.
        • Temmerman M.
        Human chorionic gonadotropin levels in early IVF/ICSI pregnancies are higher in singletons after single embryo transfer compared with singletons after double embryo transfer.
        Hum Reprod. 2008; 23: 2421-2426
        • Tummers P.
        • de Sutter P.
        • Dhont M.
        Risk of spontaneous abortion in singleton and twin pregnancies after IVF/ICSI.
        Hum Reprod. 2003; 18: 1720-1723
        • Deo R.C.
        Machine learning in medicine.
        Circulation. 2015; 132: 1920-1930
        • Kohavi R.
        • Provost F.
        Glossary of terms.
        Mach Learn. 1998; 30: 271-274
        • Wernick M.N.
        • Yang Y.
        • Brankov J.G.
        • Yourganov G.
        • Strother S.C.
        Machine learning in medical imaging.
        IEEE Signal Process Mag. 2010; 27: 25-38
        • Güvenir H.A.
        • Misirli G.
        • Dilbaz S.
        • Ozdegirmenci O.
        • Demir B.
        • Dilbaz B.
        Estimating the chance of success in IVF treatment using a ranking algorithm.
        Med Biol Eng Comput. 2015; 53: 911-920
        • Uyar A.
        • Bener A.
        • Ciray N.
        Predictive modeling of implantation outcome in an in vitro fertilitzation setting: an application of machine learning methods.
        Med Decis Making. 2015; 35: 714-725
        • Geurts P.
        • Irrthum A.
        • Wehenkel L.
        Supervised learning with decision tree–based methods in computational and systems biology.
        Mol Biosyst. 2009; 5: 1593-1605
        • la Marca A.
        • Sunkara S.K.
        Individualization of controlled ovarian stimulation in IVF using ovarian reserve markers: from theory to practice.
        Hum Reprod Update. 2014; 20: 124-140
        • World Health Organization
        Examination and processing of human semen.
        5th ed. 2010 (Available at:)
        • Alpha Scientists in Reproductive Medicine; European Society for Human Reproduction and Embryology Special Interest Group of Embryology
        The Istanbul consensus workshop on embryo assessment: proceedings of an expert meeting.
        Hum Reprod. 2011; 26: 1270-1283
        • van den Abbeel E.
        • Balaban B.
        • Ziebe S.
        • Lundin K.
        • Cuesta M.J.G.
        • Klein B.M.
        • et al.
        Association between blastocyst morphology and outcome of single-blastocyst transfer.
        Reprod Biomed Online. 2013; 27: 353-361
        • Gardner D.K.
        • Schoolcraft W.B.
        In-vitro culture of human blastocysts.
        in: Jansen R. Mortimer D. Towards reproductive certainty: fertility and genetics beyond 1999: the plenary proceedings of the 11th World Congress. Parthenon Publishing, Carnforth1999: 378-388
        • Kotsiantis S.B.
        • Zaharakis I.D.
        • Pintelas P.E.
        Machine learning: a review of classification and combining techniques.
        Artif Intell Rev. 2006; 26: 159-190
        • Fawcett T.
        An introduction to ROC analysis.
        Pattern Recognit Lett. 2006; 27: 861-874
        • Racowsky C.
        • Kovacs P.
        • Martins W.P.
        A critical appraisal of time-lapse imaging for embryo selection: where are we and where do we need to go?.
        J Assist Reprod Genet. 2015; 32: 1025-1030
        • Reichman D.E.
        • Goldschlag D.
        • Rosenwaks Z.
        Value of antimüllerian hormone as a prognostic indicator of in vitro fertilization outcome.
        Fertil Steril. 2014; 101: 1012-1018
        • Bhattacharya S.
        • Maheshwari A.
        • Mollison J.
        Factors associated with failed treatment: an analysis of 121,744 women embarking on their first IVF cycles.
        PLoS One. 2013; 8: 1-13