AI-Adaptive AR Training for Balance and Falls Prevention in Older Adults

NCT07781995 | Not Yet Recruiting DMC

• 1 other identifier: 20142
• Study Type: interventional
• Target: 30
• Locations: 1 country
• Sites: 1

Brief Summary

Falls are a common problem in adults within the age of 55-80 years and can lead to injury and loss of independence. This study is testing a new type of balance training using augmented reality (AR). In this intervention, participants will see virtual objects, such as obstacles, placed in their environment and will practice stepping over or moving around them. The system will adjust the difficulty based on each person's performance. Participants will complete training sessions over several weeks. We will measure changes in balance, walking ability, and confidence before and after the program. The goal is to see if this training can help improve balance and reduce the risk of falls in older adults.

Conditions

Older Adults; Older Adults, Balance

Keywords

Augmented Reality; Gait; Balance; Falls Prevention

Outcome Measures

Primary Outcomes (3)

• Participant Retention Rate

  Retention will be calculated as the percentage of enrolled participants who complete the post-intervention assessment (T2): number completing T2 divided by the number enrolled at baseline (T1), multiplied by 100.

  From baseline (T1) through post-intervention assessment (T2), approximately 8 weeks

• Adherence to the Augmented Reality Training Program

  Adherence will be calculated for each participant as the percentage of prescribed AR training sessions completed during the 8-week intervention. Participants are prescribed 3-5 sessions per week, with each session lasting approximately 30 minutes.

  Throughout the 8-week intervention

• Weekly Augmented Reality Training Session Completion

  Weekly training participation will be assessed based on the number of AR training sessions completed each week. Completion of 3-5 sessions per week will be used to characterize adherence to the intended training frequency.

  Weekly throughout the 8-week intervention

Secondary Outcomes (7)

• Change in Mini Balance Evaluation Systems Test (Mini-BESTest) Score

  Baseline (T1) and immediately post-intervention (T2), approximately 8 weeks

• Change in Timed Up and Go (TUG) Performance

  Baseline (T1) and immediately post-intervention (T2), approximately 8 weeks

• Change in Activities-specific Balance Confidence (ABC) Scale Score

  Baseline (T1) and immediately post-intervention (T2), approximately 8 weeks

• Change in BTrackS Limits of Stability

  Baseline (T1) and immediately post-intervention (T2), approximately 8 weeks

• Change in BTrackS Fall Risk Assessment

  Baseline (T1) and immediately post-intervention (T2), approximately 8 weeks

Study Arms (1)

Participants receive the 8-week AI-enhanced AR balance and mobility training, 3-5 sessions per week.

EXPERIMENTAL

Participants will complete an 8-week AI-enhanced augmented reality balance and mobility training program, with 3-5 sessions per week lasting approximately 30 minutes each. Training includes standing- and walking-based tasks such as obstacle negotiation, path following, step targeting, turning, and directional changes. Task difficulty is adaptively adjusted based on participant performance using a machine learning model designed to maintain an approximately 80% task success rate.

Device: AI-Enhanced Augmented Reality Balance and Mobility Training

Interventions

AI-Enhanced Augmented Reality Balance and Mobility Training DEVICE

Participants will complete an 8-week AI-enhanced augmented reality (AR) balance and mobility training program, consisting of 3-5 sessions per week of approximately 30 minutes each. Using AR smart glasses connected to a dedicated smartphone, participants will perform standing- and walking-based tasks, including obstacle negotiation, path following, step targeting, turning, and directional changes. A machine learning model adapts task difficulty based on individual performance using a challenge-point framework targeting approximately 80% task success. Difficulty is iteratively increased or decreased based on performance, including adjustments to target speed and target size. Training may be completed at McMaster University or, following an initial supervised session and home safety assessment, at the participant's home.

Participants receive the 8-week AI-enhanced AR balance and mobility training, 3-5 sessions per week.

