M-CARE: Standardized Clinical Case Reporting for AI Model Behavioral Disorders, with a 20-Case Atlas and Experimental Validation

• URL: http://arxiv.org/abs/2604.20871v1
• Date: Fri, 27 Mar 2026 12:52:20 GMT
• Title: M-CARE: Standardized Clinical Case Reporting for AI Model Behavioral Disorders, with a 20-Case Atlas and Experimental Validation
• Abstract summary: M-CARE is a clinical case report framework for AI model behavioral disorders adapted from human medicine.<n>M-CARE provides a 13-section report format, a 4-axis diagnostic assessment system, and a nosological classification of AI behavioral conditions.
• Score: 4.358468367889626
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce M-CARE (Model Clinical Assessment and Reporting for Evaluation), a clinical case report framework for AI model behavioral disorders adapted from human medicine. M-CARE provides a 13-section report format, a 4-axis diagnostic assessment system, and a nosological classification of AI behavioral conditions. We present 20 cases from three source categories: field observations of deployed agents (8), controlled experiments across three platforms (8), and published sources (4). Cases are organized into five categories: RLHF Performance Artifacts, Shell-Core Override Pathology, Context & Memory Conditions, Core Identity & Plasticity, and Stress, Methodology, & Boundary Conditions. As a featured case, we present Shell-Induced Behavioral Override (SIBO) -- a controlled experiment showing that Shell instructions categorically override a model's default cooperative behavior. SIBO was validated across five game domains (Trust Game, Poker, Avalon, Codenames, Chess), revealing a domain-dependent spectrum (SIBO Index: 0.75 to 0.10) that varies with action space complexity, Core domain expertise, and temporal directness. M-CARE is extensible: new cases and categories integrate without framework modification. We release the framework, all 20 case reports, and experimental data as open resources.

Related papers

• Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation [66.62662330558906]
  CORAL is a multimodal framework that integrates spatial grounding and concept-level supervision into a unified reasoning process.<n>CORAL employs a prompt-driven medical segmentation model to localize lesions and predicts multi-class clinical attributes through a Concept Bottleneck module.<n>Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs.
  arXiv  Detail & Related papers  (2026-09-14T10:21:23Z)
• 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)
• Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases [71.12461204050985]
  MedSP1000 is an SP-derived interactive benchmark for clinical-agent evaluation.<n>It converts peer-reviewed SP teaching cases into executable scenarios with defined SP case scripts, clinical environment contexts, and human-validated structured rubrics.<n>Applying MedSP1000 to a range of general-purpose and medically specialized LLMs, we find that performance on static benchmarks does not reliably translate to such educational scenarios.
  arXiv  Detail & Related papers  (2026-06-03T17:17:16Z)
• iTRIALSPACE: Programmable Virtual Lesion Trials for Controlled Evaluation of Lung CT Models [0.8477463841895917]
  iTRIALSPACE is a programmable evaluation framework for controlled assessment of lung CT models.<n>We evaluate iTRIALSPACE in a 55,469-sample Virtual Lesion Study spanning three medical VLMs, four spatialguidance conditions, and three clinical tasks.
  arXiv  Detail & Related papers  (2026-05-07T06:55:44Z)
• MedPRMBench: A Fine-grained Benchmark for Process Reward Models in Medical Reasoning [7.000170880015254]
  We propose MedPRMBench, the first process-level reward model benchmark for the medical domain.<n>It is built through a three-phase pipeline based on Clinical Reasoning Blueprints (CRBs)<n>The benchmark comprises 6,500 questions with 13,000 reasoning chains and 113,910 step-level labels, plus 6,879 questions for training.
  arXiv  Detail & Related papers  (2026-04-19T06:44:07Z)
• Cerebra: A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment [56.62016795093786]
  Cerebra is an interactive multi-agent AI team that coordinates specialized agents for EHR, clinical notes, and medical imaging analysis.<n>It supports privacy-preserving deployment by operating on structured representations and remains robust when modalities are incomplete.<n>Cerebra significantly improved expert performance, increasing accuracy by 17.5 percentage points in prospective dementia risk estimation.
  arXiv  Detail & Related papers  (2026-03-23T05:46:45Z)
• GOLDMARK: Governed Outcome-Linked Diagnostic Model Assessment Reference Kit [7.891604152731754]
  Computational biomarkers (CBs) are histo-derived patterns extracted from hematoxylin-eosin (H&E) whole-slide images (WSIs) to predict therapeutic response or prognosis.<n>We introduce GOLDMARK, a standardized benchmarking framework built on a curated TCGA cohort with clinically actionable OncoKB level 1-3 biomarker labels.
  arXiv  Detail & Related papers  (2026-03-21T15:09:06Z)
• Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs [63.535652574541764]
  Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in medical image analysis.<n>Their application in gastrointestinal endoscopy is currently hindered by two critical limitations.<n>We propose a novel Clinical-Cognitive-Aligned (CogAlign) framework to address these challenges.
  arXiv  Detail & Related papers  (2026-03-21T07:47:37Z)
• AEGIS: An Operational Infrastructure for Post-Market Governance of Adaptive Medical AI Under US and EU Regulations [39.89241412792336]
  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.
  arXiv  Detail & Related papers  (2026-03-20T11:56:59Z)
• Surg-R1: A Hierarchical Reasoning Foundation Model for Scalable and Interpretable Surgical Decision Support with Multi-Center Clinical Validation [51.897472694590356]
  We present Surg-R1, a surgical Vision-Language Model that addresses the gap through hierarchical reasoning trained via a four-stage pipeline.<n>Our approach introduces three key contributions: (1) a three-level reasoning hierarchy decomposing surgical interpretation into perceptual grounding, relational understanding, and contextual reasoning; and (2) the largest surgical chain-of-thought dataset with 320,000 reasoning pairs.
  arXiv  Detail & Related papers  (2026-03-12T20:26:28Z)
• 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)
• MMedExpert-R1: Strengthening Multimodal Medical Reasoning via Domain-Specific Adaptation and Clinical Guideline Reinforcement [63.82954136824963]
  Medical Vision-Language Models excel at perception tasks with complex clinical reasoning required in real-world scenarios.<n>We propose a novel reasoning MedVLM that addresses these challenges through domain-specific adaptation and guideline reinforcement.
  arXiv  Detail & Related papers  (2026-01-16T02:32:07Z)
• DeVisE: Behavioral Testing of Medical Large Language Models [14.832083455439749]
  DeVisE is a behavioral testing framework for probing fine-grained clinical understanding.<n>We construct a dataset of ICU discharge notes from MIMIC-IV.<n>We evaluate five LLMs spanning general-purpose and medically fine-tuned variants.
  arXiv  Detail & Related papers  (2025-06-18T10:42:22Z)
• Medchain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence [68.05876437208505]
  We present MedChain, a dataset of 12,163 clinical cases that covers five key stages of clinical workflow.<n>We also propose MedChain-Agent, an AI system that integrates a feedback mechanism and a MCase-RAG module to learn from previous cases and adapt its responses.
  arXiv  Detail & Related papers  (2024-12-02T15:25:02Z)
• ICDBigBird: A Contextual Embedding Model for ICD Code Classification [71.58299917476195]
  Contextual word embedding models have achieved state-of-the-art results in multiple NLP tasks. ICDBigBird is a BigBird-based model which can integrate a Graph Convolutional Network (GCN) Our experiments on a real-world clinical dataset demonstrate the effectiveness of our BigBird-based model on the ICD classification task.
  arXiv  Detail & Related papers  (2022-04-21T20:59:56Z)

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.