Accuracy of diagnostic codes and algorithms used to identify rheumatoid arthritis and juvenile idiopathic arthritis in electronic health records: systematic review and meta-analysis

Accuracy of diagnostic codes and algorithms used to identify rheumatoid arthritis and juvenile idiopathic arthritis in electronic health records: systematic review and meta-analysis | medRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-P4HH5NV'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search Accuracy of diagnostic codes and algorithms used to identify rheumatoid arthritis and juvenile idiopathic arthritis in electronic health records: systematic review and meta-analysis Constanza Saka-Herrán , Jessica Bennett , Yara Alkabti , Muhammad Fatir , Barbara Clyne , Caroline McCarthy , Gráinne Tynan , Nikki Dunne , Michelle Flood , Eoghan McCarthy , Frank Moriarty doi: https://doi.org/10.1101/2025.06.30.25330552 Constanza Saka-Herrán 1 School of Pharmacy and Biomolecular Sciences, Royal College of Surgeons in Ireland (RCSI) , Dublin, Ireland PhD, MSc Find this author on Google Scholar Find this author on PubMed Search for this author on this site Jessica Bennett 1 School of Pharmacy and Biomolecular Sciences, Royal College of Surgeons in Ireland (RCSI) , Dublin, Ireland BSc (Pharm), MPharm Find this author on Google Scholar Find this author on PubMed Search for this author on this site Yara Alkabti 2 School of Medicine, Royal College of Surgeons in Ireland (RCSI) , Dublin, Ireland Roles: Medical Student Find this author on Google Scholar Find this author on PubMed Search for this author on this site Muhammad Fatir 2 School of Medicine, Royal College of Surgeons in Ireland (RCSI) , Dublin, Ireland Roles: Medical Student Find this author on Google Scholar Find this author on PubMed Search for this author on this site Barbara Clyne 3 Dept Public Health & Epidemiology, School of Population Health, Royal College of Surgeons in Ireland (RCSI) , Dublin, Ireland PhD, MSocSc Find this author on Google Scholar Find this author on PubMed Search for this author on this site Caroline McCarthy 4 Department of General Practice, Royal College of Surgeons in Ireland (RCSI) , Dublin, Ireland MB, BCh, MD Find this author on Google Scholar Find this author on PubMed Search for this author on this site Gráinne Tynan 1 School of Pharmacy and Biomolecular Sciences, Royal College of Surgeons in Ireland (RCSI) , Dublin, Ireland BSc Find this author on Google Scholar Find this author on PubMed Search for this author on this site Nikki Dunne 1 School of Pharmacy and Biomolecular Sciences, Royal College of Surgeons in Ireland (RCSI) , Dublin, Ireland PhD, MsC Find this author on Google Scholar Find this author on PubMed Search for this author on this site Michelle Flood 1 School of Pharmacy and Biomolecular Sciences, Royal College of Surgeons in Ireland (RCSI) , Dublin, Ireland PhD, MSc Find this author on Google Scholar Find this author on PubMed Search for this author on this site Eoghan McCarthy 5 Department of Rheumatology, Beaumont Hospital/Royal College of Surgeons in Ireland (RCSI) , Dublin, Ireland PhD, MD Find this author on Google Scholar Find this author on PubMed Search for this author on this site Frank Moriarty 1 School of Pharmacy and Biomolecular Sciences, Royal College of Surgeons in Ireland (RCSI) , Dublin, Ireland PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site For correspondence: frankmoriarty{at}rcsi.com Abstract Full Text Info/History Metrics Supplementary material Data/Code Preview PDF Abstract Objective This systematic review aimed to assess the diagnostic accuracy of algorithms used to identify rheumatoid arthritis (RA) and juvenile idiopathic arthritis (JIA) in electronic health records (EHRs). Methods We searched MEDLINE, Embase, and CENTRAL databases and included studies that validated case definitions against a reference standard such as rheumatologist-confirmed diagnosis or ACR/EULAR classification criteria. Title/abstract screening, full-text review, data extraction and quality assessment were all completed in duplicate. Results were synthesised narratively and using a bivariate random-effects meta-analysis of sensitivity and specificity. Results A total of 35 studies were included. Algorithms varied widely in complexity, ranging from single ICD codes to combinations including disease-modifying antirheumatic drugs (DMARDs), hospitalisation records, and