{"id":1510,"date":"2024-05-17T20:11:14","date_gmt":"2024-05-17T20:11:14","guid":{"rendered":"https:\/\/www.lunit.io\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/"},"modified":"2025-11-02T12:36:50","modified_gmt":"2025-11-02T12:36:50","slug":"performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload","status":"publish","type":"publication","link":"https:\/\/lunit.supremeclients.com\/en\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/","title":{"rendered":"Performance of AI to exclude normal chest radiographs to reduce radiologists\u2019 workload"},"content":{"rendered":"<h3>Performance of AI to exclude normal chest radiographs to reduce radiologists\u2019 workload<\/h3>\n<p>Steven Schalekamp, Kicky van Leeuwen, Erdi Calli, Keelin Murphy, Matthieu Rutten, Bram Geurts, Liesbeth Peters-Bax, Bram van Ginneken &amp; Mathias Prokop<\/p>\n<p><strong>European Radiology, 2024<\/strong><\/p>\n<p><strong>Abstract<\/strong><br \/>\n<strong>Introduction<\/strong><br \/>\nThis study investigates the performance of a commercially available artificial intelligence (AI) system to identify normal chest radiographs and its potential to reduce radiologist workload.<\/p>\n<p><strong>Methods<\/strong><br \/>\nRetrospective analysis included consecutive chest radiographs from two medical centers between Oct 1, 2016 and Oct 14, 2016. Exclusions comprised follow-up exams within the inclusion period, bedside radiographs, incomplete images, imported radiographs, and pediatric radiographs. Three chest radiologists categorized findings into normal, clinically irrelevant, clinically relevant, urgent, and critical. A commercial AI system processed all radiographs, scoring 10 chest abnormalities on a 0\u2013100 confidence scale. AI system performance was evaluated using the area under the ROC curve (AUC), assessing the detection of normal radiographs. Sensitivity was calculated for the default and a conservative operating point. the detection of negative predictive value (NPV) for urgent and critical findings, as well as the potential workload reduction, was calculated.<\/p>\n<p><strong>Results<\/strong><br \/>\nA total of 2603 radiographs were acquired in 2141 unique patients. Post-exclusion, 1670 radiographs were analyzed. Categories included 479 normal, 332 clinically irrelevant, 339 clinically relevant, 501 urgent, and 19 critical findings. The AI system achieved an AUC of 0.92. Sensitivity for normal radiographs was 92% at default and 53% at the conservative operating point. At the conservative operating point, NPV was 98% for urgent and critical findings, and could result in a 15% workload reduction.<\/p>\n<p><strong>Conclusion<\/strong><br \/>\nA commercially available AI system effectively identifies normal chest radiographs and holds the potential to lessen radiologists\u2019 workload by omitting half of the normal exams from reporting.<\/p>\n<p style=\"text-align: center;\"><a href=\"https:\/\/link.springer.com\/article\/10.1007\/s00330-024-10794-5?utm_source=rct_congratemailt&amp;utm_medium=email&amp;utm_campaign=oa_20240517&amp;utm_content=10.1007%2Fs00330-024-10794-5\"><strong>Read the full paper<\/strong><\/a><\/p>\n","protected":false},"featured_media":0,"template":"","publication-oncology":[],"publication-region":[89],"publication-type":[],"radiology":[104,105,96],"class_list":["post-1510","publication","type-publication","status-publish","hentry","publication-region-europe","radiology-chest","radiology-enhancing-workflow-efficiency-chest","radiology-lunit-insight"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.6 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Performance of AI to exclude normal chest radiographs to reduce radiologists\u2019 workload - Lunit<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/lunit.supremeclients.com\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Performance of AI to exclude normal chest radiographs to reduce radiologists\u2019 workload - Lunit\" \/>\n<meta property=\"og:description\" content=\"Performance of AI to exclude normal chest radiographs to reduce radiologists\u2019 workload Steven Schalekamp, Kicky van Leeuwen, Erdi Calli, Keelin Murphy, Matthieu Rutten, Bram Geurts, Liesbeth Peters-Bax, Bram van Ginneken &amp; Mathias Prokop European Radiology, 2024 Abstract Introduction This study investigates the performance of a commercially available artificial intelligence (AI) system to identify normal chest [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/lunit.supremeclients.com\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/\" \/>\n<meta property=\"og:site_name\" content=\"Lunit\" \/>\n<meta property=\"article:modified_time\" content=\"2025-11-02T12:36:50+00:00\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@lunit_ai\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/lunit.supremeclients.com\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/\",\"url\":\"https:\/\/lunit.supremeclients.com\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/\",\"name\":\"Performance of AI to exclude normal chest radiographs to reduce radiologists\u2019 workload - Lunit\",\"isPartOf\":{\"@id\":\"https:\/\/lunit.supremeclients.com\/en\/#website\"},\"datePublished\":\"2024-05-17T20:11:14+00:00\",\"dateModified\":\"2025-11-02T12:36:50+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/lunit.supremeclients.com\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/lunit.supremeclients.com\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/lunit.supremeclients.com\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/lunit.supremeclients.com\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Performance