AEGIS: An Operational Infrastructure for Post-Market Governance of Adaptive Medical AI Under US and EU Regulations

• URL: http://arxiv.org/abs/2603.22322v1
• Date: Fri, 20 Mar 2026 11:56:59 GMT
• Title: AEGIS: An Operational Infrastructure for Post-Market Governance of Adaptive Medical AI Under US and EU Regulations
• Abstract summary: This paper presents AEGIS, a governance framework applicable to any healthcare AI system.<n>We implement a four-category deployment decision taxonomy (APPROVE, CONDITIONAL APPROVAL, CLINICAL REVIEW, REJECT) with an independent PMS ALARM signal.<n>Results demonstrate that AEGIS translates regulatory change-control concepts into executable governance procedures.
• Score: 39.89241412792336
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Machine learning systems deployed in medical devices require governance frameworks that ensure safety while enabling continuous improvement. Regulatory bodies including the FDA and European Union have introduced mechanisms such as the Predetermined Change Control Plan (PCCP) and Post-Market Surveillance (PMS) to manage iterative model updates without repeated submissions. This paper presents AI/ML Evaluation and Governance Infrastructure for Safety (AEGIS), a governance framework applicable to any healthcare AI system. AEGIS comprises three modules, i.e., dataset assimilation and retraining, model monitoring, and conditional decision, that operationalize FDA PCCP and EU AI Act Article 43(4) provisions. We implement a four-category deployment decision taxonomy (APPROVE, CONDITIONAL APPROVAL, CLINICAL REVIEW, REJECT) with an independent PMS ALARM signal, enabling detection of the critical state in which no deployable model exists while the released model is simultaneously at risk. To illustrate how AEGIS can be instantiated across heterogeneous clinical contexts, we provide two examples: sepsis prediction from electronic health records and brain tumor segmentation from medical imaging. Both cases use identical governance architecture, differing only in configuration. Across 11 simulated iterations on the sepsis example, AEGIS yielded 8 APPROVE, 1 CONDITIONAL APPROVAL, 1 CLINICAL REVIEW, and 1 REJECT decision, exercising all four categories. ALARM signals were co-issued at iterations 8 and 10, including the critical state where no deployable model exists and the released model is simultaneously failing. AEGIS detected drift before observable performance degradation. These results demonstrate that AEGIS translates regulatory change-control concepts into executable governance procedures, supporting safe continuous learning for adaptive medical AI across diverse clinical applications.

