https://doi.org/10.55788/aba3909c
In many patients, clinically suspect arthralgia (CSA) progresses to early onset arthritis, RA, or other arthritides. Predicting early RA from MRI images can help initiate prompt treatment, possibly preventing the chronicity of the disease. Until present, visual scoring (e.g. with the RAMRIS scoring system) from extremity MRI scans is used to manually identify key risk factors for the chance of developing RA. The study group of Dr Yanli Li (Leiden University Center, the Netherlands) assessed whether AI interpretations of MRI images could provide more accurate predictions than visual scoring by medical staff [1].
The model was first trained to understand anatomy from MRIs of wrists and metacarpophalangeal joints of healthy controls. In a second step, it learnt to distinguish between the different groups (patients with CSA vs healthy controls and early-onset arthritis vs healthy controls). In a third step, the AI was taught to distinguish RA from other arthritides. Finally, the system had to predict RA development in 2 years in patients with CSA. The model’s accuracy was evaluated with the area under the receiver operator curve (AUC).
The AI analysed MRI scans from 1,974 people with either early-onset arthritis (n=1,247) or CSA (n=727), of whom 651 went on to develop RA.
On the test set, the proposed model obtained a mean AUC of 0.683 in the early-onset arthritis group and 0.727 in the CSA group. These accuracies are close to the expert levels using RAMRIS.
As Dr Li emphasised, the system can be further improved with more clinical data. Moreover, the self-learning AI system showed similar efficacy for scans of either wrists or feet. As Dr Li explained during the presentation, AI-based RA prediction is reliable as it looks at known inflammatory signs and features such as synovial inflammation.
- Li Y, et Exploring the Use of Artificial Intelligence in Predicting Rheumatoid Arthritis, Based on Extremity MR Scans in Early Arthritis and Clinically Suspect Arthralgia Patients. OP0002, EULAR 2023, 31 May–3 June, Milan, Italy.
Copyright ©2023 Medicom Medical Publishers
Posted on
Previous Article
« Worse self-management in patients with inflammatory arthritis in the presence of comorbid anxiety or depression Next Article
COBRA-Slim bio-induction: no benefit compared with the standard regimen »
« Worse self-management in patients with inflammatory arthritis in the presence of comorbid anxiety or depression Next Article
COBRA-Slim bio-induction: no benefit compared with the standard regimen »
Table of Contents: EULAR 2023
Featured articles
Late-breaking Oral Abstracts
Selective JAK1/TYK 2 inhibitor effective in patients with difficult-to-treat RA
Novel 2-drug combo improves treatment possibilities for patients with refractory gout
Dazodalibep improves dryness, fatigue, and pain in patients with Sjögren’s syndrome with a high symptom burden
COVID-19: Young adults with auto-immune diseases have different risks than their healthy counterparts
RA in 2023
Poly-refractory RA: not common, but still present
AI almost as successful as experts in predicting early RA
Worse self-management in patients with inflammatory arthritis in the presence of comorbid anxiety or depression
Disease activity-guided dose reduction may be a long-term option for stable RA
Cardiovascular safety of JAK inhibitors: reassuring results from a real-world study
Spondylarthropathies: New Developments
AxSpA: Adalimumab biosimilar equally effective as IL-17 inhibitor in hindering radiographic progression
Vascular inflammation may be characteristic of PsA
Obesity in PsA is increasingly affecting male patients
PsA patients: highest risk of developing NAFLD
What is Hot in Osteoarthritis
Lorecivivint shows long-term benefits for severe knee OA
Methotrexate lowers pain in inflammatory hand OA
Systemic Sclerosis: State of the Art
Targeted DMARDs advantageous in SSc patients with pre-capillary pulmonary hypertension
Osteoporosis: New Data
Drugs for osteoporosis: time to reach fracture risk reduction varies
Romosozumab: the new option for glucocorticoid-induced osteoporosis with high fracture risk?
Best of the Posters
Therapy with biological DMARDs shows no correlation with fracture risk in RA
Basic Science
In vitro and in vivo studies confirm the role of regulatory volume decrease
Related Articles
June 5, 2023
HUNT study: DMARDs influence the fracture risk in RA
February 4, 2020
Proteome abnormalities improve prediction of RA development
November 22, 2021
ACR 2021 Highlights Podcast
© 2024 Medicom Medical Publishers. All rights reserved. Terms and Conditions | Privacy Policy