Menu
Recruiting NCT05146193

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

Observational Spinal Deformity

For patients and families

In plain language

An automatic summary of structured registry data. It is an orientation aid, not a substitute for the official protocol or a physician assessment.

What is being studied
The protocol lists: Nude back photo.
Who it may be relevant to
Registry conditions: Spinal Deformity. Basic parameters: 10 years — 80 years · All.
What needs checking
Age, condition and sex are only basic indicators. Prior treatment, laboratory values and other mandatory requirements appear in the eligibility criteria below.
Where it takes place
Hong Kong
Next step
Save the trial, show it to the treating physician, and confirm current recruitment with the study center. Costs, documents and travel →

Overview

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:

1. 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. 2. 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). 3. Use transfer learning to update the current AlignProCARE for scoliosis analysis to form AlignProCARE+.

4 Qualitatively analyse the AlignProCARE+ using an independent dataset.

Interventions

  • Other Nude back photo
    Nude back photo at baseline and at follow-ups for each patient and visual severity and curve type classifications

Primary outcome measures

  • Cobb angle [Time frame: 1 year]
Secondary outcome measures (7)
  • Thoracic kyphosis [Time frame: 1 year]
  • Lumbar lordosis [Time frame: 1 year]
  • Pelvic tilt [Time frame: 1 year]
  • Sacral slope [Time frame: 1 year]
  • Pelvic incidence [Time frame: 1 year]
  • Maximum thoracic kyphosis [Time frame: 1 year]
  • Curve severity [Time frame: 1 year]

Eligibility criteria

Inclusion criteria

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

Exclusion criteria

  • Refusal for imaging, postoperative patients

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Study design

Observational model
Cohort

Study locations

Hong Kong · 1 center
  • Duchess of Kent Children's Hospital — Hong Kong

Identifiers

NCT: NCT05146193 · AI_Scoliosis

Primary sources (government registries)

View this study on ClinicalTrials.gov ↗