Large language model-driven sentiment analysis for facilitating fibromyalgia diagnosis.

BACKGROUND: Fibromyalgia (FM) is a complex disorder with widespread pain and emotional distress, posing diagnostic challenges. FM patients show altered cognitive and emotional processing, with a preferential allocation of attention to pain-related information. This attentional bias towards pain cues can impair cognitive functions such as inhibitory control, affecting patients' ability to manage and express emotions. Sentiment analysis using large language models (LLMs) can provide insights by detecting nuances in pain expression. This study investigated whether open-source LLM-driven sentiment analysis could aid FM diagnosis. METHODS: 40 patients with FM, according to the 2016 American College of Rheumatology Criteria and 40 non-FM chronic pain controls referred to rheumatology clinics, were enrolled. Transcribed responses to questions on pain and sleep were machine translated to English and analysed by the LLM Mistral-7B-Instruct-v0.2 using prompt engineering targeting FM-associated language nuances for pain expression ('prompt-engineered') or an approach without this targeting ('ablated'). Accuracy, precision, recall, specificity and area under the receiver operating characteristic curve (AUROC) were calculated using rheumatologist diagnosis as ground truth. RESULTS: The prompt-engineered approach demonstrated accuracy of 0.87, precision of 0.92, recall of 0.84, specificity of 0.82 and AUROC of 0.86 for distinguishing FM. In comparison, the ablated approach had an accuracy of 0.76, precision of 0.75, recall of 0.77, specificity of 0.75 and AUROC of 0.76. The accuracy was superior to the ablated approach (McNemar's test p<0.001). CONCLUSION: This proof-of-concept study suggests LLM-driven sentiment analysis, especially with prompt engineering, may facilitate FM diagnosis by detecting subtle differences in pain expression. Further validation is warranted, particularly the inclusion of secondary FM patients.

Explainable artificial intelligence for microbiome data analysis in colorectal cancer biomarker identification.

Background: Colorectal cancer (CRC) is a type of tumor caused by the uncontrolled growth of cells in the mucosa lining the last part of the intestine. Emerging evidence underscores an association between CRC and gut microbiome dysbiosis. The high mortality rate of this cancer has made it necessary to develop new early diagnostic methods. Machine learning (ML) techniques can represent a solution to evaluate the interaction between intestinal microbiota and host physiology. Through explained artificial intelligence (XAI) it is possible to evaluate the individual contributions of microbial taxonomic markers for each subject. Our work also implements the Shapley Method Additive Explanations (SHAP) algorithm to identify for each subject which parameters are important in the context of CRC. Results: The proposed study aimed to implement an explainable artificial intelligence framework using both gut microbiota data and demographic information from subjects to classify a cohort of control subjects from those with CRC. Our analysis revealed an association between gut microbiota and this disease. We compared three machine learning algorithms, and the Random Forest (RF) algorithm emerged as the best classifier, with a precision of 0.729 ± 0.038 and an area under the Precision-Recall curve of 0.668 ± 0.016. Additionally, SHAP analysis highlighted the most crucial variables in the model's decision-making, facilitating the identification of specific bacteria linked to CRC. Our results confirmed the role of certain bacteria, such as Fusobacterium, Peptostreptococcus, and Parvimonas, whose abundance appears notably associated with the disease, as well as bacteria whose presence is linked to a non-diseased state. Discussion: These findings emphasizes the potential of leveraging gut microbiota data within an explainable AI framework for CRC classification. The significant association observed aligns with existing knowledge. The precision exhibited by the RF algorithm reinforces its suitability for such classification tasks. The SHAP analysis not only enhanced interpretability but identified specific bacteria crucial in CRC determination. This approach opens avenues for targeted interventions based on microbial signatures. Further exploration is warranted to deepen our understanding of the intricate interplay between microbiota and health, providing insights for refined diagnostic and therapeutic strategies.

Effectiveness of biological targeted therapies may discriminate seronegative from seropositive rheumatoid arthritis.

