3D CT-Inclusive Deep-Learning Model to Predict Mortality, ICU Admittance, and Intubation in COVID-19 Patients.

Chest CT is a useful initial exam in patients with coronavirus disease 2019 (COVID-19) for assessing lung damage. AI-powered predictive models could be useful to better allocate resources in the midst of the pandemic. Our aim was to build a deep-learning (DL) model for COVID-19 outcome prediction inclusive of 3D chest CT images acquired at hospital admission. This retrospective multicentric study included 1051 patients (mean age 69, SD = 15) who presented to the emergency department of three different institutions between 20th March 2020 and 20th January 2021 with COVID-19 confirmed by real-time reverse transcriptase polymerase chain reaction (RT-PCR). Chest CT at hospital admission were evaluated by a 3D residual neural network algorithm. Training, internal validation, and external validation groups included 608, 153, and 290 patients, respectively. Images, clinical, and laboratory data were fed into different customizations of a dense neural network to choose the best performing architecture for the prediction of mortality, intubation, and intensive care unit (ICU) admission. The AI model tested on CT and clinical features displayed accuracy, sensitivity, specificity, and ROC-AUC, respectively, of 91.7%, 90.5%, 92.4%, and 95% for the prediction of patient's mortality; 91.3%, 91.5%, 89.8%, and 95% for intubation; and 89.6%, 90.2%, 86.5%, and 94% for ICU admission (internal validation) in the testing cohort. The performance was lower in the validation cohort for mortality (71.7%, 55.6%, 74.8%, 72%), intubation (72.6%, 74.7%, 45.7%, 64%), and ICU admission (74.7%, 77%, 46%, 70%) prediction. The addition of the available laboratory data led to an increase in sensitivity for patient's mortality (66%) and specificity for intubation and ICU admission (50%, 52%, respectively), while the other metrics maintained similar performance results. We present a deep-learning model to predict mortality, ICU admittance, and intubation in COVID-19 patients. KEY POINTS: • 3D CT-based deep learning model predicted the internal validation set with high accuracy, sensibility and specificity (> 90%) mortality, ICU admittance, and intubation in COVID-19 patients. • The model slightly increased prediction results when laboratory data were added to the analysis, despite data imbalance. However, the model accuracy dropped when CT images were not considered in the analysis, implying an important role of CT in predicting outcomes.

Application of Ultrasound in the Assessment of Oligoarticular Psoriatic Arthritis Subset: Results from Patients Treated with Apremilast.

BACKGROUND: Psoriatic arthritis (PsA) is an inflammatory rheumatic disease characterized by different phenotypes in terms of joint involvement. The so-called oligoarticular pattern involves fewer than five active joints at a different time points. The evaluation of disease activity in this subset of patients is an unmet need due to the lack of specific indices able to capture modifications over time. OBJECTIVES: To evaluate the ability of musculoskeletal ultrasound to monitor the response to apremilast treatment in oligoarticular PsA patients. METHODS: We evaluated 24 oligoarticular patients (19 women, 5 men; median age 56 years, interquartile range (IQR) 19; median disease duration 5 years, IQR 5.75). All patients were assessed at baseline (T0), and after 6 (T1), 12 (T2), and 24 (T3) weeks. Clinical assessment included evaluation of 66 swollen joints and patient global health assessment. All the patients underwent ultrasound assessment of the clinically involved joints. Synovial effusion/hypertrophy and power Doppler were scored with a semi-quantitative scale (0-3). The total inflammatory score was the sum of the scores. RESULTS: We found a reduction in the ultrasound inflammatory score at all time points, with a significant improvement at 6 and 12 weeks of treatment compared with baseline: T0 median 8.5 (IQR 5.0); T1 3.5 (3.0); T2 2.0 (3.5); P = 0.01. We observed a significant reduction of patient global health assessment after 24 weeks (T0 median 50 (32.5); T3 40 (57.5); P = 0.01). CONCLUSIONS: Musculoskeletal ultrasound could be useful in the assessment of treatment response in PsA patients with oligoarticular subset.

Burden of COVID-19 on Italian Internal Medicine Wards: Delphi, SWOT, and Performance Analysis after Two Pandemic Waves in the Local Health Authority "Roma 6" Hospital Structures.

