Trial · NCT07879937
Artificial Intelligence Integration in Breast Cancer Screening: The ANIHTA Study
NCT07879937, Not yet recruiting, Fondazione Policlinico Universitario Agostino Gemelli IRCCS
3 sourcestrials-2026-11-12-0.5.0
Cite this record
ConductScience Library. Artificial Intelligence Integration in Breast Cancer Screening: The ANIHTA Study. Trials, record NCT07879937. Release trials-2026-11-12-0.5.0, 12 Nov 2026. https://conductscience.org/library/trials/NCT07879937
On this page
Trial
As registered on ClinicalTrials.gov, in the graph's capture of the registry.
- Title
- Artificial Intelligence Integration in Breast Cancer Screening: The ANIHTA Study
- NCT number
- NCT07879937
- Status
- Not yet recruiting
- Enrollment
- 200,075 participants, estimated
- Lead sponsor
- Fondazione Policlinico Universitario Agostino Gemelli IRCCS
- Conditions
- Breast Neoplasms
- Interventions
- Artificial intelligence-based software for mammography, Discrete Choice Experiment on AI-Supported Breast Cancer Screening
- First posted
- 2026-10-19
- Last updated
- 2026-10-19
Source ClinicalTrials.gov
Registered outcomes12
Each outcome the trial registered, primary first, in ClinicalTrials.gov's words.
| 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. |
1 to 10 of 12Source ClinicalTrials.gov
See all 12 registered outcomesOutcomes0
Each outcome the trial posted results for, in ClinicalTrials.gov's words.
None in this release.
Results by group0
Each measurement the trial posted, group by group, in the words and numbers it posted.
None in this release.
Participant flow0
How many started, completed or left each group, period by period.
None in this release.
Adverse events0
Each adverse event the trial posted, group by group: the participants affected out of those at risk.
None in this release.
Adverse event totals0
The totals the trial posted for each group.
None in this release.
Papers13
The papers the trial lists on ClinicalTrials.gov.
Grants0
The grants NIH RePORTER links to the trial, newest funded first: NIH's, and some of AHRQ's, CDC's, FDA's and VA's. Each shows its title, principal investigators, organization and funder in its newest year.
None in this release.
Trial comparisons0
Comparisons of the trial's two groups, calculated by ConductScience from the counts it posted.
None in this release.
Tests0
The ConductCognition tests this trial's registered outcomes name, as ScienceGraph matched them in trial-tests-2026-11-12-0.2.1.
None in this release.
Data dates
The day each source was copied for this release.
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 trial from software.
The record and each of its lists are JSON, twenty rows a page. No key.
GET https://conductscience.org/api/trials/v1/NCT07879937
GET https://conductscience.org/api/trials/v1/NCT07879937/registered