Deep learning versus manual morphology-based embryo selection in IVF: a randomized, double-blind noninferiority trial

Peter J. Illingworth; Christos Venetis; David K. Gardner; Scott M. Nelson; Jørgen Berntsen; Mark G. Larman; Franca Agresta; Saran Ahitan; Aisling Ahlström; Fleur Cattrall; Simon Cooke; Kristy Demmers; Anette Gabrielsen; Johnny Hindkjær; Rebecca L. Kelley; Charlotte Knight; Lisa Lee; Robert Lahoud; Manveen Mangat; Hannah Park; Anthony Price; Geoffrey Trew; Bettina Troest; Anna Vincent; Susanne Wennerström; Lyndsey Zujovic; Thorir Hardarson

doi:10.1038/s41591-024-03166-5

Deep learning versus manual morphology-based embryo selection in IVF: a randomized, double-blind noninferiority trial

Peter J. Illingworth^*, Christos Venetis, David K. Gardner, Scott M. Nelson, Jørgen Berntsen, Mark G. Larman, Franca Agresta, Saran Ahitan, Aisling Ahlström, Fleur Cattrall, Simon Cooke, Kristy Demmers, Anette Gabrielsen, Johnny Hindkjær, Rebecca L. Kelley, Charlotte Knight, Lisa Lee, Robert Lahoud, Manveen Mangat, Hannah ParkAnthony Price, Geoffrey Trew, Bettina Troest, Anna Vincent, Susanne Wennerström, Lyndsey Zujovic, Thorir Hardarson

^*Corresponding author af dette arbejde

Institut for Klinisk Medicin - Fertilitetsklinikken, Horsens

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Tidsskriftartikel › Forskning › peer review

15 Citationer (Scopus)

Abstract

To assess the value of deep learning in selecting the optimal embryo for in vitro fertilization, a multicenter, randomized, double-blind, noninferiority parallel-group trial was conducted across 14 in vitro fertilization clinics in Australia and Europe. Women under 42 years of age with at least two early-stage blastocysts on day 5 were randomized to either the control arm, using standard morphological assessment, or the study arm, employing a deep learning algorithm, intelligent Data Analysis Score (iDAScore), for embryo selection. The primary endpoint was a clinical pregnancy rate with a noninferiority margin of 5%. The trial included 1,066 patients (533 in the iDAScore group and 533 in the morphology group). The iDAScore group exhibited a clinical pregnancy rate of 46.5% (248 of 533 patients), compared to 48.2% (257 of 533 patients) in the morphology arm (risk difference −1.7%; 95% confidence interval −7.7, 4.3; P = 0.62). This study was not able to demonstrate noninferiority of deep learning for clinical pregnancy rate when compared to standard morphology and a predefined prioritization scheme. Australian New Zealand Clinical Trials Registry (ANZCTR) registration: 379161.

Originalsprog	Engelsk
Tidsskrift	Nature Medicine
Vol/bind	30
Nummer	11
Sider (fra-til)	3114-3120
Antal sider	7
ISSN	1078-8956
DOI	https://doi.org/10.1038/s41591-024-03166-5
Status	Udgivet - nov. 2024

Adgang til dokumentet

10.1038/s41591-024-03166-5Licens: CC BY

Andre filer og links

Link to publication in Scopus

Citationsformater

Illingworth, P. J., Venetis, C., Gardner, D. K., Nelson, S. M., Berntsen, J., Larman, M. G., Agresta, F., Ahitan, S., Ahlström, A., Cattrall, F., Cooke, S., Demmers, K., Gabrielsen, A., Hindkjær, J., Kelley, R. L., Knight, C., Lee, L., Lahoud, R., Mangat, M., ... Hardarson, T. (2024). Deep learning versus manual morphology-based embryo selection in IVF: a randomized, double-blind noninferiority trial. Nature Medicine, 30(11), 3114-3120. https://doi.org/10.1038/s41591-024-03166-5

@article{08d394695c024589927feee094a09385,

title = "Deep learning versus manual morphology-based embryo selection in IVF: a randomized, double-blind noninferiority trial",

abstract = "To assess the value of deep learning in selecting the optimal embryo for in vitro fertilization, a multicenter, randomized, double-blind, noninferiority parallel-group trial was conducted across 14 in vitro fertilization clinics in Australia and Europe. Women under 42 years of age with at least two early-stage blastocysts on day 5 were randomized to either the control arm, using standard morphological assessment, or the study arm, employing a deep learning algorithm, intelligent Data Analysis Score (iDAScore), for embryo selection. The primary endpoint was a clinical pregnancy rate with a noninferiority margin of 5%. The trial included 1,066 patients (533 in the iDAScore group and 533 in the morphology group). The iDAScore group exhibited a clinical pregnancy rate of 46.5% (248 of 533 patients), compared to 48.2% (257 of 533 patients) in the morphology arm (risk difference −1.7%; 95% confidence interval −7.7, 4.3; P = 0.62). This study was not able to demonstrate noninferiority of deep learning for clinical pregnancy rate when compared to standard morphology and a predefined prioritization scheme. Australian New Zealand Clinical Trials Registry (ANZCTR) registration: 379161.",

author = "Illingworth, {Peter J.} and Christos Venetis and Gardner, {David K.} and Nelson, {Scott M.} and J{\o}rgen Berntsen and Larman, {Mark G.} and Franca Agresta and Saran Ahitan and Aisling Ahlstr{\"o}m and Fleur Cattrall and Simon Cooke and Kristy Demmers and Anette Gabrielsen and Johnny Hindkj{\ae}r and Kelley, {Rebecca L.} and Charlotte Knight and Lisa Lee and Robert Lahoud and Manveen Mangat and Hannah Park and Anthony Price and Geoffrey Trew and Bettina Troest and Anna Vincent and Susanne Wennerstr{\"o}m and Lyndsey Zujovic and Thorir Hardarson",

