A Personalized Risk Model Leverages MRI-based Structural Phenotypes and Clinical Factors to Predict Incidence of Radiographic Osteoarthritis.

Researchers

Journal

Modalities

Models

Abstract

Our study aimed to investigate the association between time to incidence of radiographic osteoarthritis (OA) and MRI-based structural phenotypes proposed by Rapid OsteoArthritis MRI Eligibility Score (ROAMES).A retrospective cohort of 2,328 participants without radiographic OA at baseline were selected from Osteoarthritis Initiative study. Utilizing deep learning model, we automatically assessed the presence of inflammatory, meniscus/cartilage, subchondral bone, and hypertrophic phenotypes from MRIs acquired at baseline, 12-, 24-, 36-, 48-, 72-, and 96- month follow-up visits. In addition to four structural phenotypes, we examined severe knee injury history and Western Ontario and McMaster University Osteoarthritis Index pain score as time-dependent. We used Cox proportional hazards regression to analyze the association between four structural phenotypes and radiographic OA disease-free survival, both univariate and adjusted for known risk factors including age, sex, race, body mass index, presence of Heberden nodes, and knee malalignment.Inflammatory (HR: 3.37, 95% CI: 2.45 – 4.63), meniscus/cartilage (HR: 1.55, 95%CI: 1.21 – 1.98) and subchondral bone (HR: 1.84, 95%CI: 1.63 – 2.09) phenotypes were associated with time to radiographic OA at p < 0.05 when adjusted for the risk factors. Sex was a modifier of hypertrophic phenotype association with time to radiographic OA. Female participants with hypertrophic phenotype were associated with 2.8 times higher risk of radiographic OA (95% CI: 2.25 – 7.54) compared to male participants without hypertrophic phenotype.Four ROAMES phenotypes may contribute to time to radiographic OA incidence and if validated could be used as promising tool for personalized OA management.This article is protected by copyright. All rights reserved.