People-Centred Medical Image Analysis

2026-04-28

AI Summary

This work addresses the limited clinical deployment of medical AI, which suffers from insufficient fairness and poor integration into clinical workflows, leading to performance disparities and suboptimal human–AI collaboration. To tackle these challenges, we propose PecMan, a novel framework that, for the first time, jointly models fairness, diagnostic accuracy, and clinical workflow efficiency. PecMan employs a dynamic gating mechanism to intelligently route cases to either the AI, the clinician, or a collaborative decision-making process, optimizing the trade-offs among these three objectives under constrained physician workload. Integrating insights from Learning to Defer and Learning to Complement while incorporating explicit fairness constraints, PecMan achieves superior performance on our newly established FairHAI benchmark, striking a better balance among fairness, accuracy, and clinician burden, thereby enhancing the trustworthiness and practical utility of AI systems in clinical settings.

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.

Problem

• medical AI
• fairness
• workflow integration
• clinical adoption
• human-AI collaboration

Innovation

• People-Centred AI
• Medical Image Analysis
• Fairness
• Workflow Integration
• Dynamic Gating