Deep learning-based classification of erosion, synovitis and osteitis in hand MRI of patients with inflammatory arthritis.

OBJECTIVES: To train, test and validate the performance of a convolutional neural network (CNN)-based approach for the automated assessment of bone erosions, osteitis and synovitis in hand MRI of patients with inflammatory arthritis. METHODS: Hand MRIs (coronal T1-weighted, T2-weighted fat-suppressed, T1-weighted fat-suppressed contrast-enhanced) of rheumatoid arthritis (RA) and psoriatic arthritis (PsA) patients from the rheumatology department of the Erlangen University Hospital were assessed by two expert rheumatologists using the Outcome Measures in Rheumatology-validated RA MRI Scoring System and PsA MRI Scoring System scores and were used to train, validate and test CNNs to automatically score erosions, osteitis and synovitis. Scoring performance was compared with human annotations in terms of macro-area under the receiver operating characteristic curve (AUC) and balanced accuracy using fivefold cross-validation. Validation was performed on an independent dataset of MRIs from a second patient cohort. RESULTS: In total, 211 MRIs from 112 patients (14 906 region of interests (ROIs)) were included for training/internal validation using cross-validation and 220 MRIs from 75 patients (11 040 ROIs) for external validation of the networks. The networks achieved high mean (SD) macro-AUC of 92%±1% for erosions, 91%±2% for osteitis and 85%±2% for synovitis. Compared with human annotation, CNNs achieved a high mean Spearman correlation for erosions (90±2%), osteitis (78±8%) and synovitis (69±7%), which remained consistent in the validation dataset. CONCLUSIONS: We developed a CNN-based automated scoring system that allowed a rapid grading of erosions, osteitis and synovitis with good diagnostic accuracy and using less MRI sequences compared with conventional scoring. This CNN-based approach may help develop standardised cost-efficient and time-efficient assessments of hand MRIs for patients with arthritis.

Anatomical pattern of entheseal and synovial fibroblast activation in patients with psoriasis and its risk of developing psoriatic arthritis.

OBJECTIVES: To assess the presence and anatomical distribution of activated fibroblasts in the joints and entheses of patients with psoriasis with arthralgia and to test how fibroblast activation visualised by 68gallium-labelled fibroblast activation protein inhibitor-04 (68Ga-FAPI-04)-positron emission tomography (PET)/CT correlates with clinical tenderness, musculoskeletal ultrasound findings and progression to psoriatic arthritis (PsA). METHODS: We conducted a prospective cohort study in patients with psoriasis and arthralgia who underwent clinical and ultrasound evaluation and whole-body PET/CT imaging with 68Ga-FAPI-04. 68Ga-FAPI-04 uptake at synovial and entheseal sites was assessed by maximal standardised uptake values (SUVmax) and PET/CT Joint Index (JI); logistic regression models were used to investigate its correlation with clinical and ultrasound findings. Survival analyses were performed on patients with at least 6 months of follow-up. RESULTS: 36 patients with psoriasis were enrolled. 68Ga-FAPI-04 uptake was found in 318 (7.9%) joints and 369 (7.3%) entheses in 29 (80.6%) participants, with a mean SUVmax (SD) of 3.2 (1.8) for joints and 2.9 (1.6) for entheses. Large joints and the lower limbs were predominantly affected. A significant positive relationship was found between 68Ga-FAPI-04-PET/CT signal intensity and the 68 tender joint count (SUVmax: p<0.001; PET/CT-JI: p<0.001) and tender entheses count (SUVmax: p<0.001; PET/CT-JI: p=0.002). No correlations were found with ultrasound findings (SUVmax: p=0.969; PET/CT-JI: p=0.720). Patients with relevant synovio-entheseal 68Ga-FAPI-04 uptake showed a statistically significant higher risk of developing PsA (p=0.02), independent of ultrasound findings. CONCLUSIONS: Patients with psoriasis presenting with arthralgia show localised signs of resident tissue activation in joints and entheses, which are associated with higher risk of developing PsA.

