Search

BackgroundFinancial codes are often used to extract diagnoses from electronic health records. This approach is prone to false positives. Alternatively, queries are constructed, but these are highly center and language specific. A tantalizing alternative is the automatic identification of patients by employing machine learning on format-free text entries. ObjectiveThe aim of this study was to develop an easily implementable workflow that builds a machine learning algorithm capable of accurately identifying patients with rheumatoid arthritis from format-free text fields in electronic health records. MethodsTwo electronic health record data sets were employed: Leiden (n=3000) and Erlangen (n=4771). Using a portion of the Leiden data (n=2000), we compared 6 different machine learning methods and a naïve word-matching algorithm using 10-fold cross-validation. Performances were compared using the area under the receiver operating characteristic curve (AUROC) and the area under the precision recall curve (AUPRC), and F1 score was used as the primary criterion for selecting the best method to build a classifying algorithm. We selected the optimal threshold of positive predictive value for case identification based on the output of the best method in the training data. This validation workflow was subsequently applied to a portion of the Erlangen data (n=4293). For testing, the best performing methods were applied to remaining data (Leiden n=1000; Erlangen n=478) for an unbiased evaluation. ResultsFor the Leiden data set, the word-matching algorithm demonstrated mixed performance (AUROC 0.90; AUPRC 0.33; F1 score 0.55), and 4 methods significantly outperformed word-matching, with support vector machines performing best (AUROC 0.98; AUPRC 0.88; F1 score 0.83). Applying this support vector machine classifier to the test data resulted in a similarly high performance (F1 score 0.81; positive predictive value [PPV] 0.94), and with this method, we could identify 2873 patients with rheumatoid arthritis in less than 7 seconds out of the complete collection of 23,300 patients in the Leiden electronic health record system. For the Erlangen data set, gradient boosting performed best (AUROC 0.94; AUPRC 0.85; F1 score 0.82) in the training set, and applied to the test data, resulted once again in good results (F1 score 0.67; PPV 0.97). ConclusionsWe demonstrate that machine learning methods can extract the records of patients with rheumatoid arthritis from electronic health record data with high precision, allowing research on very large populations for limited costs. Our approach is language and center independent and could be applied to any type of diagnosis. We have developed our pipeline into a universally applicable and easy-to-implement workflow to equip centers with their own high-performing algorithm. This allows the creation of observational studies of unprecedented size covering different countries for low cost from already available data in electronic health record systems.

Outcomes of patients with inflammatory rheumatic diseases have significantly improved over the last three decades, mainly due to therapeutic innovations, more timely treatment, and a recognition of the need to monitor response to treatment and to titrate treatments accordingly. Diagnostic delay remains a major challenge for all stakeholders. The combination of electronic health (eHealth) and serologic and genetic markers holds great promise to improve the current management of patients with inflammatory rheumatic diseases by speeding up access to appropriate care. The Joint Pain Assessment Scoring Tool (JPAST) project, funded by the European Union (EU) European Institute of Innovation and Technology (EIT) Health program, is a unique European project aiming to enable and accelerate personalized precision medicine for early treatment in rheumatology, ultimately also enabling prevention. The aim of the project is to facilitate these goals while at the same time, reducing cost for society and patients.

Objective Recently, a genome-wide association study identified an association between RA-associated interstitial lung disease (ILD) and RPA3-UMAD1 rs12702634 in the Japanese population, especially for patients with a usual interstitial pneumonia (UIP) pattern. We aimed to replicate this association in a European population and test for interaction with MUC5B rs35705950. Methods In this genetic case–control association study, patients with RA and ILD and controls with RA and no ILD were included from France, the USA and the Netherlands. Only cases and controls from European genetic ancestries determined by principal components analysis were included in the analyses. RA was defined by the 1987 ACR or 2010 ACR/EULAR criteria and ILD by chest high-resolution CT scan, except in the control dataset from the Netherlands, where the absence of ILD was determined by chart review. Patients were genotyped for RPA3-UMAD1 rs12702634 and MUC5B rs35705950. Associations were tested using logistic regression adjusted for sex, age at RA onset, age at ILD onset or at certified absence of ILD, tobacco smoking status and country of origin. Results Among the 883 patients included, 322 were RA-ILD cases (36.5%). MUC5B rs35705950 was strongly associated with RA-ILD in all datasets {combined adjusted odds ratio [OR] 2.9 [95% CI 2.1, 3.9], P  = 1.1 × 10−11. No association between RPA3-UMAD1 rs12702634 and RA-ILD was observed [combined OR 1.2 (95% CI 0.8, 1.6), P  = 0.31. No interaction was found between RPA3-UMAD1 rs12702634 and MUC5B rs35705950 (P  = 0.70). Conclusion Our findings did not support a contribution of RPA3-UMAD1 rs12702634 to the overall RA-ILD susceptibility in the European population. [ABSTRACT FROM AUTHOR]