specialist diagnosis. Algorithms combining ICD codes with DMARD prescriptions (pooled sensitivity= 0.79 95% CI 0.61-0.90, specificity= 0.96 95% CI 0.72-1.00, PPV= 0.78 95% CI 0.63-0.88) or requiring an ICD code assigned by a rheumatologist (pooled sensitivity= 0.91 95% CI 0.70-0.98, specificity= 0.94 95% CI 0.49-1.00, PPV= 0.70 95% CI 0.64-0.75) showed the highest accuracy, with balanced sensitivity, specificity, and positive predictive value (PPV). Less restrictive algorithms demonstrated high sensitivity but lower PPV. Substantial heterogeneity was observed across studies, likely due to differences in algorithm structure, data sources, and validation methods. Despite this variability, we used conceptually coherent categories to allow for meaningful synthesis, prioritising clinical interpretability. Conclusions These findings support the use of more specific algorithms when diagnostic certainty is essential and highlight the need for further validation of high-performing algorithms across diverse healthcare systems. Significance and Innovations ▪ This is the first comprehensive systematic review to evaluate and synthesize the accuracy of algorithms used to identify rheumatoid arthritis and juvenile idiopathic arthritis in electronic health records (EHRs), addressing a growing need as real-world data become increasingly central in rheumatology research. ▪ The findings provide critical guidance for researchers and clinicians on the strengths and limitations of commonly used case definitions, helping improve validity of studies using administrative or EHR data. ▪ By categorizing algorithms based on their components and reference standards, this review offers a practical framework for selecting the most appropriate algorithm depending on the study purpose and data source. ▪ The review highlight gaps in validation efforts and emphasizes the need to validate high-performing algorithms across diverse healthcare settings and evolving coding systems, ensuring accurate disease identification in current and future research. 1. Introduction Rheumatoid arthritis (RA) and juvenile idiopathic arthritis (JIA) are autoimmune diseases characterised by joint inflammation, and systemic complications, leading to disability, and reduced quality of life 1 . Despite differences in onset and classification criteria, they share key pathogenic mechanisms, clinical manifestations and therapeutic strategies 2 , 3 . A challenge in RA/JIA research is obtaining robust epidemiological data to understand the natural history of disease and impact of therapy on disease outcomes 4 . Electronic health records (EHRs), have greatly facilitated studying these conditions in large populations, providing comprehensive data on patient demographics, symptoms, diagnoses, and treatment history 5 , 6 , in a real-world setting. However, the reliability and validity of research based on EHR data depend on the accuracy of the diagnostic codes and algorithms used to identify the condition 7 , 8 . Combining multiple diagnostic codes with clinical data, such as prescriptions and laboratory results, enhances RA identification accuracy. For instance, algorithms incorporating at least three physician diagnostic codes, achieve specificity and positive predictive values (PPVs) of over 90% 9 . The inclusion of disease-modifying antirheumatic drug (DMARD) prescriptions with diagnostic codes, significantly improves case identification 10 . Standardised algorithms that integrate International Classification of Diseases (ICD) codes with other clinical parameters have also been assessed for their utility in diverse healthcare systems 11 . Despite advances in identifying RA/JIA cases, limitations persist due to coding inaccuracy, population heterogeneity, and differences across healthcare systems and methodological approaches. A 2013 systematic review, part of the Mini-Sentinel pilot project sponsored by the Food and Drug Administration (FDA), reported substantial variability in the accuracy of algorithms (PPV 34%-97%) applied to EHRs 12 . The data sources of interest were limited to the US or Canada reflecting Mini-Sentinel’s focus on US-based data for surveillance system 13 , thus limiting the global applicability of the findings. The aim of this systematic review is to synthesise and critically assess evidence on the accuracy of diagnostic codes and algorithms used to identify RA and JIA in EHRs and other administrative databases. By expanding the focus to include other regions, this review provides a more comprehensive evaluation of the tools used to identify the disease across various key data sources in the context of the significant changes in RA/JIA treatment and outcomes over the past decade. 