medRxiv - Rheumatology最新文献

{"title":"Mosaic loss of chromosome Y characterizes late-onset rheumatoid arthritis and contrasting associations of polygenic risk score based on age at onset.","authors":"Shunsuke Uchiyama, Yuki Ishikawa, Katsunori Ikari, Suguru Honda, Keiko Hikino, Eiichi Tanaka, Yoichiro Kamatani, Takahisa Gono, Giulio Genovese, Masataka Kuwana, Chikashi Terao","doi":"10.1101/2024.09.12.24313215","DOIUrl":"https://doi.org/10.1101/2024.09.12.24313215","url":null,"abstract":"Objectives: mosaic chromosomal alterations (mCAs) increase with age and are associated with age-related diseases. The association between mCAs and rheumatoid arthritis (RA), particularly late-onset rheumatoid arthritis (LORA), has not been explored.\u0000Methods: mCAs were detected in peripheral blood samples from two independent Japanese datasets (Set 1:2,107 RA cases and 86,998 controls; Set 2:2,359 RA cases and 86,998 controls). The associations between mCAs and RA were evaluated in each dataset using logistic regression models and meta-analysis. In each dataset, we evaluated the effect sizes of mosaic loss of Y (mLOY) and polygenic risk score (PRS) of RA in males and subsequently performed a meta-analysis. The interaction between mLOY and PRS was assessed. These models were applied separately to RA, LORA, and young-onset RA (YORA).\u0000Results: mLOY increased significantly in LORA (OR=1.43, P=0.0070). We observed a negative association between mLOY and YORA (OR=0.66, P=0.0034). On the other hand, we found consistently negative associations of autosomal mCAs or mosaic loss of X (mLOX) with RA, LORA, and YORA. The effect sizes of PRS were lower for LORA than for YORA. mLOY with a high cell fraction strengthened the association between PRS and LORA (P=0.0036), whereas the association with YORA was independent of mLOY.\u0000Conclusion: LORA was characterised by the presence of a high burden of mLOY. The observed interaction between mLOY and PRS in LORA, but not in YORA, supports different gene-environment interactions between the subsets. These data suggest that distinct pathophysiological mechanisms underlie the development of LORA and YORA.","PeriodicalId":501212,"journal":{"name":"medRxiv - Rheumatology","volume":"20 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142251333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Use of Metagenomic Microbial Plasma Cell-Free DNA Next-Generation Sequencing Assay in Outpatient Rheumatology Practice","authors":"Rachel Jenkins, Matthew Samec, Courtney Arment, Kenneth J Warrington, John M Davis, Matthew J Koster","doi":"10.1101/2024.09.09.24313356","DOIUrl":"https://doi.org/10.1101/2024.09.09.24313356","url":null,"abstract":"Objectives\u0000To assess the utility of a metagenomic microbial plasma cell-free DNA next-generation sequencing assay (Karius TestTM; KT) in the evaluation of patients in an outpatient rheumatology practice. Methods\u0000All patients with a KT ordered and obtained by a rheumatology provider in the outpatient setting from 1 January 2020 through 31 December 2022 were retrospectively identified. Demographic, clinical, laboratory, radiologic, histopathology, and microbial studies were abstracted. Indication for KT testing was categorized. KT results were defined based on positive result and clinical relevance regarding the symptoms under investigation at the time of the rheumatologic investigation. Review of cases three months after KT was undertaken to determine clinical outcome. Results 150 patients with a KT were included (53% female, mean age 52 years). The reason for KT was evaluation of atypical presentation of rheumatic disease (80%), assessing flare versus infection in patient on immunosuppression (16.7%), and fever of unknown origin (3.3%). 24 (16%) KTs were positive, 6 of which were considered clinically relevant and altered the final diagnosis and treatment. Of the 126 negative KTs, 5 (4%) were found to have a clinically relevant infection by conventional testing methodologies. Conclusions\u0000In this large retrospective cohort study, the most frequent reason for KT utilization was an atypical presentation of rheumatic disease. 