JMIR Publications

ABSTRACT

Background:

Accurately predicting ovarian response and determining the optimal starting dose of follicular-stimulating hormone (FSH) remain critical yet challenging for effective ovarian stimulation. Currently, there is a lack of a comprehensive model capable of simultaneously forecasting the number of oocytes retrieved (NOR) and assessing the risk of early-onset moderate-to-severe ovarian hyperstimulation syndrome (OHSS).

Objective:

To establish an integrated mode capable of forecasting the NOR and assessing the risk of early-onset moderate-to-severe OHSS across varying starting doses of FSH.

Methods:

This prognostic study included patients undergoing their first ovarian stimulation cycles at two independent IVF clinics. Automated classifiers were employed for variable selection. Machine learning models (11 for NOR, 11 for OHSS) were developed and validated using internal (n = 6,401) and external (n = 3,805) datasets. Shapley Additive Explanations (SHAP) were applied for variable interpretation. The best-performing models were incorporated into a web-based prediction tool.

Results:

For NOR prediction, 17 variables were selected, with the gradient boosting regressor achieving the highest performance (R2= 0.7978 internal, 0.7924 external). For OHSS prediction, 19 variables were identified, and the LightGBM model demonstrated superior performance (AUC = 0.7588 internal, 0.7287 external). SHAP analysis highlighted the FSH starting dose relative to body mass index (BMI) and baseline antral follicle counts (AFC) as key predictors for NOR and OHSS, respectively. Dose-response curves were generated to visualize predicted outcomes varying FSH starting doses, and the models were deployed as a user-friendly online tool, InOvaSGuide.

Conclusions:

This study introduces an integrated framework for predicting NOR and early-onset moderate-to-severe OHSS risk across different FSH doses. Future prospective evaluation is needed before clinical implementation. Clinical Trial: None.