Predicting live birth success using hybrid attention models in IVF
Predicting Live Birth After Fresh Embryo Transfer in IVF/ICSI: Differential ICM/Trophectoderm Morphology Encoding and a Hybrid Attention--Logistic Regression Ensemble
Machine Learning
Summary
Deciding if an embryo will lead to a live birth before transfer in IVF is difficult because the available medical data is small and complicated. The authors created a special dataset from one clinic and developed a new prediction model that focuses on different parts of the embryo. Their hybrid model, combining a small neural network and a standard method, predicted live birth better than previous approaches. This method is clear and can be used again with other data, but still needs testing elsewhere.
What this means in practice
- •For clinical data scientists: Use the curated IVF dataset and hybrid attention model to improve live birth predictions from small clinical data.
- •For fertility clinic decision makers: Incorporate the model’s predictions before embryo transfer to support informed patient counseling and treatment choices in IVF/ICSI.
Tested on one dataset.
Authors
Abdul Raheem Shahzad, Jinxin Chen, Ming Zhang, Juan Deng
Abstract
Predicting live birth before fresh embryo transfer could support shared decision-making in IVF/ICSI, but routine clinical data are small, heterogeneous, and contain pathway-dependent variables prone to outcome leakage. We aimed to construct a curated single-centre IVF/ICSI dataset and develop a prediction model suited to small tabular clinical data. \textit{Materials and Methods:} We assembled 616 fresh embryo-transfer cycles (251 live birth, 365 non-live birth) with clinical, laboratory, and embryological predictors, and embryo morphology encoded with a novel differential weighting of the inner cell mass and trophectoderm. After KNN imputation, robust scaling, and selection of 50 features, we developed a Hybrid Attention Network (HAN), a learnable feature-attention gate followed by a compact multilayer perceptron, and a HAN + logistic-regression (LR) ensemble with a validation-tuned weight. Models were benchmarked against classical machine learning, TabPFN, and text-serialized language models on a held-out test set; AUC-ROC was the primary metric. \textit{Results:} The HAN + LR ensemble achieved the highest test AUC-ROC (0.710; accuracy 0.710, F1 0.630), ahead of the HAN backbone alone (0.700), logistic regression (0.667), the TabPFN + LR hybrid (0.666), and TabPFN (0.650). Text-serialized language models performed near chance (AUC $\le$ 0.61). The differentially weighted trophectoderm feature ranked highest by consensus importance across models. \textit{Discussion:} A compact attention network combined with a linear model outperformed both components and strong foundation-model baselines on a small clinical cohort. \textit{Conclusion:} The curated dataset and HAN + LR ensemble offer a transparent, reproducible basis for IVF/ICSI live-birth prediction; external validation is the next step.