IL-1 Inhibitors in the Treatment of Familial Mediterranean Fever: Treatment Indications and Clinical Features in a Large Real-World Cohort.

Background: The accruing evidence about the efficacy of anti-IL-1 agents in Familial Mediterranean Fever (FMF) patients led to their widespread off-label use. Therefore, identifying precise indications and clinical characteristics of IL-1i-warranting patients are important. This study investigated the clinical characteristics and treatment indications of patients with FMF requiring interleukin 1 inhibition therapy (IL-1i). Methods: Hospital records of FMF patients attending a tertiary care center at the Department of Rheumatology, University of Health Sciences, Basaksehir Cam and Sakura City Hospital were retrospectively analyzed. Data on symptoms and disease manifestations, age of symptom onset, time to diagnosis, MEFV variants, type of treatment, and their indications were collected. Results: Between June 2020 and March 2023, 312 FMF patients were identified. The mean age at the onset of symptoms was 14.0, and the mean time to diagnosis was 11.9 years. In total, 87.1% of patients were receiving colchicine monotherapy, while the remaining 11.8% warranted IL-1i. Clinical symptoms and flare manifestations did not show a significant difference between the two groups. However, patients receiving IL-1i started having symptoms at younger age (11.5 vs. 14.5, p = 0.042) and time to diagnosis was longer (18.2 vs. 11.0, p < 0.01). M694V homozygosity was more common in patients receiving IL-1i. Indications for patients receiving IL-1i were colchicine resistance (8.0%), secondary amyloidosis (5.1%), and colchicine intolerance (2.2%). Conclusions: This study shows that a subset of FMF patients, particularly those with a more severe phenotype with an earlier disease onset and M694V homozygosity, require IL-1i treatment despite the overall good efficacy and tolerability of colchicine, primarily due to colchicine resistance, intolerance, or complications such as amyloidosis.

Unveiling Metabolic Similarities of Entheses in Patients with Psoriasis and Psoriatic Arthritis Using Noninvasive In Vivo Molecular Imaging: Results From a Cross-sectional Exploratory Study.

OBJECTIVE: We assessed and compared molecular tissue changes at the entheses in patients with psoriasis (PsO) and psoriatic arthritis (PsA) and in healthy controls (HCs) in vivo using multispectral optoacoustic tomography (MSOT) and described their relationship with clinical and ultrasound findings of enthesitis. METHODS: A cross-sectional study (MSOT and Arthrosonography in PsA) in biologic disease-modifying antirheumatic drug-naïve patients with PsA and PsO and HCs was performed. Participants underwent clinical, ultrasonographic, and MSOT examination of six entheses (lateral humeral epicondyle, distal patellar tendon attachment, and Achilles tendon attachment). MSOT-measured hemoglobin (Hb), oxygen saturation (SO2), collagen, and lipid levels were quantified, and mean differences between groups were calculated using linear mixed effects models. MSOT-measured analytes were compared between entheses with and without clinical and ultrasound anomalies. RESULTS: Ninety participants were included (30 PsO, 30 PsA, and 30 HCs), 540 entheses were clinically assessed, and 540 ultrasound and 830 MSOT scans were obtained. Patients with PsA and PsO showed increased oxygenated Hb (PsA: P = 0.003; PsO: P = 0.054) and SO2 (PsA: P < 0.001; PsO: P = 0.001) levels and decreased collagen signals (PsA: P < 0.001; PsO: P < 0.001) compared with HCs, with more pronounced changes in PsA. Significantly lower collagen levels (P = 0.01) and increased lipids (P = 0.03) were recorded in tender entheses compared with nontender ones. Erosions and enthesophytes on ultrasound were associated with significant differences in SO2 (P = 0.014) and lipid signals (P = 0.020), respectively. CONCLUSION: Patients with PsA and PsO exhibit an analogous metabolic pattern at the entheses that is exacerbated in the presence of inflammation. These findings support the notion of a psoriatic disease spectrum characterized by common immunometabolic tissue changes.