2. Methods The study protocol was registered on PROSPERO (Registration ID: CRD42024619130). The systematic review is reported in line with the PRISMA-DTA statement 14 . 2.1 Eligibility criteria We included studies assessing the accuracy of codes and algorithms identifying RA and JIA in EHRs or other administrative databases against a “reference standard” based on clinician-documented diagnosis, clinician-conducted chart review, another form of clinician confirmed diagnosis, or application of the American College of Rheumatology/ European League Against Rheumatism (ACR/EULAR) criteria (e.g., to GP records, medical charts, office records) regardless of study design. Studies relying on self-reported diagnoses as the reference standard were excluded, as previously recommended 15 . Eligible studies had to clearly report algorithm components and describe methods for accuracy assessment. We excluded: case reports, editorials, commentaries, and narrative reviews. While systematic reviews were not included, relevant ones were used for reference checking. No restrictions were placed on language or publication date. 2.2 Information sources We searched MEDLINE (PubMed interface), EMBASE and the Cochrane Central Register for Controlled Trials. Search strategies used medical subject headings (MeSH) terms and text-words aligned with our eligibility criteria (Supplementary Appendix 1) and were adapted for each database. To ensure literature saturation, we manually reviewed references of eligible studies and included articles from prior systematic reviews. 2.3 Search strategy Our strategy was based on the Mini-Sentinel project search strategies 12 , 16 , and updated with additional terms. We reviewed the PubMed MeSH terms, as well as abstracts and full-texts of primary studies from a prior systematic review to identify relevant terminology. The search was developed collaboratively and validated by confirming it retrieved all articles from the Chung et al review 12 . After finalizing the MEDLINE search, it was adapted to the other databases. Full search strategies and validation process details are in Supplementary Appendix 2. Searches were conducted on November 11, 2024. 2.4 Study records 2.4.1 Data management We used Covidence software for record management and deduplication. Screening questions for title/abstract review were developed and tested. Reviewers completed training and pilot screening (50 abstracts by five reviewers) to calibrate eligibility criteria. 2.4.2 Study selection Two reviewers (of CSH, JB, YA, MuF, FM) independently screened titles/abstracts against eligibility criteria. Full-texts of potentially eligible studies were reviewed in duplicate. Disagreements were resolved by discussion or a third reviewer. Reasons for full-text exclusions were documented. 2.4.3 Data collection process and items Two reviewers independently extracted data using a standardized template based on the STARD criteria 17 , adapted for administrative databases. Discrepancies were resolved through discussion or a third reviewer. Extracted data included study characteristics, algorithms definitions, validation methods, and accuracy measures. The template is available as a data supplement (see availability of data statement). Classifications for target condition are provided in Supplementary Appendix 3. 2.5 Diagnostic accuracy measures Primary accuracy measures were sensitivity, specificity, PPV, and negative predictive value (NPV). When not reported, these were calculated from two-by-two tables. For practical interpretation, accuracy was categorized is high (≥80%), moderate (60-80%), or low (<60%) 18 . The unit of assessment was the individual. Further details are provided in Supplementary Appendix 3. 2.6 Risk of bias and applicability Quality was assessed using the QUADAS-2 tool, which examines risk of bias and applicability across four domains: patient selection, index test, reference standard, and flow/timing 19 . Domains were rated as low, unclear or high for each domain. Overall study bias followed QUADAS-2 guidance (i.e., any high-risk domain rendered the study high risk overall) 14 . Two reviewers independently assessed study quality, resolving disagreements through discussion. 