OBJECTIVE: To assess the real-world effectiveness of targeting biologic drugs (bDMARD) in rheumatoid arthritis (RA) patients negative for rheumatoid factor (RF) and anti-citrullinated protein antibodies (ACPA). METHODS: We retrospectively selected 81 seronegative and 404 seropositive RA patients receiving treatment with abatacept, anti-tumor necrosis factor (TNF) alpha, or tocilizumab. Effectiveness was evaluated by analyzing drug survival using Kaplan-Meyer analysis over 10-year follow-up. Survival rates were compared by log rank test, and hazard ratios (HRs) of therapy discontinuation were estimated through multivariate Cox-regression. RESULTS: Clinical characteristics were similar between the two groups, except for a significantly higher percentage of inadequate responders to prior bDMARDs in the seronegative RA patients (p= 0.02). Among seronegative RA, tocilizumab demonstrated a survival rate of 73.9% with a mean survival time (MST) of 76.8 months (95% CI 61-92), which was significantly higher than abatacept (37.5%, MST 37.1 months (95% CI 22-51; p= 0.01). Anti-TNF alpha therapy fell in the middle (50.0%, MST 63.5 months (95% CI 47-79) but the difference was not significant. Nevertheless, seropositive RA patients did not show significantly different drug survival rates. Negative predictors of drug discontinuation were RF/ACPA positivity (HR 0.56) and sex male (HR 0.58), but treatment with abatacept (HR 1.88) or anti-TNF alpha (HR 1.79), no co-therapy with cDMARD (HR 1.74), absence of bone erosions (HR 1.41), and higher HAQ (HR 1.58) were positive predictors. CONCLUSIONS: To confirm these preliminary findings and to explore the hypothesis of a distinctive therapeutic algorithm in seronegative RA, prospective studies on larger cohorts are needed.

Anti-SARS-CoV-2 antibody decay after vaccination and immunogenicity of the booster dose of the BNT162b2 mRNA vaccine in patients with psoriatic arthritis on TNF inhibitors.

OBJECTIVES: Scanty data on the anti- SARS-CoV-2 IgG level decay after two-dose BNT162b2 vaccination have been published in patients with psoriatic arthritis (PsA) on TNF inhibitors (TNFi). Similarly, no reports on the immunogenicity of a booster dose in such patients have been provided yet.We aimed to investigate the IgG level decay after two-dose BNT162b2 vaccination and the immunogenicity and safety of the booster dose in PsA patients on TNFi. METHODS: Forty patients with classified PsA on TNFi undergoing booster dose with the BNT162b2 mRNA SARS- CoV-2 vaccine (BioNTech/Pfizer) were enrolled. Fifteen days after the third shot, serum IgG levels against SARS-CoV-2 (Abbott®ARCHITECT i2000SR, positivity cut-off 50 AU/mL) were assayed in all patients. Clinimetrics and treatment data were gathered. TNFi treatment was not discontinued. Sera from healthcare professionals were considered as healthy controls for 1:1 propensity score-matching. Student's t-test and logistic regression were used for investigating differences in immunogenicity between groups and predictors of antibody response. RESULTS: Even though the decay of IgG levels showed similar magnitude between groups, PsA patients had a lower IgG level than matched controls at 4 months after two-dose vaccination (2009.22±4050.22 vs. 6206.59±4968.33 AU/mL, respectively p=0.0006). Booster dose restored IgG levels to a similar extent in both groups (15846.47±12876.48 vs. 20374.46±12797.08 AU/ml p=0.20, respectively). Clinical Disease Activity Index (CDAI) did not change before and after vaccination (6.68±4.38 vs. 4.95±4.20, p=0.19). CONCLUSIONS: A BNT162b2 booster dose should be recommended in PsA patients on TNFi as its administration restores anti-SARS-CoV-2 IgG levels similar to healthy individuals.

Machine learning applied to MRI evaluation for the detection of lymph node metastasis in patients with locally advanced cervical cancer treated with neoadjuvant chemotherapy.