Background: COVID-19 causes major changes in day-to-day hospital activity due to its epidemiological characteristics and the clinical challenges it poses, especially in internal medicine wards. Therefore, it is necessary to understand and manage all of the implicated factors in order to maintain a high standard of care, even in sub-par circumstances. Methods: This was a three-phase, mixed-design study. Initially, the Delphi method allowed us to analyze the causes of poor outcomes in a cohort of an aggregate of Italian COVID-19 wards via an Ishikawa diagram. Then, for each retrieved item, a score was assigned according to a pros/cons, opportunities/threats system. Scores were also assigned according to potential value/perceived risk. Finally, the performances of MCs (Medicine-COVID-19 wards) and MCFs (Medicine-COVID-19-free: Internal Medicine wards) units were represented via a Barber's nomogram. Results: MCFs hospitalized 790 patients (-23.90% compared to 2019 Internal Medicine admissions). The main risk factors for mortality were patients admitted from local facilities (+7%) and the presence of comorbidities (>3: 100%, ≥5: 24.7%). A total of 197 (25%) patients were treated with non-invasive ventilation (NIV). The most deaths (57.14%) occurred in patients admitted from local facilities. Conclusions: Medicine-COVID-19 wards show higher complexity and demand compared to non-COVID-19 ones and they are comparable to sub-intensive therapy wards. It is necessary to promote the use of NIV in such settings.

Comprehensive disease control in systemic lupus erythematosus.

OBJECTIVES: We evaluated a monocentric SLE cohort in order to assess the frequency of Lupus comprehensive disease control (LupusCDC), a condition defined by the achievement of remission and the absence of damage progression. METHODS: Our longitudinal analysis included SLE patients with 5-years follow-up and at least one visit per year. Disease activity was assessed by SLE Disease Activity Index 2000 (SLEDAI-2K) and three different remission levels were evaluated (Complete Remission, CR; Clinical remission off-corticosteroids; clinical remission on-corticosteroids). Chronic damage was assessed according to SLICC Damage Index (SDI). LupusCDC was defined as remission achievement for at least one year plus absence of chronic damage progression in the previous one year. A machine learning based analysis was carried out, applying and comparing Nonlinear Support Vector Machines (SVM) models and Decision Trees (DT), whereas features ranking was performed with the ReliefF algorithm. RESULTS: We evaluated 172 patients [M/F 16/156, median age 49 years (IQR 16.7), median disease duration 180 months (IQR 156)]. SDI values (baseline mean±SD 0.7 ± 1.1) significantly increased during the follow-up period. In all time-points analyzed, LupusCDC including CR was the most frequently detected. The failure to reach this condition was significantly associated with renal involvement and with the intake of immunosuppressant drugs and glucocorticoid (GC). Ten patients (5.8%) have maintained LupusCDC during the whole 5-year follow-up: these patients had never presented renal involvement and showed lower prevalence of anti-phospholipid antibodies (p = 0.0001). Finally, the prevalence of GC intake was significantly lower (p = 0.0001). The application of machine learning models showed that the available features were able to provide significant information to build predictive models with an AUC score of 0.703 ± 0.02 for DT and 0.713 ± 0.02 for SVM. CONCLUSIONS: Our data on a monocentric cohort suggest that the LupusCDC can efficaciously merge into one outcome SLE-related disease activity and chronic damage in order to perform an all-around evaluation of SLE patients.

Effectiveness and safety of baricitinib in rheumatoid arthritis: a monocentric, longitudinal, real-life experience.

OBJECTIVES: Baricitinib is a Janus-kinase (JAK) 1/2 inhibitor, approved for the treatment of moderate-to-severe rheumatoid arthritis (RA) patients with inadequate response to conventional synthetic disease-modifying anti-rheumatic drugs (csDMARDs). We report the first real-life experience with baricitinib in a monocentric cohort of unselected RA patients. METHODS: We enrolled consecutive RA patients starting baricitinib. At baseline and after 4, 12, 24 and 48 weeks we assessed the disease activity by composite indices (SDAI, CDAI and DAS28CRP) and ultrasonography, and we recorded any adverse events. The primary endpoint was the percentage of patients achieving SDAI remission at week 4. RESULTS: We enrolled 59 patients [(F:M = 50:9, median age 58.1 years (IQR 12.8), median disease duration 144 (IQR 150) months] treated with baricitinib in combination with a csDMARD (52.5%) or monotherapy (47.5%) for a median follow-up of 24 weeks (IQR 36). The 12-month drug retention rate was 74%. At weeks 4, 12, 24 and 48 we observed a significant reduction of DAS28, CDAI and SDAI, global health and pain (p<0.001 for all). After 4 weeks of treatment, 12% of patients achieved SDAI remission. Concomitant csDMARDs, previous biological DMARDs, gender, seropositivity and BMI did not affect the efficacy of baricitinib. Baricitinib allowed a significant reduction in prednisone dose after 12 and 24 weeks and a rapid and sustained ultrasound improvement. No serious adverse events, serious infections or cardiovascular events were recorded. CONCLUSIONS: Our study confirms the efficacy and safety profile and rapid onset of the effect of baricitinib in RA patients in a real-life setting.

