{"entity":{"id":"screentrustcad","kind":"trial","name":"ScreenTrustCAD","aka":["ScreenTrust CAD","STGKS001"],"tldr":"In Stockholm's screening programme, replacing one of the two radiologists with Lunit's mammography software found at least as many breast cancers as two radiologists reading together, the first prospective evidence that this software can take over one reader's seat.","summary":"ScreenTrustCAD (NCT04778670; organisation id STGKS001) was a prospective, population-based, paired-reader, non-inferiority study at Capio Sankt Göran Hospital in Stockholm, sponsored by Karolinska University Hospital with Lunit as a collaborator and part funder. Consecutive women aged 40 to 74 without breast implants attending population screening in the hospital's catchment were included. Every examination was read independently by two radiologists and by Lunit INSIGHT MMG. The primary outcome was screen-detected breast cancer within three months of mammography, and the primary analysis tested whether double reading by one radiologist plus AI was non-inferior (margin 0.15 relative reduction in cancer diagnoses) to standard double reading by two radiologists; AI alone and triple reading by two radiologists plus AI were also compared.\n\nFrom 1 April 2021 to 9 June 2022, 58,344 women were screened and 55,581 were included. Screen-detected cancer followed an initial positive read in 269 women (0.5 percent). One radiologist plus AI detected 261 cancers (0.5 percent) against 250 (0.4 percent) for two radiologists (relative proportion 1.04, 95 percent CI 1.00 to 1.09), meeting non-inferiority. AI alone detected 246 (relative proportion 0.98, 0.93 to 1.04) and two radiologists plus AI detected 269 (1.08, 1.04 to 1.11), both also non-inferior. The authors conclude that replacing one radiologist with AI gave a 4 percent higher, non-inferior detection rate and that the software has potential for controlled implementation with risk management and real-world follow-up.\n\nThe registry lists the study as interventional with no drug phase, which is why the phase 2 and 3 pass never attached it. MASAI, the Swedish randomised trial of AI-supported screening, used Transpara and is a separate record.","status":"positive","asOf":"2026-09-24","links":[{"label":"ClinicalTrials.gov NCT04778670","url":"https://clinicaltrials.gov/study/NCT04778670"},{"label":"Lancet Digital Health 2023","url":"https://doi.org/10.1016/S2589-7500(23)00153-X"}],"tags":[],"related":[],"cancers":["breast-hr-positive","tnbc"],"sections":[],"technologies":["mammography","radiology-ai-screening"],"targets":[],"drugs":["lunit-insight-mmg"],"companies":["lunit"],"institutions":["karolinska"],"pathways":[],"terms":["screening"],"trials":[],"people":[],"bottlenecks":[],"keyPapers":["paper-screentrustcad-dembrower-lancet-digit-health-2023"],"journals":[],"dependsOn":[],"notes":[],"nct":"NCT04778670","phase":"observational","setting":"Population mammography screening at Capio Sankt Göran Hospital, Stockholm: paired-reader non-inferiority comparison of one radiologist plus Lunit INSIGHT MMG against standard double reading by two radiologists, with AI alone and two radiologists plus AI as further comparisons","sponsor":"Karolinska University Hospital","result":"One radiologist plus AI detected 261 screen-detected cancers vs 250 for two radiologists (relative proportion 1.04, 95% CI 1.00 to 1.09), meeting non-inferiority; AI alone 246 and two radiologists plus AI 269 were also non-inferior.","yearReported":2023,"enrolled":55581,"enrolledBasis":"analysed","enrolledNote":"The Lancet Digital Health 2023 report includes 55,581 of the 58,344 women screened between April 2021 and June 2022; ClinicalTrials.gov NCT04778670 lists an actual enrolment of 55,579.","outcomes":[{"endpoint":"Screen-detected breast cancers (primary comparison: one radiologist plus AI versus two radiologists)","primary":true,"unit":"cases","arms":[{"name":"One radiologist + Lunit INSIGHT MMG","n":55581,"value":261,"note":"0.5%; relative proportion 1.04 (95% CI 1.00 to 1.09) vs two radiologists; non-inferiority margin 0.15 relative reduction"},{"name":"Two radiologists (standard double reading)","n":55581,"value":250,"note":"0.4%"}],"source":"https://doi.org/10.1016/S2589-7500(23)00153-X"},{"endpoint":"Screen-detected breast cancers, AI alone versus two radiologists","unit":"cases","arms":[{"name":"Lunit INSIGHT MMG alone","n":55581,"value":246,"note":"Relative proportion 0.98 (95% CI 0.93 to 1.04); non-inferior"},{"name":"Two radiologists (standard double reading)","n":55581,"value":250}],"source":"https://doi.org/10.1016/S2589-7500(23)00153-X"},{"endpoint":"Screen-detected breast cancers, two radiologists plus AI versus two radiologists","unit":"cases","arms":[{"name":"Two radiologists + Lunit INSIGHT MMG","n":55581,"value":269,"note":"Relative proportion 1.08 (95% CI 1.04 to 1.11)"},{"name":"Two radiologists (standard double reading)","n":55581,"value":250}],"source":"https://doi.org/10.1016/S2589-7500(23)00153-X"}],"replication":"MASAI (NCT04838756; Transpara) is the randomised Swedish trial of AI-supported screening and reached a similar conclusion with a different product; a Radiology 2025 secondary analysis of ScreenTrustCAD examined recall and positive predictive value by reader and is not used for outcome values here."},"route":"/trials/screentrustcad/","neighbours":{"cancer":[{"id":"breast-hr-positive","kind":"cancer","name":"HR-positive / HER2-negative breast cancer","route":"/cancers/breast-hr-positive/"},{"id":"tnbc","kind":"cancer","name":"Triple-negative breast cancer (TNBC)","route":"/cancers/tnbc/"}],"technology":[{"id":"radiology-ai-screening","kind":"technology","name":"AI in radiology","route":"/technologies/radiology-ai-screening/"},{"id":"mammography","kind":"technology","name":"Mammography & tomosynthesis","route":"/technologies/mammography/"}],"drug":[{"id":"lunit-insight-mmg","kind":"drug","name":"Lunit INSIGHT MMG","route":"/drugs/lunit-insight-mmg/"}],"company":[{"id":"lunit","kind":"company","name":"Lunit","route":"/companies/lunit/"}],"institution":[{"id":"karolinska","kind":"institution","name":"Karolinska University Hospital","route":"/institutions/karolinska/"}],"term":[{"id":"screening","kind":"term","name":"Screening","route":"/terms/screening/"}],"paper":[{"id":"paper-screentrustcad-dembrower-lancet-digit-health-2023","kind":"paper","name":"Artificial intelligence for breast cancer detection in screening mammography in Sweden: a prospective, population-based, paired-reader, non-inferiority study (ScreenTrustCAD)","route":"/key-papers/paper-screentrustcad-dembrower-lancet-digit-health-2023/"}]}}