Bispecific T cell engager therapy for refractory rheumatoid arthritis.

Bispecific T cell engagers (BiTEs) kill B cells by engaging T cells. BiTEs are highly effective in acute lymphoblastic leukemia. Here we treated six patients with multidrug-resistant rheumatoid arthritis (RA) with the CD19xCD3 BiTE blinatumomab under compassionate use. Low doses of blinatumomab led to B cell depletion and concomitant decrease of T cells, documenting their engager function. Treatment was safe, with brief increase in body temperature and acute phase proteins during first infusion but no signs of clinically relevant cytokine-release syndrome. Blinatumomab led to a rapid decline in RA clinical disease activity in all patients, improved synovitis in ultrasound and FAPI-PET-CT and reduced autoantibodies. High-dimensional flow cytometry analysis of B cells documented an immune reset with depletion of activated memory B cells, which were replaced by nonclass-switched IgD-positive naïve B cells. Together, these data suggest the feasibility and potential for BiTEs to treat RA. This approach warrants further exploration on other B-cell-mediated autoimmune diseases.

Risk of developing psoriatic arthritis in psoriasis cohorts with arthralgia: exploring the subclinical psoriatic arthritis stage.

OBJECTIVE: Subjects with subclinical psoriatic arthritis (PsA), defined as the presence of arthralgia in psoriasis (PsO), are at higher risk of PsA but scant real-world data exist. Our aims were to (1) estimate the probability of PsA development in subclinical PsA, (2) characterise subclinical PsA symptoms and (3) determine the clinical patterns at PsA diagnosis. METHODS: Patients with PsO, mainly subclinical PsA, were evaluated longitudinally in two European cohorts. The key outcome was new-onset PsA. Musculoskeletal symptoms including inflammatory and non-inflammatory symptoms before PsA diagnosis were collected. Occurrence of PsA was analysed with survival analysis and cumulative incidence functions (CIFs). RESULTS: 384 patients with PsO were included with a mean follow-up of 33.0 (±20.9) months. 311 of 384 (80.9%) had subclinical PsA with a PsA incidence rate of 7.7 per 100 patient-years. Subclinical PsA displayed a higher risk of PsA development compared with PsO (HR=11.7 (95% CI 1.57 to 86.7), p=0.016). The probability of new-onset PsA estimated by the CIF was 9.4% (95% CI 4.7% to 10.6%) at month 12 and 22.7% (95% CI 17.2% to 28.6%) at month 36. 58.9% of cases reported inflammatory symptoms in the months immediately prior to PsA diagnosis but prior non-inflammatory symptoms were evident in 83.9% prior to PsA diagnosis. Peripheral joint swelling was the predominant PsA presentation pattern (82.1%). CONCLUSIONS: The probability of PsA development among subclinical PsA was relatively high, emphasising the importance of emergent musculoskeletal symptoms when aiming for PsA prevention. Joint swelling was the dominant feature in new-onset PsA, likely reflecting clinical confidence in recognising joint swelling.

Metabolic and molecular imaging in inflammatory arthritis.

It is known that metabolic shifts and tissue remodelling precede the development of visible inflammation and structural organ damage in inflammatory rheumatic diseases such as the inflammatory arthritides. As such, visualising and measuring metabolic tissue activity could be useful to identify biomarkers of disease activity already in a very early phase. Recent advances in imaging have led to the development of so-called 'metabolic imaging' tools that can detect these changes in metabolism in an increasingly accurate manner and non-invasively.Nuclear imaging techniques such as 18F-D-glucose and fibroblast activation protein inhibitor-labelled positron emission tomography are increasingly used and have yielded impressing results in the visualisation (including whole-body staging) of inflammatory changes in both early and established arthritis. Furthermore, optical imaging-based bedside techniques such as multispectral optoacoustic tomography and fluorescence optical imaging are advancing our understanding of arthritis by identifying intra-articular metabolic changes that correlate with the onset of inflammation with high precision and without the need of ionising radiation.Metabolic imaging holds great potential for improving the management of patients with inflammatory arthritis by contributing to early disease interception and improving diagnostic accuracy, thereby paving the way for a more personalised approach to therapy strategies including preventive strategies. In this narrative review, we discuss state-of-the-art metabolic imaging methods used in the assessment of arthritis and inflammation, and we advocate for more extensive research endeavours to elucidate their full field of application in rheumatology.

