Retrospective Case-Control Study for Developing an Artificial Intelligence (AI) Tool for Lesion Detection Using Magnetic Resonance Imaging (MRI) and Clinical Variables for Early Diagnosis of Axial Spondyloarthritis (axSpA)

NCT06591481 | Completed

• 1 other identifier: axSpA-patients-stratification
• Study Type: observational
• Target: 925
• Locations: 4 countries
• Sites: 7

Brief Summary

The goal of this observational study is to develop and validate an Artificial Intelligence (AI) tool that allows the lesion detection and early diagnosis of axial spondyloarthritis (axSpA) based on Magnetic Resonance Imaging (MRI). This study will gather MRI scans from axSpA patients and a control group of participants.

Conditions

Axial Spondyloarthritis (AxSpA)

Keywords

Artificial Intelligence; AI; lesion detection; axial Spondyloarthritis; axSpA; MRI; Magnetic Resonance; medical imaging; tool; algorithm; diagnosis; early

Outcome Measures

Primary Outcomes (6)

• Area Under the Curve (AUC)

  The metric used for parameter optimization and model selection will be the area under the curve (AUC) for balanced dataset.

  From diagnosis until sample completion (an average of 2 years)

• F1 score

  In case of unbalanced dataset, F1 score will be used for parameter optimization and model selection.

  From diagnosis until sample completion (an average of 2 years)

• Balanced accuracy

  From diagnosis until sample completion (an average of 2 years)

• Matthews correlation coefficient

  From diagnosis until sample completion (an average of 2 years)

• Sensitivity

  From diagnosis until sample completion (an average of 2 years)

• Specificity

  From diagnosis until sample completion (an average of 2 years)

Study Arms (2)

Active axSpA patients

Participants diagnosed with axSpA (according to ASAS criteria for axSpA) showing active lesions in their MRI exams.

Control

This group is composed by: 1) Participants with buttock or low back pain that not fulfil ASAS criteria for axSpA and 2) axSpA patients that do not show active lesions in their MRI exams.

Eligibility Criteria

• Age: 18 Years - 44 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64)
• Sampling Method: Non-Probability Sample

Study Population

Participants come from 4 different countries within the EMEA region (Spain, United Arab Emirates, Jordan and Saudi Arabia)

You may qualify if:

• Fulfillment of the ASAS criteria for axSpA (i.e. MRI and/or clinical arm, Rudwaleit M, et al., Ann Rheum Dis. 2009 Oct;68(10):1520-7).
• axSpA diagnosis according to the physician.
• Fulfillment of the following MRI criteria (a-c must be fulfilled):
• a) Availability of MRI images of the sacroiliac joint (SIJ) including T1- weighted and STIR and/or T2 Fat-Sat (FS) sequences in coronal-oblique planes.
• b) Fulfillment of ASAS criteria for positive MRI:
• b.1)Bone marrow oedema (BMO) on a T2-weighted sequence sensitive for free water (such as short tau inversion recovery \[STIR\] or T2FS) or bone marrow contrast enhancement on a T1-weighted sequence (such as T1FS post-gadolinium).
• b.2) Inflammation must be clearly present and located in a typical anatomical area (subchondral bone).
• b.3) MRI appearance must be highly suggestive of SpA.
• b.4) Other findings can be present but are not required for a positive MRI (erosion and/or fat metaplasia and/or ankylosis).
• b.5) Fulfillment of ASAS criteria for positive MRI.
• c) MRI expert opinion of having axial SpA.
• Buttock and/or low back pain due to known trauma, stress, disc herniation with an MRI of SIJ showing absence of bone marrow edema, fatty infiltration and bone erosions and not fulfilling ASAS axSpA classification criteria.
• Availability of MRI images of SIJ including T1-weighted and STIR and/or T2 Fat-Sat sequences in coronal-oblique planes.

You may not qualify if:

• Another known pathology in the SIJ which may influence the MRI interpretation.
• Unreadable MRI images or with insufficient diagnostic quality.

Sponsors & Collaborators

• Ángel Alberich Bayarri: lead

Study Sites (7)

Royal Medical Services

Amman, Jordan

Location

King Saud Medical City

Riyadh, 12746, Saudi Arabia

Location

General University Hospital of Valencia

Valencia, Valencia, 46014, Spain

Location

Tawam hospital (SEHA)

Al Ain City, Al Maqam, United Arab Emirates

Location

Cleveland Clinic Abu Dhabi

Abu Dhabi, United Arab Emirates

Location

YAS Clinic

Abu Dhabi, United Arab Emirates

Location

Emirates Health Services (EHS)

Dubai, United Arab Emirates

Location

Related Publications (8)

• Rudwaleit M, Jurik AG, Hermann KG, Landewe R, van der Heijde D, Baraliakos X, Marzo-Ortega H, Ostergaard M, Braun J, Sieper J. Defining active sacroiliitis on magnetic resonance imaging (MRI) for classification of axial spondyloarthritis: a consensual approach by the ASAS/OMERACT MRI group. Ann Rheum Dis. 2009 Oct;68(10):1520-7. doi: 10.1136/ard.2009.110767. Epub 2009 May 18.