2.7 Synthesis of results We categorized algorithms based on the number and type of codes used to identify RA/JIA (e.g., ICD, prescriptions, diagnostic tests, procedures). Classification followed Shrestha et al 20 with modifications: ▪ Less restrictive algorithms : required a single diagnostic code from an outpatient visit or unspecified source (e.g., single ICD code). ▪ Restrictive algorithms : required multiple codes or inclusion of specific types (e.g., procedures, prescriptions, tests, or hospitalisation codes). Algorithms were categorised as either restrictive or less restrictive. For further analysis, we developed sub-categories among restrictive algorithms based on expected accuracy and usage frequency in included studies. These were: RA diagnosis codes and DMARD prescription codes, ≥2 ICD codes for RA, ≥1 ICD code for RA by rheumatologist, and ≥1 ICD hospitalisation code for RA (full description are in Supplementary Appendix 3). 2.8 Meta-analysis We performed a bivariate random-effects meta-analysis using a generalised linear mixed-effects model (GLMM) to jointly synthesise sensitivity and specificity estimates, accounting for within- and between-study variability and their correlation 21 – 23 . Pooled PPV estimates were obtained via meta-analysis of proportions using the meta package in R, applying random-effects models within subgroups defined by algorithm and reference standard categories ( metaprop function). For each study, sensitivity and specificity with 95% CIs were calculated. Forest plots were generated for PPV, sensitivity, and specificity, displaying individual and pooled estimates by algorithm subgroup to capture between-study heterogeneity. Heterogeneity was assessed using I 2 statistics derived from variance components of the random-effects model. Analyses were conducted using R (version 4.4.3). 3. Results 3.1 Study selection The search yielded 4,109 records; after removing duplicates, 3,452 were screened based on eligibility criteria, and 108 underwent full-text review. Seventy-seven articles were excluded, reasons provided in Figure 1 . Reference checks of the 31 eligible articles identified 4 additional studies, totalling 35 included in the review ( Figure 1 ). Download figure Open in new tab Figure 1. Flow diagram for study selection. 3.2 Study characteristics Most studies were from the US and Canada (n=21), followed by Europe, (mainly Italy, UK, Denmark and Sweden; n=10), Asia (Japan and South Korea; n=3), and Australia (n=1). The majority were retrospective cohorts (n=25), followed by cross-sectional (n=6) and case-control studies (n=4). Two-thirds (n=23, 66%) were published since the 2013 review (Supplementary Appendix 4- Table 1 ). View this table: View inline View popup Download powerpoint Table 1. Summary characteristics and accuracy measures of included studies (n=35) The included studies (n=35) used diverse electronic databases, including national health insurance claims-i.e. Korean National Health Insurance database 24 , Medicare 10 , 25 – 27 , and Ontario Health Insurance Plan 9 , 28 ; hospital discharge records-i.e. Stockholm County Medical Information System 29 , Danish National Patient Registry 30 , 31 , Partners Healthcare database used by the Brigham and Women’s Hospital and the Massachusetts General Hospital 32 – 34 , and Canadian Institute for Health Information Discharge Abstract Database 9 , 28 ; and institutional EHRs-i.e. Vanderbilt University Medical Center’s Synthetic Derivate 32 , 35 , 36 , University of California Los Angeles Health System 37 , Mayo Clinic Biobank 38 , and from specific rheumatological institutions or disease registries 11 , 39 – 41 . Some also incorporated pharmacy data 30 , 42 , 43 , and physician billing records 41 , 44 , 45 . Most studies focused on RA patients, though five examined JIA 35 , 39 , 45 – 47 . Samples sizes ranged from small cohorts, i.e., 31 48 and 94 46 participants, to large datasets exceeding 55,000 individuals 24 . Women comprised 50-80% of participants. Mean age varied, typically between 50-70 years for RA, and <19 years for JIA. Full study characteristics are detailed in Supplementary Appendix 4 - Table 1 . RA case identification relied mainly on ICD codes ( Table 1 ), with ICD-9 (62.8%) and ICD-10 (48.6%) being the most used (Supplementary Appendix 4- Table 1 ). Some older datasets also used