year = "2024",

month = nov,

doi = "10.1038/s41591-024-03166-5",

language = "English",

volume = "30",

pages = "3114--3120",

journal = "Nature Medicine",

issn = "1078-8956",

publisher = "Nature Research",

number = "11",

}

Illingworth, PJ, Venetis, C, Gardner, DK, Nelson, SM, Berntsen, J, Larman, MG, Agresta, F, Ahitan, S, Ahlström, A, Cattrall, F, Cooke, S, Demmers, K, Gabrielsen, A, Hindkjær, J, Kelley, RL, Knight, C, Lee, L, Lahoud, R, Mangat, M, Park, H, Price, A, Trew, G, Troest, B, Vincent, A, Wennerström, S, Zujovic, L & Hardarson, T 2024, 'Deep learning versus manual morphology-based embryo selection in IVF: a randomized, double-blind noninferiority trial', Nature Medicine, bind 30, nr. 11, s. 3114-3120. https://doi.org/10.1038/s41591-024-03166-5

Deep learning versus manual morphology-based embryo selection in IVF: a randomized, double-blind noninferiority trial. / Illingworth, Peter J.; Venetis, Christos; Gardner, David K. et al.
I: Nature Medicine, Bind 30, Nr. 11, 11.2024, s. 3114-3120.

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Tidsskriftartikel › Forskning › peer review

TY - JOUR

T1 - Deep learning versus manual morphology-based embryo selection in IVF

T2 - a randomized, double-blind noninferiority trial

AU - Illingworth, Peter J.

AU - Venetis, Christos

AU - Gardner, David K.

AU - Nelson, Scott M.

AU - Berntsen, Jørgen

AU - Larman, Mark G.

AU - Agresta, Franca

AU - Ahitan, Saran

AU - Ahlström, Aisling

AU - Cattrall, Fleur

AU - Cooke, Simon

AU - Demmers, Kristy

AU - Gabrielsen, Anette

AU - Hindkjær, Johnny

AU - Kelley, Rebecca L.

AU - Knight, Charlotte

AU - Lee, Lisa

AU - Lahoud, Robert

AU - Mangat, Manveen

AU - Park, Hannah

AU - Price, Anthony

AU - Trew, Geoffrey

AU - Troest, Bettina

AU - Vincent, Anna

AU - Wennerström, Susanne

AU - Zujovic, Lyndsey

AU - Hardarson, Thorir

PY - 2024/11

Y1 - 2024/11

N2 - To assess the value of deep learning in selecting the optimal embryo for in vitro fertilization, a multicenter, randomized, double-blind, noninferiority parallel-group trial was conducted across 14 in vitro fertilization clinics in Australia and Europe. Women under 42 years of age with at least two early-stage blastocysts on day 5 were randomized to either the control arm, using standard morphological assessment, or the study arm, employing a deep learning algorithm, intelligent Data Analysis Score (iDAScore), for embryo selection. The primary endpoint was a clinical pregnancy rate with a noninferiority margin of 5%. The trial included 1,066 patients (533 in the iDAScore group and 533 in the morphology group). The iDAScore group exhibited a clinical pregnancy rate of 46.5% (248 of 533 patients), compared to 48.2% (257 of 533 patients) in the morphology arm (risk difference −1.7%; 95% confidence interval −7.7, 4.3; P = 0.62). This study was not able to demonstrate noninferiority of deep learning for clinical pregnancy rate when compared to standard morphology and a predefined prioritization scheme. Australian New Zealand Clinical Trials Registry (ANZCTR) registration: 379161.

AB - To assess the value of deep learning in selecting the optimal embryo for in vitro fertilization, a multicenter, randomized, double-blind, noninferiority parallel-group trial was conducted across 14 in vitro fertilization clinics in Australia and Europe. Women under 42 years of age with at least two early-stage blastocysts on day 5 were randomized to either the control arm, using standard morphological assessment, or the study arm, employing a deep learning algorithm, intelligent Data Analysis Score (iDAScore), for embryo selection. The primary endpoint was a clinical pregnancy rate with a noninferiority margin of 5%. The trial included 1,066 patients (533 in the iDAScore group and 533 in the morphology group). The iDAScore group exhibited a clinical pregnancy rate of 46.5% (248 of 533 patients), compared to 48.2% (257 of 533 patients) in the morphology arm (risk difference −1.7%; 95% confidence interval −7.7, 4.3; P = 0.62). This study was not able to demonstrate noninferiority of deep learning for clinical pregnancy rate when compared to standard morphology and a predefined prioritization scheme. Australian New Zealand Clinical Trials Registry (ANZCTR) registration: 379161.

UR - http://www.scopus.com/inward/record.url?scp=85200984745&partnerID=8YFLogxK

U2 - 10.1038/s41591-024-03166-5

DO - 10.1038/s41591-024-03166-5

M3 - Journal article

C2 - 39122964

AN - SCOPUS:85200984745

SN - 1078-8956

VL - 30

SP - 3114

EP - 3120

JO - Nature Medicine

JF - Nature Medicine

IS - 11

ER -

Deep learning versus manual morphology-based embryo selection in IVF: a randomized, double-blind noninferiority trial

Abstract

Adgang til dokumentet

Andre filer og links

Fingeraftryk

Citationsformater