25% of positive KTs altered the final diagnosis and treatment, whereas a false-negative rate of 4% was observed. KT has utility in the outpatient rheumatology assessment. Further delineation of which patients are best suited for KT testing remains to be defined.","PeriodicalId":501212,"journal":{"name":"medRxiv - Rheumatology","volume":"38 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142211274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Proteomic profiling of the large vessel vasculitis spectrum identifies shared signatures of innate immune activation and stromal remodelling","authors":"Robert T Maughan, Erin MacDonald-Dunlop, Lubna Haroon-Rashid, Louise Sorensen, Natalie Chaddock, Shauna Masters, Andrew Porter, Marta Peverelli, Charis Pericleous, Andrew Hutchings, James Robinson, Taryn Youngstein, Raashid Luqmani, Justin C. Mason, Ann W Morgan, James E Peters","doi":"10.1101/2024.09.06.24313218","DOIUrl":"https://doi.org/10.1101/2024.09.06.24313218","url":null,"abstract":"Takayasu arteritis (TAK) and giant cell arteritis (GCA) are the primary forms of large vessel vasculitis (LVV) and can result in serious cardiovascular morbidity. Improved understanding of the molecular basis of these diseases is required to develop novel biomarkers and targeted treatments. Moreover, it is unclear whether shared or distinct pathogenic processes underpin the LVV spectrum. To address this, we performed plasma proteomic profiling, quantifying 184 plasma proteins using Olink immunoassays in two independent cohorts totalling 405 individuals. In Cohort 1, comparison of patients with TAK (N=96) and large vessel-GCA (LV-GCA) (N=35) versus healthy controls (HCs) (N=35) revealed 52 and 72 significant differentially abundant proteins, respectively. Correlation with disease activity status identified novel TAK and LV-GCA disease activity markers. Cohort 2 consisted of patients presenting acutely with possible cranial GCA (C-GCA); C-GCA was subsequently confirmed (n=150) or excluded (n=89). 31 proteins were associated with C-GCA. Analyses stratified by temporal artery biopsy results revealed enrichment of the proteomic signal in biopsy-proven GCA, suggesting the presence of distinct endotypes within C-GCA. Cross-disease comparison revealed that active TAK, LV-GCA and biopsy-proven C-GCA had highly similar plasma proteomic profiles. Twenty-six proteomic associations were shared across all three groups including IL6, monocyte/macrophage related proteins (CCL5, CCL7, CSF1), tissue remodelling proteins (VEGFA, TIMP1, TNC) and proteins not previously linked to LVV (TNFSF14, IL7R). We also observed disease-specific associations including increased CXCL9 in LV-GCA and C-GCA but not in TAK and decreases in the extracellular matrix protein COMP in TAK but not in LV-GCA or C-GCA. Evaluation of publicly available transcriptomic data from LV-GCA aortic tissue revealed that 47 of the 112 proteins significantly altered in ≥1 LVV type had significantly altered mRNA expression in LVV aortic tissue. Similarities in LVV proteomic profiles suggest shared pathobiology involving innate immunity, particularly monocyte/macrophages, lymphocyte homeostasis and tissue remodelling processes. Our results highlight a signature of immune-stromal cross talk in LVV and identify potential novel therapeutic targets in this axis (e.g. TNFSF14). The correspondence of plasma signatures to tissue phenotype highlights the potential for non-invasive monitoring of arterial inflammation and injury.","PeriodicalId":501212,"journal":{"name":"medRxiv - Rheumatology","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142211273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pre-trained convolutional neural network with transfer learning by artificial illustrated images classify power Doppler ultrasound images of rheumatoid arthritis joints","authors":"Jun Fukae, Yoshiharu Amasaki, Yuichiro Fujieda, Yuki Sone, Ken Katagishi, Tatsunori Horie, Tamotsu Kamishima, Tatsuya Atsumi","doi":"10.1101/2024.08.30.24312848","DOIUrl":"https://doi.org/10.1101/2024.08.30.24312848","url":null,"abstract":"This research aimed to study the classification performance of a pre-trained convolutional neural network (CNN) with transfer learning by artificial images of the joint ultrasonography in rheumatoid arthritis (RA). We focused on abnormal synovial vascularity and created 870 artificial ultrasound joint images based on the European League Against Rheumatism/Outcome Measure in Rheumatology scoring system. One CNN, the Visual Geometry Group (VGG)-16 was trained with transfer learning using the 870 artificial