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 .

Fig. 1. Patient flow diagram.

The number of patients randomized in the electronic case report form (eCRF) to the study group and the control group then, following exclusions for discontinued intervention, the number analyzed per protocol.

Fig. 2. Non-inferiority analysis and risk ratio per center.

a, Crude and adjusted risk difference (red circle represents mean risk difference and blue error bars represent 95% CI of the risk difference) in clinical pregnancy rates between the iDAScore and the control groups (a negative risk difference indicates lower clinical pregnancy rate in the iDAScore group) per intention-to-treat (ITT) analysis (n = 1,066) and PP analysis (n = 1,002). b, Risk ratio (red circle represents mean risk ratio and blue error bars represent 95% CI of the risk ratio) of clinical pregnancy rate for each participating center (a ratio >1 indicates better results in the iDAScore group).

Fig. 3. Time use for day 5 evaluation in the iDAScore group and control group.

Mean and standard deviation for all patients (n = 38) and for embryo cohort sizes from 2–5 (n = 9), 6–9 (n = 16) or 10 or more (n = 13) in the treatment.