[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-353705-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-353705-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","humanai-interaction-in-a-cancer-enriched-double-reading-breast-screening-cohort-diagnostic-accuracy-and-second-reader-behavior","Human–AI interaction in a cancer-enriched double-reading breast screening cohort - diagnostic accuracy and second-reader behavior","","Evaluate the impact of deploying AI as the first reader in a double-reading breast screening workflow and characterize second-reader behavior, including how disclosure of whether the first read was AI or human alters decisions. Use a retrospective cancer-enriched cohort (220 women, 95 cancers) with randomized case assignment and GEE logistic regression to estimate effects separately for first-reader accuracy and second-reader arbitration. Results assess sensitivity, specificity, recall, corrections, and overturning patterns.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/humanai-interaction-in-a-cancer-enriched-double-reading-breast-screening-cohort-diagnostic-accuracy-and-second-reader-behavior/353705/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/humanai-interaction-in-a-cancer-enriched-double-reading-breast-screening-cohort-diagnostic-accuracy-and-second-reader-behavior/353705.png","ImageObject",300,407,{"name":42,"@type":43},"Asher","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-05","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",11,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What was the primary objective of using AI as the first reader (R1) in this workflow?","Question",{"text":63,"@type":64},"To evaluate how deploying AI as R1 affects diagnostic performance within an unblinded double-reading breast screening workflow, and to quantify overall screening accuracy and discordance effects.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How were second-reader (R2) cases randomized in the study?",{"text":68,"@type":64},"For each R2, cases were randomized 1:1 to AI-first versus human-first, and independently to disclosure versus concealment of whether R1 was AI or human. R2 then could validate, dismiss, or add annotations.",{"name":70,"@type":61,"acceptedAnswer":71},"What effect did disclosure of R1 identity have on second-reader behavior?",{"text":72,"@type":64},"Disclosure that R1 was AI increased R2 corrections, with corrections rising from 13.6% to 19.1% (p = 0.029). The study also reported that second readers overturned AI-initiated errors more often than human-initiated ones.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},353705,1790910349,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":55,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":33,"preview_urls":146},687197207639,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Sossavi et al. Cancer Imaging (2026) 26:29 [https://doi.org/10.1186/s40644-026-00995-0](https://doi.org/10.1186/s40644-026-00995-0)  \nCancer Imaging  \nRESEARCH Open Access  \nHuman–AI interaction in a cancer-enriched double-reading breast screening cohort: diagnostic accuracy and second-reader behavior  \nEloïse Sossavi1, Mickaël Tardy2,3, Florie Hurstel4, Jean Schwartz1, Antoine Wackenthaler1, Claire Harter1, Julien Uttner 1, Mélanie Mollion1, Marie-Françoise Bretz1 and Sébastien Molière1,5,6*  \nAbstract  \nRationale and objectives To evaluate the impact of deploying AI as the first reader (R1) in a double-reading breastscreening workflow and to characterize second-reader (R2) behavior—including the effect of disclosing whether R1 was AI or human.  \nMaterials and methods This retrospective study used a cancer-enriched cohort of 220 women (95 cancers), with prevalence-weighted analyses performed to approximate population screening metrics. Five radiologists and one commercially available AI (Breast-SlimView®, Hera-MI) each served as R1; four radiologists served as R2 . For each R2, cases were randomized 1:1 to AI-first versus human-first and, independently, to disclosure versus concealment of R1 identity. R2 could validate, dismiss, or add annotations. The primary endpoint was final decision correctness by breast. We used GEE logistic regression to estimate the overall effect of using AI as the first reader and to isolate secondreader behavior independently of first-reader accuracy.  \nResults At the prespecified R1 operating point, AI had sensitivity/specificity/accuracy of 85 . 2%/79 . 5%/80 . 8% versus 84. 3%/84 . 5%/85 . 0% for human R1s; crude final accuracy was lower for AI-first. At 0 . 6% prevalence, AI-first yielded higher recalls (20 . 8% vs. 16. 8%) with slightly lower PPV (2 . 7% vs. 3. 0%) . Conditioning on R1 correctness, R2s were approximately twice more likely to overturn an incorrect AI-initiated opinion than an incorrect human-initiated one (OR ≈ 2. 05, p \u003C 0. 001) . Disclosure that R1 was AI increased R2 corrections (from 13. 6% to 19. 1%, p = 0 . 029) . Thirteen AI-true-positive cues were dismissed by R2 .  \nConclusions At this operating point, AI-first reduced crude accuracy due to lower specificity, yet reader-behavior analyses indicate greater scrutiny of AI-initiated opinions. Protocol, threshold, and user-interface choices may raise specificity while preserving beneficial human–AI dynamics.  \n*Correspondence:  \nSébastien Molière [sebastien.moliere@chru-strasbourg.fr](sebastien.moliere@chru-strasbourg.fr)  \nFull list of author information is available at the end of the article  \n© The Author(s) 2026. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creativecommons.org/licenses/by/4.0/](http://creativecommons.org/licenses/by/4.0/. The)[. The](http://creativecommons.org/licenses/by/4.0/. The)[ ](http://creativecommons.org/licenses/by/4.0/. The)Creative Commons Public Domain Dedication waiver ([http://creativecommons.org/publicdomain/zero/1.0/](http://creativecommons.org/publicdomain/zero/1.0/)) applies to the data made available in this article, unless otherwise stated in a credit line to the data.  \nHighlights  \n• In a double-reading breast screening simulat","cbCaimHDKc0bDFjE","https://ap.wps.com/l/cbCaimHDKc0bDFjE","pdf",1960542,"English","# Introduction\n## Study aims and rationale\n# Materials and methods\n## Cohort and reader design\n## Randomization and disclosure\n## Statistical approach\n# Results\n## Performance at the prespecified operating point\n## Recall and PPV effects\n## Reader arbitration and correction behavior\n# Conclusions\n## Implications for specificity and UI choices","[{\"question\":\"What was the primary objective of using AI as the first reader (R1) in this workflow?\",\"answer\":\"To evaluate how deploying AI as R1 affects diagnostic performance within an unblinded double-reading breast screening workflow, and to quantify overall screening accuracy and discordance effects.\"},{\"question\":\"How were second-reader (R2) cases randomized in the study?\",\"answer\":\"For each R2, cases were randomized 1:1 to AI-first versus human-first, and independently to disclosure versus concealment of whether R1 was AI or human. R2 then could validate, dismiss, or add annotations.\"},{\"question\":\"What effect did disclosure of R1 identity have on second-reader behavior?\",\"answer\":\"Disclosure that R1 was AI increased R2 corrections, with corrections rising from 13.6% to 19.1% (p = 0.029). The study also reported that second readers overturned AI-initiated errors more often than human-initiated ones.\"}]","Human–AI interaction in a cancer-enriched double-reading breast screening cohort - diagnostic accuracy and second-reader behavior | PDF",1790106837,28,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/c55f195817e6d03e6b5c7ab70bc0ecc3.webp",983,1310,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/8ee1804c00b27987700430ef40c01623.webp",982,1309,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/d7195e39acfe166305afd7550b94564e.webp",981,1308,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/4c04f8b22558d829272e4b8819fb9354.webp",980,1306]