Developing generalizable eHealth methodology for large-scale biomedical knowledge extraction and interpretable, uncertainty-aware AI modeling in rare cancer diagnostics.
Sarcomas represent a rare and heterogeneous group of malignancies characterized by complex diagnostic pathways and significant clinical challenges. These tumors encompass more than 100 distinct histological subtypes, each requiring specialized knowledge of subtype-specific morphological features, molecular markers, and therapeutic approaches.
"More than 40% of initial histological diagnoses are wrong—modified upon expert review, with major discrepancies related to histological grade (43%), histological type (24%), and combined grade and subtype classifications (29%). Expert review leads to management changes in 14.2% of patients."
AEGIS addresses sarcoma diagnostics through an integrated methodology combining large-scale knowledge extraction with clinical application, leveraging large language models (LLMs) and retrieval-augmented reasoning. The system provides a "digital second opinion" backed by comprehensive data and rigorous uncertainty measures— augmenting rather than replacing the pathologist.
University Medical Center Göttingen (UMG)
Department of Pathology, Sarcoma Referral Center
Leibniz University Hannover (LUH)
L3S Research Center
University Medical Center Göttingen (UMG)
Department of Medical Statistics
AEGIS represents a new model for interdisciplinary eHealth research embedded within the CAIMed network: three early-career researchers combining clinical medicine, artificial intelligence, and statistical methodology around a shared challenge that none could address alone.
A CodeAct-based system demonstrating autonomous multi-step diagnostic reasoning with complete provenance tracking. The agent orchestrates literature retrieval, clinical data integration, image analysis, and interpretable models through unified tool invocation. The sarcoma-specific retrieval infrastructure will be released as the first open-source, domain-specific knowledge engine for rare tumor diagnostics.
ART-based models providing human-readable decision logic that distill ensemble predictions into transparent decision trees. Conformal prediction delivers calibrated confidence estimates with ≥90% empirical coverage guarantee. The resulting uncertainty atlas maps diagnostic confidence across the feature space of sarcoma classification.
A production-grade methodology for transforming unstructured biomedical literature into structured diagnostic knowledge. Validated on ~20,000 sarcoma publications against expert-curated ground truth, achieving precision/recall ≥85% for core diagnostic entities. Outputs aligned with standard terminologies (SNOMED CT, ICD-O-3, NCIt) and MII data models.
Meta-learning approaches enabling sarcoma subtype classification from whole-slide images with limited training examples—directly addressing the data scarcity barrier excluding rare diseases from deep learning advances. Target: AUROC ≥0.85 for primary diagnostic categories with ≤50 training examples per subtype.
Retrospective validation of the complete integrated system benchmarked against expert tumor board decisions. Demonstrates the "digital second opinion" concept with diagnostic probability estimates and uncertainty quantification. Accompanied by governance framework addressing GDPR, EU MDR, and EU AI Act requirements; multi-center deployment pathway via CAIMed; usability validation (target: SUS ≥70).
LLM-based agent system built on the CodeAct framework, capable of autonomous retrieval, extraction, and synthesis of biomedical knowledge with full provenance tracking and multi-step reasoning.
Hybrid RAG infrastructure combining dense semantic embeddings with sparse lexical indexing, re-ranking strategies, and rationale-guided approaches for optimal retrieval from ~20,000 sarcoma publications.
Meta-learning algorithms (Prototypical Networks, MAML) enabling classification of rare sarcoma subtypes with limited training examples from whole-slide images.
Interpretable surrogate models distilling complex ensemble predictions into human-readable decision trees while maintaining prediction accuracy and fidelity to ensemble boundaries.
Distribution-free uncertainty quantification with finite-sample coverage guarantees, providing calibrated confidence estimates that have reduced diagnostic errors from 2% to 0.1% in pathology applications.
All outputs aligned with SNOMED CT, ICD-O-3, NCIt, ICCR reporting elements, and MII data models ensuring FHIR/OMOP interoperability across clinical systems.
Transform existing clinical documentation into computationally accessible formats. Terminology standardization, quality assessment, diagnostic uncertainty formalization from tumor board records.
Establish production-grade RAG infrastructure. PDF parsing, semantic chunking, hybrid retrieval with re-ranking, LLM generator with citations, validation against human-curated datasets.
Develop agentic orchestration with CodeAct for autonomous multi-step reasoning. API layer for tools, multimodal data integration, human-in-the-loop validation, safety guardrails.
Develop ART generation and conformal prediction implementations. Feature integration, ensemble training, uncertainty atlas with interactive visualization.
Foundation model evaluation, weakly supervised MIL, few-shot implementation with Prototypical Networks/MAML, morphometric extraction, multimodal integration with agentic framework.
Shadow-mode retrospective validation, performance benchmarking against expert diagnoses, usability assessment (SUS), translational blueprint for EU MDR/AI Act compliance.
Computationally accessible with standardized terminology; validation protocol defined
Literature corpus indexed; nDCG@10 ≥ 0.75
Micro-F1 ≥ 0.85; structured reference operational
Multi-tool orchestration functional; expert validation initiated
Conformal coverage ≥ 90% achieved
AUROC ≥ 0.85 for major categories
Retrospective validation documented; translational blueprint finalized
| Category | Year 1 | Year 2 | Year 3 | Total |
|---|---|---|---|---|
| Subproject 1 (UMG Pathology) | €255,215 | €262,151 | €269,296 | €786,662 |
| Subproject 2 (L3S) | €117,137 | €127,427 | €130,609 | €375,173 |
| Subproject 3 (UMG MedStat) | €118,971 | €127,946 | €131,010 | €377,926 |
| Total | €491,323 | €517,524 | €530,915 | €1,539,762 |
AEGIS is anchored within CAIMed, Lower Saxony's strategic initiative for medical AI research connecting university medical centers, technical universities, and research institutes across the state. CAIMed maintains affiliations with leading German research infrastructures including the Medical Informatics Initiative (MII) and the German Center for Cardiovascular Research (DZHK).
L3S Research Center, Founding Director CAIMed
UMG, Computational Pathology, CAIMed Director UMG
Director, Institute of Pathology, Sarcoma Referral Center
Director, Institute of Medical Statistics