PURPOSE: Concurrent cisplatin-based chemotherapy and radiotherapy (CCRT) plus brachytherapy is the standard treatment for locally advanced cervical cancer (LACC). Platinum-based neoadjuvant chemotherapy (NACT) followed by radical hysterectomy is an alternative for patients with stage IB2-IIB disease. Therefore, the correct pre-treatment staging is essential to the proper management of this disease. Pelvic magnetic resonance imaging (MRI) is the gold standard examination but studies about MRI accuracy in the detection of lymph node metastasis (LNM) in LACC patients show conflicting data. Machine learning (ML) is emerging as a promising tool for unraveling complex non-linear relationships between patient attributes that cannot be solved by traditional statistical methods. Here we investigated whether ML might improve the accuracy of MRI in the detection of LNM in LACC patients. METHODS: We analyzed retrospectively LACC patients who underwent NACT and radical hysterectomy from 2015 to 2020. Demographic, clinical and MRI characteristics before and after NACT were collected, as well as information about post-surgery histopathology. Random features elimination wrapper was used to determine an attribute core set. A ML algorithm, namely Extreme Gradient Boosting (XGBoost) was trained and validated with tenfold cross-validation. The performances of the algorithm were assessed. RESULTS: Our analysis included n.92 patients. FIGO stage was IB2 in n.4/92 (4.3%), IB3 in n.42/92 (45%), IIA1 in n.1/92 (1.1%), IIA2 in n.16/92 (17.4%) and IIB in n.29/92 (31.5%). Despite detected neither at pre-treatment and post-treatment MRI in any patients, LNM occurred in n.16/92 (17%) patients. The attribute core set used to train ML algorithms included grading, histotypes, age, parity, largest diameter of lesion at either pre- and post-treatment MRI, presence/absence of fornix infiltration at pre-treatment MRI and FIGO stage. XGBoost showed a good performance (accuracy 89%, precision 83%, recall 78%, AUROC 0.79). CONCLUSIONS: We developed an accurate model to predict LNM in LACC patients in NACT, based on a ML algorithm requiring few easy-to-collect attributes.

Benralizumab for eosinophilic granulomatosis with polyangiitis: a retrospective, multicentre, cohort study.

BACKGROUND: Interleukin-5 (IL-5) inhibitors represent novel therapies for eosinophilic granulomatosis with polyangiitis (EGPA). This study assessed the effectiveness and safety of the IL-5 receptor inhibitor benralizumab in a European cohort of patients with EGPA. METHODS: This retrospective cohort study included patients with EGPA from 28 European referral centres of the European EGPA Study Group across six countries (Italy, France, UK, Russia, Spain, and Switzerland) who received benralizumab as any line of treatment between Jan 1, 2019, and Sep 30, 2022. We assessed the rates of complete response, defined as no disease activity (Birmingham Vasculitis Activity Score [BVAS] of 0) and a prednisone dose of up to 4 mg/day, in contrast to partial response, defined as a BVAS of 0 and a prednisone dose greater than 4 mg/day. Active disease manifestations, pulmonary function, variation in glucocorticoid dose, and safety outcomes were also assessed over a 12-month follow-up. FINDINGS: 121 patients with relapsing-refractory EGPA treated with benralizumab at the dose approved for eosinophilic asthma were included (64 [53%] women and 57 [47%] men; median age at the time of beginning benralizumab treatment 54·1 years [IQR 44·2-62·2]). Complete response was reported in 15 (12·4%, 95% CI 7·1-19·6) of 121 patients at month 3, 25 (28·7%, 19·5-39·4) of 87 patients at month 6, and 32 (46·4%, 34·3-58·8) of 69 patients at month 12; partial response was observed in an additional 43 (35·5%, 27·0-44·8) patients at month 3, 23 (26·4%, 17·6-37·0) at month 6, and 13 (18·8%, 10·4-30·1) at month 12. BVAS dropped from 3·0 (IQR 2·0-8·0) at baseline to 0·0 (0·0-2·0) at months 3 and 6, and to 0·0 (0·0-1·0) at month 12. The proportion of patients with systemic manifestations, active peripheral neurological disease, ear, nose, and throat involvement, and pulmonary involvement decreased, with an improvement in lung function tests. Six patients relapsed after having a complete response. The oral prednisone (or equivalent) dose decreased from 10·0 mg/day (5·0-12·5) at baseline to 5·0 mg/day (3·6-8·5) at month 3 (p<0·01), to 5·0 mg/day (2·5-6·3) at month 6, and to 2·5 mg/day (0·0-5·0) at month 12 (p<0·0001). 19 (16%) of 121 patients had adverse events and 16 (13%) discontinued benralizumab. INTERPRETATION: These data suggest that benralizumab could be an effective treatment for EGPA in real-life clinical practice. Further clinical trials are required to confirm the efficacy of benralizumab in patients with a higher baseline disease activity. FUNDING: None.