Tolerability of low to moderate biomechanical stress during leisure sport activity in patients with psoriasis and psoriatic arthritis.

OBJECTIVES: To assess the impact of low to moderate biomechanical stress on entheses in patients with psoriasis and psoriatic arthritis (PsA). METHODS: We conducted a prospective interventional study on a cohort of psoriasis and PsA patients who underwent a 60 min badminton training session. Pain assessment by Visual Analogue Scale (VAS), physical examination of 29 entheses (SPARCC, LEI, MASES) and bilateral ultrasound at the lateral humeral epicondyle, inferior patellar pole and Achilles tendon were performed before and after training. Ultrasound changes were assessed using the OMERACT scoring system. A follow-up assessment of pain and adverse events was performed at 1 week. RESULTS: Sixteen patients were included (n=7 PsA; n=9 psoriasis) and 196 entheseal ultrasound scans were acquired. At baseline, median VAS pain (IQR) was 0.5 cm (0-2.3) and the total number of tender entheses was 12/464. Mean (min; max) Disease Activity Index for Psoriatic Arthritis was 6.1 (0.8; 19) and 5/7 PsA patients had an Minimal Disease Activity status. After training, no significant change in VAS pain (0.0 cm (0.0-2.0)) nor in tender entheses (13/464) emerged. Four patients (n=2 PsA, n=2 psoriasis) developed a grade-1 power Doppler-signal at six entheses, which, however, remained non-tender. At 1 week, median VAS pain remained stable (0.0 cm (0.0-3.0); p>0.05) and only one participant with active PsA at baseline reported increased arthralgias in three joints. CONCLUSIONS: Low to moderate physical strain, as in the context of leisure sport activity, seems well tolerated in psoriatic patients without increases in tenderness, pain and ultrasound-proven inflammation. Evidence-based recommendations for physical activity in PsA are direly needed and larger controlled studies should be conducted to define safe exercise thresholds.

Imaging in inflammatory arthritis: progress towards precision medicine.

Imaging techniques such as ultrasonography and MRI have gained ground in the diagnosis and management of inflammatory arthritis, as these imaging modalities allow a sensitive assessment of musculoskeletal inflammation and damage. However, these techniques cannot discriminate between disease subsets and are currently unable to deliver an accurate prediction of disease progression and therapeutic response in individual patients. This major shortcoming of today's technology hinders a targeted and personalized patient management approach. Technological advances in the areas of high-resolution imaging (for example, high-resolution peripheral quantitative computed tomography and ultra-high field MRI), functional and molecular-based imaging (such as chemical exchange saturation transfer MRI, positron emission tomography, fluorescence optical imaging, optoacoustic imaging and contrast-enhanced ultrasonography) and artificial intelligence-based data analysis could help to tackle these challenges. These new imaging approaches offer detailed anatomical delineation and an in vivo and non-invasive evaluation of the immunometabolic status of inflammatory reactions, thereby facilitating an in-depth characterization of inflammation. By means of these developments, the aim of earlier diagnosis, enhanced monitoring and, ultimately, a personalized treatment strategy looms closer.

Application of clinical and molecular profiling data to improve patient outcomes in psoriatic arthritis.

