Pose Estimation and Inertial Measurement Unit Systems for Gait Analysis in Older Adults

NCT07119944 | Active Not Recruiting

• 2 other identifiers: 9768-GOADecision No: 2025/12-08
• Study Type: observational
• Target: 30
• Locations: 1 country
• Sites: 1

Brief Summary

1. 1.Are gait analyses using pose estimation algorithms consistent with those performed using an inertial measurement unit-based system in older adults?
2. 2.Are gait analyses using pose estimation algorithms reliable in older adults?

Conditions

Older Adults (65 Years and Older)

Keywords

older adults; gait analysis; pose estimation; Inertial Measurement Units; reliability

Outcome Measures

Primary Outcomes (16)

• Inertial Measurement Unit (IMU)-Based Gait Analysis Parameters-Gait Speed

  Gait analysis will be performed using the BTS G-WALK device, a validated and reliable inertial measurement unit (IMU)-based system. The device will be securely attached at the level of the S1 vertebra using a belt. Start and end points will be marked on the floor, and participants will be asked to walk a distance of 4 meters. The system will measure walking speed as meters/second.

  Baseline

• Inertial Measurement Unit (IMU)-Based Gait Analysis Parameters-Cadance

  Gait analysis will be performed using the BTS G-WALK device, a validated and reliable inertial measurement unit (IMU)-based system. The device will be securely attached at the level of the S1 vertebra using a belt. Start and end points will be marked on the floor, and participants will be asked to walk a distance of 4 meters. The system will measure cadence as steps/minute.

  Baseline

• Inertial Measurement Unit (IMU)-Based Gait Analysis Parameters-Step Length

  Gait analysis will be performed using the BTS G-WALK device, a validated and reliable inertial measurement unit (IMU)-based system. The device will be securely attached at the level of the S1 vertebra using a belt. Start and end points will be marked on the floor, and participants will be asked to walk a distance of 4 meters. The system will measure step length as meters.

  Baseline

• Inertial Measurement Unit (IMU)-Based Gait Analysis Parameters-Step Duration

  Gait analysis will be performed using the BTS G-WALK device, a validated and reliable inertial measurement unit (IMU)-based system. The device will be securely attached at the level of the S1 vertebra using a belt. Start and end points will be marked on the floor, and participants will be asked to walk a distance of 4 meters. The system will measure step duration as seconds.

  Baseline

• Inertial Measurement Unit (IMU)-Based Gait Analysis Parameters-Stance Time

  Gait analysis will be performed using the BTS G-WALK device, a validated and reliable inertial measurement unit (IMU)-based system. The device will be securely attached at the level of the S1 vertebra using a belt. Start and end points will be marked on the floor, and participants will be asked to walk a distance of 4 meters. Stance time will be measured by the system and expressed as a percentage of the gait cycle (%).

  Baseline

• Inertial Measurement Unit (IMU)-Based Gait Analysis Parameters-Swing Time

  Gait analysis will be performed using the BTS G-WALK device, a validated and reliable inertial measurement unit (IMU)-based system. The device will be securely attached at the level of the S1 vertebra using a belt. Start and end points will be marked on the floor, and participants will be asked to walk a distance of 4 meters. Swing time will be measured by the system and expressed as a percentage of the gait cycle (%).

  Baseline

• Inertial Measurement Unit (IMU)-Based Gait Analysis Parameters-Double Support Time

  Gait analysis will be performed using the BTS G-WALK device, a validated and reliable inertial measurement unit (IMU)-based system. The device will be securely attached at the level of the S1 vertebra using a belt. Start and end points will be marked on the floor, and participants will be asked to walk a distance of 4 meters. Double support time will be measured by the system and expressed as a percentage of the gait cycle (%).

  Baseline

• Inertial Measurement Unit (IMU)-Based Gait Analysis Parameters-Single Support Time

  Gait analysis will be performed using the BTS G-WALK device, a validated and reliable inertial measurement unit (IMU)-based system. The device will be securely attached at the level of the S1 vertebra using a belt. Start and end points will be marked on the floor, and participants will be asked to walk a distance of 4 meters. Single support time will be measured by the system and expressed as a percentage of the gait cycle (%).

  Baseline

• Gait Analysis Using Pose Estimation Algorithms-Gait Speed

  Video recordings captured simultaneously with the inertial measurement unit (IMU)-based gait analysis system will be processed using a pose estimation algorithm. To ensure temporal alignment with the BTS G-WALK system, the videos will be trimmed and synchronized accordingly. The YOLO 11X-Pose algorithm version 0.25 with a threshold score will be employed for pose estimation. This algorithm dynamically tracks 17 key joint points on the body diagram during gait to extract dynamic gait parameters. To allow valid comparison with the IMU-based system, the algorithm will derive gait speed as meters/second.

  Baseline (first session) and 1-3 days after the baseline (second session)

• Gait Analysis Using Pose Estimation Algorithms-Cadance

  Video recordings captured simultaneously with the inertial measurement unit (IMU)-based gait analysis system will be processed using a pose estimation algorithm. To ensure temporal alignment with the BTS G-WALK system, the videos will be trimmed and synchronized accordingly. The YOLO 11X-Pose algorithm version 0.25 with a threshold score will be employed for pose estimation. This algorithm dynamically tracks 17 key joint points on the body diagram during gait to extract dynamic gait parameters. To allow valid comparison with the IMU-based system, the algorithm will derive the cadence as steps/minute.

