Rheumatology Advances in Practice最新文献

{"title":"Disease burden in inflammatory arthritis: an unsupervised machine learning approach of the COVAD-2 e-survey dataset.","authors":"Vincenzo Venerito, Sergio Del Vescovo, Sergio Prieto-González, Marco Fornaro, Lorenzo Cavagna, Florenzo Iannone, Masataka Kuwana, Vishwesh Agarwal, Jessica Day, Mrudula Joshi, Sreoshy Saha, Kshitij Jagtap, Wanruchada Katchamart, Phonpen Akarawatcharangura Goo, Binit Vaidya, Tsvetelina Velikova, Parikshit Sen, Samuel Katsuyuki Shinjo, Ai Lyn Tan, Nelly Ziade, Marcin Milchert, Abraham Edgar Gracia-Ramos, Carlo V Caballero-Uribe, Hector Chinoy, Latika Gupta, Vikas Agarwal","doi":"10.1093/rap/rkaf031","DOIUrl":"10.1093/rap/rkaf031","url":null,"abstract":"<p><strong>Objectives: </strong>To comprehensively compare the disease burden among patients with RA, PsA and AS using Patient-Reported Outcome Measurement Information System (PROMIS) scores and to identify distinct patient clusters based on comorbidity profiles and PROMIS outcomes.</p><p><strong>Methods: </strong>Data from the global COVID-19 Vaccination in Autoimmune Diseases (COVAD) 2 e-survey were analysed. Patients with RA, PsA or AS undergoing treatment with DMARDs were included. PROMIS scores (global physical health, global mental health, fatigue 4a and physical function short form 10a), comorbidities and other variables were compared among the three groups, stratified by disease activity status. Unsupervised hierarchical clustering with eXtreme Gradient Boosting feature importance analysis was performed to identify patient subgroups based on comorbidity profiles and PROMIS outcomes.</p><p><strong>Results: </strong>The study included 2561 patients (1907 RA, 311 PsA, 343 AS). After adjusting for demographic factors, no significant differences in PROMIS scores were observed among the three groups, regardless of disease activity status. Clustering analysis identified four distinct patient groups: low burden, comorbid PsA/AS, low burden with depression and high-burden RA. Feature importance analysis revealed PROMIS global physical health as the strongest determinant of cluster assignment, followed by depression and diagnosis. The comorbid PsA/AS and high-burden RA clusters showed a higher prevalence of comorbidities (56.47% and 69.7%, respectively) and depression (41.18% and 41.67%, respectively), along with poorer PROMIS outcomes.</p><p><strong>Conclusion: </strong>Disease burden in inflammatory arthritis is determined by a complex interplay of factors, with physical health status and depression playing crucial roles. The identification of distinct patient clusters suggests the need for a paradigm shift towards more integrated care approaches that equally emphasize physical and mental health, regardless of the underlying diagnosis.</p>","PeriodicalId":21350,"journal":{"name":"Rheumatology Advances in Practice","volume":"9 2","pages":"rkaf031"},"PeriodicalIF":2.1,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12007600/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144036755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ethical challenges and regulatory pathways for artificial intelligence in rheumatology.","authors":"Vincenzo Venerito, Latika Gupta, Saverio Mileto, Florenzo Iannone, Emre Bilgin","doi":"10.1093/rap/rkaf035","DOIUrl":"https://doi.org/10.1093/rap/rkaf035","url":null,"abstract":"","PeriodicalId":21350,"journal":{"name":"Rheumatology Advances in Practice","volume":"9 2","pages":"rkaf035"},"PeriodicalIF":2.1,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12007595/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143996348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting EQ-5D full health state in systemic lupus erythematosus using machine learning algorithms.","authors":"João Botto, Nursen Cetrez, Dionysis Nikolopoulos, Malin Regardt, Emelie Heintz, Julius Lindblom, Ioannis Parodis","doi":"10.1093/rap/rkaf032","DOIUrl":"10.1093/rap/rkaf032","url":null,"abstract":"<p><strong>Objectives: </strong>To determine factors associated with reports of EuroQol 5-Dimensions (EQ-5D) full health state (FHS) before and after a trial intervention in patients with SLE, resorting to machine learning algorithms.