Breast MRI / Breast Cancer / MIRAI · Interventional Study

MIRAI-MRI: Comparing Screening MRI for Patients at High Risk for Breast Cancer Identified by Mirai and Tyrer-Cuzick

ClinicalTrials.gov · September 8, 2026

Preliminary Why this matters to you Expert discussion

Early or partial results. Treat as a signal, not a conclusion.

AI Summary

This is a completed prospective study registration comparing Mirai (a deep learning breast cancer risk model) to Tyrer-Cuzick in identifying high-risk patients for supplemental MRI screening. The registry record documents enrollment of 145 participants and study aims but contains no outcome data, and results are not yet posted in this registry.

What was studied

Interventional, Non Randomized, Parallel, Open label, Screening purpose. Breast Cancer; Female; age from 40 Years. Intervention: High Risk Participants--MIRAI. Compared with: High Risk Participants--non-MIRAI — Active Comparator. n = 145. 1 site: United States.

Key findings

Safety

Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.

Who this may help

This study will provide prospective evidence on whether Mirai-based risk stratification improves cancer detection rates compared to existing clinical standards. Results are not yet available in this registry record and should be awaited before drawing clinical conclusions.

Plain-language summary

This is a completed registry record reporting enrollment and study design only, with no outcome data posted; it describes a prospective diagnostic comparison study that has finished recruitment but results are not yet available.

Study design

As stated by the source record.

MethodsPrimary outcome measure: CDR Mirai Assessment versus CDR Traditional High Risk Screening (assessed at 1.5 years (duration of patient recruitment and outcome data collection))

DesignInterventional, Non Randomized, Parallel, Open label, Screening purpose

PopulationBreast Cancer; Female; age from 40 Years

Sample size145

InterventionHigh Risk Participants--MIRAI

ComparatorHigh Risk Participants--non-MIRAI — Active Comparator

Setting1 site: United States

Reported figures

Quoted from the source exactly as published.

Planned enrollment145

Primary outcome measureCDR Mirai Assessment versus CDR Traditional High Risk Screening, 1.5 years

Follow-up duration1.5 years

Clinical bottom line

Caveats

Results not posted in this registry record; outcome data (cancer detection rates, comparisons) are not reported.
Sample size justification and adequacy for the primary endpoint are not provided.
Recruitment setting, eligibility criteria, and baseline characteristics are not described in this registry entry.
Blinding, allocation method, and risk of bias mitigation strategies are not detailed in the registry record.

Evidence assessment

Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.

Study design

moderate

Prospective interventional design comparing two risk stratification algorithms with diagnostic outcome.

Directness

strong

Direct comparison of Mirai versus Tyrer-Cuzick in identifying high-risk patients for supplemental MRI.

Consistency

insufficient

Registry record does not report results; consistency cannot be assessed.

Risk of bias

insufficient

No methods detail on blinding, allocation concealment, or outcome adjudication provided in registry.

Sample adequacy

limited

145 participants enrolled; sample size justification and adequacy for primary outcome not stated.

What is missing. This record has no key findings. That is a gap in the analysis, not a judgement about the study.

Source abstract

Registry record from ClinicalTrials.gov (NCT05968157). This is a study registration, not published results. Lead sponsor: University of Massachusetts, Worcester. Recruitment status: COMPLETED. Phase: NA. Study type: INTERVENTIONAL. Enrollment: 145 participants (ACTUAL). Conditions: Breast Cancer. Interventions: DIAGNOSTIC_TEST: Breast MRI; DEVICE: MIRAI. Primary outcome measures: CDR Mirai Assessment versus CDR Traditional High Risk Screening , 1.5 years (duration of patient recruitment and outcome data collection). Brief summary: Accurate risk assessment is essential for the success of population screening programs and early detection efforts in breast cancer. Mirai is a new deep learning model based on full resolution mammograms. Mirai is a mammography-based deep learning model designed to predict risk at multiple timepoints, leverage potentially missing risk factor information, and produce predictions that are consistent across mammography machines. Mirai was trained on a large dataset from Massachusetts General Hospital (MGH) in the United States and found to be significantly more accurate than the Tyrer-Cuzick model, a current clinical standard. The primary aim of this study is to prospectively quantify the clinical benefit (i.e. MRI/CEM cancer detection rate) of Mirai-based guidelines and to compare them to the current standard of care. 1. Conduct a prospective study where patients who are identified as high risk by Mirai guidelines are invited to receive supplemental MRI within 12 months. 2. Compare cancer outcomes between patients only identified as high risk by Mirai and patients identified as high risk by existing guidelines The secondary aim is to study the impact of new guidelines by race and ethnicity, to ensure equitable improvements in cancer screening.

Follow from this

Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.

Breast MRIUniversity of Massachusetts, WorcesterNCT05968157Breast CancerMIRAI