Artificial Intelligence-Based Postural Feedback for Scoliosis

The Effect of Artificial Intelligence-Based Postural Feedback on Posture Correction in Idiopathic Scoliosis Patients

Due to advancements in technology, Posture-Analyzing and Virtual Reconstructing (PAViR) systems were developed. They used Red-Green-Blue-Depth camera sensors and artificial intelligence to evaluate human posture alignment, muscle balance, and movement without the use of radiation or physical markers. This technology served as a portable, X-ray-like device that was safe and user-friendly, providing detailed views of bone and muscle models alongside easy-to-understand 3D visualizations. However, how to utilize the data obtained from PAViR to support traditional treatment remained unclear. To fill this gap, this study aimed to investigate the effects of AI-based postural feedback on posture correction in patients with idiopathic scoliosis.

Study Overview

• Status: Not yet recruiting
• Conditions: Idiopathic Adolescent Scoliosis; Postural Alignment
• Intervention / Treatment: Other: Postural feedback; Other: Physical therapy for scoliosis

• Study Type: Interventional
• Enrollment (Estimated): 30
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Rommanee Rojasavastera, M.Sc.; Phone Number: +66837830777; Email: rommanee.roj@mahidol.ac.th

Study Locations

• Thailand
  • Changwat Nakhon Pathom
    • Salaya, Changwat Nakhon Pathom, Thailand, 73170
      • Faculty of Physical Therapy, Mahidol University
      • Contact: Rommanee Rojasavastera, M.Sc.; Phone Number: +66837830777; Email: rommanee.roj@mahidol.ac.th

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Diagnosis of adolescent idiopathic scoliosis (AIS) by a physician.
• Aged between 10 and 18 years.
• Cobb angle between 10 and 40 degrees.

Exclusion Criteria:

• Leg length discrepancy greater than 2 cm, measured from the anterior superior iliac spine (ASIS) to the lateral malleolus.
• Previous history of spinal surgery.
• Musculoskeletal or neurological injuries that affect balance and gait.
• Inability to follow the research procedures.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Treatment
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Single

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: AI-Based Postural Feedback Group; Participants in the experimental group received postural feedback via the PAViR system, integrated with posture correction exercises and physical therapy for scoliosis.	Other: Postural feedback; The physical therapist reported the findings from the PAViR system to the participants during a 10-minute session. Data regarding skeletal alignment and muscle imbalances were provided to enhance participants' self-awareness of their specific postural issues. Furthermore, these insights were integrated into the subsequent training sessions for the experimental group.; Other: Physical therapy for scoliosis; The physical therapist conducted 60-minute sessions. These sessions were grounded in the principles of the Schroth Method and Physiotherapeutic Scoliosis-Specific Exercises (PSSE).
Active Comparator: Conventional Postural Feedback Group; Participants in the control group received the same exercise and therapy sessions, but without the postural feedback provided by the PAViR system.	Other: Physical therapy for scoliosis; The physical therapist conducted 60-minute sessions. These sessions were grounded in the principles of the Schroth Method and Physiotherapeutic Scoliosis-Specific Exercises (PSSE).

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
REEDCO postural score	The REEDCO Posture Assessment was used to evaluate postural scores during comfortable standing and postural self-correction.	before and immediately after intervention
Angle of trunk rotation	A scoliometer was used to evaluate the angle of trunk rotation during Adam's Forward Bend Test.	before and immediately after intervention
Postural Variables Derived from a 3D Motion Analysis System	A 3D motion analysis system (VICON Motion Systems Ltd., Oxford, UK) was used to evaluate postural variables during comfortable standing, postural self-correction, and the Adam's Forward Bend Test.	before and immediately after intervention
Postural Variables Derived from a PAViR System	A PAViR system (MGsolutions Inc., Seoul, South Korea) was used to evaluate postural variables during comfortable standing, postural self-correction, and the Adam's Forward Bend Test.	before and immediately after intervention

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Illness Perception	The Brief Illness Perception Questionnaire (IPQ-B) was an accurate and valid assessment tool to measure and monitor illness perceptions. It consisted of nine items rated on a scale from 0 (minimum) to 10 (maximum). The first five assessed cognitive perceptions such as the effect on life (item 1); duration of illness (item 2); control over illness (item 3); beliefs about the effectiveness of treatment (item 4); and experience of symptoms (item 5). Items 6 and 8 assessed emotional aspects, which included concern about the illness and a multifaceted question about mood. Item 7 assessed the degree of understanding of the illness. The final item was open-ended, asking respondents to rank the three most important factors causing their illness.	before and immediately after intervention
Exercise Motivation	The Behavioral Regulation in Exercise Questionnaire-2 (BREQ-2) was a 19-item questionnaire that measured the stages of the self-determination continuum with respect to motivation to exercise using a 5-point Likert scale (0 = not true for me, 4 = very true for me) and was modified by Markland and Tobin. The version by Markland and Tobin added an amotivation factor to the original external, introjected, identified, and intrinsic regulation factors.	before and immediately after intervention

Collaborators and Investigators

• Sponsor: Mahidol University

Study record dates

Study Major Dates

• Study Start (Estimated): July 1, 2026
• Primary Completion (Estimated): July 1, 2027
• Study Completion (Estimated): July 1, 2027

Study Registration Dates

• First Submitted: June 17, 2026
• First Submitted That Met QC Criteria: June 22, 2026
• First Posted (Actual): June 25, 2026

Study Record Updates

• Last Update Posted (Actual): June 25, 2026
• Last Update Submitted That Met QC Criteria: June 22, 2026
• Last Verified: June 1, 2026

More Information

Terms related to this study

• Keywords: scoliosis; posture; artificial Intelligence; three-dimensional imaging
• Additional Relevant MeSH Terms: Bone Diseases; Musculoskeletal Diseases; Spinal Diseases; Spinal Curvatures; Scoliosis; Therapeutics; Rehabilitation; Physical Therapy Modalities
• Other Study ID Numbers: MU-CIRB 2026/171.2603

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: Research data will be shared in a de-identified format only; for instance, participant names will be replaced with codes, and faces will be blurred in all images.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No