Achieving a good outcome for a person with Psoriatic Arthritis (PsA) is made difficult by late diagnosis, heterogenous clinical disease expression and in many cases, failure to adequately suppress inflammatory disease features. Single-centre studies have certainly contributed to our understanding of disease pathogenesis, but to adequately address the major areas of unmet need, multi-partner, collaborative research programmes are now required. HIPPOCRATES is a 5-year, Innovative Medicines Initiative (IMI) programme which includes 17 European academic centres experienced in PsA research, 5 pharmaceutical industry partners, 3 small-/medium-sized industry partners and 2 patient-representative organizations. In this review, the ambitious programme of work to be undertaken by HIPPOCRATES is outlined and common approaches and challenges are identified. It is expected that, when completed, the results will ultimately allow for changes in the approaches to diagnosing, managing and treating PsA allowing for better short-term and long-term outcomes.

Improving outcomes in Psoriatic Arthritis Psoriatic Arthritis (PsA) is a form of arthritis which is found in approximately 30% of people who have the skin condition, Psoriasis. Frequently debilitating and progressive, achieving a good outcome for a person with PsA is made difficult by late diagnosis, disease clinical features and in many cases, failure to adequately control features of inflammation. Research studies from individual centres have certainly contributed to our understanding of why people develop PsA but to adequately address the major areas of unmet need, multi-centre, collaborative research programmes are now required. HIPPOCRATES is a 5-year, Innovative Medicines Initiative (IMI) programme which includes 17 European academic centres experienced in PsA research, 5 pharmaceutical industry partners, 3 small-/medium-sized industry partners and 2 patient representative organisations (see appendix). In this review, the ambitious programme of work to be undertaken by HIPPOCRATES is outlined and common approaches and challenges are identified. The participation of patient research partners in all stages of the work of HIPPOCRATES is highlighted. It is expected that, when completed, the results will ultimately allow for changes in the approaches to diagnosing, managing and treating PsA allowing for improvements in short-term and long-term outcomes.

Tixagevimab/cilgavimab for the prevention of COVID-19 in vaccine-refractory patients with autoimmune diseases: a prospective cohort study.

OBJECTIVES: To investigate the effects of passive immunization with the anti-SARS-CoV-2 monoclonal antibodies tixagevimab/cilgavimab on humoral responses and on COVID-19 outcomes in vaccine-refractory patients with immune-mediated inflammatory diseases (IMID) at high risk of severe COVID-19. METHODS: A prospective cohort study was performed on a cohort of high-risk vaccine-refractory IMID patients treated with a single dose of tixagevimab/cilgavimab (150 mg/150 mg). COVID-19 outcomes as well as serum and salivary anti-SARS-CoV-2 IgG were assessed at baseline and for at least 6 months. Results were compared with an untreated high-risk vaccine-refractory IMID population. Standardised incidence ratios (SIR) of COVID-19 compared with the general population were calculated for both groups. RESULTS: 38 high-risk IMID patients received tixagevimab/cilgavimab and were compared with 114 untreated high-risk IMID controls. Serum anti-Spike IgG increased to 6.6 OD (SD: ±0.8) at day one and remained positive up to month 6 (6.3 ± 1.4 OD). Salivary anti-Spike IgG peaked at month 2 (1.6 ± 1.1 OD)) and decreased from month 3 (0.8 ± 0.3 OD)). No severe or extended infection was observed in the tixagevimab/cilgavimab group. Compared with the general population, the SIR of COVID-19 in treated patients was 0.76 (95% CI: 0.24-1.58) despite the increased risk profile. The SIR of the control group was 1.51 (1.07-2.02), corresponding to a significantly increased incidence. CONCLUSIONS: Passive immunization with tixagevimab/cilgavimab is safe and effective in inducing anti-SARS-CoV-2 immunity and potentially in preventing COVID-19 in high-risk vaccine-refractory IMID patients. These data provide a proof of concept for the use of monoclonal antibodies as a preventative strategy against SARS-CoV-2 in vulnerable populations.

Serum Interleukin-36 α as a Candidate Biomarker to Distinguish Behçet's Syndrome and Psoriatic Arthritis.

