Registered outcomes12

Each outcome the trial registered, primary first, in ClinicalTrials.gov's words.

1 to 12 of 12

List	Outcome	Time frame	Description
Primary	Cancer Detection Rate	From the index screening mammography examination through 24 months of follow-up	Cancer detection rate (CDR) will be defined as the number of confirmed breast cancers classified as screen-detected under each strategy per 1,000 eligible screening examinations in the independent validation set. The primary non-inferiority measure will be the ratio of CDR under the emulated AI-triggered third-reader-augmented workflow (Strategy B) to CDR under the observed routine AI-supported double-reading workflow without third-reader arbitration (Strategy A). A relative non-inferiority margin of 0.85 will be used, corresponding to a maximum acceptable relative reduction of 15% in CDR under Strategy B. Non-inferiority will be concluded if the lower bound of the two-sided 95% confidence interval for the CDR ratio is greater than 0.85. The absolute difference in CDR between Strategy B and Strategy A, expressed per 1,000 screening examinations, will also be reported as a complementary measure of clinical impact.
Secondary	Sensitivity, Specificity, Positive Predictive Value, Negative Predictive Value, False-Positive Rate, and False-Negative Rate of the AIpt Threshold	From the index screening mammography examination through 24 months of follow-up	The AI-positive threshold (AIpt), derived in the prespecified derivation set and applied without recalibration to the independent validation set, will be evaluated in terms of sensitivity, specificity, positive predictive value, negative predictive value, false-positive rate, and false-negative rate, with corresponding 95% confidence intervals.
Secondary	Sensitivity, Specificity, Positive Predictive Value, Negative Predictive Value, False-Positive Rate, and False-Negative Rate of the AInt Threshold	From the index screening mammography examination through 24 months of follow-up	The AI-negative threshold (AInt), derived in the prespecified derivation set and applied without recalibration to the independent validation set, will be evaluated in terms of sensitivity, specificity, positive predictive value, negative predictive value, false-positive rate, and false-negative rate, with corresponding 95% confidence intervals.
Secondary	Proportion of Screening Examinations Requiring Emulated Third-Reader Arbitration Under Strategy B	At the index screening mammography examination	The emulated third-reader arbitration rate will be defined as the proportion of eligible screening examinations meeting the prespecified Strategy B criteria for offline third-radiologist assessment. These include concordant negative examinations with an AI score equal to or greater than AIpt and discordant examinations with an AI score equal to or lower than AInt.
Secondary	Difference in Biopsy Referral Rate Between Strategy B and Strategy A	From the index screening mammography examination through completion of the diagnostic work-up	Biopsy referral rate will be defined as the proportion of eligible screening examinations leading to recommendation or performance of tissue sampling during the diagnostic work-up. The biopsy referral rate under the emulated Strategy B workflow will be compared with that under the observed Strategy A workflow.
Secondary	Interval Cancer Rate	Within 24 months after the index screening mammography examination	Interval cancer will be defined as a breast malignancy diagnosed within 24 months after a negative screening result and before the next scheduled screening round. Interval cancers will also contribute to false-negative classification in the retrospective diagnostic-accuracy analyses.
Secondary	Modeled radiologists' workload	Up to 24 months after the index screening mammography	Radiologists' workload under each screening strategy will be modeled using the number of offline third-reader assessments, recalls, and additional diagnostic assessments attributable to the index screening episode. Results will be reported as absolute counts and, where appropriate, standardized per 1,000 eligible screening examinations.
Secondary	Professional time associated with the screening workflow	Up to 24 months after the index screening mammography	Professional time associated with the observed routine screening workflow and the emulated AI-supported workflow will be estimated by applying prespecified professional-time requirements to the screening and diagnostic activities generated under each strategy. Results will be reported as total professional time in minutes per 1,000 eligible screening examinations.
Secondary	Additional diagnostic assessments	Up to 24 months after the index screening mammography	The number of additional diagnostic assessments generated under the observed routine screening workflow and the emulated AI-supported workflow will be estimated for each strategy. Results will be reported as the number of additional diagnostic assessments per 1,000 eligible screening examinations.
Secondary	Direct healthcare costs	Up to 24 months after the index screening mammography	Direct healthcare costs will include costs borne by the healthcare provider for screening interpretation, AI implementation, second-level assessment, biopsy procedures, and related clinical activities. Prespecified unit costs will be applied to the resources generated under each strategy, and total direct healthcare costs will be reported in euros per 1,000 eligible screening examinations.
Secondary	Healthcare professionals' acceptability	At enrollment in the DCE component, during study months 19-36 (single assessment)	Acceptability will be assessed through responses to the structured questionnaire administered to healthcare professionals. Acceptability is defined as the degree to which the routine AI-supported breast cancer screening workflow is considered appropriate and satisfactory by healthcare professionals. Results will be summarized descriptively according to the questionnaire response categories.
Secondary	Healthcare professionals' perceived utility	At enrollment in the DCE component, during study months 19-36 (single assessment)	Perceived utility will be assessed through the structured questionnaire administered to healthcare professionals and will reflect the extent to which AI-supported screening is perceived as beneficial for screening performance, workflow efficiency, or decision-making. Responses will be summarized descriptively according to the questionnaire response categories.

Source ClinicalTrials.govtrials-2026-11-12-0.5.0

Sources 3

ClinicalTrials.gov's posted results, through CTTI's AACTFreely available. Acknowledgement requested
ClinicalTrials.govNo license stated
NIH RePORTER's clinical studies and project filesPublic domain

Each source's terms

ClinicalTrials.gov's posted results, through CTTI's AACTClinicalTrials.gov data via Aggregate Analysis of ClinicalTrials.gov (AACT), CTTI. CTTI makes its materials freely available and requests acknowledgement. https://aact.ctti-clinicaltrials.org/documentation/299
ClinicalTrials.govnone stated
NIH RePORTER's clinical studies and project filesPublic domain (NIH RePORTER)

ClinicalTrials.gov's data carry an international copyright outside the United States: https://clinicaltrials.gov/about-site/terms-conditions.

For software

Read this list from software.

Twenty rows a page, as JSON. No key.

GET https://conductscience.org/api/trials/v1/NCT07879937/registered

API reference For AI assistants