images for initial training and the original plus five additional images for second training. Actual joint ultrasound images obtained from patients with RA were used for testing our models. We obtained 156 actual ultrasound joint images from 74 patients with RA. Our initial model showed moderate classification performance, but grade 1 was especially low (area under curve (AUC) 0.59). In our second model, grade 1 showed improvement (AUC 0.73). We concluded that artificial images were useful for training VGG-16. Our novel approach of using artificial images as an alternative to actual images for training CNN has the potential to be applied in medical imaging fields that face difficulties in collecting real clinical images.","PeriodicalId":501212,"journal":{"name":"medRxiv - Rheumatology","volume":"185 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142226642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Associations between exposure to OPEs and rheumatoid arthritis risk among adults in NHANES, 2011-2018","authors":"Sneha Singh, Elsa Pirouz, Amir Shahmoradi","doi":"10.1101/2024.08.30.24312872","DOIUrl":"https://doi.org/10.1101/2024.08.30.24312872","url":null,"abstract":"Rheumatoid arthritis (RA) has an intricate etiology that includes environmental factors as well as genetics. Organophosphate esters (OPEs) are frequently used as chemical additives in many personal care products and household items. However, there has been limited research on their potential effects on rheumatoid arthritis (RA). The specific associations between OPEs and RA remain largely unexplored. This study investigates any potential associations between adult rheumatoid arthritis risk and exposure to OPEs. We investigated data from the National Health and Nutrition Examination Survey (NHANES) 2011–2018 among participants over 20 years old. In two models, multivariable logistic regression was utilized to investigate the relationship between exposure to OPEs and RA. Furthermore, subgroup analyses stratified by age, gender, and dose exposure response were evaluated. Generalized additive models and smooth curve fits were used to characterize the nonlinear relationship between RA and OPEs. In conclusion, 5490 individuals (RA: 319, Non-RA: 5171) were analyzed. Higher quantiles (Q4) of DPHP and DBUP showed a higher prevalence of RA than the lowest quantiles. Our findings show that adult RA prevalence is higher in those who have been exposed to OPEs (DPHP, DBUP). Interestingly, these correlations seem to be stronger among women, the elderly, those with higher BMIs, and those who have diabetes. The dose-response curve for DPHP and DBUP demonstrated an upward-sloping trend. In contrast, BCEP and BCPP showed a U-shaped relationship and an inverted U-shaped relationship with the probability of RA.BDCPP demonstrated a complex relationship with a peak at lower concentrations followed by a decrease. Finally, our study also concludes that exposure to OPEs plays a crucial role in the pathogenesis of RA.","PeriodicalId":501212,"journal":{"name":"medRxiv - Rheumatology","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142211277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Genetic analysis of asymptomatic antinuclear antibody production","authors":"Mehmet Hocaoglu, Desire Casares-Marfil, Amr H Sawalha","doi":"10.1101/2024.08.29.24312782","DOIUrl":"https://doi.org/10.1101/2024.08.29.24312782","url":null,"abstract":"Objective: Antinuclear antibodies (ANA) are detected in up to 14% of the population and the majority of individuals with ANA are asymptomatic. The literature on the genetic contribution to asymptomatic ANA positivity in the population is limited. In this study, we aimed to perform a multi-ancestry genome-wide association study (GWAS) of asymptomatic ANA positivity.\u0000Methods: Asymptomatic ANA positive and negative individuals from the All of Us Research Program were included in this study, selecting those with an ANA test by immunofluorescence and no evidence of autoimmune disease. Imputation was performed and a multi-ancestry meta-analysis including approximately 6 million single-nucleotide polymorphisms (SNPs) was conducted. Genome-wide SNP based heritability was estimated using the GCTA software. A cumulative genetic risk score for lupus was constructed using previously reported genome-wide significant loci.