ICD-8 codes 29 , 30 . Additional criteria were applied in several studies, such as medications (54.3%), and laboratory markers (22.8%) like rheumatoid factor (RF) and anticyclic citrullinated peptide (anti-CCP) antibodies 34 , 49 ( Table 1 ). Some studies implemented complex algorithms, including the eMERGE algorithm, which combined ICD codes with RF values and other autoimmune disease exclusions 37 , 38 . The algorithm developed by Liao et al, incorporating ICD codes, prescriptions and laboratory values 34 was validated in other settings by Carroll et al 32 , and Huang et al 33 (Supplementary Appendix 4- Table 1 ). Most studies (71.4%) used a rheumatologist’s clinical diagnosis as the reference standard ( Table 1 ), while others applied established classification criteria including the 1987 ACR criteria, 2010 ACR/EULAR criteria, and for JIA, the 2001 International League of Associations for Rheumatology (ILAR) criteria (Supplementary Appendix 4- Table 1 ). Four studies relied on medical records review by trained nurses or researchers, without clear specification of the reference standard 26 , 27 , 36 , 49 ( Table 1 ). 3.3 Risk of bias and applicability Risk of bias and applicability concerns varied across studies, with patient selection and flow/timing being the most affected domains ( Table 2 ). Patient selection showed the highest risk, mainly due to non-random inclusion, use of ICD codes without additional verification, and concerns regarding representativeness. The index test domain showed a low risk, generally due to clearly defined and consistently applied algorithms, though some studies lacked clarity or did not report blinding to the reference standard. The reference standard domain showed the lowest risk, using established standards like rheumatologist diagnosis or ACR/EULAR criteria, though some had unclear validation methods. Flow and timing had mixed results, with high risk in studies that did not include all participants in analysis or did not assess all diagnostic accuracy measures due to study design. View this table: View inline View popup Download powerpoint Table 2. Risk of bias and applicability concerns of included studies (QUADAS-2 tool). Overall, six studies were rated high risk of bias 25 – 27 , 29 , 40 , 48 due to limitations in multiple domains, potentially leading to misclassification and reduced generalisability. In contrast, studies by Carroll et al 32 , Cho et al 24 , Liao et al 34 , Singh et al 50 , and Widdifield et al 2014 9 had low risk, with strong design across all domains ( Table 2 .) Applicability concerns were generally low, suggesting good relevance to real-world settings. However, studies using specialised databases or narrow inclusion criteria (i.e., paediatric populations, single-centre databases, incident RA cases) had moderate concerns as they may not generalise to broader RA populations ( Table 2 ). 3.4 Results of individual studies 3.4.1 Rheumatoid Arthritis codes and algorithms Individual study results are detailed in Supplementary Appendix 5- Table 2 . Across studies, over 180 definitions/algorithms were evaluated. Percentage of studies that used less restrictive, restrictive algorithms and their categories are presented in Figure 2 . Download figure Open in new tab Figure 2. Codes/algorithms and reference standards used by the included studies assessing rheumatoid arthritis in electronic health records, % (n=31). Less restrictive algorithms typically had high sensitivity but low specificity, increasing false positives. For example, Almutairi et al 51 found 90% sensitivity but only 28.5% specificity using ≥1 RA primary code in hospital discharge records, highlighting the risk of over-identification. Other studies 28 , 44 , 50 showed similar trends, with sensitivities >90% and specificities below 65%. Adding DMARD prescriptions to ICD codes improved specificity and PPV while maintaining good sensitivity. Cho et al 24 achieved 85% sensitivity and 70% specificity using ICD-10 codes with biologic, DMARD, or NSAID prescriptions, maintaining >85% PPV values in all developed algorithms. Similarly, Singh et al 50 reported 85% sensitivity, 83% specificity, and 81% PPV when using a similar approach. Linauskas et al 30 showed PPV increased from 61.9% to 87.7% when requiring ≥1 DMARD prescription. Requiring ≥2 ICD RA codes, separated over time, improved specificity while maintaining good sensitivity, though decreasing