Leveraging Imperfection with MEDLEY A Multi-Model Approach Harnessing Bias in Medical AI

• URL: http://arxiv.org/abs/2508.21648v1
• Date: Fri, 29 Aug 2025 14:12:03 GMT
• Title: Leveraging Imperfection with MEDLEY A Multi-Model Approach Harnessing Bias in Medical AI
• Abstract summary: Bias in medical artificial intelligence is conventionally viewed as a defect requiring elimination.<n>We propose MEDLEY, a conceptual framework that orchestrates multiple AI models while preserving their diverse outputs.<n>Unlike traditional approaches that suppress disagreement, MEDLEY documents model-specific biases as potential strengths.
• Score: 42.798415096963396
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Bias in medical artificial intelligence is conventionally viewed as a defect requiring elimination. However, human reasoning inherently incorporates biases shaped by education, culture, and experience, suggesting their presence may be inevitable and potentially valuable. We propose MEDLEY (Medical Ensemble Diagnostic system with Leveraged diversitY), a conceptual framework that orchestrates multiple AI models while preserving their diverse outputs rather than collapsing them into a consensus. Unlike traditional approaches that suppress disagreement, MEDLEY documents model-specific biases as potential strengths and treats hallucinations as provisional hypotheses for clinician verification. A proof-of-concept demonstrator was developed using over 30 large language models, creating a minimum viable product that preserved both consensus and minority views in synthetic cases, making diagnostic uncertainty and latent biases transparent for clinical oversight. While not yet a validated clinical tool, the demonstration illustrates how structured diversity can enhance medical reasoning under clinician supervision. By reframing AI imperfection as a resource, MEDLEY offers a paradigm shift that opens new regulatory, ethical, and innovation pathways for developing trustworthy medical AI systems.