Joint involvement influences quality of life in systemic lupus erythematosus patients.

INTRODUCTION: Joint involvement represents the major determinant in quality of life (QoL)in Systemic Lupus Erhytematosus (SLE) patients. However, QoLhas been generally evaluated by non-specific questionnaires. We evaluated the relationship between SLE musculoskeletal manifestations and QoL, assessed by LupusQoL. METHODS: Patients with joint involvement (group A) were compared with those without this feature (group B). Disease activity was assessed by SLEDAI-2k in the whole population, while DAS28 and swollen to tender ratio were applied to assess joint activity. LupusQoL was administered to all the patients. RESULTS: Group A included 110 patients [M/F 8/102; median age 49 years (IQR 13), median disease duration 156 months (IQR 216)], group B 58 [M/F 11/47; median age 40 years (IQR 15), median disease duration 84 months (IQR 108)].We found significanlty lower values in all the LupusQoL domains except for one (burden to others) in group A in comparison with group B. A significant correlation between DAS28 values and all the LupusQoL domains in group A was found; only three domains correlated with SLEDAI-2k. CONCLUSIONS: SLE-related joint involvement significantly influences disease-specific QoL. DAS28 better correlated with LupusQoL domains in comparison with SLEDAI-2k, confirming the need for specific musculoskeletal activity indices.

Belimumab is Able to Induce a Significant Improvement of Joint Activity Status in Patients Diagnosed with Systemic Lupus Erythematosus: Results From a 12-Month Longitudinal Study.

BACKGROUND: Belimumab was the first biological drug approved for the treatment of systemic lupus erythematosus (SLE) patients. Phase II/III randomized controlled trials and real-life studies identified patients with musculoskeletal involvement as best responders. OBJECTIVES: To evaluate the effectiveness of belimumab in SLE-related joint involvement. METHODS: The cohort comprised SLE patients receiving belimumab for musculoskeletal indications. Belimumab was intravenously administrated according to protocols; all the patients were evaluated at baseline (T0) and after 3 (T1), 6 (T2), and 12 (T3) months. We assessed joint activity by disease activity score 28, simple disease activity index (SDAI), clinical disease activity index (CDAI), and swollen tender ratio. Each patient underwent musculoskeletal ultrasound of 34 joints to assess synovial effusion synovial hypertrophy, and power Doppler; by using a semi-quantitative scale (0-3) we obtained the total inflammatory score (0-216). RESULTS: We evaluated 20 patients (males/females 1/19, median age 45 years [interquartile range (IQR) 12], median disease duration 144 months [IQR 144]). CDAI and SDAI significantly decreased at T1 (P = 0.02 and P = 0.01 respectively) and this improvement was maintained at the following time-points (CDAI: T2 P = 0.008, T3 P = 0.004; SDAI: T2 P = 0.006, T3 P = 0.01). A significant reduction of median ultrasound score was identified at T1 (T0 20.5 [IQR 13.5] vs. T1 7.5 [IQR 4.7], P < 0.001), and maintained at T2 (7.0 [IQR 5], P < 0.0001), and T3 (7.0 [IQR 9.0], P < 0.0001). CONCLUSIONS: Belimumab induces a sustained improvement of ultrasound-detected inflammatory status at the articular level.

Caffeine intake influences disease activity and clinical phenotype in systemic lupus erythematosus patients.

