Fibromyalgia & musculoskeletal pain
fAI-BRO: a multimodal artificial intelligence (AI) decision-support system to address diagnostic delay in fibromyalgia syndrome
Authors' conclusion
fAI-BRO demonstrates promising diagnostic accuracy for FMS screening as a human-in-the-loop decision-support tool, with perfect inflammatory arthritis classification and high patient acceptability.
Study context
- Population
- Patients at the University of Bari undergoing standardised interviews in Italian
- Participants
- 100 patients
- Comparison
- fAI-BRO multimodal AI system for distinguishing FM from other rheumatic and musculoskeletal diseases
- Fibromyalgia syndrome (FMS)n = 50
- RMD controlsn = 50reference
- Outcome
- Diagnostic accuracy of fAI-BRO for FMS detection on a 0-100 composite score
Methodological detailscross-sectional, proof-of-concept, zero-shot configuration, thresholds optimised post hoc via Youden's J index
- Cross-sectional
- Proof-of-concept
- Zero-shot configuration
- Thresholds optimised post hoc via Youden's J index
Performance
As reported in the abstract
FMS detection (0-100 composite score)
| Test or model | Accuracy | Sensitivity | Specificity | AUC |
|---|---|---|---|---|
| fAI-BRO | 91% | 94% (95% CI 83.5% to 98.7%) | 88% (95% CI 75.7% to 95.5%) | 0.96 |
fAI-BRO
Accuracy91%
Sensitivity94% (95% CI 83.5% to 98.7%)
Specificity88% (95% CI 75.7% to 95.5%)
AUC0.96
Further findings
Classification of inflammatory arthritis (rheumatoid arthritis (RA), psoriatic arthritis (PsA), spondyloarthritis (SpA), systemic lupus erythematosus (SLE); n=36) and mechanical conditions (OA, impingement; n=8)
- All correctly classified as RMD
False positives for FMS
- All six false positives in DM (n=3) and PMR (n=3)
- 6
- Hypothesis-generating observation
Perturbation analysis
- Widespread pain descriptors the dominant classification drivers
Translation effect
- Binary classification robust to the English translation effect
Patient comfort
- Mean patient comfort (/5)
- 4.5
Processing time
- Mean processing time (s)
- 324
Original publication
fAI-BRO: a multimodal AI decision-support system to address diagnostic delay in fibromyalgia syndrome. RMD Open. Published 13 July 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →