Artificial Intelligence-based Models for Spine Malalignment Auto-analysis

NCT06711757 | Completed

• 1 other identifier: UW 24-350
• Study Type: observational
• Target: 3,015
• Locations: 1 country
• Sites: 1

Brief Summary

This retrospective study aimed to enhance and validate a model for diagnosing adolescent idiopathic scoliosis (AIS) across multiple medical centers. The study included 2,763 participants from prestigious hospitals in mainland China and Hong Kong. X-rays were used to develop and validate the model, with data from different hospitals to ensure robustness. Participants aged 10-18 with confirmed AIS were enrolled, and data were deidentified for privacy. The model was optimized using training data and validated internally before being deployed for real-world application. A novel data augmentation technique was used to address data heterogeneity, and a standardized analysis platform, AlignProCARE, was employed for evaluation. X-rays were annotated with vertebra landmarks, and traditional and intensity-based data augmentation methods were applied for image processing. Coronal Cobb angle was used to evaluate spinal alignment, with severity classified as normal-mild, moderate, or severe. The model's performance was statistically assessed for accuracy in predicting Cobb angle and severity grading. Overall, the study aimed to provide a reliable diagnostic tool for AIS analysis in clinical practice, improving efficiency and standardization in diagnosis and treatment.

Conditions

Adolescent Idiopathic Scoliosis

Keywords

Adolescent idiopathic scoliosis; spine malalignment; artificial intelligence; data heterogeneity; multi-centre cohort study

Outcome Measures

Primary Outcomes (1)

• Cobb Angle prediction accuracy

  Coronal Cobb angle was adopted as the standard measurement to evaluate the coronal alignment of each AIS patient. We evaluate the performance of our artificial intelligence model based on Cobb Angle prediction accuracy.

  through study completion, an average of 1 year

Secondary Outcomes (1)

• AIS severity classification accuracy

  through study completion, an average of 1 year

Study Arms (6)

QMH&DKCH cohort

A total of 1,950 whole spine posteroanterior X-rays collected from two local hospitals (QMH and DKCH) were utilized for the development and internal validation of our model.

PUMCH cohort

314 whole spine posteroanterior X-rays from Peking Union Medical College Hospital, Beijing, China

NFH cohort

94 whole spine posteroanterior X-rays from Nanfang Hospital, Guangzhou, China

JSTH cohort

187 whole spine posteroanterior X-rays from Jishuitan Hospital, Beijing, China

RJH cohort

294 whole spine posteroanterior X-rays from Ruijin Hospital, Shanghai, China

HSH cohort

176 whole spine posteroanterior X-rays from Huashan Hospital, Shanghai, China

Eligibility Criteria

• Age: 10 Years - 18 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64)
• Sampling Method: Non-Probability Sample

Study Population

Patients diagnosed with adolescent idiopathic scoliosis.

You may qualify if:

• Participants aged between 10 and 18 years old,
• A pathological confirmation of the presence or absence of AIS

You may not qualify if:

• Patients with other types of scoliosis, such as congenital or neuromuscular scoliosis
• Patients with skin diseases, such as acne, psoriasis, skin pigmentation and rash that can affect imaging
• Individuals that cannot stand up
• Cases where standing imaging was not feasible or other conditions that could impair image acquisition.

Sponsors & Collaborators

• The University of Hong Kong: lead
• Peking Union Medical College Hospital: collaborator
• Queen Mary Hospital, Hong Kong: collaborator
• The Duchess of Kent Children's Hospital at Sandy Bay: collaborator
• Ruijin Hospital: collaborator
• Huashan Hospital: collaborator
• Beijing Jishuitan Hospital: collaborator
• Nanfang Hospital, Southern Medical University: collaborator

Study Sites (1)

Digital Health Laboratory, Li Ka Shing Faculty of Medicine, The University of Hong Kong

Hong Kong, Hong Kong

Location

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: November 20, 2024
• First Posted: December 2, 2024
• Study Start: January 5, 2022
• Primary Completion: October 5, 2024
• Study Completion: November 5, 2024
• Last Updated: December 2, 2024

Record last verified: 2024-11

Data Sharing

• IPD Sharing: Will not share

Locations

HK (1)