4arXiv cs.AI (Artificial Intelligence)·
Large Cancer Assistant (LCA): Model-agnostic orchestration framework for oncology clinical decision support
Researchers propose the Large Cancer Assistant (LCA), a model-agnostic orchestration framework for multimodal AI in oncology that decouples data ingestion, clinical routing, and AI inference via a 7-tuple architecture grounded in 'Algorithmic Impermeability.' The system uses Geometric Deep Learning to standardize multimodal patient data and outputs a Standardized Intermediate Payload (SIP) to isolate AI execution from hospital IT infrastructure. A proof-of-concept validated orchestration logic across four scenarios, demonstrating invariant routing during model swaps and 100% recall on failure-safety under injected data anomalies. The framework targets EMR interoperability and modular deployment of heterogeneous oncology AI models.
Related guides (2)
Related events (8)
ClaMPAPP: Hybrid LLM-ML system uses language models as interfaces for pediatric appendicitis diagnosis
Researchers introduce ClaMPAPP, a hybrid clinical decision support system that uses an LLM solely for structured feature extraction from free-text clinical notes, then passes validated features to an XGBoost classifier for final diagnosis. Evaluated on two independent German pediatric appendicitis cohorts, ClaMPAPP outperformed end-to-end LLM baselines on diagnostic performance and showed greater robustness to narrative reordering. The work formalizes an 'LLM-as-interface, ML-as-predictor' design pattern that separates natural-language usability from predictive inference, offering a more auditable pathway for clinical AI.
MedRLM: Recursive multimodal agent framework for long-context clinical decision support
MedRLM is a proposed framework for clinical decision support that uses recursive multi-agent reasoning over heterogeneous patient data including EHRs, medical images, physiological sensor streams, and clinical guidelines. Rather than single-step prompting, it decomposes patient cases into an inspectable external environment coordinated by specialized agents, with a Clinical Evidence Graph Memory and sensor-triggered deeper reasoning. The paper outlines an evaluation design using public and credentialed clinical datasets spanning radiology, ECG, ICU time series, and referral outcomes. The work targets a gap between static medical QA benchmarks and real-world longitudinal clinical workflows.
MOSAIC: Multi-LLM agentic framework for clinical severity phenotyping in EHR data
MOSAIC is a two-phase agentic LLM framework for disease severity phenotyping applied to type 2 diabetes, evaluated on a synthetic EHR cohort of up to 4,886 patients. The system incorporates domains absent from traditional algorithmic comparators—including glycaemic staging, beta-cell function, and social determinants of health—and shows open-weight models matching proprietary pipelines (weighted kappa 0.773). Agentic classification diverged meaningfully from deterministic rule execution of the same rubric (kappa 0.428), suggesting genuine reasoning beyond fixed rules. The work provides early evidence that agentic LLM systems can generate clinically meaningful severity phenotypes from structured EHR data.
Color Health's Cancer Copilot Uses GPT-4o for Oncology Workup Planning
Color Health has partnered with OpenAI to deploy GPT-4o in a clinical application called Cancer Copilot, designed to identify missing diagnostics and generate tailored cancer workup plans. The system aims to accelerate patient access to cancer screening and treatment by supporting evidence-based clinical decision-making. This represents a concrete enterprise deployment of GPT-4o in a high-stakes medical context.
The Open Medical-LLM Leaderboard: Benchmarking Large Language Models in Healthcare
Hugging Face has launched the Open Medical-LLM Leaderboard, a public benchmark for evaluating large language models on healthcare and medical tasks. The leaderboard aggregates performance across multiple medical question-answering datasets to enable standardized comparison of open-weight models in clinical and biomedical domains. This initiative aims to accelerate progress in medical AI by providing transparent, reproducible evaluation infrastructure.
Enabling a new model for healthcare with AI co-clinician
DeepMind has published a blog post outlining research into an AI co-clinician concept aimed at augmenting clinical care. The post describes a vision for AI-augmented healthcare where AI systems work alongside medical professionals. The content appears to be a high-level research direction announcement rather than a specific model or product release.
We Got Claude to Fine-Tune an Open Source LLM
Hugging Face demonstrates using Claude (Anthropic's model) as an orchestrating agent to autonomously fine-tune an open-source LLM, showcasing an agentic workflow for model training. The post illustrates how a frontier model can handle the end-to-end process of dataset preparation, training configuration, and execution for a smaller open-weights model. This represents a practical example of AI-assisted ML engineering and agent-tool ecosystem development.
AWS Labs releases AI-Driven Life Cycle (AI-DLC) adaptive workflow steering rules for AI coding agents
AWS Labs has open-sourced aidlc-workflows, a Python repository providing adaptive workflow steering rules for AI coding agents under an AI-Driven Life Cycle (AI-DLC) framework. The project aims to guide AI agents through structured software development lifecycle phases. With 2,367 stars and modest daily growth (+31), it represents a community-level tooling contribution from AWS Labs in the agent orchestration space.