UMIN-CTR Clinical Trial
| Unique ID issued by UMIN | UMIN000057006 |
|---|---|
| Receipt number | R000065018 |
| Scientific Title | Estimation of Skeletal Muscle Mass Using Digital Images and Machine Learning |
| Date of disclosure of the study information | 2025/02/14 |
| Last modified on | 2025/02/12 20:10:05 |
* 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
Estimation of Skeletal Muscle Mass Using Digital Images and Machine Learning
Acronym
Estimation of Skeletal Muscle Mass Using Digital Images
Scientific Title
Estimation of Skeletal Muscle Mass Using Digital Images and Machine Learning
Scientific Title:Acronym
Estimation of Skeletal Muscle Mass Using Digital Images
Region
| Japan |
Condition
Condition
Healthy adults
Classification by specialty
| Adult |
Classification by malignancy
Others
Genomic information
NO
Objectives
Narrative objectives1
The purpose of this study is to develop and validate a method for estimating skeletal muscle mass using machine learning algorithms applied to digital images of the lower leg in healthy adults.
Japan's aging rate is rapidly increasing, with predictions suggesting that by 2050, 37.1% of the total population will be 65 years or older. In this super-aged society, addressing malnutrition and sarcopenia has become a critical issue. The GLIM criteria for malnutrition diagnosis and the AWGS 2019 criteria for sarcopenia in Asians emphasize the importance of skeletal muscle mass assessment. Conventional methods for evaluating skeletal muscle mass (such as DXA, BIA, MRI, and CT) require expensive equipment and specialized skills, making them difficult to use in general medical facilities or home healthcare settings. On the other hand, simpler methods like measuring calf circumference have accuracy issues.
Recently, digital image classification using machine learning has gained attention as a highly accurate method for measuring skeletal muscle mass. This study will utilize lower leg images captured by smartphones or digital cameras to verify the predictive accuracy of skeletal muscle mass estimation using machine learning algorithms.
This research is a basic study targeting healthy adults and cannot be directly applied to sarcopenia diagnosis or skeletal muscle mass assessment in the elderly. However, the findings of this study are expected to provide fundamental insights into rapid and accurate methods for evaluating skeletal muscle mass, with potential future applications for a wide range of subjects, including hospitalized patients and community-dwelling elderly.
Basic objectives2
Efficacy
Basic objectives -Others
Trial characteristics_1
Confirmatory
Trial characteristics_2
Explanatory
Developmental phase
Not applicable
Assessment
Primary outcomes
Digital image (single evaluation time point)
Key secondary outcomes
age, sex, height, weight, Body Mass Index, skeletal muscle mass, calf circumference, grip strength, lower leg length (single evaluation time point)
Base
Study type
Interventional
Study design
Basic design
Single arm
Randomization
Non-randomized
Randomization unit
Blinding
Open -no one is blinded
Control
Uncontrolled
Stratification
NO
Dynamic allocation
NO
Institution consideration
Institution is not considered as adjustment factor.
Blocking
NO
Concealment
No need to know
Intervention
No. of arms
1
Purpose of intervention
Prevention
Type of intervention
| Device,equipment |
Interventions/Control_1
Measurement of body weight and skeletal muscle mass using InBody:
Body weight and skeletal muscle mass of the limbs will be measured in a standing position. The Skeletal Muscle mass Index (SMI) will be calculated by adjusting the skeletal muscle mass for height.
Digital image capture:
The lateral and posterior aspects of the non-dominant lower leg will be photographed against a white background floor and back panel. A digital camera (SONY Cyber-shot DSC-WX220) and a smartphone (Android, OPPO Reno5 A) will be used for capturing images. Care will be taken to ensure the non-measured leg does not appear in the frame. The distance between the lens and the lower leg will be kept constant, with the lens fixed on a tripod. A level attached to the tripod will be used to ensure horizontal alignment. To minimize hand shake, a timer will be used for the shutter release. Three images will be taken, and one will be selected after visual confirmation. The measurement position for the lateral aspect of the lower leg will be seated, while the posterior aspect will be captured in a standing position. The ankle dorsiflexion angle will be standardized at 0 degrees.
