Diagnostic performance and reliability of robotic ultrasonography and artificial intelligence-driven synovitis assessment in rheumatoid arthritis: results from the Controlled ARTHUR Trial
Authors' conclusion
A moderate to good overall agreement was seen between RUS and HUS in assessing synovitis in RA hands. However, at the joint level, low agreement was observed, particularly for MCP joints in both intrarobot and human-robot comparisons, which affected diagnostic performance.
Study context
- Population
- Healthy controls and patients with rheumatoid arthritis (RA) eligible for initiation or intensification of DMARDs, with at least one clinically swollen hand joint20 controls, 29 RA
- Comparison
- Artificial intelligence (AI)-driven robotic US vs human US by a trained rheumatologist
- Outcome
- Reliability and diagnostic performance of RUS vs HUS for synovitis (GS and CD, 0-3; EULAR-OMERACT score 0-66)
Methodological detailscontrolled, intrarobot and human-robot reliability
- Controlled
- Intrarobot and human-robot reliability
Performance
As reported in the abstract
Reliability (ICC) in RA
Intrarobot reliability ICC, Greyscale (GS) (moderate to good)
0.65
Intrarobot reliability ICC, CD
0.86
Human-robot agreement ICC, GS (moderate)
0.59
Human-robot agreement ICC, CD
0.64
Further findings
- Diagnostic accuracy of robotic ultrasonography (RUS) for clinically-detected arthritis
- 59% · diagnostic accuracy
Joint-level scores
- RUS higher scores than human ultrasonography (HUS) for MCP joints; comparable for other joint groups
Original publication
Diagnostic performance and reliability of robotic ultrasonography and artificial intelligence-driven synovitis assessment in rheumatoid arthritis: results from the Controlled ARTHUR Trial. RMD Open. Published 11 November 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →