External Validation of the Machine Learning-Based Thermographic Indices for Rheumatoid Arthritis: A Prospective Longitudinal Study.

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.

Efficacy and Safety of Long-Term Baricitinib With and Without Methotrexate for the Treatment of Rheumatoid Arthritis: Experience With Baricitinib Monotherapy Continuation or After Switching From Methotrexate Monotherapy or Baricitinib Plus Methotrexate.

OBJECTIVE: To evaluate the long-term efficacy and safety of maintaining baricitinib monotherapy in patients with active rheumatoid arthritis (RA) originally treated with baricitinib monotherapy or switched from methotrexate (MTX) or the combination of baricitinib plus MTX to baricitinib monotherapy. METHODS: This is a post hoc analysis of patients from the RA-BEGIN study who entered a long-term extension, RA-BEYOND, and were assessed for up to 24 weeks. In RA-BEGIN, MTX-naive patients with early active RA were randomized to MTX monotherapy, baricitinib 4 mg monotherapy, or baricitinib 4 mg plus MTX. At week 52, all patients entering RA-BEYOND received baricitinib 4 mg monotherapy. MTX could be prescribed during RA-BEYOND at the investigator's discretion. RESULTS: Patients in RA-BEYOND who were not rescued in RA-BEGIN (n = 423) were evaluated. Of these, 47% continued baricitinib monotherapy and 53% added MTX, with similar proportions from the 3 original arms. Patients with lower disease activity at the RA-BEYOND baseline generally continued to do well with baricitinib monotherapy as assessed by the Simplified Disease Activity Index, the Clinical Disease Activity Index, and the Health Assessment Questionnaire disability index scores. Patients prescribed MTX had higher disease activity at the RA-BEYOND baseline and had improved disease activity after the addition of MTX. Safety outcomes were similar across treatment groups. CONCLUSION: Many patients responded well to continued baricitinib monotherapy or to switching to baricitinib monotherapy from MTX monotherapy or baricitinib plus MTX, showing sustained or improved disease control. The groups of patients who had less disease control on their original therapies showed sustained or improved disease control with the addition of MTX to baricitinib.

Multinational evidence-based recommendations for pain management by pharmacotherapy in inflammatory arthritis: integrating systematic literature research and expert opinion of a broad panel of rheumatologists in the 3e Initiative.

OBJECTIVE: To develop evidence-based recommendations for pain management by pharmacotherapy in patients with inflammatory arthritis (IA). METHODS: A total of 453 rheumatologists from 17 countries participated in the 2010 3e (Evidence, Expertise, Exchange) Initiative. Using a formal voting process, 89 rheumatologists representing all 17 countries selected 10 clinical questions regarding the use of pain medications in IA. Bibliographic fellows undertook a systematic literature review for each question, using MEDLINE, EMBASE, Cochrane CENTRAL and 2008-09 European League Against Rheumatism (EULAR)/ACR abstracts. Relevant studies were retrieved for data extraction and quality assessment. Rheumatologists from each country used this evidence to develop a set of national recommendations. Multinational recommendations were then formulated and assessed for agreement and the potential impact on clinical practice. RESULTS: A total of 49,242 references were identified, from which 167 studies were included in the systematic reviews. One clinical question regarding different comorbidities was divided into two separate reviews, resulting in 11 recommendations in total. Oxford levels of evidence were applied to each recommendation. The recommendations related to the efficacy and safety of various analgesic medications, pain measurement scales and pain management in the pre-conception period, pregnancy and lactation. Finally, an algorithm for the pharmacological management of pain in IA was developed. Twenty per cent of rheumatologists reported that the algorithm would change their practice, and 75% felt the algorithm was in accordance with their current practice. CONCLUSIONS: Eleven evidence-based recommendations on the management of pain by pharmacotherapy in IA were developed. They are supported by a large panel of rheumatologists from 17 countries, thus enhancing their utility in clinical practice.

Algorithm for identification of undifferentiated peripheral inflammatory arthritis: a multinational collaboration through the 3e initiative.

OBJECTIVE: To develop an algorithm for identification of undifferentiated peripheral inflammatory arthritis (UPIA). METHODS: An algorithm for identification of UPIA was developed by consensus during a roundtable meeting with an expert panel. It was informed by systematic reviews of the literature used to generate 10 recommendations for the investigation and followup of UPIA through the 3e initiative. The final recommendations from the 3e UPIA Initiative were made available to the panel to guide development of the algorithm. The algorithm drew on the clinical experience of the consensus panel and evidence from the literature where available. RESULTS: In patients presenting with joint swelling a thorough evaluation is required prior to diagnosing UPIA. After excluding trauma, the differential diagnosis should be formulated based on history and physical examination. A minimum set of investigations is suggested for all patients, with additional ones dependent on the most probable differential diagnoses. The diagnosis of UPIA can be made if, following these evaluations, a more specific diagnosis is not reached. Once a diagnosis of UPIA is established, patients should be closely followed as they may progress to a specific diagnosis, remit, or persist as UPIA, and additional investigations may be required over time. CONCLUSION: Our algorithm presents a diagnostic approach to identifying UPIA in patients presenting with joint swelling, incorporating the dynamic nature of the condition with the potential to evolve over time.