SAGE: Agentic Framework for Interpretable and Clinically Translatable Computational Pathology Biomarker Discovery
This addresses the barrier to clinical adoption of AI in pathology by providing more interpretable biomarkers, though it appears incremental as it builds on existing biomarker discovery methods with a structured agentic approach.
The paper tackles the problem of black-box AI models in computational pathology by introducing SAGE, an agentic AI system that identifies interpretable, engineered biomarkers grounded in biological evidence, aiming to improve clinical adoption through transparency and biological validation.
Despite significant progress in computational pathology, many AI models remain black-box and difficult to interpret, posing a major barrier to clinical adoption due to limited transparency and explainability. This has motivated continued interest in engineered image-based biomarkers, which offer greater interpretability but are often proposed based on anecdotal evidence or fragmented prior literature rather than systematic biological validation. We introduce SAGE (Structured Agentic system for hypothesis Generation and Evaluation), an agentic AI system designed to identify interpretable, engineered pathology biomarkers by grounding them in biological evidence. SAGE integrates literature-anchored reasoning with multimodal data analysis to correlate image-derived features with molecular biomarkers, such as gene expression, and clinically relevant outcomes. By coordinating specialized agents for biological contextualization and empirical hypothesis validation, SAGE prioritizes transparent, biologically supported biomarkers and advances the clinical translation of computational pathology.