Improved clinical pregnancy rates in natural frozen-thawed embryo transfer cycles with machine learning ovulation prediction: insights from a retrospective cohort study

This study aims to develop physician support software for determining ovulation time and assess its impact on pregnancy outcomes in natural cycle frozen embryo transfers (NC-FET). To develop, assess, and validate an ovulation prediction model, three datasets were used: REI Ovulation Determination dataset (500 cycles) split into training (309), validation (90), and test (101) sets; the Documented Ovulation dataset (101 cycles) with confirmed ovulation (documented follicular rupture and LH surge); and the Clinical Pregnancy Rates dataset (515 NC-FET cycles), categorized into "Matched" and "Mismatched" based on alignment with the model's ovulation determination. Pregnancy outcomes were compared between the groups. The ovulation prediction model exhibited 93.85% and 92.89% matching rates with the REI Ovulation Determination and Documented Ovulation datasets, respectively. In the Clinical Pregnancy Rates dataset, the Matched group (282 cycles) showed significantly higher clinical pregnancy rates than the Mismatched group (34.6% vs. 25.9%, p = 0.04) and similar results for patients under 37 (41.1% vs. 30.7%, p = 0.04). Logistic regression indicated lower pregnancy rates in Mismatched cases (odds ratio 0.67 for the general population, 0.63 for patients under 37). In conclusion, we introduce a highly accurate AI ovulation prediction model. Treatment cycles aligning with the model's recommendations had significantly increased clinical pregnancy rates. This study introduces the first AI model designed for predicting ovulation, proving its high accuracy. Treatment cycles aligning with the model's recommendations had significant 8.7% increase in clinical pregnancy rates, emphasizing the potential of AI in optimizing NC-FET outcomes.