A Machine Learning Approach to Predict Remission in Patients With Psoriatic Arthritis on Treatment With Secukinumab.

Background: Psoriatic Arthritis (PsA) is a multifactorial disease, and predicting remission is challenging. Machine learning (ML) is a promising tool for building multi-parametric models to predict clinical outcomes. We aimed at developing a ML algorithm to predict the probability of remission in PsA patients on treatment with Secukinumab (SEC). Methods: PsA patients undergoing SEC treatment between September 2017 and September 2020 were retrospectively analyzed. At baseline and 12-month follow-up, we retrieved demographic and clinical characteristics, including Body Mass Index (BMI), disease phenotypes, Disease Activity in PsA (DAPSA), Leeds Enthesitis Index (LEI) and presence/absence of comorbidities, including fibromyalgia and metabolic syndrome. Two random feature elimination wrappers, based on an eXtreme Gradient Boosting (XGBoost) and Logistic Regression (LR), were trained and validated with 10-fold cross-validation for predicting 12-month DAPSA remission with an attribute core set with the least number of predictors. The performance of each algorithm was assessed in terms of accuracy, precision, recall and area under receiver operating characteristic curve (AUROC). Results: One-hundred-nineteen patients were selected. At 12 months, 20 out of 119 patients (25.21%) achieved DAPSA remission. Accuracy and AUROC of XGBoost was of 0.97 ± 0.06 and 0.97 ± 0.07, overtaking LR (accuracy 0.73 ± 0.09, AUROC 0.78 ± 0.14). Baseline DAPSA, fibromyalgia and axial disease were the most important attributes for the algorithm and were negatively associated with 12-month DAPSA remission. Conclusions: A ML approach may identify SEC good responders. Patients with a high disease burden and axial disease with comorbid fibromyalgia seem challenging to treat.

Immunogenicity of BNT162b2 mRNA SARS-CoV-2 vaccine in patients with psoriatic arthritis on TNF inhibitors.

BACKGROUND: Scanty data on the immunogenicity of the BNT162b2 vaccine in patients with psoriatic arthritis (PsA) on Tumor Necrosis Factor inhibitors (TNFi) have been published. OBJECTIVE: To investigate the humoral response to BNT162b2 vaccination patients with PsA on TNFi, comparing immunogenicity with healthy controls. METHODS: Forty patients with classified PsA on TNFi undergoing vaccination with the BNT162b2 mRNA SARS-CoV-2 vaccine (BioNTech/Pfizer) were enrolled. Fifteen days after the second shot, serum IgG levels against SARS-CoV-2 (Abbott ARCHITECT i2000SR, positivity cut-off 50 AU/mL) were assayed in all patients. Clinimetrics and treatment data were gathered. TNFi treatment was not discontinued throughout the whole period, whereas methotrexate (MTX) was discontinued for 1 week after each shot in those on combination therapy. Sera from healthcare professionals were considered as healthy controls for 1:1 propensity score matching; any of them was taking medication.Student's t-test and logistic regression were used for investigating differences in immunogenicity between groups and predictors of antibody response. RESULTS: Clinical Disease Activity Index did not change before and after vaccination (7.06±5.23 to 7.10±5.27, p=0.92).Patients with PsA achieved a positive anti-SARS-CoV-2 IgG level with a mean (±SD) of 13794.44±15 815.42 AU/mL. Although lower, the antibody level was not significantly different from matched controls (19227.4±11.8460.45 AU/mL, p=0.08). In the overall sample, those on MTX (12/80, 15%) had a trend toward lower immune response (p=0.07); glucocorticoid therapy (11/80, 13.8%) predicted lower antibody levels (p=0.04). CONCLUSIONS: Continuing TNFi in patients with PsA throughout the vaccination did not hamper immunogenicity.