</p><p><strong>Methods: </strong>We conducted a post hoc analysis of two phase 3 clinical trials of belimumab (BLISS-52, BLISS-76). Demographic, laboratory and clinical features were retrieved and the Monte Carlo Feature Selection algorithm was employed, then further refined upon consideration of collinearity and clinical relevance. We used support vector machine with radial basis function kernel (SVMRadial), least absolute shrinkage and selection operator (LASSO), neural network (NNet) and logistic regression (LR) to capture both linear and non-linear relationships while ensuring interpretability and robustness.</p><p><strong>Results: </strong>Among 1642 SLE patients, 12.9% reported FHS at baseline and 23.1% at week 52. Selected features were age, sex, Asian ancestry, baseline cSLEDAI-2K, SELENA-SLEDAI PGA, and urine protein:creatinine ratio (UPCR) and baseline EQ-5D 3-Levels (EQ-5D-3L) index score (week 52 models only). The models predicting FHS demonstrated comparable performance at baseline and week 52. A maximum area under the curve of 0.73 was seen for the baseline LASSO and LR models and a maximum of 0.77 for the week 52 LASSO and NNet models. Negative predictive values were high for all models (0.88-0.94). Calibration showed marginal improvement in week 52 models.</p><p><strong>Conclusion: </strong>Machine learning identified older age, female sex, non-Asian ancestry, high disease activity and low UPCR to be associated with a lack of FHS experience in SLE patients at baseline and week 52. High baseline EQ-5D-3L index scores constituted the strongest predictor of FHS at week 52.</p><p><strong>Trial registration: </strong>The BLISS-52 and BLISS-76 trials are registered at www.clinicaltrials.gov (NCT00424476 and NCT00410384, respectively).</p>","PeriodicalId":21350,"journal":{"name":"Rheumatology Advances in Practice","volume":"9 2","pages":"rkaf032"},"PeriodicalIF":2.1,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12007597/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144029725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning <i>vs</i> human experts: sacroiliitis analysis from the RAPID-axSpA and C-OPTIMISE phase 3 axSpA trials.","authors":"Fabian Proft, Janis L Vahldiek, Joeri Nicolaes, Rachel Tham, Bengt Hoepken, Baran Ufuktepe, Denis Poddubnyy, Keno K Bressem","doi":"10.1093/rap/rkae118","DOIUrl":"https://doi.org/10.1093/rap/rkae118","url":null,"abstract":"<p><strong>Objective: </strong>Diagnosis of axial spondyloarthritis (axSpA) is primarily established through the identification of the presence or absence of radiographic sacroiliitis. However, the reliability of conventional radiographs (X-rays) is undermined by significant interreader variability. A machine learning tool could reduce diagnosis time, thereby minimising interreader variability. The present study aimed to evaluate the performance of a deep learning model for detecting radiographic sacroiliitis in axSpA patients from the RAPID-axSpA (NCT01087762) and C-OPTIMISE (NCT02505542) trials.</p><p><strong>Methods: </strong>Radiographs from the RAPID-axSpA and C-OPTIMISE cohorts were retrospectively used. The deep learning model was previously trained by using a transfer learning approach on non-medical data. The model's agreement with expert readers was tested on baseline X-rays using central reader data. Sensitivity, specificity, Cohen's κ, positive and negative predictive values and the area under the receiver operating characteristics curve were calculated.</p><p><strong>Results: </strong>The model's performance was evaluated in the RAPID-axSpA (<i>n</i> = 277) and C-OPTIMISE (<i>n</i> = 739) cohorts. In RAPID-axSpA, the model achieved 82% sensitivity, 81% specificity and a Cohen's κ of 0.61, closely matching central reader performance. In C-OPTIMISE, the model demonstrated 90% sensitivity, 56% specificity and a Cohen's κ of 0.48. The agreement between the model and central readers was 82% (RAPID-axSpA) and 75% (C-OPTIMISE).</p><p><strong>Conclusions: </strong>The tested deep learning model exhibited accurate radiographic sacroiliitis detection in axSpA patients from diverse clinical trials. The proposed deep learning model could expedite diagnosis, reduce healthcare resource usage and improve patient care pathways.</p>","PeriodicalId":21350,"journal":{"name":"Rheumatology Advances in Practice","volume":"9 2","pages":"rkae118"},"PeriodicalIF":2.1,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12007599/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144050999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Single-camera motion capture of finger joint mobility as a digital biomarker for disease activity in rheumatoid arthritis.","authors":"Vincenzo Venerito, Tobias Manigold, Marco Capodiferro, Deborah Markham, Marc Blanchard, Florenzo Iannone, Thomas Hügle","doi":"10.1093/rap/rkae143","DOIUrl":"https://doi.org/10.1093/rap/rkae143","url":null,"abstract":"<p><strong>Objective: </strong>To investigate the association between hand motion tracking features obtained through computer vision from smartphone cameras and disease activity in patients with RA.