Improving Intelligence of Machine Learning models for achieving higher success rate in In vitro fertilization (IVF)

In vitro fertilization (IVF) success prediction remains a challenging task due to the complexity of factors influencing outcomes, such as patient demographics, clinical parameters, and embryological data. Existing machine learning models, including Artificial Neural Networks (ANN) and traditional feature selection techniques, have shown promise but often face limitations in feature optimization and model generalization. To address these challenges, this study proposes a hybrid machine learning model combining Genetic Algorithms (GA) for feature selection with ANN for prediction. The GA efficiently identifies relevant features, while the ANN captures non-linear relationships among them, resulting in improved prediction accuracy. Experimental evaluations on IVF datasets demonstrate that the hybrid ANN-GA model outperforms traditional methods in terms of accuracy, precision, recall, and F1-score. This model has the potential to support clinicians in making data-driven decisions, thereby enhancing the personalization and success rates of IVF treatments.