of AI to exclude normal chest radiographs to reduce radiologists\u2019 workload\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/lunit.supremeclients.com\/en\/#website\",\"url\":\"https:\/\/lunit.supremeclients.com\/en\/\",\"name\":\"Lunit\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/lunit.supremeclients.com\/en\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/lunit.supremeclients.com\/en\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/lunit.supremeclients.com\/en\/#organization\",\"name\":\"Lunit\",\"url\":\"https:\/\/lunit.supremeclients.com\/en\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/lunit.supremeclients.com\/en\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/lunit.supremeclients.com\/en\/wp-content\/uploads\/2025\/10\/Logo-black.svg\",\"contentUrl\":\"https:\/\/lunit.supremeclients.com\/en\/wp-content\/uploads\/2025\/10\/Logo-black.svg\",\"width\":189,\"height\":52,\"caption\":\"Lunit\"},\"image\":{\"@id\":\"https:\/\/lunit.supremeclients.com\/en\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/lunit_ai\",\"https:\/\/www.linkedin.com\/company\/lunit-inc\",\"https:\/\/x.com\/lunitoncology\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Performance of AI to exclude normal chest radiographs to reduce radiologists\u2019 workload - Lunit","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/lunit.supremeclients.com\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/","og_locale":"en_US","og_type":"article","og_title":"Performance of AI to exclude normal chest radiographs to reduce radiologists\u2019 workload - Lunit","og_description":"Performance of AI to exclude normal chest radiographs to reduce radiologists\u2019 workload Steven Schalekamp, Kicky van Leeuwen, Erdi Calli, Keelin Murphy, Matthieu Rutten, Bram Geurts, Liesbeth Peters-Bax, Bram van Ginneken &amp; Mathias Prokop European Radiology, 2024 Abstract Introduction This study investigates the performance of a commercially available artificial intelligence (AI) system to identify normal chest [&hellip;]","og_url":"https:\/\/lunit.supremeclients.com\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/","og_site_name":"Lunit","article_modified_time":"2025-11-02T12:36:50+00:00","twitter_card":"summary_large_image","twitter_site":"@lunit_ai","twitter_misc":{"Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/lunit.supremeclients.com\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/","url":"https:\/\/lunit.supremeclients.com\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/","name":"Performance of AI to exclude normal chest radiographs to reduce radiologists\u2019 workload - Lunit","isPartOf":{"@id":"https:\/\/lunit.supremeclients.com\/en\/#website"},"datePublished":"2024-05-17T20:11:14+00:00","dateModified":"2025-11-02T12:36:50+00:00","breadcrumb":{"@id":"https:\/\/lunit.supremeclients.com\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/lunit.supremeclients.com\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/lunit.supremeclients.com\/publication\/performance-of-ai-to-exclude-normal-chest-radiographs-to-reduce-radiologists-workload\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/lunit.supremeclients.com\/en\/"},{"@type":"ListItem","position":2,"name":"Performance of AI to exclude normal chest radiographs to reduce radiologists\u2019 workload"}]},{"@type":"WebSite","@id":"https:\/\/lunit.supremeclients.com\/en\/#website","url":"https:\/\/lunit.supremeclients.com\/en\/","name":"Lunit","description":"","publisher":{"@id":"https:\/\/lunit.supremeclients.com\/en\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/lunit.supremeclients.com\/en\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/lunit.supremeclients.com\/en\/#organization","name":"Lunit","url":"https:\/\/lunit.supremeclients.com\/en\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/lunit.supremeclients.com\/en\/#\/schema\/logo\/image\/","url":"https:\/\/lunit.supremeclients.com\/en\/wp-content\/uploads\/2025\/10\/Logo-black.svg","contentUrl":"https:\/\/lunit.supremeclients.com\/en\/wp-content\/uploads\/2025\/10\/Logo-black.svg","width":189,"height":52,"caption":"Lunit"},"image":{"@id":"https:\/\/lunit.supremeclients.com\/en\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/lunit_ai","https:\/\/www.linkedin.com\/company\/lunit-inc","https:\/\/x.com\/lunitoncology"]}]}},"_links":{"self":[{"href":"https:\/\/lunit.supremeclients.com\/en\/wp-json\/wp\/v2\/publication\/1510","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lunit.supremeclients.com\/en\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lunit.supremeclients.com\/en\/wp-json\/wp\/v2\/types\/publication"}],"wp:attachment":[{"href":"https:\/\/lunit.supremeclients.com\/en\/wp-json\/wp\/v2\/media?parent=1510"}],"wp:term":[{"taxonomy":"publication-oncology","embeddable":true,"href":"https:\/\/lunit.supremeclients.com\/en\/wp-json\/wp\/v2\/publication-oncology?post=1510"},{"taxonomy":"publication-region","embeddable":true,"href":"https:\/\/lunit.supremeclients.com\/en\/wp-json\/wp\/v2\/publication-region?post=1510"},{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lunit.supremeclients.com\/en\/wp-json\/wp\/v2\/publication-type?post=1510"},{"taxonomy":"radiology","embeddable":true,"href":"https:\/\/lunit.supremeclients.com\/en\/wp-json\/wp\/v2\/radiology?post=1510"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}