</p><p><strong>Methods: </strong>The PyPI package of MediaPipe (version 0.9.0.1) was used for key landmark detection. Finger joint angles were calculated in each frame using the normalized dot product of the vectors (equations). RA patients were instructed to perform a rapid repetition of five fist closures. Hand movements were captured using standard smartphone cameras. Kinetic features time to maximum flexion for MCP, PIP and DIP joints were correlated with RA disease activity and disability outcomes. Logistic regression was used to investigate associations of range of motion and kinetic features with 28-joint DAS (DAS28) low disease activity/remission.</p><p><strong>Results: </strong>Our model showed promising performance in predicting low disease activity/remission in RA patients. Internal validation using 5-fold cross-validation on the training dataset (<i>n</i> = 81) yielded a mean accuracy of 0.72 (s.d. 0.09), specificity of 0.65 (s.d. 0.17), recall of 0.86 (s.d. 0.05) and area under the receiver operating characteristics curve (AUROC) of 0.80 (s.d. 0.09). External validation on the test dataset (<i>n</i> = 19) demonstrated improved performance with an accuracy of 0.84, specificity of 0.75, recall of 0.91 and AUROC of 0.89. Greater PIP and DIP joint angle changes, along with faster time to maximal flexion, were associated with lower disease activity. Significant correlations were observed between kinetic metrics and standard clinical measures, including DAS28, swollen joint count, tender joint count and HAQ Disability Index.</p><p><strong>Conclusion: </strong>Single-camera motion capture of repeated fist closure may serve as an accessible digital biomarker for disease activity in RA.</p>","PeriodicalId":21350,"journal":{"name":"Rheumatology Advances in Practice","volume":"9 2","pages":"rkae143"},"PeriodicalIF":2.1,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12007596/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144043940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence in rheumatology: days of a future past.","authors":"Vincenzo Venerito","doi":"10.1093/rap/rkaf022","DOIUrl":"10.1093/rap/rkaf022","url":null,"abstract":"","PeriodicalId":21350,"journal":{"name":"Rheumatology Advances in Practice","volume":"9 2","pages":"rkaf022"},"PeriodicalIF":2.1,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12007593/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143995950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"External validation of the polymyalgia rheumatica impact scale: a prospective cohort study.","authors":"Lien Moreel, Michaël Doumen, Albrecht Betrains, Ellen De Langhe, Daniel Blockmans, Steven Vanderschueren","doi":"10.1093/rap/rkaf046","DOIUrl":"10.1093/rap/rkaf046","url":null,"abstract":"<p><strong>Objectives: </strong>To externally validate the PMR impact scale (PMR-IS).</p><p><strong>Methods: </strong>We conducted a prospective cohort study at the University Hospitals Leuven, Leuven, Belgium. Recently diagnosed PMR patients were included between July 2022 and December 2023 and followed until 1 year after diagnosis. All patients completed the PMR-IS, HAQ Disability Index, 36-item Short Form and a visual analogue scale for pain at every visit. Internal consistency, floor and ceiling effects, construct validity, responsiveness and discriminatory power for detecting relapse on the PMR-IS were assessed.</p><p><strong>Results: </strong>Fifty-five PMR patients (mean age 71 years, 47% female) were included, who had a total of 246 visits. Internal consistency, construct validity and responsiveness met the quality criteria for the symptoms, function and emotional and psychological well-being subdomains. The internal consistency of the glucocorticoid side effects subdomain was insufficient and only one of the three hypotheses for construct validity were met. The function and emotional and psychological well-being subdomains showed a floor effect, while no ceiling effect was observed. The symptoms, function and emotional and psychological well-being subdomains had a good discriminatory power for detecting relapse [area under the curve (AUC) 0.89, 0.86 and 0.72, respectively], but the PMR activity score performed better (AUC 0.94, <i>P</i> < 0.05 for all subdomains).