AI system
- System
-
Mia
- Model
-
Not assessed
- Release
-
Not assessed
- Application developer
-
Kheiron Medical Technologies
- Role
-
Not assessed
- Configuration
-
Not assessed
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
Deployment of Mia alongside routine human double reading in a screening program. A safety-net workflow in which AI-flagged, reader-negative cases are re-reviewed.
- Human oversight
-
Not assessed
- Relation to AI
-
Mia flagged a lesion that the hospital radiologists had not identified on the same scan. Clinicians then confirmed and treated the cancer. Both the BBC and the University of Aberdeen attribute the detection to Mia. The counterfactual is that the cancer would have been found later, at a larger size, rather than never.
- AI contribution
-
Mia flagged a lesion that the hospital radiologists had not identified on the same scan. Clinicians then confirmed and treated the cancer. Both the BBC and the University of Aberdeen attribute the detection to Mia. The counterfactual is that the cancer would have been found later, at a larger size, rather than never.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
Mia helped find 12% more cancers than routine practice
- Category
-
Improved Physical Health
- Status
-
Not assessed
- Beneficiary groups
-
People. Organizations.
- Beneficiaries
-
Not assessed
- Reach
-
Not assessed
- Distribution and access
-
Not assessed
- Duration
-
Not assessed
- Expected?
-
Yes
- Costs and harms
-
Not assessed
Measurement
- Studies
-
Not assessed
- Study design
-
Not assessed
- Measurement
-
Not assessed
- Setting and sample
-
Not assessed
- Measures
-
Mia helped find 12% more cancers than routine practice
- Comparison
-
routine practice (radiologists reading without Mia)
- Results
-
Result: an additional 12 percent more cancers than in routine practice.
- Additional value from AI
-
Not assessed
- Limitations
-
Not assessed
- Denominators
-
Not assessed
- Materials for replication
-
Not assessed
Money
- Kind of value
-
Not assessed
- Amount
-
Not assessed
- Currency and prices
-
Not assessed
- Period and unit
-
Not assessed
- Realization
-
Not assessed
- Recipients and payers
-
Not assessed
- Gross or net
-
Not assessed
- Included costs
-
Not assessed
- Comparison
-
Not assessed
- Method
-
Not assessed
- Return and payback
-
Not assessed
People and places
- Participants
-
Developer: Kheiron Medical Technologies. Operator: NHS Grampian.
- Jurisdictions
-
Benefit: Aberdeen,
United Kingdom. Developer: United Kingdom. Operator: United Kingdom. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Clinicians act on AI-only flags rather than discarding them. The AI's recall threshold is set so that extra flags do not overwhelm the service.
- Replication attempts
-
1 follow-up entries. Benefit recurred: 1.
- Later findings
-
No development dated after 21 March 2024 found in the cited sources.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0062-source-0001–0003
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Independent
- Original evidence
-
Not assessed
- Access and versions
-
Not assessed
- Supported findings
-
Not assessed
- Evidence links
-
Not assessed
- Evidence strength
-
Not assessed
- Missing evidence
-
Not assessed
Grades
- Assessed benefits
-
People. Organizations.
- Depth
-
People: 3. Organizations: 2.
- Reasons
-
People: A 6 mm cancer was treated at an early stage with surgery and a short radiotherapy course. Dr Lip states that cancers picked up under 15 mm carry around 95% survival. The benefit is potentially life-saving but not demonstrated as such for this patient. Organizations: Across the 10,889-woman evaluation Mia helped find 12% more cancers. The University of Aberdeen statement says this would not put more women through additional tests.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
Independently reported
Entry details
- Kind
-
Not assessed
- Related entries
-
Same task, AI lesion detection on radiographs, though chest X-rays rather than mammograms: the classifiers showed unequal performance that underdiagnoses women, Hispanic and low-income patients, the patient group Mia's screening flag benefited.
- Field
-
Healthcare - breast cancer screening. AI reader in population mammography screening.
- Purpose
-
Mia was built to read screening mammograms and flag suspicious findings alongside human readers. Detecting a cancer missed by readers is exactly its intended function.
- Dates
-
Date basis unassessed: 2024 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: c4fa27f84c85…
References
- Other identifiers
-
oecd_aim: 2024-03-21-b742. AI Incident Database: 81.
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
7 revisions. Latest: 21 October 2026.
Sources
-
News report Independent author
Kleinman Z (2024). NHS AI test spots tiny cancers missed by doctors. BBC News, 21 March 2024.
Barbara was one of the 11 patients whose cancer was flagged by Mia but had not been spotted on her scan when it was studied by the hospital radiologists.
Because her 6mm tumour was caught so early she had an operation but only needed five days of radiotherapy.
-
Press release Independent author
University of Aberdeen (2024). More breast cancers detected in first evaluation of breast screening AI. University news release, 21 March 2024 (quotation attributed to Dr Gerald Lip).
If you pick up cancer under 15mm, most women now will have a 95 percent survival rate.