OBJECTIVE: Caffeine, one of the most widely consumed products in the world, seems to interact with multiple components of the immune system by acting as a non-specific phosphodiesterase inhibitor. In vitro dose-dependent treatment with caffeine down-regulates mRNA levels of key inflammation-related genes in peripheral blood mononuclear cells. So far, no robust data are available about the possible contribution of caffeine in systemic lupus erythematosus (SLE). The aim of this study was to evaluate the impact of caffeine consumption on SLE-related disease phenotype and activity, in terms of clinimetric assessment and cytokine serum levels. METHODS: We performed a cross-sectional study, enrolling consecutive patients and reporting their clinical and laboratory data. Disease activity was assessed by SLE Disease Activity Index 2000 (SLEDAI-2K). Caffeine intake was evaluated by a 7-day food frequency questionnaire, including all the main sources of caffeine. As previously reported, patients were divided into four groups according to the daily caffeine intake: <29.1 mg/day (group 1), 29.2-153.7 mg/day (group 2), 153.8-376.5 mg/day (group 3) and >376.6 mg/day (group 4). At the end of questionnaire filling, blood samples were collected from each patient to assess cytokine levels. These were assessed by using a panel by Bio-Plex assays to measure the levels of IL-6, IL-10, IL-17, IL-27, IFNγ, IFNα and BLyS. RESULTS: We enrolled 89 consecutive SLE patients. We observed a negative correlation between caffeine consumption and disease activity, measured with SLEDAI-2K. A significantly higher prevalence of lupus nephritis, neuropsychiatric involvement, haematological manifestations, hypocomplementaemia and anti-dsDNA positivity was observed in patients with a low intake of caffeine. Furthermore, patients with a low intake of caffeine were more frequently treated with glucocorticoids. Regarding cytokine analysis, a negative correlation between daily caffeine consumption and serum level of IFNγ was found (p = 0.03, r = -0.2); furthermore, patients with a high intake of caffeine showed lower serum levels of IFNα (p = 0.02), IL-17 (p = 0.01) and IL-6 (p = 0.003). CONCLUSIONS: In this report we demonstrated the impact of caffeine on SLE disease activity status, as confirmed by the inverse correlation between its intake and both SLEDAI-2K values and cytokine levels. Moreover, patients with a low caffeine consumption seem to have a more severe disease phenotype.

Anti-Yo Antibodies in Children With ADHD: First Results About Serum Cytokines.

Objective: We investigated whether ADHD children who are positive to Purkinje cell antibodies display pro-inflammatory activity associated with high cytokine serum levels. Method: Fifty-eight ADHD outpatients were compared with 36 healthy, age- and sex-matched children. Forty-five of the ADHD children were positive to anti-Yo antibodies, whereas 34 of the control children were negative. Interleukin 4 (IL-4), IL-6, IL-10, IL-17, tumor necrosis factor alpha (TNFα), and interferon gamma (IFNγ) cytokine serum levels were tested in ADHD children who were positive to anti-Yo antibodies and in the control children who were negative. Results: Anti-Yo antibodies were present to a greater extent in the ADHD group: 77.58% versus 22.42%. Significant differences emerged between the two groups in IL-6 and IL-10, with higher cytokine levels being detected in ADHD children than in controls. Conclusion: Immune processes in ADHD are likely to be associated with mediators of inflammation, such as cytokines. These results contribute to our understanding of action of neural antibodies and cytokines in ADHD.

Staphylococcus aureus Nasal Carriage and Autoimmune Diseases: From Pathogenic Mechanisms to Disease Susceptibility and Phenotype.

The role of infective agents in autoimmune diseases (ADs) development has been historically investigated, but in the last years has been strongly reconsidered due to the interest in the link between the microbiome and ADs. Together with the gut, the skin microbiome is characterized by the presence of several microorganisms, potentially influencing innate and adaptive immune response. S. aureus is one of the most important components of the skin microbiome that can colonize anterior nares without clinical manifestations. Data from the literature demonstrates a significantly higher prevalence of nasal colonization in ADs patients in comparison with healthy subjects, suggesting a possible role in terms of disease development and phenotypes. Thus, in the present narrative review we focused on the mechanisms by which S. aureus could influence the immune response and on its relationship with ADs, in particular granulomatosis with polyangiitis, rheumatoid arthritis, and systemic lupus erythematosus.

Musculoskeletal ultrasound in monitoring response to apremilast in psoriatic arthritis patients: results from a longitudinal study.