Modest effect sizes have limited the clinical applicability of genetic associations with rheumatic diseases. Genetic risk scores (GRSs) have emerged as a promising solution to translate genetics into useful tools. In this review, we provide an overview of the recent literature on GRSs 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. First, the shortage of non-European genetic data restricts the application of many GRSs to European populations. Next, many GRSs are tested in settings enriched for cases that limit the transferability to real life. If intended for clinical application, GRSs are ideally tested in the relevant setting. Finally, there is much to elucidate regarding the co-occurrence of clinical traits to identify shared causal paths and elucidate relationships between the diseases. GRSs are useful instruments for this. Overall, the ever-continuing research on GRSs gives a hopeful outlook into the future of GRSs and indicates significant progress in their potential applications. [ABSTRACT FROM AUTHOR]

Objective: To investigate whether established genetic predictors for rheumatoid arthritis (RA) differentiate healthy controls, patients with clinically suspect arthralgia (CSA), and RA patients. Methods: Using analyses of variance, chi‐square tests, and mean risk difference analyses, we investigated the association of an RA polygenic risk score (PRS) and HLA shared epitope (HLA‐SE) with all participant groups, both unstratified and stratified for anti–citrullinated protein antibody (ACPA) status. We used 3 separate data sets sampled from the same Dutch population (1,015 healthy controls, 479 CSA patients, and 1,146 early classified RA patients). CSA patients were assessed for conversion to inflammatory arthritis over a period of 2 years, after which they were classified as either CSA converters (n = 84) or CSA nonconverters (n = 395). Results: The PRS was increased in RA patients (mean ± SD PRS 1.31 ± 0.96) compared to the complete CSA group (1.07 ± 0.94) and compared to CSA converters (1.12 ± 0.94). In ACPA– strata, PRS distributions differed strongly when comparing the complete CSA group (mean ± SD PRS 1.05 ± 0.94) and CSA converters (0.97 ± 0.87) to RA patients (1.20 ± 0.94), while in the ACPA+ strata, the complete CSA group (1.25 ± 0.99) differed clearly from healthy controls (1.05 ± 0.94) and RA patients (1.41 ± 0.96). HLA‐SE was more prevalent in the RA group (prevalence 0.64) than the complete CSA group (0.45), with small differences between RA patients and CSA converters (0.64 versus 0.60) and larger differences between CSA converters and CSA nonconverters (0.60 versus 0.42). HLA‐SE prevalence differed more strongly within the ACPA+ strata as follows: healthy controls (prevalence 0.43), CSA nonconverters (0.48), complete CSA group (0.59), CSA converters (0.66), and RA patients (0.79). Conclusion: We observed that genetic predisposition increased across pre‐RA participant groups. The RA PRS differed in early classified RA and inflammatory pre‐disease stages, regardless of ACPA stratification. HLA‐SE prevalence differed between arthritis patients, particularly ACPA+ patients, and healthy controls. Genetics seem to fulfill different etiologic roles. [ABSTRACT FROM AUTHOR]

The article explores the use of genetic data in diagnosing early inflammatory arthritis, introducing a tool called Genetic Probability (G-PROB). It validates this tool, showing its strong correlation with final diagnoses across various inflammatory arthritides. It emphasizes the need for further research to determine G-PROB's clinical utility, including aiding in earlier diagnosis and treatment decisions, and integrating genomic data into current diagnostic practices in rheumatology.