AI-Based Medical Data Analysis for Differentiating Inflammatory vs Degenerative Joint Diseases in Elderly Patients

Assiut University

Status: Not yet enrolling

Conditions: Arthritis, Rheumatoid (RA)

Study type: Observational

Funder types: Other

Identifiers

NCT07153315

AU-MEDAI-JOINT-2025-01

Details and patient eligibility

About

This study aims to evaluate the diagnostic accuracy of AI-assisted imaging analysis in differentiating between inflammatory and degenerative joint diseases in elderly patients. The performance of AI-based analysis will be compared with radiologists' assessments to determine its reliability in clinical practice. In addition, the study will explore imaging features most predictive of each disease type using advanced machine learning techniques. Finally, the feasibility of implementing AI tools in the routine management of geriatric musculoskeletal disorders will be assessed.

Full description

Musculoskeletal disorders are among the most prevalent causes of disability in the elderly. Inflammatory joint diseases, such as rheumatoid arthritis, and degenerative joint diseases, such as osteoarthritis, are both common yet challenging to differentiate, particularly in the early stages. Traditional imaging techniques often lack sensitivity and specificity when interpreted solely by human experts, and diagnostic accuracy is further limited by inter-observer variability.

Artificial Intelligence (AI), particularly deep learning-based image analysis, has emerged as a powerful tool in medical diagnostics. Convolutional neural networks (CNNs), a class of deep learning models, have been successfully applied to musculoskeletal imaging. For example, a study published in The Lancet Rheumatology (2020) trained a CNN on thousands of hand and wrist radiographs from patients with rheumatoid arthritis. The model was able to automatically detect and grade bone erosions and joint space narrowing-key radiographic features of rheumatoid arthritis-with diagnostic performance comparable to experienced musculoskeletal radiologists. Importantly, AI was able to identify early erosive changes in small joints, reduce the time required for radiographic scoring in clinical trials, and provide consistent results, thereby reducing inter-observer variability.

Building on these advances, the current study aims to explore the application of AI in enhancing diagnostic accuracy for differentiating between inflammatory and degenerative joint diseases in elderly patients. By integrating AI-based imaging analysis with clinical and laboratory data, this research will not only support accurate diagnosis but also provide predictive models for disease course, functional decline, and joint damage progression. The ultimate goal is to enable personalized treatment strategies and improve outcomes for elderly patients with musculoskeletal disorders.

Enrollment: 140 estimated patients

Sex: All

Ages: 60+ years old

Volunteers: No Healthy Volunteers

Inclusion and exclusion criteria

Inclusion criteria :

1. Age ≥ 60 years
2. Clinical suspicion or confirmed diagnosis of inflammatory joint disease (e.g., rheumatoid arthritis, psoriatic arthritis) or degenerative joint disease (e.g., osteoarthritis)
3. Availability of relevant musculoskeletal imaging (X-rays, MRI, or ultrasound) suitable for AI-based analysis
4. Ability to provide informed consent or have a legal representative consent on behalf of the

Exclusion criteria:

1. History of recent joint trauma (within the last 6 months) or previous joint surgery affecting the studied sites
2. Presence of bone or joint malignancy (primary or metastatic)
3. Diagnosis of overlapping rheumatologic syndromes or mixed pathology (e.g., RA with concurrent gout, or OA with inflammatory overlap)
4. Inadequate imaging quality or absence of required imaging modalities
5. Inability or unwillingness to provide informedconsent