INTRODUCTION/OBJECTIVE: Apremilast, PDE4 competitive inhibitor, has been recently introduced in the treatment of adult psoriatic arthritis (PsA) patients, but only preliminary data are available on imaging evaluation. Thus, we evaluated the response to apremilast in PsA patients by ultrasonographic (US) assessment. METHODS: Thirty-four patients (M/F 7/27; median age 61 years, IQR 15; median disease duration 10 years, IQR 13) treated for polyarticular involvement were longitudinally evaluated. All the patients were assessed at baseline (T0), and after 6 (T1), 12 (T2), and 24 weeks (T3) by DAS28, CDAI, SDAI, and DAPSA. At the same time-points, US assessment was performed in 22 sites (wrists, MCPs, PIPs): synovial effusion/hypertrophy and power Doppler were scored with a semi-quantitative scale (0-3). A total score, corresponding to patient's inflammatory status, was obtained by their sum (0-198). We assessed also the presence of tenosynovitis of flexor tendons of hands' fingers bilaterally, registering the number of involved tendons (US-tenosynovitis score 0-10). RESULTS: We found a significant reduction in the US inflammatory score values after 6 weeks (T0, median 15 (IQR 11.2); T1, 6 (10.0); P = 0.0002), confirmed at T2 (4.0 (4.0), P = 0.0002) and T3 (4.0 (6.0); P = 0.0003). Finally, US-detected tenosynovitis was observed in 44.1% of patients: a significant improvement in tenosynovitis score was identified at 6 weeks (T0, median 4 (IQR 4); T1, 1 (2); P < 0.0001) and maintained at T2 (0 (IQR 1); P < 0.0001) and T3 ((IQR 1.25); P < 0.0001). CONCLUSIONS: Apremilast is able to induce an early and sustained improvement of ultrasonographic inflammatory status at articular and peri-articular level. Key points •Apremilast induces a significant, early, and sustained improvement of inflammatory joint status in psoriatic arthritis patients. •Ultrasonographic assessment is able to monitor articular and peri-articular response to apremilast.

Correction: Biomarkers of erosive arthritis in systemic lupus erythematosus: Application of machine learning models.

[This corrects the article DOI: 10.1371/journal.pone.0207926.].

Biomarkers of erosive arthritis in systemic lupus erythematosus: Application of machine learning models.

OBJECTIVE: Limited evidences are available on biomarkers to recognize Systemic Lupus erythematosus (SLE) patients at risk to develop erosive arthritis. Anti-citrullinated peptide antibodies (ACPA) have been widely investigated and identified in up to 50% of X-ray detected erosive arthritis; conversely, few studies evaluated anti-carbamylated proteins antibodies (anti-CarP). Here, we considered the application of machine learning models to identify relevant factors in the development of ultrasonography (US)-detected erosive damage in a large cohort of SLE patients with joint involvement. METHODS: We enrolled consecutive SLE patients with arthritis/arthralgia. All patients underwent joint (DAS28, STR) and laboratory assessment (detection of ACPA, anti-CarP, Rheumatoid Factor, SLE-related antibodies). The bone surfaces of metacarpophalangeal and proximal interphalangeal joints were assessed by US: the presence of erosions was registered with a dichotomous value (0/1), obtaining a total score (0-20). Concerning machine learning techniques, we applied and compared Logistic Regression and Decision Trees in conjunction with the feature selection Forward Wrapper method. RESULTS: We enrolled 120 SLE patients [M/F 8/112, median age 47.0 years (IQR 15.0); median disease duration 120.0 months (IQR 156.0)], 73.3% of them referring at least one episode of arthritis. Erosive damage was identified in 25.8% of patients (mean±SD 0.7±1.6), all of them with clinically evident arthritis. We applied Logistic Regression in conjunction with the Forward Wrapper method, obtaining an AUC value of 0.806±0.02. As a result of the learning procedure, we evaluated the relevance of the different factors: this value was higher than 35% for ACPA and anti-CarP. CONCLUSION: The application of Machine Learning Models allowed to identify factors associated with US-detected erosive bone damage in a large SLE cohort and their relevance in determining this phenotype. Although the scope of this study is limited by the small sample size and its cross-sectional nature, the results suggest the relevance of ACPA and anti-CarP antibodies in the development of erosive damage as also pointed out in other studies.

Anti-carbamylated protein antibodies as a new biomarker of erosive joint damage in systemic lupus erythematosus.