</p><p><strong>Conclusion: </strong>This study validates the good measurement properties of the symptoms, function and emotional and psychological well-being subdomains of the PMR-IS. In contrast, the glucocorticoid side effects subdomain did not show adequate internal consistency and construct validity, necessitating further validation and possibly refinement of its items prior to application in clinical trials or daily practice.</p>","PeriodicalId":21350,"journal":{"name":"Rheumatology Advances in Practice","volume":"9 2","pages":"rkaf046"},"PeriodicalIF":2.1,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12080742/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144079861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Variation in blood test monitoring practices for patients treated with conventional and biologic DMARDs.","authors":"Joanne Ablewhite, Amy Fuller, Abdullah Almayahi, Abhishek Abhishek","doi":"10.1093/rap/rkaf044","DOIUrl":"https://doi.org/10.1093/rap/rkaf044","url":null,"abstract":"","PeriodicalId":21350,"journal":{"name":"Rheumatology Advances in Practice","volume":"9 2","pages":"rkaf044"},"PeriodicalIF":2.1,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12077759/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144079920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nailfold capillary abnormalities as useful clues in an atypical case suggestive of cancer-associated dermatomyositis sine dermatitis.","authors":"Hiroki Kohno, Namiho Irie, Ai Yamane, Tomoko Koura, Kenta Kaneyoshi, Takamichi Sugimoto, Yu Yamazaki, Tomohiro Sugimoto","doi":"10.1093/rap/rkaf043","DOIUrl":"10.1093/rap/rkaf043","url":null,"abstract":"","PeriodicalId":21350,"journal":{"name":"Rheumatology Advances in Practice","volume":"9 2","pages":"rkaf043"},"PeriodicalIF":2.1,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12098259/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144143482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A psychometric evaluation of the Musculoskeletal Health Questionnaire (MSK-HQ): validation and measurement invariance in inflammatory arthritis.","authors":"Nikita Arumalla, James B Galloway, Joanna Ledingham, Toby Garrood, Sam Norton","doi":"10.1093/rap/rkaf041","DOIUrl":"10.1093/rap/rkaf041","url":null,"abstract":"<p><strong>Objectives: </strong>The Musculoskeletal Health Questionnaire (MSK-HQ) is a patient reported outcome measure (PROM) co-produced for use across musculoskeletal diseases. This study analyses the validity, reliability, sensitivity to change and measurement invariance of the MSK-HQ in inflammatory arthritis (IA).</p><p><strong>Methods: </strong>A total of 5106 patients recruited to the National Early Inflammatory Arthritis Audit (NEIAA) between May 2018 and March 2020 with a diagnosis of IA were included. Patients completed PROMs at baseline and 3 and 12 months alongside clinic visits. Convergent validity was assessed in relation to the HAQ-II, Patient Health Questionnaire 4 (PHQ-4) and 28-item DAS (DAS28). Construct validity was assessed using confirmatory factor analysis (CFA). Hierarchical tests for configural, metric and scalar invariance determined measurement invariance in item CFAs.</p><p><strong>Results: </strong>The MSK-HQ total score correlated well with the HAQ-II (<i>r</i> = -0.79) and PHQ-4 (<i>r</i> = -0.66) and moderately with the DAS28 (<i>r</i> = -0.42). A unidimensional structure for the MSK-HQ was confirmed only when two items relating to illness perception were excluded. The MSK-HQ total score demonstrated good sensitivity to change. Reliability was high (α = 0.93). The minimum clinically important difference was 4 points across the IA subtypes. Significance was noted in tests of DIF for a few MSK-HQ items, but the level of bias was small.</p><p><strong>Conclusion: </strong>This study provides evidence for the validity and sensitivity to change of the MSK-HQ in patients with IA, with a change of >4 points likely to be clinically meaningful. The MSK-HQ has high convergent and construct validity and is sensitive to change, providing a valuable tool for clinical care and research studies.</p>","PeriodicalId":21350,"journal":{"name":"Rheumatology Advances in Practice","volume":"9 2","pages":"rkaf041"},"PeriodicalIF":2.1,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12064166/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144034676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}