Anakinra effectiveness in refractory polyserositis: An Italian multicenter study.

OBJECTIVES: Polyserositis is an inflammatory condition involving different serosal membranes at the same time, specifically the pericardium, pleura, and peritoneum with exudates in the respective cavities. Treatment with non-steroidal anti-inflammatory drugs (NSAIDs), colchicine and glucocorticoids may be effective in patients with polyserositis, but relapses often occur when these drugs are tapered or discontinued. The interleukin (IL)-1 receptor antagonist anakinra has shown a beneficial effect in idiopathic recurrent pericarditis, mostly in unresponsive patients who develop steroid dependence and/or colchicine resistance. To date, there are no data suggesting the best therapy for managing acute episodes and/or relapses of polyserositis. On this basis, we performed a retrospective study aimed at evaluating the effectiveness and safety profile of anakinra in treating patients with refractory polyserositis. METHODS: Patients with idiopathic polyserositis or rheumatic diseases presenting inflammation of 2 or more serous membranes were included. Serositis had to be confirmed by imaging tests comprising either echocardiography, abdominal ultrasound, chest or abdomen computed tomography and/or chest x-ray scan. We included patients with polyserositis who started anakinra from January 2011 to January 2019 due to a poorly controlled disease despite treatment with NSAIDs, conventional immunosuppressant drugs, or the need to minimize oral corticosteroids intake. Erythrocyte sedimentation rate (ESR), C reactive protein (CRP), and imaging tests, were recorded to monitor serositis at baseline and either at 3, 6 and 12-month follow-up. Patients with malignancies and infectious diseases were excluded from the analysis. RESULTS: Forty-five patients with recurrent polyserositis (23 women) (mean age 43.2±15.8 years and mean disease duration 23.1±28 years) were analysed. Polyserositis was idiopathic in 26 (57.8%) patients. Thirteen patients suffered from autoinflammatory diseases, whereas 6 were affected by autoimmune diseases. Combination treatment with colchicine and NSAIDs at anakinra baseline was administered in 38/45 (84.4%) and 37/45 (82.2%) patients, respectively. After starting anakinra, 84.5% of patients experienced a resolution of serositis with a dramatic decrease in ESR and CRP (P<0.001, for both) already at 3 months, furthermore the same beneficial effect was observed up to 12 months. No relapse was seen at 3 months, whereas the median number of relapses at 6 and 12 months was 0 (interquartile range 0-1). Glucocorticoids were discontinued in 22/45 (48.9%) patients already after 3 months (P<0.001). After 12 months 32/37 (86.5%) patients were steroid-free. Similarly, NSAIDs use significantly was decreased at 3 months (7/45 [15.6%] patients, P<0.001), whereas at 12-month follow-up no patient was on NSAIDs. Urticarial rashes at anakinra injection site occurring in 3 patients were the most common adverse events. CONCLUSIONS: Anakinra appeared to be a safe and useful therapeutic choice for patients refractory to optimal anti-inflammatory therapy (NSAIDs, colchicine and corticosteroids), allowing not only a dramatic reduction of recurrences but also of corticosteroids use. Anakinra was effective both in the idiopathic forms of polyserositis and in those with an underlying rheumatic disease, suggesting a common pathogenic pathway leading to serositis onset.

Radiomics to predict the mortality of patients with rheumatoid arthritis-associated interstitial lung disease: A proof-of-concept study.

