UMIN-CTR Clinical Trial
| Unique ID issued by UMIN | UMIN000048543 |
|---|---|
| Receipt number | R000055311 |
| Scientific Title | Development of an artificial intelligence-based primary headache diagnosis model |
| Date of disclosure of the study information | 2022/08/01 |
| Last modified on | 2023/02/06 17:05:00 |
* This page includes information on clinical trials registered in UMIN clinical trial registed system.
* We don't aim to advertise certain products or treatments
Basic information
Public title
Development of an artificial intelligence-based primary headache diagnosis model
Acronym
Artificial intelligence-based primary headache diagnosis model
Scientific Title
Development of an artificial intelligence-based primary headache diagnosis model
Scientific Title:Acronym
Artificial intelligence-based primary headache diagnosis model
Region
| Japan |
Condition
Condition
Headache
Classification by specialty
| Medicine in general | Neurology | Pediatrics |
| Neurosurgery |
Classification by malignancy
Others
Genomic information
NO
Objectives
Narrative objectives1
Few physicians can make a proper headache diagnosis from a medical interview and provide appropriate treatment according to the diagnosis. One reason for this is that the headache diagnosis is not always accurate. Therefore, it is hoped that clinicians can accurately diagnose headaches and lead to treatment without overlooking migraines, which have burdens on daily life. This study will develop an artificial intelligence (AI)-based diagnostic model that can accurately diagnose migraine from questionnaires by using a data set of approximately 4,000 outpatient headache cases at Tominaga Hospital. The development of this model will enable general practitioners who are not skilled in headache treatment to accurately diagnose migraine using this model and provide a bridge to appropriate headache treatment. To investigate the AI-based model's usefulness, the accuracy of the headache diagnosis made from the clinical questionnaire sheet by non-headache specialists will be investigated.
Basic objectives2
Efficacy
Basic objectives -Others
Trial characteristics_1
Trial characteristics_2
Developmental phase
Assessment
Primary outcomes
Diagnostic accuracy of headache diagnostic based on headache questionnaires by non-headache specialists with and without AI-based diagnostic models.
Key secondary outcomes
Diagnostic accuracy of AI-based diagnostic models in the test data.
Base
Study type
Observational
Study design
Basic design
Randomization
Randomization unit
Blinding
Control
Stratification
Dynamic allocation
Institution consideration
Blocking
Concealment
Intervention
No. of arms
Purpose of intervention
Type of intervention
Interventions/Control_1
Interventions/Control_2
Interventions/Control_3
Interventions/Control_4
Interventions/Control_5
Interventions/Control_6
Interventions/Control_7
Interventions/Control_8
Interventions/Control_9
Interventions/Control_10
Eligibility
Age-lower limit
| Not applicable |
Age-upper limit
| Not applicable |
Gender
Male and Female
Key inclusion criteria
First-time patients who visited Tominaga Hospital Headache Outpatient Clinic
Key exclusion criteria
Patients who cannot answer the questionnaire sheet
Target sample size
4000
Research contact person
Name of lead principal investigator
| 1st name | Takao |
| Middle name | |
| Last name | Takeshima |
Organization
Tominaga Hospital
Division name
Headache Center and Department of Neurology
Zip code
556-0017
Address
1 - 4 - 48 Minatomachi, Naniwa ward, Osaka, Japan
TEL
06-6568-1601
Takao.Takeshima@nifty.com
Public contact
Name of contact person
| 1st name | Tomokazu |
| Middle name | |
| Last name | Shimazu |
Organization
Saitama Neuropsychiatric Institute
Division name
Department of Neurology
Zip code
338-0003
Address
6-11-1 Honmachi-Higashi, Chuo-ku, Saitama, Saitama
TEL
048-857-6811
Homepage URL
tsyshimazu@aol.com
Sponsor or person
Institute
Tominaga Hospital
Institute
Department
Personal name
Funding Source
Organization
None
Organization
Division
Category of Funding Organization
Self funding
Nationality of Funding Organization
Other related organizations
Co-sponsor
Name of secondary funder(s)
IRB Contact (For public release)
Organization
Tominaga Hospital Research Ethics Committee
Address
1 - 4 - 48 Minatomachi, Naniwa ward, Osaka, Japan
Tel
06-6568-1601
Takao.Takeshima@nifty.com
Secondary IDs
Secondary IDs
NO
Study ID_1
Org. issuing International ID_1
Study ID_2
Org. issuing International ID_2
IND to MHLW
Institutions
Institutions
Other administrative information
Date of disclosure of the study information
| 2022 | Year | 08 | Month | 01 | Day |
Related information
URL releasing protocol
Publication of results
Published
Result
URL related to results and publications
10.1177/03331024231156925
Number of participants that the trial has enrolled
4050
Results
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.
Results date posted
| 2023 | Year | 02 | Month | 06 | Day |
Results Delayed
Results Delay Reason
Date of the first journal publication of results
Baseline Characteristics
The AI learns the data of 2,800 patients out of 4,000 patients at Tominaga Hospital Headache Center's anonymized interview data and 5 diagnoses by headache specialists (migraine, tension-type headache, trigeminal/autonomic headache, other primary headaches, secondary headaches such as cerebrovascular disorders), and develops an AI that provides the probability of each of the 5 diagnoses by entering 17 items from the medical questionnaire. The AI was developed to present the probability of each of the five types of diagnosis by inputting 17 items of the medical questionnaire. Examined diagnostic accuracy for test data of 1200 cases. Other 50 cases were diagnosed by non-headache specialists with and without AI, respectively, and their accuracy was examined.
Participant flow
Adverse events
None
Outcome measures
Accuracy, sensitivity, and specificity related to diagnosis of 1200 test dataset. Accuracy, sensitivity, and specificity of diagnosis for 50 new cases by non-headache specialists with and without AI.
Plan to share IPD
IPD sharing Plan description
Progress
Recruitment status
Main results already published
Date of protocol fixation
| 2022 | Year | 04 | Month | 05 | Day |
Date of IRB
| 2022 | Year | 04 | Month | 05 | Day |
Anticipated trial start date
| 2022 | Year | 04 | Month | 05 | Day |
Last follow-up date
| 2023 | Year | 03 | Month | 31 | Day |
Date of closure to data entry
Date trial data considered complete
Date analysis concluded
Other
Other related information
https://prtimes.jp/main/html/rd/p/000000005.000115401.html
Management information
Registered date
| 2022 | Year | 08 | Month | 01 | Day |
Last modified on
| 2023 | Year | 02 | Month | 06 | Day |
Link to view the page
Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000055311
| Research Plan | |
|---|---|
| Registered date | File name |
| 2023/02/06 | 20220705糸魚川倫理申請書AIによる頭痛診断.docx |
| Research case data specifications | |
|---|---|
| Registered date | File name |
| 2023/02/06 | 頭痛の問診表v3.pdf |
| Research case data | |
|---|---|
| Registered date | File name |
| 2023/02/06 | 20220705頭痛診断Total4000.csv |
