Mohammad T. Elhakim , Sarah W. Stougaard, Ole Graumann, Mads Nielsen, Oke Gerke, Lisbet B. Larsen, Benjamin S. B. Rasmussen<\/p>\n
Radiology: Artificial Intelligence, 2024<\/strong><\/p>\n Abstract<\/strong>
\nMammography screening supported by deep learning\u2013based artificial intelligence (AI) solutions can potentially reduce workload without compromising breast cancer detection accuracy, but the site of deployment in the workflow might be crucial. This retrospective study compared three simulated AI-integrated screening scenarios with standard double reading with arbitration in a sample of 249\u2009402 mammograms from a representative screening population. A commercial AI system replaced the first reader (scenario 1: integrated AIfirst), the second reader (scenario 2: integrated AIsecond), or both readers for triaging of low- and high-risk cases (scenario 3: integrated AItriage). AI threshold values were chosen based partly on previous validation and setting the screen-read volume reduction at approximately 50% across scenarios. Detection accuracy measures were calculated. Compared with standard double reading, integrated AIfirst showed no evidence of a difference in accuracy metrics except for a higher arbitration rate (+0.99%, P < .001). Integrated AIsecond had lower sensitivity (\u22121.58%, P < .001), negative predictive value (NPV) (\u22120.01%, P < .001), and recall rate (\u22120.06%, P = .04) but a higher positive predictive value (PPV) (+0.03%, P < .001) and arbitration rate (+1.22%, P < .001). Integrated AItriage achieved higher sensitivity (+1.33%, P < .001), PPV (+0.36%, P = .03), and NPV (+0.01%, P < .001) but lower arbitration rate (\u22120.88%, P < .001). Replacing one or both readers with AI seems feasible; however, the site of application in the workflow can have clinically relevant effects on accuracy and workload.<\/p>\n