\u0000Results: 1,955 asymptomatic ANA positive and 3,634 asymptomatic ANA negative individuals were included across three genetic ancestries. The multi-ancestry meta-analysis revealed SNPs with a suggestive association (p-value < 1X10-5) across 8 different loci, but no genome-wide significant loci were identified. A gene variant upstream of HLA-DQB1 (rs17211748, P = 1.4X10-6, OR = 0.82, 95% CI 0.76-0.89) showed the most significant association. The heritability of asymptomatic ANA positivity was estimated to be 24.9%. Asymptomatic ANA positive individuals did not exhibit increased cumulative genetic risk for lupus compared to ANA negative individuals.\u0000Conclusion: ANA production is not associated with significant genetic risk and is primarily determined by non-genetic, likely environmental, factors.","PeriodicalId":501212,"journal":{"name":"medRxiv - Rheumatology","volume":"29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142226643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Synovial Transcriptome Profiling for Predicting Biological Treatment Response in Rheumatoid Arthritis: A Feasibility study","authors":"P.N. d’Ailly, O.J.M. Schäffers, C. Deugd, M.A. Versnel, H.J.G. van de Werken, E.M.J. Bindels, S.W. Tas, J. Gribnau, N.W.L. Schep, R.J. Bisoendial","doi":"10.1101/2024.08.28.24312608","DOIUrl":"https://doi.org/10.1101/2024.08.28.24312608","url":null,"abstract":"<strong>Introduction</strong> Disease-Modifying Anti-Rheumatic Drug (DMARD) treatment fails to achieve clinical remission in a substantial proportion of patients with rheumatoid arthritis (RA). Patient-derived synovial tissue (ST)-signatures, thought to determine this heterogeneity of treatment responses, can be studied by single-cell RNA sequencing (scRNA-seq).","PeriodicalId":501212,"journal":{"name":"medRxiv - Rheumatology","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142211278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Trends and Influences in women authorship of randomized controlled trials in rheumatology: a comprehensive analysis of all published RCTs from 2009 to 2023","authors":"Kim Lauper, Diana Buitrago-Garcia, Delphine Sophie Courvoisier, Michele Iudici, Denis Mongin","doi":"10.1101/2024.08.26.24312469","DOIUrl":"https://doi.org/10.1101/2024.08.26.24312469","url":null,"abstract":"Objectives: This study aims to examine the evolution and influencing factors of women's authorship in randomized controlled trials (RCTs) published in rheumatology.\u0000Methods: This study included all rheumatology RCTs published from 2009 to 2023. The gender of authors was determined using forenames and countries of affiliation via the gender API service. The percentage of women in RCT publications and its association with potential factors was assessed using generalized estimating equations, considering women gender as the main binary outcome and the RCT's continent, international collaboration status, industrial funding, intervention type, sample size, journal adherence to ICMJE recommendations, impact factor, publication year, author's non-academic affiliation, and author position as covariates. Results: Among the 1,092 RCTs authored by 10,794 persons, women accounted for 34.1% of authors. Woman authorship was more frequent in African-based RCTs compared to North America, when the author had a non-academic affiliation and when the last author was a woman (1.83 [1.46, 2.29], +6.1 percentage points - pp). Woman authorship was less frequent in Asian and European-based RCTs, industry-funded RCTs (OR 0.64 [0.56-0.73]; -10.3pp). Women were less often in the last (0.63 [0.54-0.74]; -10.2 pp) and second to last author position (0.73 [0.62-0.85]; -7.3pp). There were no difference looking at international status or year of publication. Conclusion: The overall presence of women authors was 34.1%. The stagnant year-over-year representation of women in RCTs, and the lower likelihood of a woman having a position as senior author, underscores the need for more effective strategies to bridge the gender gap. RCTs with a woman last author were more likely to have a woman first author, suggesting a potential role-model effect.","PeriodicalId":501212,"journal":{"name":"medRxiv - Rheumatology","volume":"11 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142226804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of Risk Factors and the Establishment