Exploring the Potential of Artificial Intelligence for Earlier Breast Cancer Detection: A Retrospective Multi-Reader Study Based on AI-Assisted Mammographic Interpretation (EARLIEST-AI)

NCT07556900 | Active Not Recruiting

• 1 other identifier: TAIEK 1493
• Study Type: observational
• Target: 785
• Locations: 1 country
• Sites: 1

Brief Summary

EARLIEST-AI Study type: Two-phase, multi-reader, blinded retrospective observational study based on data from a single clinic. The primary objective of the study is to assess the sensitivity and specificity of radiologists and Artificial Intelligence (AI) in interpreting mammographic examinations for breast cancer detection in a scenario where no previous examinations are available, and to compare the diagnostic performance of radiologists with and without AI support. The secondary objectives of the study are to assess the independent diagnostic performance of Computer Aided Detection (CAD) software, including sensitivity and specificity in identifying histopathologically confirmed breast cancer cases; to assess inter-reader and intra-reader variability in interpretation with and without AI support; to assess the agreement between AI outputs and histopathological findings; and to assess the impact of mammogram technical parameters on AI performance. Time frame: Review of a subset of mammograms randomly selected from those performed between January 1, 2012 and December 31, 2024. Imaging findings were classified according to the Breast Imaging Reporting and Data System (BI-RADS). Inclusion criteria:

1. 1.Female patients aged 30 years or older.
2. 2.One or more mammograms performed between January 1, 2012 and December 31, 2024.
3. 3.Meets one of the following criteria:
4. 4.Mammograms of poor quality or artifacts that do not allow for reliable assessment.
5. 5.History of breast surgery or previous breast cancer treatment that has significantly altered breast morphology.
6. 6.Data deficiencies, including:

Conditions

Breast Cancer; AI (Artificial Intelligence); Early Detection of Cancer

Keywords

Breast Cancer; Artificial Intelligence; CAD; Early Detection; Human-AI Interaction

Outcome Measures

Primary Outcomes (5)

• Standalone reader sensitivity

  through study completion, an average of 1 year

• Standalone CAD sensitivity

  through study completion, an average of 1 year

• Augmented Reader sensitivity

  through study completion, an average of 1 year

• Standalone reader detection to diagnostic time (MAE)

  through study completion, an average of 1 year

• Augmented reader detection to diagnostic time (MAE)

  through study completion, an average of 1 year

Secondary Outcomes (6)

• Inter-reader agreement

  through study completion, an average of 1 year

• Intra-reader agreement

  through study completion, an average of 1 year

• Standalone reader specificity

  through study completion, an average of 1 year

• Augmented reader specificity

  through study completion, an average of 1 year

• Standalone reader markings region-wise annotation precision

  through study completion, an average of 1 year

Study Arms (2)

BI-RADS 1-2 patients

BI-RADS 6 patients

Eligibility Criteria

• Age: 30 Years+
• Sex: female
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

1

Sponsors & Collaborators

• Mammograaf Radioloogiakliinik: lead
• Hera-MI, SAS: collaborator

Study Sites (1)

Mammograaf Radioloogiakliinik

Tallinn, Harju, 13214, Estonia

Location

MeSH Terms

Conditions

Breast Neoplasms

Condition Hierarchy (Ancestors)

Neoplasms by Site; Neoplasms; Breast Diseases; Skin Diseases; Skin and Connective Tissue Diseases

Study Officials

• Marina Astapova, MD

  Mammograaf Radioloogiakliinik

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: CASE CONTROL
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: MD

Study Record Dates

• First Submitted: April 17, 2026
• First Posted: April 29, 2026
• Study Start: October 1, 2025
• Primary Completion: March 15, 2026
• Study Completion (Estimated): September 1, 2026
• Last Updated: April 29, 2026

Record last verified: 2026-04

Data Sharing

• IPD Sharing: Will not share

Locations

ES (1)