Objectives: Patients with rheumatoid arthritis (RA) and interstitial lung disease (ILD) have increased mortality compared to the general population and factors capable of predicting RA-ILD long-term clinical outcomes are lacking. In oncology, radiomics allows the quantification of tumour phenotype by analysing the characteristics of medical images. Using specific software, it is possible to segment organs on high-resolution computed tomography (HRCT) images and extract many features that may uncover disease characteristics that are not detected by the naked eye. We aimed to investigate whether features from whole lung radiomic analysis of HRCT may alone predict mortality in RA-ILD patients. Methods: High-resolution computed tomographies of RA patients from January 2012 to March 2022 were analyzed. The time between the first available HRCT and the last follow-up visit or ILD-related death was recorded. We performed a volumetric analysis in 3D Slicer, automatically segmenting the whole lungs and trachea via the Lung CT Analyzer. A LASSO-Cox model was carried out by considering ILD-related death as the outcome variable and extracting radiomic features as exposure variables. Results: We retrieved the HRCTs of 30 RA-ILD patients. The median survival time (interquartile range) was 48 months (36-120 months). Thirteen out of 30 (43.33%) patients died during the observation period. Whole line segmentation was fast and reliable. The model included either the median grey level intensity within the whole lung segmentation [high-resolution (HR) 9.35, 95% CI 1.56-55.86] as a positive predictor of death and the 10th percentile of the number of included voxels (HR 0.20, 95% CI 0.05-0.84), the voxel-based pre-processing information (HR 0.23, 95% CI 0.06-0.82) and the flatness (HR 0.42, 95% CI 0.18-0.98), negatively correlating to mortality. The correlation of grey level values to their respective voxels (HR 1.52 95% CI 0.82-2.83) was also retained as a confounder. Conclusion: Radiomic analysis may predict RA-ILD patients' mortality and may promote HRCT as a digital biomarker regardless of the clinical characteristics of the disease.

Extra-Articular Manifestations and Comorbidities in Psoriatic Disease: A Journey Into the Immunologic Crosstalk.

Psoriatic arthritis (PsA) is a chronic inflammatory disease primarily affecting peripheral and axial joints, with the possible presence of extra-articular manifestations (EAMs), such as psoriasis, uveitis, and inflammatory bowel disease. Recently, the concept of psoriatic disease (PsD) has been proposed to define a systemic condition encompassing, in addition to joints and EAMs, some comorbidities (e.g., metabolic syndrome, type II diabetes, hypertension) that can affect the disease outcome and the achievement of remission. EAMs and comorbidities in PsA share common immunopathogenic pathways linked to the systemic inflammation of this disease; these involve a broad variety of immune cells and cytokines. Currently, various therapeutics are available targeting different cytokines and molecules implicated in the inflammatory response of this condition; however, despite an improvement in the management of PsA, comprehensive disease control is often not achievable. There is, therefore, a big gap to fill especially in terms of comorbidities and EAMs management. In this review, we summarize the clinical aspects of the main comorbidities and EAMs in PsA, and we focus on the immunopathologic features they share with the articular manifestations. Moreover, we discuss the effect of a diverse immunomodulation and the current unmet needs in PsD.

Formalin-Fixed and Paraffin-Embedded Samples for Next Generation Sequencing: Problems and Solutions.

Over the years, increasing information has been asked of the pathologist: we have moved from a purely morphological diagnosis to biomolecular and genetic studies, which have made it possible to implement the use of molecular targeted therapies, such as anti-epidermal growth factor receptor (EGFR) molecules in EGFR-mutated lung cancer, for example. Today, next generation sequencing (NGS) has changed the approach to neoplasms, to the extent that, in a short time, it has gained a place of absolute importance and diagnostic, prognostic and therapeutic utility. In this scenario, formaldehyde-fixed and paraffin-embedded (FFPE) biological tissue samples are a source of clinical and molecular information. However, problems can arise in the genetic material (DNA and RNA) for use in NGS due to fixation, and work is being devoted to possible strategies to reduce its effects. In this paper, we discuss the applications of FFPE tissue samples in the execution of NGS, we focus on the problems arising with the use of this type of material for nucleic acid extraction and, finally, we consider the most useful strategies to prevent and reduce single nucleotide polymorphisms (SNV) and other fixation artifacts.

Retention rate of a second line with a biologic DMARD after failure of a first-line therapy with abatacept, tocilizumab, or rituximab: results from the Italian GISEA registry.