of a Predictive Model for Thrombosis in Patients with immune thrombocytopenia","authors":"Hui Liang, Lingxue Duan, Manyu Long, Songyuan Tie, Changyan Sun, Sha Ma, Jing Wang, Shuya Wang","doi":"10.1101/2024.08.21.24312388","DOIUrl":"https://doi.org/10.1101/2024.08.21.24312388","url":null,"abstract":"Objectives To explore the risk factors for thrombi occurring in patients with immune thrombocytopenia (ITP) and establish a risk prediction model to better predict the risk of thrombosis in patients with ITP. Methods We retrospectively analyzed 350 ITP patients who had been hospitalized in The First People's Hospital of Yunnan Province between January 2020 and June 2024. For all patients, we recorded demographic characteristics and clinical data, analyzed the risk factors for thrombosis in ITP patients and then developed a risk prediction model. Results Stepwise logistic regression analysis indicated that a high complement D- dimer level, a low PLT and a high Padua score were independent risk factors for thrombosis in ITP patients. According to multivariate analysis, a predictive model for thrombus risk was successfully established; the area under the ROC curve(AUC) was 0.673 (95% CI: 0.615-0.730) and the maximum Youden index, sensitivity and specificity were 0.272, 47.0% and 80.2%, respectively. Conclusion A high complement D-dimer level, low PLT level, and a high Padua score were shown to be independent risk factors for thrombosis in ITP patients. We developed a risk prediction model based on these three risk factors that could predict the risk of thrombosis in ITP patients to some extent.","PeriodicalId":501212,"journal":{"name":"medRxiv - Rheumatology","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142211275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Incorporating computer vision on smart phone photographs into screening for inflammatory arthritis: results from an Indian patient cohort","authors":"Sanat Phatak, Ruchil Saptarshi, Vanshaj Sharma, Rohan Shah, Abhishek Zanwar, Pratiksha Hegde, Somashree Chakraborty, Pranay Goel","doi":"10.1101/2024.08.19.24312283","DOIUrl":"https://doi.org/10.1101/2024.08.19.24312283","url":null,"abstract":"Background: Convolutional neural networks (CNNs) have been used to classify medical images; few studies use smartphone photographs that are scalable at point of care. We previously showed proof of principle that CNNs could detect inflammatory arthritis in three hand joints. We now studied a screening CNN to differentiate from controls. Methods: We studied consecutive patients with early inflammatory arthritis and healthy controls, all examined by a rheumatologist (15% by two). Standardized photographs of the hands were taken using a studio box, anonymized, and cropped around joints. We fine-tuned pre-trained CNN models on our dataset (80% training; 20% test set). We used an Inception-ResNet-v2 backbone CNN modified for two class outputs (Patient vs Control) on uncropped photos. Inception-ResNet-v2 CNNs were trained on cropped photos of Middle finger Proximal Interphalangeal (MFPIP), Index finger PIP (IFPIP) and wrist. We report representative values of accuracy, sensitivity, specificity. Results: We studied 800 hands from 200 controls (mean age 37.8 years) and 200 patients (mean age 49.6 years; 134 with rheumatoid arthritis amongst other diagnoses). Two rheumatologists had a concordance of 0.89 in 404 joints. The wrist was commonly involved (173/400) followed by the MFPIP (134) and IFPIP (128). The screening CNN achieved excellent accuracy (98%), sensitivity (98%) and specificity (98%) in predicting a patient compared to controls. Joint-specific CNN accuracy, sensitivity and specificity were highest for the wrist (80% , 88% , 72%) followed by the IFPIP (79%, 89% ,73%) and MFPIP (76%, 91%, 70%). Conclusion\u0000Computer vision without feature engineering can distinguish between patients and controls based on smartphone photographs with good accuracy, showing promise as a screening tool prior to joint-specific CNNs. Future research includes validating findings in diverse populations, refining models to improve specificity in joints and integrating this technology into clinical workflows.","PeriodicalId":501212,"journal":{"name":"medRxiv - Rheumatology","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142226805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}