| Unique ID issued by UMIN | UMIN000058921 |
|---|---|
| Receipt number | R000067387 |
| Scientific Title | Development of an AI Model for Detecting Heart Failure from Fundus Images |
| Date of disclosure of the study information | 2025/12/31 |
| Last modified on | 2025/08/28 23:55:13 |
Development of an AI Model for Detecting Heart Failure from Fundus Images
Development of an AI Model for Detecting Heart Failure from Fundus Images
Development of an AI Model for Detecting Heart Failure from Fundus Images
Development of an AI Model for Detecting Heart Failure from Fundus Images
| Japan |
Heart failure
| Medicine in general |
Others
NO
Fundus findings, including retinal arteries, may contain information on the early stages of heart disease. This study aims to develop an artificial intelligence (AI) model that can automatically predict heart failure using fundus images obtained non-invasively with a non-mydriatic fundus camera.
Safety,Efficacy
Exploratory
Pragmatic
Phase I
Accuracy of an AI model for predicting lifestyle-related diseases and elevated NT-proBNP, and for estimating cardiovascular disease (sensitivity, specificity, positive predictive value, negative predictive value)
Correlation between AI-derived risk scores and outcomes (mortality and incidence of cardiovascular events)
Observational
| 20 | years-old | <= |
| Not applicable |
Male and Female
(1) Adults aged 20 years or older
(2)Patients with cardiovascular disease who are outpatients or inpatients at the Department of Cardiovascular Medicine, The University of Tokyo Hospital, or Moriyama Memorial Hospital
(3)Employees of the Meiji Yasuda Health Insurance Association who undergo health checkups
Participants who meet criterion (1) and either (2) or (3), and who provide informed consent to participate in this study, will be included.
Patients who do not provide informed consent to participate in the study
400
| 1st name | Eriko |
| Middle name | |
| Last name | Hasumi |
The University of Tokyo Hospital
Department of cardiology
113-8655
1-7-3 Hongo, Bunkyo-ku, Tokyo, Japan
38155411
ehasumi@gmail.com
| 1st name | Eriko |
| Middle name | |
| Last name | Hasumi |
The University of Tokyo Hospital
Department of cardiology
113-8655
1-7-3 Hongo, Bunkyo-ku, Tokyo, Japan
0338155411
ehasumi@gmail.com
The University of Tokyo Hospital
Eriko Hasumi
Ministry of Education, Culture, Sports, Science and Technology
Japanese Governmental office
Japan
The University of Tokyo Hospital
1-7-3 Hongo, Bunkyo-ku, Tokyo, Japan
0338155411
ehasumi@gmail.com
NO
東京都
| 2025 | Year | 12 | Month | 31 | Day |
Unpublished
Enrolling by invitation
| 2024 | Year | 08 | Month | 01 | Day |
| 2024 | Year | 10 | Month | 21 | Day |
| 2025 | Year | 04 | Month | 01 | Day |
| 2027 | Year | 03 | Month | 31 | Day |
Recruitment will be conducted among outpatients or inpatients at the Department of Cardiovascular Medicine, The University of Tokyo Hospital, and Moriyama Memorial Hospital, as well as among employees of the Meiji Yasuda Health Insurance Association undergoing health checkups. After obtaining informed consent, fundus images will be captured using a portable fundus camera, and blood sampling and clinical data collection will be performed. These data will then be analyzed to develop the AI model.
| 2025 | Year | 08 | Month | 28 | Day |
| 2025 | Year | 08 | Month | 28 | Day |
Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000067387