Eligibility Criteria

• Age: 55 Years - 80 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Aged 55 - 80 years
• Able to ambulate independently with or without an assistive device
• Able to understand and follow instructions unimpeded by significant cognitive barriers (MoCA score must be 24/30 or higher)
• Self-reported balance concerns or perceived risk of falls (e.g., reduced balance confidence)
• Must be able to provide a list of current medications to the experimenters and the changes in medications during the study
• Vision that normal or near normal with/without the use of glasses/lenses
• Able to understand and follow study instructions in English

You may not qualify if:

• Engaging in any additional balance or mobility training programs while participating in the study
• Diagnosed neurological conditions that substantially impair balance or mobility (e.g., stroke, Parkinson's disease, Traumatic Brain Injury)
• Medical conditions that contraindicate moderate physical activity
• Vision impairment that cannot be corrected by glasses or lenses

Sponsors & Collaborators

• McMaster University: lead

Study Sites (1)

Ivor Wynne Center

Hamilton, Ontario, L8S 4L8, Canada

Location

Related Links

• Chen W, Li M, Li H, Lin Y and Feng Z (2023) Tai Chi for fall prevention and balance improvement in older adults: a systematic review and meta-analysis of randomized controlled trials. Front.
• Pillay, J., Gaudet, L.A., Saba, S. et al. Falls prevention interventions for community-dwelling older adults: systematic review and meta-analysis of benefits, harms, and patient values and preferences.
• Yoo HN, Chung E, Lee BH. The Effects of Augmented Reality-based Otago Exercise on Balance, Gait, and Falls Efficacy of Elderly Women. J Phys Ther Sci.
• Chen PJ, Penn IW, Wei SH, Chuang LR, Sung WH. Augmented reality-assisted training with selected Tai-Chi movements improves balance control and increases lower limb muscle strength in older adults: A prospective randomized trial. J Exerc Sci Fit.
• Im DJ, Ku J, Kim YJ, Cho S, Cho YK, Lim T, Lee HS, Kim HJ, Kang YJ. Utility of a Three-Dimensional Interactive Augmented Reality Program for Balance and Mobility Rehabilitation in the Elderly: A Feasibility Study. Ann Rehabil Med.
• Vieira ER, Civitella F, Carreno J, Junior MG, Amorim CF, D'Souza N, Ozer E, Ortega F, Estrázulas JA. Using Augmented Reality with Older Adults in the Community to Select Design Features for an Age-Friendly Park: A Pilot Study. J Aging Res.
• Blomqvist S, Seipel S, Engström M. Using augmented reality technology for balance training in the older adults: a feasibility pilot study. BMC Geriatr.
• Lamichhane P, Sukralia S, Alam B, Shaikh S, Farrukh S, Ali S, Ojha R. Augmented reality-based training versus standard training in improvement of balance, mobility and fall risk: a systematic review and meta-analysis. Ann Med Surg (Lond).
• Vinolo Gil MJ, Gonzalez-Medina G, Lucena-Anton D, Perez-Cabezas V, Ruiz-Molinero MDC, Martín-Valero R. Augmented Reality in Physical Therapy: Systematic Review and Meta-analysis. JMIR Serious Games.

Central Study Contacts

Aimee Nelson

CONTACT

(905) 525-9140; nelsonaj@mcmaster.ca

Xiru Wang

CONTACT

wangx256@mcmaster.ca

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NA
• Masking: NONE
• Purpose: PREVENTION
• Intervention Model: SINGLE GROUP
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Professor

Model Details: Single-arm open-label feasibility study where all participants will receive intervention.

Study Record Dates

• First Submitted: August 19, 2026
• First Posted: August 24, 2026
• Study Start (Estimated): November 30, 2026
• Primary Completion (Estimated): April 30, 2028
• Study Completion (Estimated): August 31, 2028
• Last Updated: August 25, 2026

Record last verified: 2026-08

Data Sharing

• IPD Sharing: Will not share

Locations

CA (1)