P-236 Simulated cohort ranking analysis estimates the number of IVF cycles needed to reach fetal heartbeat with and without artificial intelligence (AI) embryo triage

Abstract

Abstract Study question What is the impact of AI-based embryo triage on the number of IVF cycles needed to reach fetal heartbeat (FH)? Summary answer Simulated cohort ranking via the AIVF Day-5 AI model demonstrates a 27.5% reduction in the number of IVF cycles needed to achieve FH. What is known already Published reports show FH rates per first-time IVF/single euploid embryo transfer ranging from 26-43% (age <38 yrs). Likewise, the average number of autologous retrieval cycles required for FH is 2.25±0.8, depending on oocyte age and demographic. While conventional embryo morphology ranking is used as a proxy indicator for IVF success, its use is associated with observer variability and manual workflow. This leads to a non-efficient cycle number-per-FH ratio, preventing the clinic’s ability to service more patients. Study design, size, duration A single center database (N = 10,000 embryos) was used to generate 1,288 simulated cohorts reflecting known maternal age/cohort size distributions. Only cohorts containing ≥1 FH+ embryo(s) were included. The model ranked embryos within each cohort by scalar output (1-9.9). The position of the first FH+ embryo within each AI-ranked cohort was calculated and averaged across cohorts to compute number of cycles required to reach FH. Participants/materials, setting, methods Data was stratified into 5 age categories; the prevalence of top/good/fair graded embryos per cohort were included according to their known (%) prevalences per stratified age group. Data was randomized into 1,288 cohorts; positions of the first FH+ embryo in each cohort was calculated (for example, if the 2nd AI-ranked embryo was FH+, a value of 2 was assigned, respectively). Values were averaged and compared to conventional IVF. Main results and the role of chance A mean ± SD of 1.63 ±1.06 cycles was needed to reach the first FH+ embryo with AI cohort ranking (pooled mean across all age groups <38 years) with a mean cohort size N = 7.8 embryos. The relative percent reduction in cycles needed to reach FH when compared to conventional IVF without AI ranking (2.25±0.8; age <38 yrs) was 27.5%. Ranking and electronic recording time for ranking per embryo with/without AI implementation was 186.0 versus 30.9 seconds per embryo, respectively. Relative ranking time reduction was 83%. Limitations, reasons for caution Results were pooled across age groups and not stratified per age. Prospective validation is ongoing to show the influence of demographics/clinical characteristics on AI utility. Wider implications of the findings This study demonstrates the potential of shortening the time to pregnancy by using AI-based quantitative embryo assessment for cohort ranking. Trial registration number Not applicable

Ähnliche Arbeiten