TY - JOUR
T1 - Deep learning versus manual morphology-based embryo selection in IVF: 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
N1 - © 2024. The Author(s).
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
SN - 1078-8956
VL - 30
SP - 3114
EP - 3120
JO - Nature Medicine
JF - Nature Medicine
IS - 11
ER -