AI system
- System
-
SpliceAI
- Model
-
Not assessed
- Release
-
Not assessed
- Application developer
-
SpliceAI authors (Jaganathan et al., Cell 2019), as cited in the case report; the developing organization is not named in the source text
- Role
-
Not assessed
- Configuration
-
Not assessed
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
Whole-genome sequencing with SpliceAI scoring of rare intronic variants in a disease gene already implicated by one pathogenic allele. Access to parental samples for RNA-level validation.
- Human oversight
-
Not assessed
- Relation to AI
-
SpliceAI's score of 0.98 nominated the maternally inherited deep intronic variant as the second allele. Among 78,575 rare intronic PKHD1 variants in gnomAD only one scored higher. Pathogenicity was then established by RT-PCR and Sanger sequencing of maternal urine-derived cells and GeneDx's likely-pathogenic classification. The AI's contribution was candidate selection. Without it the second allele would have remained unexplained. Authors declare no relevant financial interests.
- AI contribution
-
SpliceAI's score of 0.98 nominated the maternally inherited deep intronic variant as the second allele. Among 78,575 rare intronic PKHD1 variants in gnomAD only one scored higher. Pathogenicity was then established by RT-PCR and Sanger sequencing of maternal urine-derived cells and GeneDx's likely-pathogenic classification. The AI's contribution was candidate selection. Without it the second allele would have remained unexplained. Authors declare no relevant financial interests.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
a maternally inherited deep intronic PKHD1 variant scoring 0.98
- 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
-
a maternally inherited deep intronic PKHD1 variant scoring 0.98
- Comparison
-
Not assessed
- Results
-
a maternally inherited deep intronic PKHD1 variant scoring 0.98
- 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: SpliceAI authors (Jaganathan et al., Cell 2019), as cited in the case report; the developing organization is not named in the source text. Operator: NICUnet consortium / Icahn School of Medicine at Mount Sinai (Rareservoir variant database).
- Jurisdictions
-
Benefit: New York,
United States. Developer: United States. Operator: United States. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Functional or RNA confirmation before clinical use of the variant. Genetic counseling and access to IVF with PGT-M.
- Replication attempts
-
Not assessed
- Later findings
-
The parents' IVF with PGT-M within a year of the death is reported in the case report itself; nothing dated after publication was found,.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0077-source-0001–0003
- 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: 3.
- Reasons
-
People: An identifiable family received a definitive molecular cause of their son's death. They used it for IVF with preimplantation genetic testing to avoid a lethal disease recurring. Life-changing for the family, not life-saving for the patient.
- 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
-
Not assessed
- Field
-
Healthcare - neonatology / clinical genomics. Genome reanalysis in a neonatal research network.
- Purpose
-
SpliceAI is a deep-learning model built to predict the effect of DNA variants on RNA splicing. Nominating a splice-altering deep intronic variant is exactly its intended use.
- Dates
-
Date basis unassessed: 2024 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: 8e4e4c47ca8d…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
4 revisions. Latest: 21 October 2026.
Sources
-
Case report Deployer
Richter F, Rutherford KD, Cooke AJ, Meshkati M, Eddy-Abrams V, Greene D, Kosowsky J, Park Y, Aggarwal S, Burke RJ, Chang W, Connors J, Giannone PJ, Hays T, Khattar D, Polak M, Senaldi L, Smith-Raska M, Sridhar S, Steiner L, Swanson JR, Tauber KA, Barbosa M, Guttmann KF, Turro E (2024). A Deep Intronic PKHD1 Variant Identified by SpliceAI in a Deceased Neonate With Autosomal Recessive Polycystic Kidney Disease. American Journal of Kidney Diseases 83(6):829-833 (online 10 January 2024).
Using SpliceAI scores in the NICUnet Rareservoir, we identified a maternally inherited intronic variant with a score of 0.98 (chr6:52030169 T>C, Figure 1D).
After genetic counseling, the parents proceeded with IVF and preimplantation genetic testing for monogenic disorders (PGT-M).
produced a diagnostic molecular report listing the missense pathogenic variant and classifying the intronic variant as likely pathogenic