Measurement of calf circumference:
The maximum calf circumference of the non-dominant leg will be measured using a tape measure, with the subject either seated or standing.
Grip strength measurement:
Grip strength will be measured in a standing position using a digital dynamometer, alternating between left and right hands twice each. When gripping the dynamometer, the arm should hang naturally, ensuring the device does not touch the body or clothing.
Height measurement:
Height will be measured using a stadiometer with the subject standing barefoot.
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
| 18 | years-old | <= |
Age-upper limit
| Not applicable |
Gender
Male and Female
Key inclusion criteria
(1) Those who have provided written consent to participate in the research
(2) Individuals aged 18 years or older
Key exclusion criteria
(1) Those who have difficulty maintaining a standing position
(2) Those with edema or similar conditions in the lower leg
(3) Those with implanted medical devices such as cardiac pacemakers
(4) Those with any limb amputation
(5) Those with metal implants or bolts in their body
(6) Those who are pregnant or possibly pregnant
(7) Those with a history of fractures or ligament injuries in the lower limbs
(8) Those with a history of central or peripheral nervous system disorders
(9) Those deemed unsuitable as research subjects by the principal investigator and co-investigators
Target sample size
100
Research contact person
Name of lead principal investigator
| 1st name | Hiroo |
| Middle name | |
| Last name | Matsuse |
Organization
Kurume University Hospital
Division name
Department of Rehabilitation
Zip code
830-0011
Address
67 Asahi-machi, Kurume-shi, Fukuoka 830-0011, Japan
TEL
0942-35-3311
matsuse_hiroh@kurume-u.ac.jp
Public contact
Name of contact person
| 1st name | Hiroo |
| Middle name | |
| Last name | Matsuse |
Organization
Kurume University Hospital
Division name
Department of Rehabilitation
Zip code
830-0011
Address
67 Asahi-machi, Kurume-shi, Fukuoka 830-0011, Japan
TEL
0942-35-3311
Homepage URL
matsuse_hiroh@kurume-u.ac.jp
Sponsor or person
Institute
Kurume University
Institute
Department
Personal name
Funding Source
Organization
None
Organization
Division
Category of Funding Organization
Other
Nationality of Funding Organization
Other related organizations
Co-sponsor
Name of secondary funder(s)
IRB Contact (For public release)
Organization
Clinical Research Center, Kurume University Hospital
Address
67 Asahi-machi, Kurume-shi, Fukuoka 830-0011, Japan
Tel
0942-65-3749
i_rinri@kurume-u.ac.jp
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
久留米大学病院、九州栄養福祉大学、小倉リハビリテーション病院、九州工業大学
Other administrative information
Date of disclosure of the study information
| 2025 | Year | 02 | Month | 14 | 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
Results
Results date posted
Results Delayed
Results Delay Reason
Date of the first journal publication of results
Baseline Characteristics
Participant flow
Adverse events
Outcome measures
Plan to share IPD
IPD sharing Plan description
Progress
Recruitment status
Preinitiation
Date of protocol fixation
| 2025 | Year | 01 | Month | 30 | Day |
Date of IRB
| 2025 | Year | 01 | Month | 30 | Day |
Anticipated trial start date
| 2025 | Year | 02 | Month | 14 | Day |
Last follow-up date
| 2026 | Year | 08 | Month | 31 | Day |
Date of closure to data entry
| 2026 | Year | 09 | Month | 30 | Day |
Date trial data considered complete
| 2026 | Year | 10 | Month | 31 | Day |
Date analysis concluded
| 2026 | Year | 12 | Month | 31 | Day |
Other
Other related information
Management information
Registered date
| 2025 | Year | 02 | Month | 12 | Day |
Last modified on
| 2025 | Year | 02 | Month | 12 | Day |
Link to view the page
Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000065018