Related papers

• AI Morbidity and Mortality: A Framework for Clinical AI Failure Review [4.342185705620882]
  We propose AI Morbidity and Mortality (AI M&M), a structured, blameless framework for case-based review of clinical AI failures.<n>The framework combines standardized case intake, evidence preservation and investigator-level reconstruction, tool-in-loop attribution, and corrective-action tracking.<n>It is intended to complement, rather than replace, model monitoring, patient safety reporting, and regulatory oversight by converting individual AI-in-workflow failures into actionable institutional learning.
  arXiv  Detail & Related papers  (2026-08-31T07:41:30Z)
• Taming foundation model with invariance-oriented pre-training for broad-spectrum EEG analysis across signal-level, brain-state, and brain-health tasks [46.533103231728724]
  INCEPT is an invariance-oriented EEG foundation model trained on over 11,000 hours of unlabelled clinical EEG.<n>We evaluate INCEPT on a broad-spectrum benchmark of ten datasets spanning three levels of post-acquisition EEG analysis.
  arXiv  Detail & Related papers  (2026-08-25T14:20:02Z)
• The Large Cancer Assistant (LCA): A Model-Agnostic Orchestration Framework for Scalable Clinical Decision Support in Oncology [0.0]
  Large Cancer Assistant (LCA) is a model-agnostic, post-hoc orchestration framework designed for scalable clinical decision support.<n>LCA is mathematically formalized as a 7-tuple architecture grounded in the principle of Algorithmic Impermeability.<n>System dynamically orchestrates data via a Cancer Switching Module and intentionally isolates the core AI execution from volatile hospital IT infrastructures.
  arXiv  Detail & Related papers  (2026-07-07T17:38:47Z)
• Hallucination in Medical Imaging AI: A Cross-Modality Analytical Framework for Taxonomy, Detection, and Mitigation under Regulatory Constraints [0.3437656066916039]
  hallucination is clinically plausible but factually incorrect outputs.<n>General-purpose foundation models outperform medical-specialized models on hallucination-specific benchmarks.<n>FDA lifecycle oversight remains essential.
  arXiv  Detail & Related papers  (2026-06-11T11:19:31Z)
• Model Medicine: A Clinical Framework for Understanding, Diagnosing, and Treating AI Models [4.358468367889626]
  Model Medicine is the science of understanding, diagnosing, treating, and preventing disorders in AI models.<n>This paper introduces Model Medicine as a research program, bridging the gap between current AI interpretability research and the systematic clinical practice.
  arXiv  Detail & Related papers  (2026-03-05T01:49:29Z)
• MCP-AI: Protocol-Driven Intelligence Framework for Autonomous Reasoning in Healthcare [0.0]
  We present MCP-AI, a novel architecture for explainable medical decision-making built upon the Model Context Protocol.<n>MCP-AI supports adaptive, longitudinal, and collaborative reasoning across care settings.
  arXiv  Detail & Related papers  (2025-12-05T02:02:22Z)
• Beyond Generative AI: World Models for Clinical Prediction, Counterfactuals, and Planning [2.800335887892072]
  World models learn predictive dynamics to enable multistep rollouts, counterfactual evaluation and planning.<n>Most reviewed systems achieve L1--L2, with fewer instances of L3 and rare L4 planning/control.<n>This review outlines a research agenda for clinically robust prediction-first world models.
  arXiv  Detail & Related papers  (2025-11-20T13:11:45Z)
• Organ-Agents: Virtual Human Physiology Simulator via LLMs [66.40796430669158]
  Organ-Agents is a multi-agent framework that simulates human physiology via LLM-driven agents.<n>We curated data from 7,134 sepsis patients and 7,895 controls, generating high-resolution trajectories across 9 systems and 125 variables.<n>Organ-Agents achieved high simulation accuracy on 4,509 held-out patients, with per-system MSEs 0.16 and robustness across SOFA-based severity strata.
  arXiv  Detail & Related papers  (2025-08-20T01:58:45Z)
• CardAIc-Agents: A Multimodal Framework with Hierarchical Adaptation for Cardiac Care Support [37.20545002349272]
  CardAIc-Agents is a framework to augment AI models with external tools and adaptively support diverse cardiac tasks.<n>A CardiacRAG agent generated general plans from updatable cardiac knowledge, while the chief agent integrated tools to autonomously execute these plans and deliver decisions.<n> Experiments across three datasets showed the efficiency of CardAIc-Agents compared to mainstream Vision-Language Models (VLMs), state-of-the-art agentic systems, and fine-tuned VLMs.
  arXiv  Detail & Related papers  (2025-08-18T16:17:12Z)
• Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments [50.310636905746975]
  Real-world machine learning systems often encounter model performance degradation due to distributional shifts in the underlying data generating process. Existing approaches to addressing shifts, such as concept drift adaptation, are limited by their reason-agnostic nature. We propose self-healing machine learning (SHML) to overcome these limitations.
  arXiv  Detail & Related papers  (2024-10-31T20:05:51Z)
• MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models [49.765466293296186]
  Recent progress in Medical Large Vision-Language Models (Med-LVLMs) has opened up new possibilities for interactive diagnostic tools.<n>Med-LVLMs often suffer from factual hallucination, which can lead to incorrect diagnoses.<n>We propose a versatile multimodal RAG system, MMed-RAG, designed to enhance the factuality of Med-LVLMs.
  arXiv  Detail & Related papers  (2024-10-16T23:03:27Z)
• Safe AI for health and beyond -- Monitoring to transform a health service [51.8524501805308]
  We will assess the infrastructure required to monitor the outputs of a machine learning algorithm. We will present two scenarios with examples of monitoring and updates of models.
  arXiv  Detail & Related papers  (2023-03-02T17:27:45Z)
• An Adversarial Domain Separation Framework for Septic Shock Early Prediction Across EHR Systems [7.058760708627898]
  We propose a general domain adaptation (DA) framework that tackles two categories of discrepancies in EHRs collected from different medical systems. We evaluate our framework for early diagnosis of an extremely challenging condition, septic shock, using two real-world EHRs from distinct medical systems in the U.S.
  arXiv  Detail & Related papers  (2020-10-26T23:41:33Z)
• Hierarchical Reinforcement Learning for Automatic Disease Diagnosis [52.111516253474285]
  We propose to integrate a hierarchical policy structure of two levels into the dialogue systemfor policy learning. The proposed policy structure is capable to deal with diagnosis problem including large number of diseases and symptoms.
  arXiv  Detail & Related papers  (2020-04-29T15:02:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.