|
Title |
Summary |
Authors |
|---|---|---|
|
The Application of Genetic Risk Scores in Rheumatic Diseases: A Perspective (2023) |
In this review, we provide an overview of the recent literature on Genetic Risk Scores (GRS) in rheumatic diseases. We describe six categories for which GRSs are used: (a) disease (outcome) prediction, (b) genetic commonalities between diseases, (c) disease differentiation, (d) interplay between genetics and environmental factors, (e) heritability and transferability, and (f) detecting causal relationships between traits. In our review of the literature, we identified current lacunas and opportunities for future work. |
Lotta Vaskimo |
|
Recommendation to implementation of remote patient monitoring in rheumatology: lessons learned and barriers to take (2023) |
Using the example of the Southmead rheumatology department, we address three types of barriers for the implementation of RPM: service, clinician and patients, with subsequent learning points that could be helpful for new teams planning to implement RPM. These address data governance, selecting high quality cost-effective solutions and ensuring compliance with data protection regulations. In addition, we describe five lacunas that could further improve RPM: establishing quality standards, creating a comprehensive database of available RPM tools, integrating data with electronic patient records, addressing reimbursement uncertainties and improving digital literacy among patients and healthcare professionals. |
Rachel Knevel |
|
Autoantibody Profiles in Patients with Musculoskeletal Complaints (2024) |
Timely and rapid stratification of musculoskeletal complaints is essential to ensure accurate care and to prevent irreversible negative outcomes for the patients. In this study autoantibody profiles of patients are studied as part of larger models that aim to improve the stratification of patients with musculoskeletal complaints. |
Lisa Christiansson |
| Dissecting early RA patient trajectories through time-independent disease state identification identifies distinct patterns dissected by inflammation in blood or joints (2024) 10.1136/annrheumdis-2024-eular.1512 |
This research examines how patients with rheumatoid arthritis (RA) experience different patterns in the progression of their disease. Understanding these varying trajectories and the factors influencing them is crucial for better disease management. Previous research identified smooth progression patterns of rapid, slow, or no change in disease activity scores (DAS28). However, real-life observations reveal more chaotic patterns, indicating that inadequate treatment might be a factor. The objective is to analyze these disease state trajectories over 1.5 years from the first outpatient clinic visit using pseudo-time graphs. | Nils Steinz |
| Employing machine learning to predict RA diagnosis from referral letters by the general practitioner (2024) 10.1136/annrheumdis-2024-eular.1728 |
The study focuses on improving the triaging process of newly referred patients at rheumatology outpatient clinics by using natural language processing (NLP) and machine learning. The goal is to automatically identify patients at high risk for having rheumatoid arthritis (RA) based on general practitioners' (GP) referral letters. By analyzing referral letters from Reumazorg ZWN between 2015 and 2022, the researchers developed a predictive model using eXtreme Gradient Boosting (XGB). They used the Shapley Additive Explanation (SHAP) to identify key words and their impact on the model's predictions. | Tjardo Maarseveen |
| EHR defined baseline RA-subsets characterised by localised joint involvement differentially associate with genetic risk and clinical outcomes beyond baseline (2024) 10.1136/annrheumdis-2024-eular.1924 |
The study investigates the heterogeneous nature of Rheumatoid Arthritis (RA) and aims to identify clinically relevant phenotypic subgroups in a DMARD-naive RA population using baseline clinical features. Researchers collected data from 1,387 RA patients, including lab information, demographics, and joint inflammation patterns. They employed a deep learning strategy to cluster patients into distinct subsets, validated with an independent set of 769 patients. The study also evaluated associations with methotrexate (MTX) response, one-year remission rates, and known RA genetic variants to assess the clinical and aetiological relevance of the identified subgroups. | Tjardo Maarseveen |
| Who participates in an online symptom checker? Characteristics, attrition and representativeness in the "Rheumatic?" study (2024) 10.1136/annrheumdis-2024-eular.2253 |
The study evaluates the online symptom checker "Rheumatic?" designed to provide risk assessments for rheumatic diagnoses in individuals with musculoskeletal complaints (MSCs). The primary aim is to assess attrition and selection bias by comparing participants who responded to follow-up surveys with those who did not, and comparing participants from various recruitment sources, including primary care, rheumatology clinics, and online platforms. The researchers used data containing baseline questionnaires and follow-up surveys, and compared the demographics of the participants with the expected target population to ensure representativity. |
Floor Zegers |
| Rheumatic Patients’ Self – Reported Symptoms in Free Written Text Using Natural Language Processing (2024) https://shorturl.at/sIlSJ |
This study examines the reliability of self-reported symptoms through the Rheumatic online symptom checker in predicting immune-mediated rheumatic diseases (imRD), osteoarthritis (OA), and fibromyalgia (FM). By analyzing free-text data from 5,628 respondents the researchers employed natural language processing and tested 8 machine learning models to optimize prediction accuracy. They evaluated both new and existing cases, identifying optimal probability cut-offs to maximize positive predictive value (PPV), specificity for FM and OA, and sensitivity and negative predictive value (NPV) for imRD. | Inés Pérez - Sancristóbal |
|
Impact of the digital health application ViViRA on spinal mobility, physical function, quality of life and pain perception in spondyloarthritides patients: a randomized controlled trial (2024) |
The study investigates the clinical effects of the digital health application (DHA) ViViRA compared to standard physiotherapy for patients with Spondyloarthritides (SpAs), focusing on pain, quality of life, and mobility. In a randomized controlled trial with 59 participants, the intervention group using ViViRA showed significant improvement in mobility and lower pain intensity after 12 weeks, while the control group experienced decreased mobility and higher pain levels. | Harriet Morf |
| Missing data in routinely collected electronic health records: an approach to characterize different levels of missing data (2024) ISCB2024Program_AbstractBook.pdf |
The study explores the challenge of missing data in electronic health records (EHRs) and proposes a method to characterize different levels of missing data. Researchers analyzed a subset of the ELAN primary care dataset, which includes 430,000 patients with musculoskeletal complaints from the Hague/Leiden region. Using Generalized Linear Mixed Models (GLMMs), they identified sources of missing data at various levels, such as missing measurements within visits, missing visits, and missing patients. They examined the impact of factors like the EHR information system, the decade of record, and the primary care provider's recording patterns. The goal is to improve the reliability of routinely collected EHRs for research purposes. | Georgy Gomon |
| Stratification of patients using advanced integrative modelling of data routinely acquired for diagnosing rheumatic complaints (SPIDeRR): A multicenter european consortium. (2024) 10.1136/annrheumdis-2024-eular.5262 |
The study highlights the importance of early disease stratification for musculoskeletal (MSK) symptoms to ensure timely and appropriate care. SPIDeRR aims to improve the diagnosis and treatment of MSK and rheumatic diseases by considering all factors influencing patients' symptoms. The approach includes developing advanced methods to analyze clinical and biological data, generating machine learning models for patient stratification, integrating clinical and biological data for personalized therapy, and creating a pan-European rheumatic patient journey map. Usability and acceptability studies are conducted to ensure the tools meet end-user needs and improve their adoption. |
Jyaysi Desai |