A study of an AI-assisted multimodal assessment system for aerobic gymnastics training
| ISRCTN | ISRCTN14809597 |
|---|---|
| DOI | https://doi.org/10.1186/ISRCTN14809597 |
| Sponsor | Hanyang University |
| Funder | Investigator initiated and funded |
- Submission date
- 06/07/2026
- Registration date
- 06/07/2026
- Last edited
- 06/07/2026
- Recruitment status
- No longer recruiting
- Overall study status
- Completed
- Condition category
- Other
Plain English summary of protocol
Background and study aims
This study evaluated whether an artificial intelligence (AI)-assisted multimodal system can improve the assessment of aerobic gymnastics training. The aim was to determine whether an AI-based system integrating video analysis, motion capture, physiological signals, and psychological measures can provide more objective and accurate feedback on performance, fatigue, psychological readiness, and injury risk.
Who can participate?
Adults aged 18–30 years with at least 6 months of aerobic gymnastics experience, currently training at least twice per week, and with no recent musculoskeletal injury or serious medical conditions.
What does the study involve?
Participants were randomly allocated to either an AI-assisted feedback group or a conventional training/control group for a 12-week intervention. Both groups trained three times per week (60 minutes per session). The intervention group received multimodal AI-based feedback, while the control group received standard coaching feedback. Assessments were conducted at baseline, week 6, and week 12.
What are the possible benefits and risks of participating?
Participants may benefit from improved feedback on training quality and better monitoring of fatigue and injury risk. Risks are minimal and limited to normal exercise-related fatigue or minor musculoskeletal discomfort.
Where is the study run from?
The study is conducted collaboratively at Sejong University (South Korea) and Hanyang University (South Korea).
When is the study starting and how long is it expected to run for?
March 2024 to October 2024
Who is funding the study?
Investigator initiated and funded
Who is the main contact?
Gang Qin, qingang@hanyang.ac.kr
Contact information
Public, Scientific, Principal investigator
Seoul
Seoul
04763
Thailand
 ORCID ID |
0009-0000-4147-2870 |
|---|---|
| Phone | +66 (0)1056135210 |
| qingang@hanyang.ac.kr |
Study information
| Primary study design | Interventional |
|---|---|
| Allocation | Randomized controlled trial |
| Masking | Blinded (masking used) |
| Control | Active |
| Assignment | Parallel |
| Purpose | Device feasibility |
| Scientific title | Development and validation of an AI-driven multimodal system for assessing aerobic gymnastics training using video analysis, motion capture, and physiological signals |
| Study acronym | AIM-AerobicGym |
| Study objectives | To develop and validate an AI-driven multimodal assessment system for aerobic gymnastics training by integrating video analysis, motion capture, physiological signals, cognitive tracking, and psychological measures, and to evaluate its accuracy, feasibility, and usefulness for assessing performance, fatigue, psychological readiness, and injury risk. |
| Ethics approval(s) |
Approved 28/02/2024, Ethics Committee of the School of Physical Education, Shandong Normal University (School of Physical Education, Shandong Normal University, Jinan, 250014, China; +86 (0)1056135210; qingang@hanyang.ac.kr), ref: SDNUTYDW2024019 |
| Health condition(s) or problem(s) studied | Aerobic gymnastics training performance, fatigue, psychological readiness, and injury risk assessment |
| Intervention | Participants were randomly assigned to either an AI-assisted feedback group or a conventional training/control group for 12 weeks using a computer-generated randomisation sequence. The sequence was generated by an independent researcher who was not involved in recruitment, assessment, or intervention delivery. Allocation concealment was ensured using sequentially numbered, opaque, sealed envelopes (SNOSE). Participants were assigned in a 1:1 allocation ratio. Both groups completed aerobic gymnastics training three times per week, 60 minutes per session. The AI-assisted group received multimodal feedback based on video analysis, motion capture, physiological monitoring, cognitive tracking, and psychological assessment. The control group received standard coaching and evaluator-based feedback. |
| Intervention type | Device |
| Phase | Not Applicable |
| Drug / device / biological / vaccine name(s) | AI-driven multimodal assessment system for aerobic gymnastics training |
| Primary outcome measure(s) |
|
| Key secondary outcome measure(s) |
|
| Completion date | 01/10/2024 |
Eligibility
| Participant type(s) | |
|---|---|
| Age group | Adult |
| Lower age limit | 18 Years |
| Upper age limit | 30 Years |
| Sex | All |
| Target sample size at registration | 600 |
| Total final enrolment | 600 |
| Key inclusion criteria | 1. Adults aged 18–30 years 2. At least 6 months of aerobic gymnastics experience 3. Active training at least twice per week 4. No musculoskeletal injury within the past 3 months 5. Able to complete the 12-week training protocol 6. Provided written informed consent |
| Key exclusion criteria | 1. Cardiovascular disease 2. Recent surgery 3. Musculoskeletal injury within the past 3 months 4. Inability to complete the 12-week training protocol 5. Inability or unwillingness to provide written informed consent |
| Date of first enrolment | 01/03/2024 |
| Date of final enrolment | 30/05/2024 |
Locations
Countries of recruitment
- China
- Korea, South
Study participating centres
Results and Publications
| Individual participant data (IPD) Intention to share | No |
|---|
Editorial Notes
06/07/2026: Study's existence confirmed by the Ethics Committee of the School of Physical Education, Shandong Normal University.
