Short-term Changes in Postural Sway, Gait, and fNIRS-derived Cortical Metrics After a 4-week AI-assisted Exercise Program: a Single-arm Pre-post Study

NCT07876011 | Completed

• 2 other identifiers: M20260775V1719219040846
• Study Type: interventional
• Target: 50
• Locations: 1 country
• Sites: 1

Brief Summary

This single-arm pre-post study will enroll 50 participants aged 52-65 years who will undergo a 4-week AI-assisted exercise intervention. Postural balance, functional near-infrared spectroscopy (fNIRS), and three-dimensional motion capture data will be assessed before and after the intervention under different task conditions. During the dual-task condition, the correct response rate (CRR) during serial subtraction of 7 will be recorded. Adverse events occurring during the intervention will also be monitored and recorded.

Conditions

Fall Risk in Middle-Aged and Older Adults

Outcome Measures

Primary Outcomes (1)

• gait speed

  Baseline and immediately after completion of the 4-week intervention

Secondary Outcomes (3)

• sway area

  Baseline and immediately after completion of the 4-week intervention

• PFC_HbO

  Baseline and immediately after completion of the 4-week intervention

• double support

  Baseline and immediately after completion of the 4-week intervention

Other Outcomes (2)

• lateral variability

  Baseline and immediately after completion of the 4-week intervention

• Global efficiency (fNIRS)

  Baseline and immediately after completion of the 4-week intervention

Study Arms (1)

AI-Assisted Exercise

EXPERIMENTAL

Participants will receive a 4-week combined exercise intervention, 5 days per week with 2 days of rest. Each 60-minute session will include 10 minutes of warm-up, 20 minutes of AI-assisted lower-extremity strength and functional training, 20 minutes of aerobic cycling, and 10 minutes of cool-down. The AI-assisted training system will provide individualized exercise guidance, real-time monitoring, and movement correction. Aerobic cycling will be performed at approximately 55% heart rate reserve using a recumbent cycle ergometer. Safety and adverse events will be monitored throughout the intervention.

Behavioral: AI-assited exercise

Interventions

AI-assited exercise BEHAVIORAL

A 4-week AI-assisted combined exercise intervention consisting of lower-extremity strength and functional training and aerobic cycling, delivered 5 days per week with individualized guidance and real-time movement monitoring.

AI-Assisted Exercise

Eligibility Criteria

• Age: 52 Years - 70 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Age 52-70 years, regardless of sex.
• Able to walk independently for at least 10 meters without any assistive device.
• Normal or corrected-to-normal vision and normal hearing, with the ability to understand and complete all study procedures as instructed.
• Willing to participate in the study and provide written informed consent.

You may not qualify if:

• Severe musculoskeletal, neurological, cardiopulmonary, or psychiatric diseases or a history of such conditions.
• Severe cognitive impairment.
• A history of drug or substance abuse within the past 3 months.
• Any other condition that may affect participation in or the assessment of the study.

Sponsors & Collaborators

• Peking University Third Hospital: lead

Study Sites (1)

Peking University Third Hospital Chongli Hospital, Yingbin Road, Chongli District, Zhangjiakou, Hebei, China

Zhangjiakou, Hebei, China

Location

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: Associate Researcher, Associate Chief Physician

Study Record Dates

• First Submitted: October 1, 2026
• First Posted: October 15, 2026
• Study Start: January 8, 2025
• Primary Completion: October 20, 2025
• Study Completion: October 20, 2025
• Last Updated: October 15, 2026

Record last verified: 2026-10

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)