A novel self-attentive deep learning for predicting pregnancy outcome after hysteroscopic adhesiolysis in patients with intrauterine adhesions

This study presents SDL-IUAs, a novel deep learning framework that employs a self-attention mechanism to predict pregnancy outcomes in patients with intrauterine adhesions (IUAs) following hysteroscopic adhesiolysis. By integrating random forest-based feature importance analysis with self-attention, the model achieves enhanced predictive accuracy and interpretability. The experiments were conducted on a clinical dataset of 121 patients with 163 features, where 16.05% missing values were effectively handled using a matrix decomposition approach. SDL-IUAs demonstrated superior performance compared to traditional models, attaining an AUC of 0.96, a precision of 0.95, a recall of 0.94, and an F1-score of 0.94. Feature importance analysis highlighted age as a key predictive factor, providing actionable insights for clinical decision-making and personalized treatment planning. These results underscore the potential of SDL-IUAs as a robust, interpretable, and clinically applicable tool for pregnancy outcome prediction in IUA patients. The methodological advancements introduced in this study are expected to catalyze further research and innovation in this domain, ultimately contributing to improved clinical outcomes for IUA patients.