The Large Cancer Assistant (LCA): A Model-Agnostic Orchestration Framework for Scalable Clinical Decision Support in Oncology
Summary
This paper introduces the Large Cancer Assistant (LCA), a model-agnostic orchestration framework for scalable clinical decision support in oncology that decouples multimodal data ingestion from AI inference using a 7-tuple architecture and Algorithmic Impermeability.
View Cached Full Text
Cached at: 07/08/26, 04:40 AM
# The Large Cancer Assistant (LCA): A Model-Agnostic Orchestration Framework for Scalable Clinical Decision Support in Oncology Source: [https://arxiv.org/abs/2607.06531](https://arxiv.org/abs/2607.06531) [View PDF](https://arxiv.org/pdf/2607.06531) > Abstract:\- Objective: Multimodal deep learning models in oncology are currently limited by monolithic designs that rigidly couple data ingestion, clinical routing, and artificial intelligence \(AI\) inference\. To address this inflexibility, we propose the Large Cancer Assistant \(LCA\), a model\-agnostic, post\-hoc orchestration framework designed for scalable clinical decision support\. \- Methods: The LCA is mathematically formalized as a 7\-tuple architecture grounded in the principle of Algorithmic Impermeability, ensuring the orchestration logic remains strictly independent of underlying black\-box AI models\. We introduce the Entry Theory, leveraging Geometric Deep Learning \(GDL\) to standardize multimodal patient data along distinct structural and medical axes\. The system dynamically orchestrates data via a Cancer Switching Module and intentionally isolates the core AI execution from volatile hospital IT infrastructures by outputting a Standardized Intermediate Payload \(SIP\)\. \- Results: A Proof of Concept \(PoC\) validated the orchestration logic across four technical scenarios\. The framework executed a nominal flow with negligible orchestration overhead\. It empirically demonstrated algorithmic impermeability by maintaining an invariant routing projection during AI model swaps, and it validated strict failure\-safety by achieving a 100\\% recall rate in generating targeted Supplementary Data Requests \(SDR\) under injected data anomalies\. Multi\-protocol execution capability was also successfully verified\. \- Conclusion: By structurally decoupling multimodal ingestion from feature inference, the LCA provides a highly adaptable and modular orchestration foundation\. The SIP establishes a clear architectural boundary, natively setting the stage for downstream Electronic Medical Record \(EMR\) interoperability as an independent future paradigm\. ## Submission history From: Ghassen Marrakchi \[[view email](https://arxiv.org/show-email/34fdcce0/2607.06531)\] **\[v1\]**Tue, 7 Jul 2026 17:38:47 UTC \(1,051 KB\)
Similar Articles
"OncoAgent: A Dual-Tier Multi-Agent Framework for Privacy-Preserving Oncology Clinical Decision Support"
The article introduces OncoAgent, a dual-tier multi-agent framework designed for privacy-preserving clinical decision support in oncology. It details a system architecture that combines corrective RAG, a reflexion safety loop, and dual-tier QLoRA fine-tuning optimized for AMD hardware.
Agentic systems for breast cancer treatment recommendations
Evaluates agentic LLM systems for generating breast cancer treatment recommendations using 72 clinical cases, finding that the best system (Claude Opus 4.8 with D&C+SA pipeline) achieved a global score of 0.594 but remains insufficient for unsupervised clinical use due to persistent errors.
A specialized reasoning large language model for accelerating rare disease diagnosis: a randomized AI physician assistance trial
This paper presents RaDaR, a 32B open-source reasoning LLM trained on public and synthetic rare disease cases, which outperforms larger models like DeepSeek-R1 in diagnosis benchmarks and improves physician accuracy by 21.44 percentage points in a randomized trial.
Treatment Response Optimized Clinical Decision Support AI System via Digital Twin Simulation
This paper presents an online adaptive clinical decision support AI system that integrates treatment effect estimation, digital twin simulation, and reinforcement learning to recommend treatments in a safe, clinician-supervised manner, validated on a synthetic simulator and the TCGA ovarian cancer dataset.
Information-seeking failures of large language models in agentic clinical reasoning
The paper develops an agentic evaluation framework for clinical reasoning in hematologic oncology, finding that LLMs primarily fail due to systematic information-seeking deficits rather than insufficient knowledge, with error patterns resembling cognitive biases in novice clinicians.