PPV. Hanly et al 44 , reported 83% sensitivity, 81% specificity, and 52% PPV using two RA physician codes ≥2 months apart. Similar trends were seen in Kubota et al 52 (84% sensitivity, 99% specificity, and 59% PPV) and Widdifield et al 9 (84% sensitivity, 99% specificity, and 46% PPV). Requiring ≥1 hospitalisation record improved specificity and PPV but greatly reduced sensitivity. Convertino et al 53 found 95% specificity, 81% PPV but only 37% sensitivity when requiring 1 RA hospitalisation or emergency admission code. Similarly, Hanly et al 44 achieved 98.5% specificity, 77% PPV and 20.7% sensitivity when using ≥1 hospitalisation code. Similar patterns were noted by Wididifield et al 9 , 28 . Algorithms requiring at least one rheumatologist diagnosis code showed overall moderate to high sensitivity and specificity, with moderate PPV. Widdiefield et al 2014 9 and 2013 28 , achieved 81% and 99% sensitivity, 99% and 77% specificity and 51% and 68% PPV, respectively. Similarly, Hanly et al 44 reported 88% sensitivity, 75.5% specificity, and 47% PPV when using ≥1 RA code by a rheumatologist. In contrast, Carrara et al 11 reported 99.8% specificity but only 13% sensitivity when combining one RA rheumatologist certification with other ICD-9 codes. The eMERGE algorithm-combining ICD codes, RF values, and other autoimmune disease exclusions-demonstrated high specificity (95-99%) and PPV (94-97%) in both studies evaluating it (Zheng et al 2022 37 and Kronzer et al 2020 38 , respectively). However, sensitivity varied likely due to differences in sample size and study population. Zheng et al 37 (n=4,766, UCLA Health System) reported a higher sensitivity (72%), while Kronzer et al 38 (n= 497, Mayo Clinic Biobank included in the Rochester Epidemiology Project) achieved a sensitivity of 53% in a smaller and more geographically limited sample. However, Kronzer et al 38 found sensitivity increased with RA duration and EHR history, reaching 71% for patients with ≥10 years of disease. Overall, the eMERGE algorithm performed well, with sensitivity maybe influenced by dataset scope. The RA algorithm initially developed by Liao et al 34 , validated by Carroll et al 32 and Huang et al 33 , consistently showed moderate sensitivity (51-79%) and high PPV (>87%) across different settings showing a good balance between measures for identifying RA cases. Huang et al 33 enhanced the model by incorporating ICD-10 codes and newer biologic treatments, achieving 77% sensitivity, 95% specificity, and 91% PPV. Overall, the algorithm maintains high accuracy, with sensitivity improving slightly as case definitions and coding systems evolved. Both the eMERGE and Liao algorithms used laboratory data (RF, anti-CCP), which improved specificity and PPV, and had limited effect on sensitivity. Paltta et al 42 reported 98% PPV when incorporating anti-citrullinated protein antibodies (ACPA) positivity in their algorithm, compared with ICD codes alone (82%) or ICD codes and DMARDs (89%). Singh et al also showed improved sensitivity (88%), specificity (91%), and PPV (93%) when adding positive RF to their algorithm, compared to ICD codes alone (sensitivity: 100%; specificity: 55%; PPV: 66%) or ICD codes and DMARDs (sensitivity: 85%; specificity: 83%; PPV: 81%) 50 , suggesting that laboratory data helps reduce false positives while maintaining a balanced improvement in the accuracy measures. 3.4.2 Juvenile Idiopathic Arthritis codes and algorithms JIA studies evaluated similar EHR-based algorithms (Supplementary Appendix 5- Table 2 ). Less restrictive algorithms, like ≥1 JIA diagnosis code, showed high sensitivity but moderate to low PPV. Harrold et al 39 and Peterson et al 35 both reported 100% sensitivity with PPVs of 45% and 48%, respectively. Only one study assessed the accuracy of DMARD prescription alone as a definition. Thomas et al 47 found 40% sensitivity, but 100% specificity and PPV when requiring ≥1 DMARD prescription without prior alternative indication. Requiring ≥2 ICD codes for JIA improved PPV while maintaining good sensitivity. Reported sensitivity ranged from 72-93% and PPV from 60-100% across studies 35 , 39 , 45 – 47 . Peterson et al 35 noted that increasing the number of JIA codes (≥4) raised PPV (83%) without substantial decrease in sensitivity (87%), compared to using ≥1 code (PPV=48%). Shiff et al 45 found specificity improved (85-92%) with more ICD codes over longer intervals. Two studies assessed algorithms requiring ≥1 JIA code from a rheumatologist. Harrold et al 39 showed that requiring a rheumatologist visit improved PPV from 69% to 90% while maintaining good sensitivity (81%). Stringer et al 46 showed similar sensitivity (86%) but decreased PPV (58%), which increased to 65% when using two JIA codes ≥8 weeks apart within 2 years, maintaining good sensitivity (81%). 