Evaluation the Accuracy of Generative AI in Diagnosing Rare and Complex Pediatric Cases: A Retrospective Comparative Study

Evaluation the Accuracy of Generative AI in Diagnosing Rare and Complex Pediatric Cases: A Retrospective Comparative Study - Evaluation the Accuracy of Generative AI in Diagnosing Rare and Complex Pediatric Cases

Status

Active, not recruiting

Phases

Unknown

Study type

Observational

Source

JPRN

Registry ID

JPRN-UMIN000058851

Enrollment

Registered

2025-08-20

Start date

2025-12-01

Completion date

Unknown

Last updated

2026-06-29

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

rare and complex pediatric diseases

Interventions

None listed

Eligibility

Sex/Gender

All

Inclusion criteria

Inclusion criteria: Patients aged 0 to 18 years at the time of diagnosis Diagnoses confirmed through, diagnostic testing, or specialist evaluation Conditions classified as rare (affecting fewer than 1 in 2,000 individuals) or complex, involving multisystem involvement or requiring specialized, coordinated care

Exclusion criteria

Exclusion criteria: Incomplete or ambiguous records Cases lacking definitive diagnostic confirmation Conditions that are common, self-limiting, or routinely managed in primary care settings

Design outcomes

Primary

Measure	Time frame
Diagnostic accuracy for the top three differential diagnoses generated by ChatGPT	—

Countries

Asia(except Japan)

Contacts

Public ContactRahel Ali

kurdistan technical institute Clinical Pharmacist

rahel.ali@kti.edu.iq+964-771-702-8282

Outcome results