OBJECTIVES: EULAR recommendations do not suggest which biologic disease-modifying anti-rheumatic drug (bDMARD) should be preferred after failure of a first bDMARD in the treatment of rheumatoid arthritis (RA). In particular, few data are available regarding the effectiveness of a second-line bDMARD after failure of abatacept (ABA), tocilizumab (TCZ), and rituximab (RTX). The aim of this study was to analyze the retention rate of a second line with tumor necrosis factor inhibitors (TNFi) or other mechanisms of action (MoAs), after the failure of either RTX, TCZ, or ABA. METHODS: Two hundred and seventy-eight RA patients from the Italian GISEA registry were included in the study. RTX was the first bDMARD in 18% of patients, ABA in 45.7%, and TCZ in 36.3%, while the second bDMARD was a TNFi (group 1) in 129 patients and an agent with a different MoA (group 2) in 149. RESULTS: During a median follow-up of 22 months (IQR 68), 129 patients discontinued their treatment; patients of group 1 discontinued the treatment more frequently than patients of group 2 (p<0.001) with retention rates of 33.6±5.7% and 63.6±4.6% after 104 weeks for group 1 and group 2, respectively (p<0.001). At multivariate analysis, the mechanism of action was the only predictor for the maintenance in therapy. CONCLUSIONS: According to our data, ABA, RTX, and TCZ seem to maintain a good retention rate also when used as a second-line therapy, suggesting their use after the failure of a non-TNFi as first-line therapy. However, specifically designed studies are needed to evaluate the more appropriate therapeutic strategies in RA, according to the first-line drug, including new targeted synthetic DMARDs. Key Points • A large proportion of rheumatoid arthritis patients fail the first biologic DMARD. • Few data are available about the efficacy of biologic DMARD after the failure of a non-TNF inhibitor. • Abatacept, rituximab, or tocilizumab seem to maintain a good retention rate after the failure of a first-course therapy with a non-TNF inhibitor.

A convolutional neural network with transfer learning for automatic discrimination between low and high-grade synovitis: a pilot study.

Ultrasound-guided synovial tissue biopsy (USSB) may allow personalizing the treatment for patients with inflammatory arthritis. To this end, the quantification of tissue inflammation in synovial specimens can be crucial to adopt proper therapeutic strategies. This study aimed at investigating whether computer vision may be of aid in discriminating the grade of synovitis in patients undergoing USSB. We used a database of 150 photomicrographs of synovium from patients who underwent USSB. For each hematoxylin and eosin (H&E)-stained slide, Krenn's score was calculated. After proper data pre-processing and fine-tuning, transfer learning on a ResNet34 convolutional neural network (CNN) was employed to discriminate between low and high-grade synovitis (Krenn's score < 5 or ≥ 5). We computed test phase metrics, accuracy, precision (true positive/actual results), and recall (true positive/predicted results). The Grad-Cam algorithm was used to highlight the regions in the image used by the model for prediction. We analyzed photomicrographs of specimens from 12 patients with arthritis. The training dataset included n.90 images (n.42 with high-grade synovitis). Validation and test datasets included n.30 (n.14 high-grade synovitis) and n.30 items (n.16 with high-grade synovitis). An accuracy of 100% (precision = 1, recall = 1) was scored in the test phase. Cellularity in the synovial lining and sublining layers was the salient determinant of CNN prediction. This study provides a proof of concept that computer vision with transfer learning is suitable for scoring synovitis. Integrating CNN-based approach into real-life patient management may improve the workflow between rheumatologists and pathologists.

Safety of systemic treatments for Behçet's syndrome.

INTRODUCTION: Treatment of Behçet's syndrome (BS) is aimed at controlling all symptoms of such a complex disorder, ensuring a good quality of life and preventing life-threatening complications. A better understanding of the pathogenic role of different chemokines has improved our knowledge of BS and elicited a more specific use of therapies currently available, minimizing the burden of potential side-effects related to treatment. AREAS COVERED: This work aims to provide a detailed overview of the safety profile for current therapies available in the treatment of BS, focusing on the main side-effects, toxicity and contraindications. EXPERT OPINION: The greatest experience in the management of BS has been achieved with the employment of monoclonal anti-tumor necrosis factor antibodies which have been advocated for BS refractory manifestations. Moreover, interleukin-1 inhibitors have proven to be effective as well as safe, despite escalation of their dosage, especially to manage the most severe and difficult-to-treat ocular manifestations. However, general treatment of BS patients remains awkward as protean clinical features may respond differently to the same treatment or even worsen. Therefore, patients' safety for therapies used in BS promotes the implementation of precision medicine, which could help targeting accurately the pathogenetic mechanisms concealed behind specific clinical phenotypes.

