People-Centred Medical Image Analysis

arXiv cs.LG / 5/1/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

Medical AI has achieved high diagnostic accuracy, but adoption in clinical settings remains limited due to inadequate optimization for fairness across patient populations and weak integration into clinical workflows.
The article argues that fairness and workflow integration are tightly coupled in real hospitals and must be optimized together, accounting for practical constraints such as limited clinician availability.
It proposes People-Centred Medical Image Analysis (PecMan), a human–AI framework that uses a dynamic gating mechanism to route cases to the AI, clinicians, or both while respecting clinician workload limits.
The paper introduces the Fairness and Human-Centred AI (FairHAI) benchmark to evaluate trade-offs among diagnostic accuracy, fairness, and clinician workload, and reports that PecMan outperforms prior methods on this benchmark.
The authors note that code will be released after the paper is accepted, aiming to enable more trustworthy and clinically workable AI systems.

Abstract

Recent advances in data-centric medical AI have produced highly accurate diagnostic systems, but the emphasis on data curation and performance metrics has not translated into widespread clinical adoption. We conjecture that this limited uptake stems from insufficient attention dedicated to the optimisation of fair performance across diverse patient populations and to workflow integration: performance biases can create regulatory barriers, and poorly integrated automation can disrupt clinical routines, degrade the quality of human-AI collaboration, and reduce clinicians' willingness to adopt AI tools. Prior work on workflow integration (e.g., Learning to Defer (L2D) and Learning to Complement (L2C)) and AI fairness has typically examined these challenges in isolation, overlooking their natural interdependence and the practical constraints of clinical environments, such as restricted clinician availability. We propose People-Centred Medical Image Analysis (PecMan), a human-AI framework that jointly optimises fairness, diagnostic accuracy, and workflow effectiveness through a dynamic gating mechanism that assigns cases to AI, clinicians, or both under clinician workload constraints. We also introduce the Fairness and Human-Centred AI (FairHAI) benchmark for evaluating trade-offs between accuracy, fairness, and clinician workload. Experiments using this benchmark show that PecMan consistently outperforms existing methods, paving the way for more trustworthy and clinically viable AI systems. Code will be available upon paper acceptance.