Digital Health for Lumbar Degeneration

NCT07133724 | Recruiting

• 1 other identifier: 202502072RIND
• Study Type: interventional
• Target: 100
• Locations: 1 country
• Sites: 1

Brief Summary

This study will integrate wireless wearable sensors, smartphone imaging, and multimodal artificial intelligence (AI) to address the rehabilitation needs of patients with lumbar degeneration. Patients will undergo comprehensive functional assessments, and individualized exercise instruction with real-time feedback will be provided through a smartphone application. The goals of this research are to: (1) develop a multimodal AI-based digital health system combining IMU sensors and smartphone cameras for real-time assessment and interactive rehabilitation training, (2) construct biomechanics- and gait-analysis models to support personalized rehabilitation for patients with lumbar degeneration, and (3) investigate the mechanisms and clinical efficacy of pelvic control exercise training combined with real-time smartphone feedback in improving function and quality of life for aging patients.

Conditions

Degenerative Lumbar Spine Diseases

Keywords

degenerative lumbar spine disease; real-time detection; artificial Intelligence

Outcome Measures

Primary Outcomes (3)

• Functional assessment: Walking speed

  Functional assessment is a process that allows for the identification of disability. The data from the functional assessment is used to calculate walking speed (unit: m/s).

  6 months

• Functional assessment: Walking distance

  Functional assessment is a process that allows for the identification of disability. The data from the functional assessment is used to calculate walking distance (unit: m).

  6 months

• Functional assessment: 5 Times Sit to Stand Test

  Functional assessment is a process that allows for the identification of disability. The data from the 5 Times Sit to Stand Test is used to calculate the duration it took to complete the test (unit: s).

  6 months

Secondary Outcomes (2)

• Kinematic variables: Joint angles

  6 months

• Kinetic variables

  6 months

Study Arms (1)

AI-Based Smart Assessment and Rehabilitation Training

EXPERIMENTAL

The multimodal AI-based smart assessment and rehabilitation training system developed in this study will provide patients with lumbar degeneration a convenient and precise home-based rehabilitation solution.

Other: AI-Based Smart Assessment and Rehabilitation Training

Interventions

AI-Based Smart Assessment and Rehabilitation Training OTHER

Through the integration of wireless inertial sensors and smartphone imaging, the system can monitor pelvic and lumbar movements in real time, generate a digital twin model, and deliver instant feedback to guide patients in performing correct exercises.

AI-Based Smart Assessment and Rehabilitation Training

Eligibility Criteria

• Age: 50 Years - 80 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Age between 50-80 years to capture the typical characteristics of lumbar degeneration in this age group.
• No history of low back pain lasting more than one week or severe enough to interrupt work within the past year.
• Normal lumbar functional mobility.
• Ability to walk independently for more than 10 meters.

You may not qualify if:

• Presence of systemic joint diseases such as ankylosing spondylitis, rheumatoid arthritis, or multiple sclerosis, which may significantly affect lumbar mobility and gait patterns.
• Central nervous system disorders (e.g., spinal cord injury, stroke, or Parkinson's disease) that may influence gait and motor control.
• Vestibular system disorders, to avoid balance abnormalities interfering with gait testing.
• History of spinal or lower limb surgery, as postoperative changes may affect the accuracy of gait data.
• Inability to communicate or follow instructions.

Sponsors & Collaborators

• National Taiwan University Hospital: lead

Study Sites (1)

National Taiwan University Hospital

Taipei, 100, Taiwan

RECRUITING

Central Study Contacts

Wei-Li Hsu, Ph.D.

CONTACT

886-2-3366-8127; wlhsu@ntu.edu.tw

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NA
• Masking: NONE
• Purpose: TREATMENT
• Intervention Model: SINGLE GROUP
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: August 14, 2025
• First Posted: August 21, 2025
• Study Start: August 1, 2025
• Primary Completion (Estimated): July 31, 2028
• Study Completion (Estimated): July 31, 2028
• Last Updated: August 21, 2025

Record last verified: 2025-08

Locations

TW (1)