{"paper":{"title":"People-Centred Medical Image Analysis via Fairness-Aware Human-AI Cooperation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"PecMan uses a dynamic gating mechanism to jointly optimize fairness, accuracy, and clinician workload in medical image analysis.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cuong Nguyen, David Rosewarne, Gustavo Carneiro, Kevin Wells, Milad Masroor, Tahir Hassan, Thanh-Toan Do, Yuanhong Chen, Zheng Zhang","submitted_at":"2026-04-28T22:13:36Z","abstract_excerpt":"Machine learning models for medical image analysis often exhibit subgroup-dependent performance, which impacts how decisions should be allocated between automated systems and human experts under limited resources. Prior work on AI fairness and human-AI cooperation, including learning to defer (L2D) and learning to complement (L2C), typically addresses these problems in isolation. We propose People-Centred Medical Image Analysis (PecMan), a framework for fairness-aware human-AI co-operative classification that jointly models subgroup-dependent reliability, decision allocation, and collaborative"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments using this benchmark show that PecMan consistently outperforms existing methods, paving the way for more trustworthy and clinically viable AI systems.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That real clinical environments have restricted clinician availability that can be accurately modeled as a dynamic constraint without introducing new practical barriers or unmodeled workflow disruptions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PecMan is a human-AI framework that jointly optimizes fairness, diagnostic accuracy, and workflow effectiveness in medical image analysis under clinician workload constraints, outperforming prior methods on the new FairHAI benchmark.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PecMan uses a dynamic gating mechanism to jointly optimize fairness, accuracy, and clinician workload in medical image analysis.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1decf9cae8ae324b6fcbeee0258f38ab59ea13bcb32c16f850ca6f79d3d82dc6"},"source":{"id":"2604.26991","kind":"arxiv","version":2},"verdict":{"id":"5bac617a-9929-4e29-bd1b-96787c4c055a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T16:30:00.962720Z","strongest_claim":"Experiments using this benchmark show that PecMan consistently outperforms existing methods, paving the way for more trustworthy and clinically viable AI systems.","one_line_summary":"PecMan is a human-AI framework that jointly optimizes fairness, diagnostic accuracy, and workflow effectiveness in medical image analysis under clinician workload constraints, outperforming prior methods on the new FairHAI benchmark.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That real clinical environments have restricted clinician availability that can be accurately modeled as a dynamic constraint without introducing new practical barriers or unmodeled workflow disruptions.","pith_extraction_headline":"PecMan uses a dynamic gating mechanism to jointly optimize fairness, accuracy, and clinician workload in medical image analysis."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.26991/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T03:34:17.338072Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T20:26:27.687045Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"bb9f709ae7be418d3b96153ac159aef33130d6b16f2acf0597f95c05a91916cf"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}