BACKGROUND: The application of more sensitive imaging techniques, such as ultrasonography (US), changed the concept of non-erosive arthritis in systemic lupus erythematosus (SLE), underlining the need for biomarkers to identify patients developing the erosive phenotype. Anti-citrullinated peptide antibodies (ACPA), associated with erosions in inflammatory arthritis, have been identified in about 50% of patients with SLE with erosive arthritis. More recently, anti-carbamylated proteins antibodies (anti-CarP) have been associated with erosive damage in rheumatoid arthritis. We aimed to assess the association between anti-CarP and erosive damage in a large SLE cohort with joint involvement. METHODS: We evaluated 152 patients (male/female patients 11/141; median age 46 years, IQR 16; median disease duration 108 months, IQR 168). All patients underwent blood draw to detect rheumatoid factor (RF) and ACPA (commercial enzyme-linked immunosorbent assay (ELISA) kit), and anti-CarP ("home-made" ELISA, cutoff 340 aU/mL). The bone surfaces of the metacarpophalangeal and proximal interphalangeal joints were assessed by US: the presence of erosions was registered as a dichotomous value (0/1), obtaining a total score (0-20). RESULTS: The prevalence of anti-CarP was 28.3%, similar to RF (27.6%) and significantly higher than ACPA (11.2%, p = 0.003). Erosive arthritis was identified in 25.6% of patients: this phenotype was significantly associated with anti-CarP (p = 0.004). Significant correlation between anti-CarP titer and US erosive score was observed (r = 0.2, p = 0.01). CONCLUSIONS: Significant association was identified between anti-CarP and erosive damage in SLE-related arthritis, in terms of frequency and severity, suggesting that these antibodies can represent a biomarker of severity in patients with SLE with joint involvement.

Joint involvement in systemic lupus erythematosus: From pathogenesis to clinical assessment.

OBJECTIVE: In the present review, the different phenotypes, clinimetric and imaging tools able to assess joint involvement in patients affected by Systemic Lupus Erythematosus (SLE) have been described and summarized. Furthermore, the current knowledge about the pathogenic mechanism and the potential biomarkers of this feature is reported. METHODS: A literature search was done in PubMed, accessed via the National Library of Medicine PubMed interface (http://www.ncbi.nlm.nih.gov/pubmed). Firstly, PubMed was searched using the term "systemic lupus erythematosus" OR "lupus" in combination with (AND) "joint" OR "articular".Secondly, the same PubMed research was combined with other terms, such as "pathogenesis" OR "genetic" OR "antibodies" OR "biomarkers" OR "cytokines" OR "imaging" OR "ultrasonography" OR "magnetic resonance" OR "clinimetry". RESULTS: After a stringent selection, we evaluated in the present review 13 papers concerning clinical phenotypes of SLE joint involvement, 14 concerning clinimetric assessment, 20 concerning imaging, and finally, 28 concerning pathogenesis and biomarkers. Further relevant data were obtained from the reference lists of articles returned using these search terms and from authors own experience and knowledge of the literature. CONCLUSION: Despite the prevalence and severity of SLE joint involvement, more awareness and a deeper evaluation of the clinical heterogeneity of this manifestation are mandatory. Moreover, longitudinal studies are needed to assess the progression of this manifestation and to provide standard definitions and examination/recording protocols.

Jaccoud's arthropathy in systemic lupus erythematosus: clinical, laboratory and ultrasonographic features.

OBJECTIVES: Jaccoud's arthropathy (JA) is a deforming, non-erosive arthritis, occurring in 2-35% of systemic lupus erythematosus (SLE) patients. We aimed to evaluate JA patients in a wide monocentric SLE cohort in terms of clinical, serological and ultrasonographic features. METHODS: Consecutive SLE patients (ACR criteria 1997) were evaluated. The JA index was applied for patients with reducible deformities. Patients with a JA index ≥5 underwent physical examination, blood testing and ultrasound (US) assessment. Detection of anti-citrullinated protein antibodies (ACPA) and rheumatoid factor (RF) was performed. A single rheumatologist performed the US assessment of bilateral wrist and hands. RESULTS: Four hundred and eighty SLE patients were evaluated: 17 (3.5%) showed a JA index ≥5 (M:F 1:16; mean age±SD 50.7±11.1 years; mean disease duration±SD 247.8±116.2 months). Four patients (23.5%) showed ACPA positivity. Fifteen patients (88.2%) showed at least one US abnormality. Bone erosions were found in 10 patients (58.8%). ACPA+ve patients showed erosive damage more frequently in at least one joint compared with ACPA-ve (75% vs. 53.8%, p=0.002). CONCLUSIONS: JA should no longer be considered a non-erosive condition since bone damage can occur in more than half of patients. Moreover, the erosive damage seems to be associated with the presence of ACPA.

