{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Hendrix N"],"funding":["National Center for Advancing Translational Sciences","American Cancer Society","NCATS NIH HHS","University of Washington","National Cancer Institute","NCI NIH HHS","National Institutes of Health"],"pagination":["1098-1110"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9840464"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["19(10)"],"pubmed_abstract":["<h4>Background</h4>Artificial intelligence (AI) may improve cancer detection and risk prediction during mammography screening, but radiologists' preferences regarding its characteristics and implementation are unknown.<h4>Purpose</h4>To quantify how different attributes of AI-based cancer detection and risk prediction tools affect radiologists' intentions to use AI during screening mammography interpretation.<h4>Materials and methods</h4>Through qualitative interviews with radiologists, we identified five primary attributes for AI-based breast cancer detection and four for breast cancer risk prediction. We developed a discrete choice experiment based on these attributes and invited 150 US-based radiologists to participate. Each respondent made eight choices for each tool between three alternatives: two hypothetical AI-based tools versus screening without AI. We analyzed samplewide preferences using random parameters logit models and identified subgroups with latent class models.<h4>Results</h4>Respondents (n = 66; 44% response rate) were from six diverse practice settings across eight states. Radiologists were more interested in AI for cancer detection when sensitivity and specificity were balanced (94% sensitivity with <25% of examinations marked) and AI markup appeared at the end of the hanging protocol after radiologists complete their independent review. For AI-based risk prediction, radiologists preferred AI models using both mammography images and clinical data. Overall, 46% to 60% intended to adopt any of the AI tools presented in the study; 26% to 33% approached AI enthusiastically but were deterred if the features did not align with their preferences.<h4>Conclusion</h4>Although most radiologists want to use AI-based decision support, short-term uptake may be maximized by implementing tools that meet the preferences of dissuadable users."],"journal":["Journal of the American College of Radiology : JACR"],"pubmed_title":["Radiologist Preferences for Artificial Intelligence-Based Decision Support During Screening Mammography Interpretation."],"pmcid":["PMC9840464"],"funding_grant_id":["R37 CA240403","KL2 TR002317","P01 CA154292","UL1 TR002319","CSDG-21-078-01-CPSH","TL1 TR002318"],"pubmed_authors":["Lowry KP","Hendrix N","Sorensen G","Lotter W","Elmore JG","Kolb S","Lee CI","Liao GJ","Parsian S","Naeim A","Hsu W"],"additional_accession":[]},"is_claimable":false,"name":"Radiologist Preferences for Artificial Intelligence-Based Decision Support During Screening Mammography Interpretation.","description":"<h4>Background</h4>Artificial intelligence (AI) may improve cancer detection and risk prediction during mammography screening, but radiologists' preferences regarding its characteristics and implementation are unknown.<h4>Purpose</h4>To quantify how different attributes of AI-based cancer detection and risk prediction tools affect radiologists' intentions to use AI during screening mammography interpretation.<h4>Materials and methods</h4>Through qualitative interviews with radiologists, we identified five primary attributes for AI-based breast cancer detection and four for breast cancer risk prediction. We developed a discrete choice experiment based on these attributes and invited 150 US-based radiologists to participate. Each respondent made eight choices for each tool between three alternatives: two hypothetical AI-based tools versus screening without AI. We analyzed samplewide preferences using random parameters logit models and identified subgroups with latent class models.<h4>Results</h4>Respondents (n = 66; 44% response rate) were from six diverse practice settings across eight states. Radiologists were more interested in AI for cancer detection when sensitivity and specificity were balanced (94% sensitivity with <25% of examinations marked) and AI markup appeared at the end of the hanging protocol after radiologists complete their independent review. For AI-based risk prediction, radiologists preferred AI models using both mammography images and clinical data. Overall, 46% to 60% intended to adopt any of the AI tools presented in the study; 26% to 33% approached AI enthusiastically but were deterred if the features did not align with their preferences.<h4>Conclusion</h4>Although most radiologists want to use AI-based decision support, short-term uptake may be maximized by implementing tools that meet the preferences of dissuadable users.","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022 Oct","modification":"2025-04-04T03:00:31.795Z","creation":"2025-04-04T03:00:31.795Z"},"accession":"S-EPMC9840464","cross_references":{"pubmed":["35970474"],"doi":["10.1016/j.jacr.2022.06.019"]}}