An interpretable and trustworthy AI framework for large-scale longitudinal structure-pain association studies using data from the Osteoarthritis Initiative (OAI)
Researchers have developed a new AI framework to study the relationship between structural abnormalities and pain in osteoarthritis patients. This framework combines deep learning for MRI analysis with statistical modeling, improving the accuracy of identifying bone marrow lesions, cartilage loss, and meniscal extrusion. The enhanced accuracy allowed for a larger sample size in subsequent analysis, revealing two distinct pain progression trajectories and identifying key structural abnormalities as significant risk factors for pain and functional decline. AI
IMPACT This AI framework enhances the accuracy of identifying structural abnormalities linked to osteoarthritis pain, potentially leading to better risk assessment and treatment strategies.