Prediction of chronic damage in systemic lupus erythematosus by using machine-learning models.

OBJECTIVE: The increased survival in Systemic Lupus Erythematosus (SLE) patients implies the development of chronic damage, occurring in up to 50% of cases. Its prevention is a major goal in the SLE management. We aimed at predicting chronic damage in a large monocentric SLE cohort by using neural networks. METHODS: We enrolled 413 SLE patients (M/F 30/383; mean age ± SD 46.3±11.9 years; mean disease duration ± SD 174.6 ± 112.1 months). Chronic damage was assessed by the SLICC/ACR Damage Index (SDI). We applied Recurrent Neural Networks (RNNs) as a machine-learning model to predict the risk of chronic damage. The clinical data sequences registered for each patient during the follow-up were used for building and testing the RNNs. RESULTS: At the first visit in the Lupus Clinic, 35.8% of patients had an SDI≥1. For the RNN model, two groups of patients were analyzed: patients with SDI = 0 at the baseline, developing damage during the follow-up (N = 38), and patients without damage (SDI = 0). We created a mathematical model with an AUC value of 0.77, able to predict damage development. A threshold value of 0.35 (sensitivity 0.74, specificity 0.76) seemed able to identify patients at risk to develop damage. CONCLUSION: We applied RNNs to identify a prediction model for SLE chronic damage. The use of the longitudinal data from the Sapienza Lupus Cohort, including laboratory and clinical items, resulted able to construct a mathematical model, potentially identifying patients at risk to develop damage.

HLA-DRB1 the notorious gene in the mosaic of autoimmunity.

The major histocompatibility complex system is the most polymorphic gene cluster of the mammal genome. In humans, this is a genomic locus known as the human leukocyte antigen (HLA) system. The HLA encodes mostly immune-associated proteins whose main effect is the presentation of antigens to the immune cells. Thus, it is clear that it is essential for to the proper function of the immune response against pathogens and strongly implicated in the development of autoimmune diseases. Nonetheless, there are hundreds of polymorphisms of HLA-DRB1 which have been associated with different autoimmune disorders as well as with immune response to infection and vaccines. It is possible that the interaction of specific HLA with pathogenic antigens is one of the keys favoring (or protecting) toward the development of an autoimmune disease. In the era of personalized medicine, it would be of great help to build a map of the genomic risk of each individual to evaluate the risk of developing an autoimmune condition.

Assessment of disease activity in Systemic Lupus Erythematosus: Lights and shadows.

The assessment of disease activity in patients affected by Systemic Lupus Erythematosus (SLE) represents an important issue, as recommended by the European League Against Rheumatism (EULAR). Two main types of disease activity measure have been proposed: the global score systems, providing an overall measure of activity, and the individual organ/system assessment scales, assessing disease activity in different organs. All the activity indices included both clinical and laboratory items, related to the disease manifestations. However, there is no gold standard to measure disease activity in patients affected by SLE. In this review, we will analyze the lights and shadows of the disease activity indices, by means of a critical approach. In particular, we will focus on SLE Disease Activity Index (SLEDAI) and British Isles Lupus Assessment Group (BILAG), the most frequently used in randomized controlled trials and observational studies. The evaluation of data from the literature underlined some limitations of these indices, making their application in clinical practice difficult and suggesting the possible use of specific tools in the different subset of SLE patients, in order to capture all the disease features.

Genetic Factors in Systemic Lupus Erythematosus: Contribution to Disease Phenotype.

Genetic factors exert an important role in determining Systemic Lupus Erythematosus (SLE) susceptibility, interplaying with environmental factors. Several genetic studies in various SLE populations have identified numerous susceptibility loci. From a clinical point of view, SLE is characterized by a great heterogeneity in terms of clinical and laboratory manifestations. As widely demonstrated, specific laboratory features are associated with clinical disease subset, with different severity degree. Similarly, in the last years, an association between specific phenotypes and genetic variants has been identified, allowing the possibility to elucidate different mechanisms and pathways accountable for disease manifestations. However, except for Lupus Nephritis (LN), no studies have been designed to identify the genetic variants associated with the development of different phenotypes. In this review, we will report data currently known about this specific association.