Chest X-rays remain a simple and widely used tool for screening diseases such as lung cancer. In Japan, they are part of mandatory workplace health examinations. However, interpreting them requires significant expertise. To minimize errors, two doctors typically analyze each image, which increases their workload.<\/p>\n
A recent study evaluated whether artificial intelligence software could take on the role of the first reader in this double-reading system. Researchers analyzed over 320,000 X-rays taken between 2018 and 2020. Among cases suspected of lung cancer, three AI models were tested. The result: these tools detected between 62% and 77% of abnormalities, compared to 59% for human doctors. Even when focusing solely on lung nodules, the most common, AI performance remained superior, with detection rates ranging from 64% to 76%, whereas doctors achieved 59%.<\/p>\n
Artificial intelligence thus demonstrated at least equivalent, if not better, capability compared to professionals. However, it generated more false alarms. While doctors produced very few, the software identified between 6 and 15 false positives per 100 exams, depending on the model used. These errors often occur when normal structures, such as ribs or blood vessels, are mistaken for lesions.<\/p>\n
These results suggest that AI could indeed replace the first reader in screening. This would reduce the doctors’ workload while maintaining diagnostic quality. However, the subtlest or smallest nodules remain a challenge for these tools. Increased vigilance from the second human reader would therefore be necessary for difficult cases.<\/p>\n
This approach could standardize interpretations and limit variations based on practitioners’ experience. Further studies in multiple medical centers will be needed to confirm these benefits and assess the impact on healthcare organization. The goal is to gradually integrate these technologies into routine practice without sacrificing screening accuracy.<\/p>\n
DOI:<\/strong> https:\/\/doi.org\/10.1007\/s11604-026-01973-z<\/a><\/p>\n Title:<\/strong> Can AI substitute the first reader in chest radiograph screening? A retrospective non-inferiority evaluation<\/p>\n Journal:<\/strong> Japanese Journal of Radiology<\/p>\n Publisher:<\/strong> Springer Science and Business Media LLC<\/p>\n Authors:<\/strong> Kotaro Yoshida; Atsushi Takamatsu; Rie Tanaka; Tetsuo Matsunaga; Antoine Choppin; Aya Tonouchi; Satoshi Kobayashi; Takeshi Kobayashi<\/p>\n","protected":false},"excerpt":{"rendered":" Can Artificial Intelligence Replace a Doctor in Lung Cancer Screening via X-ray? Chest X-rays remain a simple and widely used tool for screening diseases such as lung cancer. In Japan, they are part of mandatory workplace health examinations. However, interpreting them requires significant expertise. To minimize errors, two doctors typically analyze each image, which increases… Continue reading Can Artificial Intelligence Replace a Doctor in Lung Cancer Screening via X-ray?<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3,4],"tags":[],"class_list":["post-17","post","type-post","status-publish","format-standard","hentry","category-health","category-human-humanitarian","entry"],"_links":{"self":[{"href":"https:\/\/theroboticsreview.com\/en\/wp-json\/wp\/v2\/posts\/17","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/theroboticsreview.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/theroboticsreview.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/theroboticsreview.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/theroboticsreview.com\/en\/wp-json\/wp\/v2\/comments?post=17"}],"version-history":[{"count":1,"href":"https:\/\/theroboticsreview.com\/en\/wp-json\/wp\/v2\/posts\/17\/revisions"}],"predecessor-version":[{"id":18,"href":"https:\/\/theroboticsreview.com\/en\/wp-json\/wp\/v2\/posts\/17\/revisions\/18"}],"wp:attachment":[{"href":"https:\/\/theroboticsreview.com\/en\/wp-json\/wp\/v2\/media?parent=17"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/theroboticsreview.com\/en\/wp-json\/wp\/v2\/categories?post=17"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/theroboticsreview.com\/en\/wp-json\/wp\/v2\/tags?post=17"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}