MedPath

Development of an artificial intelligence-based primary headache diagnosis model

Not Applicable
Conditions
Headache
Registration Number
JPRN-UMIN000048543
Lead Sponsor
Tominaga Hospital
Brief Summary

76% correct, 56% sensitivity, 92% specificity for the 1200 patients' testdata. Non-specialist headache diagnostic accuracy for new 50 patients without AI was 46%, but improved to 83% with AI.

Detailed Description

Not available

Recruitment & Eligibility

Status
Complete: follow-up complete
Sex
All
Target Recruitment
4050
Inclusion Criteria

Not provided

Exclusion Criteria

Patients who cannot answer the questionnaire sheet

Study & Design

Study Type
Observational
Study Design
Not specified
Primary Outcome Measures
NameTimeMethod
Diagnostic accuracy of headache diagnostic based on headache questionnaires by non-headache specialists with and without AI-based diagnostic models.
Secondary Outcome Measures
NameTimeMethod
Diagnostic accuracy of AI-based diagnostic models in the test data.
© Copyright 2025. All Rights Reserved by MedPath