CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance

• URL: http://arxiv.org/abs/2604.01113v1
• Date: Wed, 01 Apr 2026 16:37:01 GMT
• Title: CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance
• Abstract summary: We introduce MIMIC-DOS, a dataset for short-horizon organ dysfunction worsening prediction in the intensive care unit (ICU) setting.<n>We construct it exclusively from cases in which discordance between signs and symptoms exists.<n>This setting poses a substantial challenge for existing LLM-based approaches.<n>We propose CARE: a multi-stage privacy-compliant agentic reasoning framework.
• Score: 32.43119949391787
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model (LLM) systems are increasingly used to support high-stakes decision-making, but they typically perform worse when the available evidence is internally inconsistent. Such a scenario exists in real-world healthcare settings, with patient-reported symptoms contradicting medical signs. To study this problem, we introduce MIMIC-DOS, a dataset for short-horizon organ dysfunction worsening prediction in the intensive care unit (ICU) setting. We derive this dataset from the widely recognized MIMIC-IV, a publicly available electronic health record dataset, and construct it exclusively from cases in which discordance between signs and symptoms exists. This setting poses a substantial challenge for existing LLM-based approaches, with single-pass LLMs and agentic pipelines often struggling to reconcile such conflicting signals. To address this problem, we propose CARE: a multi-stage privacy-compliant agentic reasoning framework in which a remote LLM provides guidance by generating structured categories and transitions without accessing sensitive patient data, while a local LLM uses these categories and transitions to support evidence acquisition and final decision-making. Empirically, CARE achieves stronger performance across all key metrics compared to multiple baseline settings, showing that CARE can more robustly handle conflicting clinical evidence while preserving privacy.

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)
• Primary ICD Category Prediction using LLM-based Probing [7.948368617192842]
  We constructed a MIMIC-IV cohort of 13,645 admissions from the 10 most frequent primary ICD-10 codes.<n>We extracted hidden states from five transformer layers and trained linear probes for structured-only, unstructured-only, and combined inputs.<n>The combined probe performed best on MIMIC-IV (87.69% strict; 91.45% medical accuracy), exceeding both single-modality probes and baselines.
  arXiv  Detail & Related papers  (2026-06-27T08:10:05Z)
• Green Shielding: A User-Centric Approach Towards Trustworthy AI [19.485991712624095]
  Green Shielding is a user-centric agenda for building evidence-backed deployment guidance.<n>We instantiate Green Shielding in medical diagnosis through HealthCareMagic-Diagnosis.<n>Although instantiated here in medical diagnosis, the agenda extends naturally to other decision-support settings and agentic AI systems.
  arXiv  Detail & Related papers  (2026-04-27T17:04:17Z)
• Statistics, Not Scale: Modular Medical Dialogue with Bayesian Belief Engine [51.722324399751294]
  Large language models are increasingly deployed as autonomous diagnostic agents, yet they conflate two fundamentally different capabilities.<n>We introduce BMBE, a modular diagnostic dialogue framework that enforces a strict separation between language and reasoning.
  arXiv  Detail & Related papers  (2026-04-21T21:59:57Z)
• A Federated and Parameter-Efficient Framework for Large Language Model Training in Medicine [59.78991974851707]
  Large language models (LLMs) have demonstrated strong performance on medical benchmarks, including question answering and diagnosis.<n>Most medical LLMs are trained on data from a single institution, which faces limitations in generalizability and safety in heterogeneous systems.<n>We introduce the model-agnostic and parameter-efficient federated learning framework for adapting LLMs to medical applications.
  arXiv  Detail & Related papers  (2026-01-29T18:48:21Z)
• SoK: Privacy-aware LLM in Healthcare: Threat Model, Privacy Techniques, Challenges and Recommendations [0.6533091401094101]
  Large Language Models (LLMs) are increasingly adopted in healthcare to support clinical decision-making and enhance patient care.<n>This work examines the evolving threat landscape across the three core LLM phases: Data preprocessing, Fine-tuning, and Inference within realistic healthcare settings.<n>We present a detailed threat model that characterizes adversaries, capabilities, and attack surfaces at each phase, and we systematize how existing privacy-preserving techniques (PPTs) attempt to mitigate these vulnerabilities.
  arXiv  Detail & Related papers  (2026-01-15T02:28:57Z)
• From EMR Data to Clinical Insight: An LLM-Driven Framework for Automated Pre-Consultation Questionnaire Generation [9.269061009613033]
  We propose a novel framework for generating pre-consultation questionnaires from complex Electronic Medical Records (EMRs)<n>This framework overcomes limitations of direct methods by building explicit clinical knowledge.<n> Evaluated on a real-world EMR dataset and validated by clinical experts, our method demonstrates superior performance in information coverage, diagnostic relevance, understandability, and generation time.
  arXiv  Detail & Related papers  (2025-08-01T12:24:49Z)
• AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator [69.51568871044454]
  We introduce textbfAI Hospital, a framework simulating dynamic medical interactions between emphDoctor as player and NPCs. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the Multi-View Medical Evaluation benchmark, utilizing high-quality Chinese medical records and NPCs.
  arXiv  Detail & Related papers  (2024-02-15T06:46:48Z)
• Retrieving Evidence from EHRs with LLMs: Possibilities and Challenges [18.56314471146199]
  Large volume of notes often associated with patients together with time constraints renders manually identifying relevant evidence practically infeasible. We propose and evaluate a zero-shot strategy for using LLMs as a mechanism to efficiently retrieve and summarize unstructured evidence in patient EHR.
  arXiv  Detail & Related papers  (2023-09-08T18:44:47Z)
• Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
  Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area. We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions. We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
  arXiv  Detail & Related papers  (2023-08-31T00:36:10Z)
• SPeC: A Soft Prompt-Based Calibration on Performance Variability of Large Language Model in Clinical Notes Summarization [50.01382938451978]
  We introduce a model-agnostic pipeline that employs soft prompts to diminish variance while preserving the advantages of prompt-based summarization. Experimental findings indicate that our method not only bolsters performance but also effectively curbs variance for various language models.
  arXiv  Detail & Related papers  (2023-03-23T04:47:46Z)

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.