Behçet's syndrome (BS) is a rare systemic vasculitis characterized by different clinical manifestations. As no specific laboratory tests exist, the diagnosis relies on clinical criteria, and the differential diagnosis with other inflammatory diseases can be challenging. Indeed, in a relatively small proportion of patients, BS symptoms include only mucocutaneous, articular, gastrointestinal, and non-typical ocular manifestations, which are frequently found also in psoriatic arthritis (PsA). We investigate the ability of serum interleukin (IL)-36α-a pro-inflammatory cytokine involved in cutaneous and articular inflammatory diseases-to differentiate BS from PsA. A cross-sectional study was performed on 90 patients with BS, 80 with PsA and 80 healthy controls. Significantly lower IL-36α concentrations were found in patients with BS as compared to PsA, although in both groups IL-36α was significantly increased compared to healthy controls. An empirical cut-off of 420.6 pg/mL displayed a specificity of 0.93, with a sensitivity of 0.70 (AUC 0.82) in discriminating PsA from BS. This cut-off displayed a good diagnostic performance also in BS patients lacking highly specific BS manifestations. Our results indicate that IL-36α might be involved in the pathogenesis of both BS and PsA, and might be a candidate biomarker to support the differential diagnosis of BS.

DeepNAPSI multi-reader nail psoriasis prediction using deep learning.

Nail psoriasis occurs in about every second psoriasis patient. Both, finger and toe nails can be affected and also severely destroyed. Furthermore, nail psoriasis is associated with a more severe course of the disease and the development of psoriatic arthritis. User independent quantification of nail psoriasis, however, is challenging due to the heterogeneous involvement of matrix and nail bed. For this purpose, the nail psoriasis severity index (NAPSI) has been developed. Experts grade pathological changes of each nail of the patient leading to a maximum score of 80 for all nails of the hands. Application in clinical practice, however, is not feasible due to the time-intensive manual grading process especially if more nails are involved. In this work we aimed to automatically quantify the modified NAPSI (mNAPSI) of patients using neuronal networks retrospectively. First, we performed photographs of the hands of patients with psoriasis, psoriatic arthritis, and rheumatoid arthritis. In a second step, we collected and annotated the mNAPSI scores of 1154 nail photos. Followingly, we extracted each nail automatically using an automatic key-point-detection system. The agreement among the three readers with a Cronbach's alpha of 94% was very high. With the nail images individually available, we trained a transformer-based neural network (BEiT) to predict the mNAPSI score. The network reached a good performance with an area-under-receiver-operator-curve of 88% and an area-under precision-recall-curve (PR-AUC) of 63%. We could compare the results with the human annotations and achieved a very high positive Pearson correlation of 90% by aggregating the predictions of the network on the test set to the patient-level. Lastly, we provided open access to the whole system enabling the use of the mNAPSI in clinical practice.

Prevalence and clinical associations of ultrasound-confirmed enthesitis in systemic lupus erythematosus.

OBJECTIVES: To assess the prevalence of US-confirmed enthesitis in a cohort of patients with SLE and to analyse the clinical associations to enthesitis during the course of SLE. METHODS: In a retrospective analysis of the SLE cohort of the Lupus Unit of the Careggi University Hospital, US examinations of SLE patients presenting with tender and/or swollen joints were retrieved to assess the presence of enthesitis. Patients with US-proven enthesitis were compared with SLE controls with tender and/or swollen joints who showed no US evidence of enthesitis. Clinical and laboratory features were compared at disease onset and during follow-up. RESULTS: A total of 400 patients fulfilling EULAR/ACR classification criteria for SLE were assessed. Of these, 106 underwent articular US examination. Evidence of enthesitis was found in 31/106 (29.2%) patients. Seventy-one patients without US-enthesitis were included as controls; four were excluded due to lack of follow-up data. Laboratory and clinical features were comparable between cases and controls at disease onset. Throughout a median follow-up of 10.0 (interquartile range [IQR] 8.3-23.3) years for cases and 12.4 (IQR 7.2-13.3) years for controls, patients with enthesitis were less likely to develop renal involvement (22.6% vs 46.5%, P = 0.028) and failed B cell depletion more frequently (75.0% vs 0%). CONCLUSION: In SLE patients with clinically active joints, US-proven enthesitis is a fairly common finding. Enthesitis in SLE could be the hallmark of a distinct disease phenotype with less renal involvement, more arthritis and low response to anti-CD 20 therapy, potentially requiring a tailored treatment.

