[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-362500-105":59,"doc-detail-362500-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","a-novel-statistical-framework-for-quantifying-risks-and-benefits-of-ai-automation-in-screening-mammography","A novel statistical framework for quantifying risks and benefits of AI automation in screening mammography","","AI has been proposed as a triage or “rule-out” tool to lessen radiologist workload, yet the choice of an AI “rule-out” threshold remains unclear. A retrospective single-site analysis of 114,229 bilateral 2D digital screening mammograms (2006–2023) used Mirai to generate a 1-year risk score. Two thresholds (0.2 and 0.05) were evaluated with metrics for false omission probabilities and caseload reduction, enabling quantification of workload–diagnostic trade-offs. Results show markedly different missed-cancer counts and caseload reduction rates.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/a-novel-statistical-framework-for-quantifying-risks-and-benefits-of-ai-automation-in-screening-mammography/362500/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/a-novel-statistical-framework-for-quantifying-risks-and-benefits-of-ai-automation-in-screening-mammography/362500.png","ImageObject",300,407,{"name":92,"@type":93},"WPS_1786070896","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-10","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the study address about AI rule-out thresholds?","Question",{"text":112,"@type":113},"It addresses the uncertainty in how to determine an optimal AI “rule-out” threshold for screening mammography triage while balancing workload reduction and diagnostic risk.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which data and AI model were used in the analysis?",{"text":117,"@type":113},"The study analyzed 114,229 bilateral 2D digital screening mammograms from 2006–2023 at one site and assigned each exam an AI 1-year risk score using Mirai, an open-source deep-learning model.",{"name":119,"@type":110,"acceptedAnswer":120},"How were thresholds compared and what metrics were used?",{"text":121,"@type":113},"Two risk-score thresholds (0.2 and 0.05) were compared using caseload reduction (CRR) and false omission–based error rates (G-FOR, N-FOR, and AN-FOR at 30%), which estimate missed cancer probabilities under different rule-out scenarios.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},362500,1790688459,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":39,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":19,"preview_urls":146},549768072016,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","OPEN ACCESS  \nCitation: Bernstein MH, Chung M, Yala A, Baird GL (2026) A novel statistical framework for quantifying risks and benefits of AI automation in screening mammography. PLOS Digit Health 5(2): e0001231. [https://doi.org/10.1371/](https://doi.org/10.1371/)[ ](https://doi.org/10.1371/)[journal.pdig.0001231](journal.pdig.0001231)  \nEditor: Matthew Watson, Durham University, UNITED KINGDOM OF GREAT BRITAIN AND NORTHERN IRELAND  \nReceived: August 6, 2025  \nAccepted: January 26, 2026  \nPublished: February 26, 2026  \nCopyright: © 2026 Bernstein et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.  \nData availability statement: Code for statistical analysis from this study is available at [https://osf.io/ve2m8/overview](https://osf.io/ve2m8/overview).  \nFunding: The author(s) received no specific funding for this work.  \nRESEARCH ARTICLE  \nA novel statistical framework for quantifying risks and benefits of AI automation in screening mammography  \nMichael H. Bernstein1☯, Maggie Chung2☯*, Adam Yala3, Grayson L. Baird1  \n1 Brown Radiology Human Factors Lab, Department of Radiology, The Warren Alpert Medical School, Brown University, and Brown University Health, Providence, Rhode Island, United States of America,  \n2 Department of Radiology and Biomedical Imaging, University of California, San Francisco, California, United States of America, 3 Program in Computational Precision Health, University of California, Berkeley and University of California, San Francisco, California, United States of America  \n☯ These authors contributed equally to this work.  \n* [Maggie.chung@ucsf.edu](Maggie.chung@ucsf.edu)  \nAbstract  \nAI has been proposed as a triage or “rule-out” device to reduce radiologist workload, but it is presently unclear how an AI “rule-out” threshold should be determined. We present a framework for determining an optimal threshold. Using a retrospective study design, 114,229 bilateral 2D digital screening mammograms were analyzed from 2006-2023 at a single study site. All mammograms were given an AI score using Mirai, an open-source deep-learning model which provides a 1-year risk score. Several metrics were examined using two thresholds for determining ruled out versus retained cases: 1) Caseload Reduction Rate (CRR; percent of caseload reduced due to rule-out), 2) Gross AI False Omission Rate (G-FOR; probability of a patient having breast cancer if ruled out), 3) AI Net False Omission Rate (N-FOR; probability of a patient having breast cancer if ruled out and the radiologist would have caught in standard care [i.e. , no triage]), 4) AI Adjusted Net False Omission Rate (30%)(AN-FOR[30%]; N-FOR adjusted for the hypothetical scenario where radiologists detect an extra 30% of breast cancers among AI retained cases) . The two thresholds were risk scores of 0.2 (Youden’s J) and 0.05 (AN-FOR[30%]=0) . The former is mathematically optimal; the latter reflects a threshold where AI “rule-out” does not introduce any total increase in False Negatives. At the 0.20 threshold, G-FOR, N-FOR, and AN-FOR (30%) are 0.26%, 0. 17%, and 0. 14%, respectively (223, 141, and 121, respectively, missed cancer cases) and CRR = 75% . At the 0.05 threshold, the G-FOR, N-FOR, and AN-FOR (30%) are 0. 12%, 0.07%, and 0.00%(49, 30, and 0, respectively, missed cancer cases) and CRR = 36% . We demonstrate how radiology practices can consider the trade-offs of using different AI scores as “rule-out” thresholds. At the AN-FOR rate of 30%, the Youden’s J threshold results in 121 additional missed cancers for a 75% caseload reduction. We estimate no additional missed cancers at a 36% caseload reduction.  \nPLOS Digital Health | [https://doi.org/10.1371/journal.pdig.0001231](https://doi.org/10.1371/journal.pdig.0001231) February 26, 2026 1 / 14  \nCompeting interests: I have r","cbCainm7hvZ7gCwc","https://ap.wps.com/l/cbCainm7hvZ7gCwc","pdf",1031822,14,"English","# Abstract\n## Metrics for threshold evaluation\n## Threshold comparison and outcomes\n## Workload–diagnostic trade-offs","[{\"question\":\"What problem does the study address about AI rule-out thresholds?\",\"answer\":\"It addresses the uncertainty in how to determine an optimal AI “rule-out” threshold for screening mammography triage while balancing workload reduction and diagnostic risk.\"},{\"question\":\"Which data and AI model were used in the analysis?\",\"answer\":\"The study analyzed 114,229 bilateral 2D digital screening mammograms from 2006–2023 at one site and assigned each exam an AI 1-year risk score using Mirai, an open-source deep-learning model.\"},{\"question\":\"How were thresholds compared and what metrics were used?\",\"answer\":\"Two risk-score thresholds (0.2 and 0.05) were compared using caseload reduction (CRR) and false omission–based error rates (G-FOR, N-FOR, and AN-FOR at 30%), which estimate missed cancer probabilities under different rule-out scenarios.\"}]","A novel statistical framework for quantifying risks and benefits of AI automation in screening mammography | PDF",1790147987,35,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/03a747215a796d122cdde75497ffa793.webp",983,1272,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/3c1d23c35dd88ae033d18fb060f30684.webp",982,1270,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/2fac5ce82f657dac7e629f9b49add4b3.webp",981,1269,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/9c77a139e471d98a15f21910bbb013a3.webp",980,1268]