Transfer Learning and Machine Learning for Training Five Year Survival Prognostic Models in Early Breast Cancer

2025-09-27

AI Summary

To address the limited robustness of prognostic models for five-year survival in early-stage breast cancer—stemming from missing clinical data and multi-center distributional shifts—we propose a novel predictive framework integrating transfer learning, machine learning, and weighted ensemble modeling. Specifically, we adapt the PREDICT v3 pre-trained model to local cohorts via fine-tuning and combine it with random survival forests and XGBoost, augmented by SHAP-based interpretability analysis, yielding a robust predictor capable of handling missing inputs. On the MA.27 cohort, our method significantly reduces the integrated calibration index (ICI) from 0.042 to ≤0.007 and achieves an AUC of 0.744–0.799. External validation on the SEER cohort further confirms strong cross-center generalizability. This approach provides a scalable, clinically applicable solution for accurate prognosis in resource-constrained or incomplete-data settings.

Technology Category

• Machine Learning: Ensemble Methods
• Reasoning under Uncertainty: Relational Probabilistic Models
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Prognostic information is essential for decision-making in breast cancer management. Recently trials have predominantly focused on genomic prognostication tools, even though clinicopathological prognostication is less costly and more widely accessible. Machine learning (ML), transfer learning and ensemble integration offer opportunities to build robust prognostication frameworks. We evaluate this potential to improve survival prognostication in breast cancer by comparing de-novo ML, transfer learning from a pre-trained prognostic tool and ensemble integration. Data from the MA.27 trial was used for model training, with external validation on the TEAM trial and a SEER cohort. Transfer learning was applied by fine-tuning the pre-trained prognostic tool PREDICT v3, de-novo ML included Random Survival Forests and Extreme Gradient Boosting, and ensemble integration was realized through a weighted sum of model predictions. Transfer learning, de-novo RSF, and ensemble integration improved calibration in MA.27 over the pre-trained model (ICI reduced from 0.042 in PREDICT v3 to <=0.007) while discrimination remained comparable (AUC increased from 0.738 in PREDICT v3 to 0.744-0.799). Invalid PREDICT v3 predictions were observed in 23.8-25.8% of MA.27 individuals due to missing information. In contrast, ML models and ensemble integration could predict survival regardless of missing information. Across all models, patient age, nodal status, pathological grading and tumor size had the highest SHAP values, indicating their importance for survival prognostication. External validation in SEER, but not in TEAM, confirmed the benefits of transfer learning, RSF and ensemble integration. This study demonstrates that transfer learning, de-novo RSF, and ensemble integration can improve prognostication in situations where relevant information for PREDICT v3 is lacking or where a dataset shift is likely.

Problem

• Improving breast cancer survival prognostication using machine learning
• Comparing transfer learning with de-novo models for prediction accuracy
• Addressing missing data limitations in existing prognostic tools

Innovation

• Transfer learning fine-tunes pre-trained prognostic tool
• De-novo machine learning uses survival forests and boosting
• Ensemble integration combines models via weighted predictions