Skip to content

The Effect of an AIoT-Based Smart Exercise System in Older Adults

Development of a Precision Exercise System for Older Adults and People With Stroke Using Deep Learning and Facial Action Units

Status
Recruiting
Phases
Unknown
Study type
Interventional
Source
ClinicalTrials.gov
Registry ID
NCT07779824
Enrollment
200
Registered
2026-08-21
Start date
2026-02-20
Completion date
2028-07-31
Last updated
2026-08-26

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Exercise, Seniors

Keywords

Seniors, Exercise, facial action unit

Brief summary

This clinical trial aims to evaluate the effectiveness of an artificial intelligence of things (AIoT)-based exercise system for seniors. Participants will undergo a 12-week AIoT-based cycle ergometer training program. Physical fitness and functional performance will be assessed at baseline and after completion of the intervention. Throughout the intervention, exercise-related data, including exercise duration, workload, heart rate, oxygen consumption, perceived exertion, and facial expressions, will be continuously and simultaneously collected for analysis.

Detailed description

At baseline (Week 0), participants will undergo a personal health assessment and physical fitness evaluation. The health assessment includes the collection of demographic information, medical history, and general health status. The physical fitness assessment includes measurement of body composition, muscle strength, balance, flexibility, walking speed, and other relevant physical fitness measures. Following the baseline assessment, the participants will undergo the exercise program based on an AIoT-based exercise system twice weekly for 12 weeks. blood pressure will assessed before each exercise for safety concern. At Week 13, participants will undergo the same evaluations conducted at baseline. In addition, a user experience questionnaire will be administered. During the exercise sessions, exercise-related metrics, including workload, cadence (revolutions per minute, RPM), exercise duration, heart rate, and facial action units (AUs), will be continuously recorded in real time. Ratings of perceived exertion will also be collected at regular intervals throughout the exercise sessions.

Interventions

DEVICEAIoT-based cycle ergometer exercise system

AIoT-based cycle ergometer exercise system The system also continuously records exercise-related device data, personal physiological parameters, and facial action units in a structured and systematic manner.

Sponsors

I-Shou University
Lead SponsorOTHER
National Cheng-Kung University Hospital
CollaboratorOTHER

Study design

Allocation
NA
Intervention model
SINGLE_GROUP
Primary purpose
OTHER
Masking
NONE

Eligibility

Sex/Gender
ALL
Age
50 Years to No maximum
Healthy volunteers
No

Inclusion criteria

* Adult over 50 years old * No significant limb disability or joint deformation * No history of cardiovascular disease * Never lost balance due to dizziness in the past 12 months

Exclusion criteria

* Limb disability or joint deformation * History of cardiovascular disease * Lost balance due to dizziness in the past 12 months * Cognitive deficits

Design outcomes

Primary

MeasureTime frameDescription
30 second chair stand testbaselineNumber of full stands that can completed in 30 seconds with arms folded across chest.

Secondary

MeasureTime frameDescription
Back scratchbaselineBack scratch with one hand reaching over shoulder and one up the middle of the back, the distance (cm) between extended middle fingers is recorded.
Chair sit-&-reach testbaselineFrom a sitting position at front of chair, with leg extended and hands reaching toward toes, the distance (cm) between extended fingers and tip of toe is recorded.
2-minute step testbaseline2-minute step test is to complete steps in 2 minutes. Number of full steps completed in 2 minutes is recorded.
Single leg balance with eyes open testbaselineParticipant is instructed to stand by one leg with eye open, the number of seconds is recorded.
Hand grip strength testbaselineHand grip strength test is performed by HandGRIP Dynamometer
SOF (Study of Osteoporotic Fractures) frailty index (Questionnaire for physical function and health status)baselineRisk factors for fractures and falls and has grown to look at various determinants of successful aging. Three questions about frailty and two questions about depression.
SARC-FbaselineThe SARC-F questionnaire is a Fast diagnostic test for SARCopenia that assesses strength, assistance in walking, rising from a chair, climbing stairs, and falls. Scores range from 0 to 10, with scores ≥4 indicating a higher risk of sarcopenia.
EQ-5D (EuroQol- 5 Dimensions)baselineThe EQ-5D is a standardized questionnaire that assesses health-related quality of life across five dimensions: mobility, self-care, usual activities, pain/discomfort, and anxiety/depression. Higher scores indicate greater health problems.
QUEST (Questionnaire for satisfaction)Within 7 days after completion of the 12-week interventionThe 8 items of the questionnaire included Dimensions, Weight, Ease in Adjusting, Safety and Security, Durability, Ease of Use, Comfortable, and Effectiveness. Each item employed a 5-point scale, with 1-point representing not satisfied at all, and 5-point representing very satisfied. Evaluation of Satisfaction with Assistive Technology.
System Usability Scale (SUS)Within 7 days after completion of the 12-week interventionThe System Usability Scale (SUS) is a reliable, 10-item Likert-scale questionnaire utilized to provide a global evaluation of a system's usability and user-friendliness. Each item is scored from 1 (strongly disagree) to 5 (strongly agree). Higher scores indicate better system usability.
Facial MovementPeriproceduralFacial movement will be recorded by video during exercise.
Heart RatePeriproceduralHeart rate is monitored continuously during exercise sessions.
Rating of perceived exertionPeriproceduralRating of perceived exertion is assessed during exercise sessions to characterize participants' perceived exercise intensity.
BMIbaselineSarcopenia weight in kilograms divided by the square of height in meters is recorded as Body Mass Index (BMI).
Up and Go testbaselineNumber of seconds required to get up from a seated position, walk 8 feet, turn, and return to seated position.
SMIbaselineSkeletal muscle mass index (SMI), which is the sum of the muscle masses of the four limbs as appendicular skeletal mass (ASM) in kilograms divided by the square of height in meters, is detected by TANITA MC-780MA body composition analyzer.
Six-minute walk testbaselineTo walk as much as possible within six minutes and measure the total distance traveled.

Countries

Taiwan

Contacts

CONTACTChih-Chun Lin
chihchunlin@isu.edu.tw+886-76151100 Ext. 7566
CONTACTChien-Yu Hsu
sophia992104@isu.edu.tw+886-76151100 Ext. 7597

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Aug 27, 2026