Cardiovascular risk estimation with 5 different algorithms before and after 5 years of bDMARD treatment in rheumatoid arthritis.

BACKGROUND: Assessing cardiovascular (CV) risk represents a challenge for clinicians because more variables can impact CV risk. The aim of this study was to evaluate the change of CV risk after 5 years of biological treatment in rheumatoid arthritis (RA) patients and impact of prolonged low disease activity on 5 different CV risk algorithms. MATERIALS AND METHODS: We estimated the CV risk, at baseline and at 5-year follow-up (FU), with the Systematic COronary Risk Evaluation(SCORE) charts, the algorithm 'Progetto Cuore', the QRISK3-2018 score, the Reynold Risk Score(RRS) and the Expanded Risk Score in RA(ERS-RA). Clinical disease activity index(CDAI) was used to define RA activity. Wilcoxon signed-rank test was used to compare CV risk scores. RESULTS: In 110 patients with a 5-year FU on biological disease-modifying anti-rheumatic drug treatment, we observed an increase in the 10-year CV risk estimated by SCORE charts [from mean (SD) 0.9% (1.4) to 1.1% (1.5), P < .001], 'Progetto Cuore' [from mean (SD) 5.5% (7.2) to 6.2% (6.8), P < .001], QRISK3-2018 [from mean (SD) 9.3% (10.1) to 11.9% (10.8), P < .001) and RRS [from mean (SD) 5.6% (6.4) to 6.2% (7.5), P < .05], mainly due to age raise. ERS-RA highlighted a significant decrease of estimated CV risk in patients with persistent CDAI ≤ 10[from mean (SD) 9.6% (11.2) to 7.3% (6.4), P < .05], despite age increase and its impact on the CV risk score. CONCLUSIONS: Algorithms commonly used to estimate 10-year CV risk in RA perform differently. Scores that include specific inflammatory RA-related variables seem to decrease with amelioration of disease activity. Further investigations are warranted to explore the predictive value of their changing over time.

Effectiveness and safety profile of anakinra in a HLA-B27 positive patient with multiple sclerosis-associated uveitis.

Multiple sclerosis (MS) is a chronic demyelinating disorder of central nervous system (CNS) leading to neurological disability. A wide variety of ophthalmic and neuro-ophthalmic manifestations have been associated with MS. Although this link is well recognized, controversial is still the risk of developing MS in patients with ophthalmic manifestations. Intermediate uveitis followed by panuveitis are the most common manifestations among the ophthalmic involvement in MS. Timely management of uveitis, is a crucial step to prevent irreversible visual impairment. A multidisciplinary team including ophthalmologists together with other specialists is required in the majority of cases for an adequate diagnostic and therapeutic approach of uveitis. Corticosteroids represent the mainstay of therapy in the acute phase, whereas conventional immunosuppressive drugs such as azathioprine may allow a steroid sparing effect. Increasing evidence from anti-CD 20 monoclonal antibodies such as rituximab have proven the efficacy on clinical and radiological outcomes in MS, on the contrary anti-Tumor Necrosis Factor (TNF) monoclonal antibodies such as infliximab and adalimumab are contraindicated in patients with demyelinating disorders, as they seem to worsen disease and neurological clinical symptoms. On this basis, MS-associated uveitis may deeply influence the therapeutic choices suggesting targeting inflammatory cytokines different from TNF. Recently, interleukin (IL)-1 blockade has been investigated as possible therapeutic tool in several inflammatory eye conditions such as Behcet's disease related uveitis, strengthening that IL-1 is also critical for the development of uveitis. Herein, we report our experience in a HLA-B27 positive patient with MS-associated uveitis successfully treated with the short-acting IL-1 receptor antagonist anakinra.