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)
• Rethinking Artificial Intelligence in Medical Imaging: Assumptions, Reality, and Reframing [29.25526289599026]
  We argue that a decade of intense research has not translated into proportionate bedside impact.<n>This Perspective identifies six interconnected dimensions of this misalignment.<n>We propose a vision of agentic, physician-aligned AI that extends, rather than replaces, clinical judgment.
  arXiv  Detail & Related papers  (2026-07-29T19:55:49Z)
• ConceptM$^3$oE: Concept-Guided Multimodal Mixture of Experts for Interpretable Computational Pathology [33.27476666910628]
  ConceptM$3$oE embeds concept formation directly within interaction-aware mixture-of-experts pathways.<n>The architecture decomposes evidence into modality-specific, redundant, and synergistic experts, which are then projected into structured concept bottlenecks.<n>In data-limited regimes, ConceptM$3$oE improves limited-data performance, increasing macro-F1 from 56.41% to 66.70% at small training sizes.
  arXiv  Detail & Related papers  (2026-05-23T04:55:16Z)
• What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models [3.552218268811112]
  Medicine is inherently pluralistic. Principles such as autonomy, beneficence, nonmaleficence, and justice routinely conflict.<n>Good clinical practice navigates these tensions in concert with each patient's values rather than imposing a single ethical stance.<n>We present a framework for auditing value pluralism in medical AI, comprising a benchmark of clinician-verified dilemmas and an attribution method that recovers value priorities directly from decisions.
  arXiv  Detail & Related papers  (2026-05-18T17:56:13Z)
• Medical Model Synthesis Architectures: A Case Study [72.46211022258122]
  Current AI systems struggle with calibrated reasoning under uncertainty.<n>We propose a framework for AI systems that can make practically useful but formally transparent clinical predictions under uncertainty.<n>We show how an initial proof-of-concept of this framework can be used for differential diagnosis.
  arXiv  Detail & Related papers  (2026-05-10T19:30:16Z)
• Dialectic-Med: Mitigating Diagnostic Hallucinations via Counterfactual Adversarial Multi-Agent Debate [2.645243404278707]
  We propose Dialectic-Med, a multi-agent framework that enforces diagnostic rigor through adversarial dialectics.<n>By explicitly modeling the cognitive process of falsification, our framework guarantees that diagnostic reasoning is tightly grounded in verified visual regions.
  arXiv  Detail & Related papers  (2026-04-13T10:09:36Z)
• Bridging AI and Clinical Reasoning: Abductive Explanations for Alignment on Critical Symptoms [5.220940151628734]
  Key challenge is that AI reasoning diverges from structured clinical frameworks.<n>We leverage formal abductive explanations, which offer consistent, guaranteed reasoning.<n>This enables a clear understanding of AI decision-making and allows alignment with clinical reasoning.
  arXiv  Detail & Related papers  (2026-02-15T04:27:59Z)
• Adaptive Diagnostic Reasoning Framework for Pathology with Multimodal Large Language Models [34.28963665009494]
  We present RECAP-PATH, an interpretable framework that establishes a self-learning paradigm.<n>It shifts off-the-shelf multimodal large language models from passive pattern recognition to evidence-linked diagnostic reasoning.<n>This self-learning approach requires only small labeled sets and no white-box access or weight updates to generate cancer diagnoses.
  arXiv  Detail & Related papers  (2025-11-15T03:06:59Z)
• BiomedXPro: Prompt Optimization for Explainable Diagnosis with Biomedical Vision Language Models [0.16419687521433918]
  We introduce BiomedXPro, a framework that generates a diverse ensemble of interpretable natural-language prompts for disease diagnosis.<n> Experiments show that BiomedXPro consistently outperforms state-of-the-art prompt-tuning methods.<n>By producing a diverse ensemble of interpretable prompts, BiomedXPro provides a verifiable basis for model predictions.
  arXiv  Detail & Related papers  (2025-10-17T17:58:31Z)
• RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis [56.373297358647655]
  Retrieval-Augmented Diagnosis (RAD) is a novel framework that injects external knowledge into multimodal models directly on downstream tasks.<n>RAD operates through three key mechanisms: retrieval and refinement of disease-centered knowledge from multiple medical sources, a guideline-enhanced contrastive loss transformer, and a dual decoder.
  arXiv  Detail & Related papers  (2025-09-24T10:36:14Z)
• On Arbitrary Predictions from Equally Valid Models [49.56463611078044]
  Model multiplicity refers to multiple machine learning models that admit conflicting predictions for the same patient.<n>We show that even small ensembles can mitigate/eliminate predictive multiplicity in practice.
  arXiv  Detail & Related papers  (2025-07-25T16:15:59Z)
• Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models [52.2001050216955]
  Existing methods aim to enhance the performance of Medical Vision Language Model (MedVLM) by adjusting model structure, fine-tuning with high-quality data, or through preference fine-tuning.<n>We propose an expert-in-the-loop framework named Expert-Controlled-Free Guidance (Expert-CFG) to align MedVLM with clinical expertise without additional training.
  arXiv  Detail & Related papers  (2025-07-12T09:03:30Z)
• MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models [20.781551849965357]
  We introduce MediConfusion, a challenging medical Visual Question Answering (VQA) benchmark dataset.<n>We reveal that state-of-the-art models are easily confused by image pairs that are otherwise visually dissimilar and clearly distinct for medical experts.<n>We also extract common patterns of model failure that may help the design of a new generation of more trustworthy and reliable MLLMs in healthcare.
  arXiv  Detail & Related papers  (2024-09-23T18:59:37Z)
• Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models [49.95603725998561]
  We propose a new paradigm to build robust and interpretable medical image classifiers with natural language concepts. Specifically, we first query clinical concepts from GPT-4, then transform latent image features into explicit concepts with a vision-language model.
  arXiv  Detail & Related papers  (2023-10-04T21:57:09Z)
• Ambiguous Medical Image Segmentation using Diffusion Models [60.378180265885945]
  We introduce a single diffusion model-based approach that produces multiple plausible outputs by learning a distribution over group insights. Our proposed model generates a distribution of segmentation masks by leveraging the inherent sampling process of diffusion. Comprehensive results show that our proposed approach outperforms existing state-of-the-art ambiguous segmentation networks.
  arXiv  Detail & Related papers  (2023-04-10T17:58:22Z)
• Context-dependent Explainability and Contestability for Trustworthy Medical Artificial Intelligence: Misclassification Identification of Morbidity Recognition Models in Preterm Infants [0.0]
  Explainable AI (XAI) aims to address this requirement by clarifying AI reasoning to support the end users. We built our methodology on three main pillars: decomposing the feature set by leveraging clinical context latent space, assessing the clinical association of global explanations, and Latent Space Similarity (LSS) based local explanations.
  arXiv  Detail & Related papers  (2022-12-17T07:59:09Z)
• Representational Ethical Model Calibration [0.7078141380481605]
  Epistem equity is the comparative fidelity of intelligence in decision-making. No general framework for its quantification, let alone assurance, exists. We introduce a comprehensive framework for Representational Ethical Model.
  arXiv  Detail & Related papers  (2022-07-25T10:33:39Z)
• Semi-Supervised Variational Reasoning for Medical Dialogue Generation [70.838542865384]
  Two key characteristics are relevant for medical dialogue generation: patient states and physician actions. We propose an end-to-end variational reasoning approach to medical dialogue generation. A physician policy network composed of an action-classifier and two reasoning detectors is proposed for augmented reasoning ability.
  arXiv  Detail & Related papers  (2021-05-13T04:14:35Z)

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.