  PMID: 19454404 BACKGROUND

• Lambert RG, Bakker PA, van der Heijde D, Weber U, Rudwaleit M, Hermann KG, Sieper J, Baraliakos X, Bennett A, Braun J, Burgos-Vargas R, Dougados M, Pedersen SJ, Jurik AG, Maksymowych WP, Marzo-Ortega H, Ostergaard M, Poddubnyy D, Reijnierse M, van den Bosch F, van der Horst-Bruinsma I, Landewe R. Defining active sacroiliitis on MRI for classification of axial spondyloarthritis: update by the ASAS MRI working group. Ann Rheum Dis. 2016 Nov;75(11):1958-1963. doi: 10.1136/annrheumdis-2015-208642. Epub 2016 Jan 14.

  PMID: 26768408 BACKGROUND

• Huang Y, Chen Y, Liu T, Lin S, Yin G, Xie Q. Impact of tumor necrosis factor alpha inhibitors on MRI inflammation in axial spondyloarthritis assessed by Spondyloarthritis Research Consortium Canada score: A meta-analysis. PLoS One. 2020 Dec 31;15(12):e0244788. doi: 10.1371/journal.pone.0244788. eCollection 2020.

  PMID: 33382842 BACKGROUND

• Lukas C, Cyteval C, Dougados M, Weber U. MRI for diagnosis of axial spondyloarthritis: major advance with critical limitations 'Not everything that glisters is gold (standard)'. RMD Open. 2018 Jan 12;4(1):e000586. doi: 10.1136/rmdopen-2017-000586. eCollection 2018.

  PMID: 29479474 BACKGROUND

• Khmelinskii N, Regel A, Baraliakos X. The Role of Imaging in Diagnosing Axial Spondyloarthritis. Front Med (Lausanne). 2018 Apr 17;5:106. doi: 10.3389/fmed.2018.00106. eCollection 2018.

  PMID: 29719835 BACKGROUND

• Dougados M, van der Linden S, Juhlin R, Huitfeldt B, Amor B, Calin A, Cats A, Dijkmans B, Olivieri I, Pasero G, et al. The European Spondylarthropathy Study Group preliminary criteria for the classification of spondylarthropathy. Arthritis Rheum. 1991 Oct;34(10):1218-27. doi: 10.1002/art.1780341003.

  PMID: 1930310 BACKGROUND

• Rudwaleit M, van der Heijde D, Landewe R, Akkoc N, Brandt J, Chou CT, Dougados M, Huang F, Gu J, Kirazli Y, Van den Bosch F, Olivieri I, Roussou E, Scarpato S, Sorensen IJ, Valle-Onate R, Weber U, Wei J, Sieper J. The Assessment of SpondyloArthritis International Society classification criteria for peripheral spondyloarthritis and for spondyloarthritis in general. Ann Rheum Dis. 2011 Jan;70(1):25-31. doi: 10.1136/ard.2010.133645. Epub 2010 Nov 24.

  PMID: 21109520 BACKGROUND

• Stolwijk C, Boonen A, van Tubergen A, Reveille JD. Epidemiology of spondyloarthritis. Rheum Dis Clin North Am. 2012 Aug;38(3):441-76. doi: 10.1016/j.rdc.2012.09.003.

  PMID: 23083748 BACKGROUND

MeSH Terms

Conditions

Axial Spondyloarthritis; Disease

Condition Hierarchy (Ancestors)

Spondylarthropathies; Spondylarthritis; Spondylitis; Spinal Diseases; Bone Diseases; Musculoskeletal Diseases; Ankylosis; Joint Diseases; Arthritis; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Design

• Study Type: observational
• Observational Model: CASE CONTROL
• Time Perspective: RETROSPECTIVE
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: CEO and co-founder of Quibim

Study Record Dates

• First Submitted: September 8, 2024
• First Posted: September 19, 2024
• Study Start: February 19, 2023
• Primary Completion: April 3, 2025
• Study Completion: April 3, 2025
• Last Updated: April 16, 2025

Record last verified: 2025-04

Data Sharing

• IPD Sharing: Will not share

Locations

ES (1); JO (1); AE (4); SA (1)