Search

Can a machine learning model better predict the cumulative live birth rate for a couple after intrauterine insemination or embryo transfer than Cox regression based on their personal characteristics?Retrospective cohort study conducted in two French infertility centres (Créteil and Tenon Hospitals) between 2012 and 2019, including 1819 and 1226 couples at Créteil and Tenon, respectively. Two models were applied: a Cox regression, which is almost exclusively used in assisted reproductive technology (ART) predictive modelling, and a tree ensemble-based model using XGBoost implementation. Internal validations were performed on each hospital dataset separately; an external validation was then carried out on the Tenon Hospital's population.The two populations were significantly different, with Tenon having more severe cases than Créteil, although internal validations show comparable results (C-index of 60% for both populations). As for the external validation, the XGBoost model stands out as being more stable than Cox regression, with the latter having a higher performance loss (C-index of 60% and 58%, respectively). The explicability method indicates that the XGBoost model relies strongly on features such as the ages of a couple, causes of infertility, and the woman's body mass index or infertility duration, which is consistent with the ART literature about risk factors.Overall performances are still relatively modest, which is coherent with all reported ART predictive models. Explicability-based methods would allow access to new knowledge, to gain a greater comprehension of which characteristics and interactions really influence a couple's journey. These models can be used by practitioners and patients to make better informed decisions about performing ART.

Results from studies reporting the optimal stimulation duration of IVF-ICSI cycles are inconsistent. The aim of this study was to determine whether, in the presence of early ovulation-triggering criteria, prolonged ovarian stimulation modified the chances of a live birth. This cross-sectional study included 312 women presenting triggering criteria beginning from D8 of ovarian stimulation. Among the 312 women included in the study, 135 were triggered for ovulation before D9 (D ≤ nine group) and 177 after D9 (D > nine group). The issues of fresh +/− frozen embryo transfers were taken into consideration. Cumulative clinical pregnancy and live-birth rates after fresh +/− frozen embryo transfers were similar in both groups (37% versus 46.9%, p = 0.10 and 19.3% versus 28.2%, p = 0.09, respectively). No patient characteristics were found to be predictive of a live birth depending on the day of ovulation trigger. Postponing of ovulation trigger did not impact pregnancy or live-birth rates in early responders. A patient’s clinical characteristics should not influence the decision process of ovulation trigger day in early responders. Further prospective studies should be conducted to support these findings.