UMIN-CTR Clinical Trial
| Unique ID issued by UMIN | UMIN000057871 |
|---|---|
| Receipt number | R000066127 |
| Scientific Title | A prospective diagnostic cohort study to evaluate the usefulness of AI-based heart failure diagnosis using a simple electrocardiogram acquisition device |
| Date of disclosure of the study information | 2025/05/15 |
| Last modified on | 2025/07/02 01:49:54 |
* 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
A prospective diagnostic cohort study to evaluate the usefulness of AI-based heart failure diagnosis using a simple electrocardiogram acquisition device
Acronym
usefulness of AI-based heart failure diagnosis
Scientific Title
A prospective diagnostic cohort study to evaluate the usefulness of AI-based heart failure diagnosis using a simple electrocardiogram acquisition device
Scientific Title:Acronym
usefulness of AI-based heart failure diagnosis
Region
| Japan |
Condition
Condition
Acute heart failure
Classification by specialty
| Cardiology |
Classification by malignancy
Others
Genomic information
NO
Objectives
Narrative objectives1
To verify the diagnostic ability of HF index measured using "SHINDENKUN" (SIMPLEX QUANTUM Inc, Tokyo, JAPAN) in Japanese patients with dyspnea or peripheral edema.
Basic objectives2
Efficacy
Basic objectives -Others
Trial characteristics_1
Confirmatory
Trial characteristics_2
Pragmatic
Developmental phase
Not applicable
Assessment
Primary outcomes
Diagnostic accuracy of heart failure by HF index (sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, AUC)
Key secondary outcomes
Identification of factors affecting the diagnostic ability of the HF index for heart failure, diagnostic accuracy of the HF index for each of the heart failure pathological classifications (HFpEF, HFmrEF, HFrEF), severity (NYHA classification), and clinical scenario classifications, and diagnostic accuracy of NT-proBNP for heart failure
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
| 20 | years-old | <= |
Age-upper limit
| Not applicable |
Gender
Male and Female
Key inclusion criteria
Patients aged 20 years or older who visited a hospital with complaints of shortness of breath or leg edema
Key exclusion criteria
Patients who do not consent
Target sample size
100
Research contact person
Name of lead principal investigator
| 1st name | HIROSHI |
| Middle name | |
| Last name | HORI |
Organization
Minamiuonuma City Hospital
Division name
Internal Medicine
Zip code
9496680
Address
2643-1 Muikamachi, Minamiuonuma City, Niigata, 949-6680, Japan
TEL
+81-25-788-1222
ubm5134@mbr.nifty.com
Public contact
Name of contact person
| 1st name | HIROSHI |
| Middle name | |
| Last name | HORI |
Organization
Minamiuonuma City Hospital
Division name
Internal Medicine
Zip code
9496680
Address
2643-1 Muikamachi, Minamiuonuma City, Niigata, 949-6680, Japan
TEL
09061749328
Homepage URL
ubm5134@mbr.nifty.com
Sponsor or person
Institute
Minamiuonuma City Hospital
Institute
Department
Personal name
HIROSHI HORI
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
Minamiuonuma City Hospital Institutional Review Board
Address
2643-1 Muikamachi, Minamiuonuma City, Niigata, 949-6680, Japan
Tel
+81-25-788-1222
ubm5134@mbr.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
新潟県
Institutions
Institutions
南魚沼市民病院（新潟市）
Other administrative information
Date of disclosure of the study information
| 2025 | Year | 05 | Month | 15 | Day |
Related information
URL releasing protocol
Publication of results
Unpublished
Result
URL related to results and publications
Number of participants that the trial has enrolled
122
Results
The final diagnosis was heart failure in 50 cases.
HF index was higher in heart failure patients than in non-heart failure patients (80.5 vs 15 p <0.01), and NT-proBNP was also higher in heart failure patients (4955 pg/mL vs 157.5 pg/mL p<0.01).
HFpEF accounted for 40% of heart failure patients, with most being CS1 (16%) and CS2 (82%). NYHA3 and NYHA4 accounted for 88%, with many severe cases.
Results date posted
| 2025 | Year | 05 | Month | 13 | Day |
Results Delayed
Results Delay Reason
Date of the first journal publication of results
Baseline Characteristics
A total of 122 participants had a median age of 81.5 years (range, 72.0-88.0), and 52.6% were male.
Edema was observed in 43.7% of patients, and dyspnea was observed in 75.8%.
Respiratory failure (SpO2 <90%) occurred in 21.4% of patients, and hospitalization was common in 74.1% of patients.
Hypertension was the most common comorbidity, occurring in 53.57% of patients.
Heart failure was the final diagnosis in 50 cases.
Participant flow
All patients who met the eligibility criteria were able to complete data collection without any exclusions or dropouts.
Adverse events
None
Outcome measures
In the ROC analysis of the HF index value for determining the presence or absence of heart failure, the AUC was excellent at 0.905 (95% CI 0.846-0.964), and the optimal cutoff of the HF index was 56.5. The sensitivity of the optimal cutoff for diagnosing heart failure was 0.800, the specificity was 0.871, the positive likelihood ratio was 6.20155, and the negative likelihood ratio was 0.22962.
On the other hand, the predictive ability of NT-proBNP value for determining the presence or absence of heart failure was evaluated with an AUC of 0.986 (0.971-1.000), and the cutoff was 1152 pg/mL.
In examining the influence of the HF index on the diagnosis of heart failure in terms of the presence or absence of hospitalization, patient background, electrocardiogram findings, etc., no statistically significant interactions were observed for each factor examined, and the association between the HF index and heart failure was considered to be similar regardless of these factors.
There was no difference in the HF index between HFpEF, HFmrEF, and HFrEF, or between CS1, 2, and 3. The median HF index was lower in NYHA2 than in NYHA3 and NYHA4, but no significant difference was detected, possibly due to the small number of cases.
Plan to share IPD
IPD sharing Plan description
Progress
Recruitment status
Completed
Date of protocol fixation
| 2023 | Year | 03 | Month | 15 | Day |
Date of IRB
| 2023 | Year | 03 | Month | 15 | Day |
Anticipated trial start date
| 2023 | Year | 03 | Month | 15 | Day |
Last follow-up date
| 2025 | Year | 05 | Month | 13 | Day |
Date of closure to data entry
| 2025 | Year | 07 | Month | 01 | Day |
Date trial data considered complete
| 2025 | Year | 07 | Month | 01 | Day |
Date analysis concluded
| 2025 | Year | 07 | Month | 01 | Day |
Other
Other related information
For study participants, a single lead ECG will be recorded for 30 seconds using SHINDENKUN. The quantitative index of HF severity (HF index) derived from this ECG recording using a CNN algorithm will be measured three times in a row, and the average value will be recorded. Participants' age, sex, smoking history, BMI, physical examination findings, comorbidities, medication history, HFindex, laboratory results including NTproBNP, ECG findings, Xray findings, and cardiac ultrasound findings will be recorded. In addition, for cases of heart failure, classification based on ejection fraction (HFrEF, HFpEF, or HFmrEF), clinical scenario, Nohria classification, and NYHA (New York Heart Association) classification will be recorded. Heart failure will be diagnosed according to the Framingham Criteria, and for HFpEF, the HFpEF confirmed criteria from the existing literature (Eur Heart J. 2019 Oct 21 40(40)3297-3317) will be used.
Management information
Registered date
| 2025 | Year | 05 | Month | 14 | Day |
Last modified on
| 2025 | Year | 07 | Month | 02 | Day |
Link to view the page
Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000066127
