Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{201822,
        author = {Anita and Gopal Khorwal},
        title = {Beyond the Clinic: Predicting In Vitro Fertilization Outcomes Using Ensemble Machine Learning and Deep Neural Architectures},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {4992-4997},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201822},
        abstract = {Background: In vitro fertilization (IVF) remains the most data-intensive intervention in reproductive medicine, yet live birth rates per cycle rarely exceed 35–40%. Conventional prognostic tools rely on narrow, linearly modeled variable sets, overlooking the complex non-linear interactions that govern reproductive biology.
Methods: A retrospective multi-algorithm predictive framework was applied to 11,284 IVF cycles from four fertility clinics (2018–2023). Six machine learning models—logistic regression, SVM, random forest, XGBoost, multilayer perceptron, and a stacked ensemble—were compared under a unified evaluation protocol. SHapley Additive exPlanations (SHAP) provided patient-level interpretability.
Results: The stacked ensemble achieved an AUC-ROC of 0.893 (95% CI: 0.881–0.906), sensitivity of 84.7%, and specificity of 81.3%—meaningfully surpassing all individual models. The five leading predictors were antral follicle count (AFC), female age, serum AMH, grade-A embryos transferred, and endometrial thickness.
Conclusion: This interpretable ensemble framework offers clinically actionable live-birth probability estimates suitable for integration into physician decision-support systems, outperforming existing nomogram-based approaches by a substantial margin.},
        keywords = {In vitro fertilization; IVF outcome prediction; machine learning; stacked ensemble; SHAP interpretability; reproductive medicine},
        month = {May},
        }