Objectives Sensitive detection of joint inflammation in rheumatoid arthritis (RA) is crucial to the success of the treat-to-target strategy. In this study, we characterise a novel machine learning-based computational method to automatically assess joint inflammation in RA using thermography of the hands, a fast and non-invasive imaging technique. Methods We recruited 595 patients with arthritis and osteoarthritis, as well as healthy subjects at two hospitals over 4 years. Machine learning was used to assess joint inflammation from the thermal images of the hands using ultrasound as the reference standard, obtaining a Thermographic Joint Inflammation Score (ThermoJIS). The machine learning model was trained and tuned using data from 449 participants with different types of arthritis, osteoarthritis or without rheumatic disease (development set). The performance of the method was evaluated based on 146 patients with RA (validation set) using Spearman’s rank correlation coefficient, area under the receiver-operating curve (AUROC), average precision, sensitivity, specificity, positive and negative predictive value and F1-score. Results ThermoJIS correlated moderately with ultrasound scores (grey-scale synovial hypertrophy=0.49, p<0.001; and power Doppler=0.51, p<0.001). The AUROC for ThermoJIS for detecting active synovitis was 0.78 (95% CI, 0.71 to 0.86; p<0.001). In patients with RA in clinical remission, ThermoJIS values were significantly higher when active synovitis was detected by ultrasound. Conclusions ThermoJIS was able to detect joint inflammation in patients with RA, even in those in clinical remission. These results open an opportunity to develop new tools for routine detection of joint inflammation.
Objectives Remote assessment of patients with rheumatoid arthritis (RA) has increased during recent years. However, telematic consultations preclude the possibility of carrying out a physical examination and obtaining objective inflammation. In this study, we developed and validated two novel composite disease activity indexes (Thermographic Disease Activity Index (ThermoDAI) and ThermoDAI-CRP) based on thermography of hands and machine learning, in order to assess disease activity easily, rapidly and without formal joint counts. Methods ThermoDAI was developed as the sum of Thermographic Joint Inflammation Score (ThermoJIS), a novel joint inflammation score based on the analysis of thermal images of the hands by machine learning, the Patient Global Assessment (PGA) and, for ThermoDAI-CRP, the C reactive protein (CRP). Construct validity was tested in 146 patients with RA by using Spearman’s correlation with ultrasound-determined grey-scale synovial hypertrophy (GS) and power Doppler (PD) scores, CDAI, SDAI and DAS28-CRP. Results Correlations of ultrasound scores with ThermoDAI (GS=0.52; PD=0.56) and ThermoDAI-CRP (GS=0.58; PD=0.61) were moderate to strong, while the correlations of ultrasound scores with PGA (GS=0.35; PD=0.39) and PGA+CRP (GS=0.44; PD=0.46) were weak to moderate. ThermoDAI and ThermoDAI-CRP also showed strong correlations with Clinical Disease Activity Index (ρ>0.83), Simplified Disease Activity Index (ρ>0.85) and Disease Activity Score with 28-Joint Counts-CRP (ρ>0.81) and high sensitivity for detecting active synovitis using remission criteria. Conclusions ThermoDAI and ThermoDAI-CRP showed stronger correlations with ultrasound-determined synovitis than PGA and PGA + CRP, thus presenting an opportunity to improve remote consultations with patients with RA.
External validation is crucial in developing reliable machine learning models. This study aimed to validate three novel indices—Thermographic Joint Inflammation Score (ThermoJIS), Thermographic Disease Activity Index (ThermoDAI), and Thermographic Disease Activity Index-C-reactive protein (ThermoDAI-CRP)—based on hand thermography and machine learning to assess joint inflammation and disease activity in rheumatoid arthritis (RA) patients. A 12-week prospective observational study was conducted with 77 RA patients recruited from rheumatology departments of three hospitals. During routine care visits, indices were obtained at baseline and week 12 visits using a pre-trained machine learning model. The performance of these indices was assessed cross-sectionally and longitudinally using correlation coefficients, the area under the receiver operating curve (AUROC), sensitivity, specificity, and positive and negative predictive values. ThermoDAI and ThermoDAI-CRP correlated with CDAI, SDAI, and DAS28-CRP cross-sectionally (ρ = 0.81; ρ = 0.83; ρ = 0.78) and longitudinally (ρ = 0.55; ρ = 0.61; ρ = 0.60), all p < 0.001. ThermoDAI and ThermoDAI-CRP also outperformed Patient Global Assessment (PGA) and PGA + C-reactive protein (CRP) in detecting changes in 28-swollen joint counts (SJC28). ThermoJIS had an AUROC of 0.67 (95% CI, 0.58 to 0.76) for detecting patients with swollen joints and effectively identified patients transitioning from SJC28 > 1 at baseline visit to SJC28 ≤ 1 at week 12 visit. These results support the effectiveness of ThermoJIS in assessing joint inflammation, as well as ThermoDAI and ThermoDAI-CRP in evaluating disease activity in RA patients.