Identification of circulating microRNA patterns in patients in psoriasis and psoriatic arthritis.

OBJECTIVE: miRNAs are small non-coding RNAs that control gene expression. Specific intra- and extracellular miRNA signatures have been identified in various diseases. Whether certain miRNA signatures are associated with psoriasis (PsO) and PsA is currently unknown. We aimed to search for circulating miRNA signatures associated with PsO and PsA patients. METHODS: Expression of miRNAs was analysed by reverse transcription quantitative real-time PCR (RT-qPCR) in the serum of PsA, PsO patients and healthy controls. Demographic and disease-specific characteristics and imaging data from hand MRI were recorded. In the discovery phase, 192 miRNA assays were analysed in 48 samples (PsA, PsO, controls: each N = 16). For validation, 17 selected miRNAs were measured in the total population. RESULTS: A total of 141 patients and controls were analysed (51 PsA, 40 PsO, 50 controls). In the discovery phase 51 miRNAs in PsO and 64 miRNAs in PsA were down- or upregulated compared with controls, with 33 miRNAs being changed in both (adj. P < 0.05). The 17 top candidates from discovery were assessed in the validation phase, 9 of them discriminated PsA and PsO from controls [area under the curve (AUC) ≥0.70, all P < 0.05]. Four miRNAs (miR-19b-3p, miR-21-5p, miR-92a-3p and let-7b-5p) were significantly differently regulated between PsO and PsA. A combination of these miRNAs increased the AUC to 0.92 in multivariate regression model to discriminate PsO and PsA. CONCLUSION: miRNA signatures in PsA and PsO patients differ from controls. Nine miRNAs were differentially regulated in PsA and PsO patients, five of them previously reported to be involved in bone and cartilage metabolism, indicating an intimate association of psoriatic inflammation and bone/cartilage changes.

An AI-Powered Clinical Decision Support System to Predict Flares in Rheumatoid Arthritis: A Pilot Study.

Treat-to-target (T2T) is a main therapeutic strategy in rheumatology; however, patients and rheumatologists currently have little support in making the best treatment decision. Clinical decision support systems (CDSSs) could offer this support. The aim of this study was to investigate the accuracy, effectiveness, usability, and acceptance of such a CDSS-Rheuma Care Manager (RCM)-including an artificial intelligence (AI)-powered flare risk prediction tool to support the management of rheumatoid arthritis (RA). Longitudinal clinical routine data of RA patients were used to develop and test the RCM. Based on ten real-world patient vignettes, five physicians were asked to assess patients' flare risk, provide a treatment decision, and assess their decision confidence without and with access to the RCM for predicting flare risk. RCM usability and acceptance were assessed using the system usability scale (SUS) and net promoter score (NPS). The flare prediction tool reached a sensitivity of 72%, a specificity of 76%, and an AUROC of 0.80. Perceived flare risk and treatment decisions varied largely between physicians. Having access to the flare risk prediction feature numerically increased decision confidence (3.5/5 to 3.7/5), reduced deviations between physicians and the prediction tool (20% to 12% for half dosage flare prediction), and resulted in more treatment reductions (42% to 50% vs. 20%). RCM usability (SUS) was rated as good (82/100) and was well accepted (mean NPS score 7/10). CDSS usage could support physicians by decreasing assessment deviations and increasing treatment decision confidence.