AI-Powered Scoliosis Auto-Analysis System Multicenter Dev... | NCT05146193

Studies
AI-Powered Scoliosis Auto-Analysis System Multicenter Development and Validations

NCT05146193

Sponsor

The University of Hong Kong

Status

Recruiting

Last Update Posted

May 1, 2026Actual

Enrollment

2,500Estimated

Phase

Not provided

Conditions

Spinal Deformity

Interventions

Nude back photo

Countries

Hong Kong

Protocol Section

Identification Module Status Module Sponsor/Collaborators Module Oversight Module Description Module Conditions Module Design Module Arms/Interventions Module Outcomes Module Eligibility Module Contacts/Locations Module References Module IPD Sharing Statement Module

Results Section

Participant Flow Module Baseline Characteristics Module Outcome Measures Module Adverse Events Module More Info Module

Annotation Section

Annotation Module

Document Section

Large Document Module

Derived Section

Miscellaneous Info Module Condition Browse Module Intervention Browse Module

Protocol Section

Identification Module

NCT ID

Results Section

No data available

No data is available for this block.

Annotation Section

No data available

No data is available for this block.

Document Section

No data available

No data is available for this block.

Derived Section

Miscellaneous Info Module

Version Holder

Status Module

Record Verification Date

Apr 2026

Overall Recruitment Status or Expanded Access Status

Recruiting

Last Known Status

Not provided

Delayed Posting

Not provided

Why Stopped

Not provided

Expanded Access Info

Start Date

May 1, 2022Actual

Primary Completion Date

Feb 1, 2029Estimated

Completion Date

Feb 1, 2030Estimated

First Submitted Date

Nov 12, 2021

First Submission Date that Met QC Criteria

Nov 23, 2021

First Posted Date

Dec 6, 2021Actual

Results Waived

Not provided

Results First Submitted Date

Not provided

Results First Submitted that Met QC Criteria

Not provided

Results First Posted Date

Not provided

Certification/Extension (aka Delayed Results) First Submitted Date

Not provided

Certification/Extension First Submitted that Passed QC Review

Not provided

Certification/Extension First Posted Date

Not provided

Last Update Submitted Date

Apr 27, 2026

Last Update Posted Date

May 1, 2026Actual

Sponsor/Collaborators Module

Responsible Party, by Official Title

Dr. Jason Pui Yin Cheung, Clinical Associate Professor, The University of Hong KongPrincipal Investigator

Lead Sponsor

The University of Hong KongOTHER

Collaborators

Name	Class
Peking Union Medical College	OTHER
Peking University Third Hospital	OTHER
Beijing Chao Yang Hospital	OTHER
University of Malaya

Oversight Module

Has Data Monitoring Committee (DMC)

Is FDA Regulated Drug

Is FDA Regulated Device

Is Unapproved Device

Not provided

Pediatric Postmarket Surveillance of a Device Product

Not provided

Product Exported from US

Not provided

FDAAA801 Violation

Not provided

Description Module

Brief Summary

The investigators aim to use artificial intelligence (AI) to help clinicians in diagnosing and assessing spinal deformities.

Detailed Description

Background Spinal deformity is a prevalent spinal disorder in both paediatric and adult populations. The spine alignment need to be quantitively assessed for further treatment planning. However, the current practice requires spine surgeons to manually place landmarks of endplates and key vertebrae. The process is laborious and prone to inter- and intra-rater variance. Thus, the investigators have developed an AI-powered spine alignment assessment system (AlignProCARE) to facilitate clinicians in fast, accurate and consistent analytical results.

The investigators aim to test and improve the performance of the spine alignment auto-analysis in all patients with spinal deformities in multiple centers including Malaysia, China, and Japan

Objectives:

prospectively test the alignment assessment of patients' spinal deformities with whole spine X-rays (both PA and lateral) and nude back image with the assessment via AlignProCARE.
Collect 500 labeled deformity radiographs and nude back images in both PA and lateral views per center. 150 patients need to be followed up with radiographs and nude back photos collected (all parameters measured again).
Use transfer learning to update the current AlignProCARE for scoliosis analysis to form AlignProCARE+.

4 Qualitatively analyse the AlignProCARE+ using an independent dataset.

Design Module

Study Type

Observational

Number of References to an Expanded Access Study

Not provided

Expanded Access Types

Not provided

Patient Registry

Target Follow-Up Duration

Not provided

Phases

Not provided

Interventional Study Design

Allocation

Not provided

Intervention Model

Biospecimen

No data available

No data is available for this block.

Enrollment

2,500Estimated

Arms/Interventions Module

Arm Groups

Label	Type	Description	Intervention Names
All subjects are diagnosed of having a spinal deformity		Routine care of patients with spinal deformities	Other: Nude back photo

Interventions

Name	Type	Description	Arm Group Labels	Other Names
Nude back photo	Other	Nude back photo at baseline and at follow-ups for each patient and visual severity and curve type classifications	All subjects are diagnosed of having a spinal deformity

Outcomes Module

Primary Outcomes

Measure	Description	Time Frame
Cobb angle	Coronal Cobb angle of the spinal deformity. The most tilted end vertebrae away from the apex will be used for measurement of the Cobb angle.The anteroposterior radiograph is used to assess	1 year

Secondary Outcomes

Measure	Description	Time Frame
Thoracic kyphosis	Thoracic kyphosis T5-12: angle between upper endplate of T5 to lower endplate of T12 in the lateral radiograph	1 year
Lumbar lordosis	Lumbar lordosis L1-S1: angle between upper endplate of L1 to top of S1 in the lateral radiograph

Other Outcomes

Not provided

Eligibility Module

Eligibility Criteria

Inclusion Criteria:

Idiopathic scoliosis, adult deformity (spondylolisthesis, idiopathic kyphosis, kyphoscoliosis, lordoscoliosis)

Exclusion Criteria:

Refusal for imaging, postoperative patients

Accepts Healthy Volunteers

Not provided

Sex

All

Sex/Gender Based

Not provided

Sex/Gender Description

Not provided

Minimum Age

10 Years

Maximum Age

80 Years

Standard Ages

ChildAdultOlder Adult

Study Population

All subjects with spinal deformities

Sampling Method

Non-Probability Sample

Contacts/Locations Module

Central Contacts

Name	Role	Phone	Extension	Email
Jason Pui Yin Cheung, MD, MS	Contact	(852) 22554254		cheungjp@hku.hk
Teng Zhang, PhD	Contact	(852) 22554254		tgzhang@hku.hk

Overall Officials

Name	Affiliation	Role
Jason Pui Yin Cheung, MD, MS	Queen Mary Hospital, Duchess of Kent Children's Hospital	Principal Investigator

Locations

Facility	Status	City	State	ZIP	Country	Contacts
Duchess of Kent Children's Hospital	Recruiting	Hong Kong			Hong Kong

IPD Sharing Statement Module

Plan to Share IPD

Description

Not provided

Types

Not provided

Time Frame

Not provided

Access Criteria

Not provided

URL

Not provided

Condition Browse Module

MeSH Terms

ID	Term
D000013	Congenital Abnormalities
D012600	Scoliosis
D013168	Spondylolisthesis

Ancestor Terms

ID	Term
D009358	Congenital, Hereditary, and Neonatal Diseases and Abnormalities
D013121	Spinal Curvatures
D013122	Spinal Diseases
D001847	Bone Diseases

Browse Leaves

Not provided

Browse Branches

Not provided