NCT04778670

Brief Summary

This is a prospective clinical trial following a paired screen-positive design, with the aims to assess the performance of an artificial intelligence (AI) computer-aided detection (CAD) algorithm as an independent reader, in addition to two radiologists, of screening mammograms in a true screening population. Since all decisions by individual readers will be recorded, it is possible to determine what the outcome would have been had one or two of the readers not been allowed to assess images, and to determine what the outcome would have been had the recall decision been performed by consensus decision (actual) compared to single reader arbitration of discordant cases.

Trial Health

43
At Risk

Trial Health Score

Automated assessment based on enrollment pace, timeline, and geographic reach

Trial has exceeded expected completion date
Enrollment
55,579

participants targeted

Target at P75+ for not_applicable

Timeline
Completed

Started Apr 2021

Longer than P75 for not_applicable

Geographic Reach
1 country

1 active site

Status
unknown

Health score is calculated from publicly available data and should be used for screening purposes only.

Trial Relationships

Click on a node to explore related trials.

Study Timeline

Key milestones and dates

First Submitted

Initial submission to the registry

February 22, 2021

Completed
9 days until next milestone

First Posted

Study publicly available on registry

March 3, 2021

Completed
29 days until next milestone

Study Start

First participant enrolled

April 1, 2021

Completed
1.2 years until next milestone

Primary Completion

Last participant's last visit for primary outcome

June 9, 2022

Completed
2.5 years until next milestone

Study Completion

Last participant's last visit for all outcomes

December 1, 2024

Completed
Last Updated

March 14, 2023

Status Verified

March 1, 2023

Enrollment Period

1.2 years

First QC Date

February 22, 2021

Last Update Submit

March 10, 2023

Conditions

Breast Neoplasm Female

Keywords

Artificial IntelligenceBreast CancerMammographyScreening

Outcome Measures

Primary Outcomes (3)

  • Incident breast cancer

    Breast cancer diagnosis by pathologist

    At Screening

  • Incident breast cancer

    Breast cancer diagnosis by pathologist

    Within 12 months after screening

  • Incident breast cancer

    Breast cancer diagnosis by pathologist

    Within 23 months after screening

Secondary Outcomes (4)

  • Reader flagging

    At screening

  • Consensus recall

    At screening

  • Tissue sampling

    At screening

  • Process failure

    At screening

Study Arms (2)

Standard of Care

ACTIVE COMPARATOR

Standard of Care means all examinations will receive a flagging decision by: first reader and second reader radiologist as usual. However, in this paired design all participants will belong to both arms.

Diagnostic Test: Radiologist reading

AI CAD combination

EXPERIMENTAL

AI CAD combination in the primary end-point means the combination of the flagging decision of the first reader and AI CAD; in the secondary end-points it means any combination of AI alone, or AI in combination with first, second and both readers.

Diagnostic Test: AI CADDiagnostic Test: Radiologist reading

Interventions

AI CADDIAGNOSTIC_TEST

The Lunit INSIGHT MMG will be used as the AI CAD in our study. Initially, version 1.6.1.1 will be installed. The software version will be continuously updated with subsequent software releases, after confirming in a historic calibration dataset that the performance is improved. The operating point will be set based on a historic calibration dataset to attain a joint sensitivity of breast cancer detection of AI and first reader which is 2% higher than for first and second reader.

Also known as: Lunit INSIGHT MMG
AI CAD combination
Radiologist readingDIAGNOSTIC_TEST

Standard of care, each radiologist will assess the mammography examination, making a binary flagging decision (flag the examination to continue to consensus discussion, or not)

AI CAD combinationStandard of Care

Eligibility Criteria

Age40 Years - 74 Years
Sexfemale
Healthy VolunteersNo
Age GroupsAdult (18-64), Older Adult (65+)

You may qualify if:

  • Participants in regular population-based breast cancer screening at Capio St Göran Hospital

You may not qualify if:

  • Incomplete exam (complete exam: mediolateral oblique and craniocaudal images of Left and Right breast)
  • Breast implant
  • Complete mastectomy (excluded from screening positive group)
  • Participant in surveillance program for prior breast cancer

Contact the study team to confirm eligibility.

Sponsors & Collaborators

Study Sites (1)

Capio St Göran Hospital

Stockholm, 11219, Sweden

Location

Related Publications (2)

  • Dembrower KE, Crippa A, Eklund M, Strand F. Human-AI Interaction in the ScreenTrustCAD Trial: Recall Proportion and Positive Predictive Value Related to Screening Mammograms Flagged by AI CAD versus a Human Reader. Radiology. 2025 Mar;314(3):e242566. doi: 10.1148/radiol.242566.

    PMID: 40100021DERIVED

  • Dembrower K, Crippa A, Colon E, Eklund M, Strand F; ScreenTrustCAD Trial Consortium. Artificial intelligence for breast cancer detection in screening mammography in Sweden: a prospective, population-based, paired-reader, non-inferiority study. Lancet Digit Health. 2023 Oct;5(10):e703-e711. doi: 10.1016/S2589-7500(23)00153-X. Epub 2023 Sep 8.

    PMID: 37690911DERIVED

MeSH Terms

Conditions

Breast Neoplasms

Condition Hierarchy (Ancestors)

Neoplasms by SiteNeoplasmsBreast DiseasesSkin DiseasesSkin and Connective Tissue Diseases

Study Officials

  • Fredrik Strand, MD PhD

    Karolinska University Hospital

    PRINCIPAL INVESTIGATOR

Study Design

Study Type
interventional
Phase
not applicable
Allocation
NON RANDOMIZED
Masking
TRIPLE
Who Masked
PARTICIPANT, CARE PROVIDER, INVESTIGATOR
Masking Details
Positive disease status is ascertained by pathology-verified breast cancer. Disease status is not known to any of the actors (except for the outcomes assessor by necessity). AI decision is not known by the care provider radiologists until they have made their decisions. In the subsequent consensus discussion where a decision is made to recall or not to recall a woman, the AI decision is known. After AI decision has been recorded and outcomes have been assessed, the investigators will have full information on outcomes and AI decisions.
Purpose
DIAGNOSTIC
Intervention Model
SINGLE GROUP
Model Details: This is a prospective clinical trial following a paired screen-positive design (Pepe, Alonzo; 2001), with the aims to assess the performance of an AI algorithm combined with radiologists(s) compared to standard-of-care being two radiologists assessing screening mammograms in a true screening population. Since all decisions by individual readers will be recorded, it is possible to determine what the outcome would have been had one or two of the readers not been allowed to assess images, and to determine what the outcome would have been had the recall decision been performed by consensus decision (actual) compared to single reader arbitration of discordant cases.
Sponsor Type
OTHER
Responsible Party
PRINCIPAL INVESTIGATOR
PI Title
Registrar (biträdande överläkare)

Study Record Dates

First Submitted

February 22, 2021

First Posted

March 3, 2021

Study Start

April 1, 2021

Primary Completion

June 9, 2022

Study Completion

December 1, 2024

Last Updated

March 14, 2023

Record last verified: 2023-03

Data Sharing

IPD Sharing
Will share

To the extent allowed by source institution, legal agreements, and applicable laws and regulations

Shared Documents
STUDY PROTOCOL, SAP
Time Frame
At study start
Access Criteria
Anyone can access study protocol and SAP.

Locations

SE(1)