  Baseline (first session) and 1-3 days after the baseline (second session)

• Gait Analysis Using Pose Estimation Algorithms-Step Length

  Video recordings captured simultaneously with the inertial measurement unit (IMU)-based gait analysis system will be processed using a pose estimation algorithm. To ensure temporal alignment with the BTS G-WALK system, the videos will be trimmed and synchronized accordingly. The YOLO 11X-Pose algorithm version 0.25 with a threshold score will be employed for pose estimation. This algorithm dynamically tracks 17 key joint points on the body diagram during gait to extract dynamic gait parameters. To allow valid comparison with the IMU-based system, the algorithm will derive step length as meters.

  Baseline (first session) and 1-3 days after the baseline (second session)

• Gait Analysis Using Pose Estimation Algorithms-Step Duration

  Video recordings captured simultaneously with the inertial measurement unit (IMU)-based gait analysis system will be processed using a pose estimation algorithm. To ensure temporal alignment with the BTS G-WALK system, the videos will be trimmed and synchronized accordingly. The YOLO 11X-Pose algorithm version 0.25 with a threshold score will be employed for pose estimation. This algorithm dynamically tracks 17 key joint points on the body diagram during gait to extract dynamic gait parameters. To allow valid comparison with the IMU-based system, the algorithm will derive the step duration as seconds.

  Baseline (first session) and 1-3 days after the baseline (second session)

• Gait Analysis Using Pose Estimation Algorithms-Stance Time

  Video recordings captured simultaneously with the inertial measurement unit (IMU)-based gait analysis system will be processed using a pose estimation algorithm. To ensure temporal alignment with the BTS G-WALK system, the videos will be trimmed and synchronized accordingly. The YOLO 11X-Pose algorithm version 0.25 with a threshold score will be employed for pose estimation. This algorithm dynamically tracks 17 key joint points on the body diagram during gait to extract dynamic gait parameters. To enable valid comparisons with the IMU-based system, the algorithm will calculate stance time and express it as a percentage of the gait cycle (%).

  Baseline (first session) and 1-3 days after the baseline (second session)

• Gait Analysis Using Pose Estimation Algorithms-Swing Time

  Video recordings captured simultaneously with the inertial measurement unit (IMU)-based gait analysis system will be processed using a pose estimation algorithm. To ensure temporal alignment with the BTS G-WALK system, the videos will be trimmed and synchronized accordingly. The YOLO 11X-Pose algorithm version 0.25 with a threshold score will be employed for pose estimation. This algorithm dynamically tracks 17 key joint points on the body diagram during gait to extract dynamic gait parameters. To enable valid comparisons with the IMU-based system, the algorithm will calculate swing time and express it as a percentage of the gait cycle (%).

  Baseline (first session) and 1-3 days after the baseline (second session)

• Gait Analysis Using Pose Estimation Algorithms-Double Support Time

  Video recordings captured simultaneously with the inertial measurement unit (IMU)-based gait analysis system will be processed using a pose estimation algorithm. To ensure temporal alignment with the BTS G-WALK system, the videos will be trimmed and synchronized accordingly. The YOLO 11X-Pose algorithm version 0.25 with a threshold score will be employed for pose estimation. This algorithm dynamically tracks 17 key joint points on the body diagram during gait to extract dynamic gait parameters. To enable valid comparisons with the IMU-based system, the algorithm will calculate double support time and express it as a percentage of the gait cycle (%).

  Baseline (first session) and 1-3 days after the baseline (second session)

• Gait Analysis Using Pose Estimation Algorithms-Single Support Time

  Video recordings captured simultaneously with the inertial measurement unit (IMU)-based gait analysis system will be processed using a pose estimation algorithm. To ensure temporal alignment with the BTS G-WALK system, the videos will be trimmed and synchronized accordingly. The YOLO 11X-Pose algorithm version 0.25 with a threshold score will be employed for pose estimation. This algorithm dynamically tracks 17 key joint points on the body diagram during gait to extract dynamic gait parameters. To enable valid comparisons with the IMU-based system, the algorithm will calculate single support time and express it as a percentage of the gait cycle (%).

  Baseline (first session) and 1-3 days after the baseline (second session)

Other Outcomes (3)

• Mini-Mental Test

  Baseline

• Timed Up and Go Test

  Baseline

• Baseline Demographics

  Baseline

Study Arms (1)

Older Adults

Only one group of participants is included in this study, since the focus is on evaluating and comparing two gait analysis measurement techniques within the same individuals.

Other: Not Related

Interventions

Not Related OTHER

This observational study does not involve any therapeutic intervention. Instead, all participants undergo gait analysis using two different measurement methods-2D pose estimation algorithms and an inertial measurement unit (G-Walk system)-to compare their outputs. Both assessments are performed on the same individuals under standardized conditions without altering their routine care.

Older Adults

Eligibility Criteria

• Age: 60 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Community dwelling older adults aged above 65

You may qualify if:

• Ability to walk independently
• Mini-Mental State Examination (MMSE) score ≤ 23/30

You may not qualify if:

• Inability to walk independently for more than 20 meters without assistive devices
• Inability to understand or comply with test instructions
• Lack of consent to participate
• Presence of severe neurological, musculoskeletal, cardiac, or psychological disorders

Sponsors & Collaborators

• Bozok University: lead
• Dokuz Eylul University: collaborator

Study Sites (1)

Dokuz Eylul University, Faculty of Physical Therapy and Rehabilitation

Izmir, Balcova, 35330, Turkey (Türkiye)

Location

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: CROSS SECTIONAL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Assistant Professor

Study Record Dates

• First Submitted: July 1, 2025
• First Posted: August 13, 2025
• Study Start: April 9, 2025
• Primary Completion: April 9, 2026
• Study Completion (Estimated): July 9, 2026
• Last Updated: November 25, 2025

Record last verified: 2025-11

Data Sharing

• IPD Sharing: Will not share

Locations

TU (1)