The Large Cancer Assistant (LCA): A Model-Agnostic Orchestration Framework for Scalable Clinical Decision Support in Oncology

2026-07-07

AI Summary

This study addresses the limited scalability and adaptability of existing monolithic multimodal deep learning models in oncology, which stem from their inability to decouple data ingestion, clinical routing, and AI inference. To overcome this, the authors propose LCA, a model-agnostic post-hoc orchestration framework that achieves structural disentanglement through standardized multimodal data representation, dynamic clinical routing, and isolated AI execution. The framework introduces the principles of algorithmic impermeability and ingress theory, implementing a Standardized Intermediate Payload (SIP), a cancer-switching module, and a Supplemental Data Request (SDR) mechanism. Geometric deep learning is employed to align heterogeneous modalities. Experimental results demonstrate negligible orchestration overhead, stable routing projections during model replacement, 100% SDR recall under data anomalies, and seamless interoperability across multi-protocol electronic medical record (EMR) systems.

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.

Problem

• multimodal deep learning
• clinical decision support
• model rigidity
• oncology
• scalability

Innovation

• model-agnostic orchestration
• Algorithmic Impermeability
• Geometric Deep Learning
• Standardized Intermediate Payload
• multimodal clinical decision support