AI system
- System
-
Face2Gene (DeepGestalt facial phenotyping)
- Model
-
Not assessed
- Release
-
Not assessed
- Application developer
-
FDNA - Role
-
Not assessed
- Configuration
-
Not assessed
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
Frontal facial photograph plus clinical features uploaded to Face2Gene. A prior clinical diagnosis that no longer fit the clinical score. Access to whole-exome sequencing to confirm.
- Human oversight
-
Not assessed
- Relation to AI
-
Face2Gene listed MRD7 among four candidates. The paper gives no ranking. Whole-exome sequencing made the diagnosis. The AI redirected the differential after the clinical score undermined the prior diagnosis.
- AI contribution
-
Face2Gene listed MRD7 among four candidates. The paper gives no ranking. Whole-exome sequencing made the diagnosis. The AI redirected the differential after the clinical score undermined the prior diagnosis.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
Face2Gene suggested MRD7 for a 22-year-old misdiagnosed with Cornelia de Lange at age 4; exome sequencing confirmed a DYRK1A variant.
- Category
-
Improved Physical Health
- Status
-
Not assessed
- Beneficiary groups
-
People.
- 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
-
Not assessed
- Comparison
-
the clinical diagnosis of Cornelia de Lange syndrome made at age four
- Results
-
Reference: At four years of age, he was clinically diagnosed with Cornelia de Lange syndrome (CdLS; OMIM 122470, 300590, 300882, 610759, and 614701) due to his facial dysmorphism, microcephaly, short stature, and intellectual disability. Result: Face2Gene introduced the following candidate diseases: Angelman syndrome (AS, OMIM 105833), Witteveen-Kolk syndrome (WKOS; MIM 613406), Rubinstein-Taybi syndrome (RTS; OMIM 180849), and MRD7.
- 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:
FDNA. Operator: Department of Neurology, National Hospital Organization Akita National Hospital. - Jurisdictions
-
Benefit: Yurihonjo,
Japan. Developer: 
United States. Operator: Japan. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
The true syndrome is represented in Face2Gene's training data (authors note MRD7 recommendations improve as cases are registered). Clinicians pursue a candidate that is one of several suggestions.
- Replication attempts
-
1 follow-up entries. Benefit recurred: 1.
- Later findings
-
No later development found.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0037-source-0001
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Operator
- 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.
- Depth
-
People: 2.
- Reasons
-
People: A correct molecular diagnosis replaced a misdiagnosis held since age four. The report documents no treatment change, so material rather than life-changing.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
The deployer's account
Entry details
- Kind
-
Not assessed
- Related entries
-
Clinician-facing diagnostic algorithm: Face2Gene redirected an 18-year misdiagnosis, while a race-adjusted lung-function diagnostic algorithm led to inaccurate or delayed diagnoses for Black men at the University of Pennsylvania Health System.
- Field
-
Healthcare / clinical genetics. Rare disease diagnosis.
- Purpose
-
Face2Gene is built to suggest candidate syndromes from facial images and clinical features. This suggestion was that purpose.
- Dates
-
Date basis unassessed: 2023 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: d5a1a59dc709…
References
- Other identifiers
-
AI Incident Database: 582.
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
7 revisions. Latest: 21 October 2026.
Sources
-
Case report Deployer
Obara K, Abe E, Toyoshima I (2023). Whole-Exome Sequencing Identified a Novel DYRK1A Variant in a Patient With Intellectual Developmental Disorder, Autosomal Dominant 7. Cureus (PMC9822525).
As a result, Face2Gene introduced the following candidate diseases: Angelman syndrome (AS, OMIM 105833), Witteveen-Kolk syndrome (WKOS; MIM 613406), Rubinstein-Taybi syndrome (RTS; OMIM 180849), and MRD7.