3.5 Meta-analysis Meta-analyses showed substantial variability in the accuracy of RA identification algorithms in EHRs, depending on algorithms components and reference standards. Using rheumatologist diagnosis as reference, algorithms requiring ≥2 ICD codes had the highest pooled sensitivity (0.89 95% CI 0.75-0.95, n=4 studies) and specificity (0.96 95% CI 0.74-1.00, n=4), though with high heterogeneity (I 2 = 91.3%, I 2 = 99.8%, respectively). Algorithms combining ICD codes with DMARD prescriptions also showed good pooled sensitivity (0.79 95% CI 0.61-0.90, I 2 = 90.6%, n=5) and high specificity (0.96 95% CI 0.72-1.00, I 2 = 98.9%, n=5) ( Table 3 , Supplementary Appendix 6- Figure 1 ). Algorithms using ≥1 ICD code by rheumatologist also showed high performance (sensitivity 0.91, 95% CI 0.70-0.98; specificity 0.94, 95% CI 0.49-1.00, n=3), but were based on only three studies, warranting cautious interpretation. A meta-analysis of sensitivity and specificity using ACR/EULAR classification criteria as the reference standard was not feasible due to insufficient data. View this table: View inline View popup Download powerpoint Table 3. Pooled estimates of sensitivity and specificity and across algorithms categories (reference standard= diagnosis by rheumatologist). PPV results varied by reference standard and showed substantial heterogeneity. Using rheumatologist diagnosis as the reference, the highest pooled PPVs were seen in algorithms combining ICD and DMARDs codes (0.78 95% CI 0.63-0.88, n=10), those including ≥1 ICD code by rheumatologist (0.64 95% CI 0.51-075, n=4), and those requiring ≥1 hospitalisation code (0.79 95% CI 0.77-0.81, n=7). In contrast, when using ACR/EULAR classification criteria, PPVs were slightly lower when requiring ≥2 ICD codes (0.62 95% CI 0.14-0.94, n=2) or ICD and DMARDs codes (0.73 95% CI 0.45-0.90, n=6). Algorithms requiring ≥1 ICD code by rheumatologist demonstrated the highest pooled PPV (0.85 95% CI 0.35-0.98, n=3), though with high heterogeneity (I 2 = 96.3%) ( Table 4 , Supplementary Appendix 7– Figure 2 ). View this table: View inline View popup Download powerpoint Table 4. Pooled estimates of PPV across algorithms categories by reference standards. 4. Discussion 4.1 Summary of evidence This systematic review analysed the accuracy of algorithms for identifying RA and JIA in EHRs. Overall, algorithms combining ICD codes with DMARD prescriptions, or those that include ≥1 ICD code assigned by rheumatologist, demonstrated the highest accuracy, balancing sensitivity, specificity, and PPV. These algorithms are more reliable for identifying confirmed RA cases, though rheumatologist-assigned codes may miss cases diagnosed in primary care, potentially leading to underestimation of disease prevalence. Less restrictive algorithms are useful for initial case identification (highly sensitive) but may require additional criteria to enhance specificity and PPV. Requiring ≥2 ICD codes is a well-balanced approach, reducing false positives (higher specificity) without significantly lowering sensitivity, though achieving moderate PPV. Hospitalisation-based codes are highly specific for identifying severe RA cases but may exclude many non-hospitalised, mild/moderate cases, making it less suitable for general RA case identification. For JIA, a single ICD code is highly sensitive but may overestimate prevalence due to false positives. Requiring ≥2 spaced ICD codes improves accuracy and seems to be the best approach, providing a good balance of sensitivity, specificity and PPV in EHRs or administrative data. However, validation evidence for JIA remains limited, highlighting the need for further research. Our findings align with and extend previous systematic reviews on RA and connective tissue diseases algorithms in EHRs. Compared to the 35 studies we included, the 2013 review by Chung et al 12 included 9 studies and found that algorithms combining diagnostic and prescription data-particularly those including specialist codes, medication or laboratory data-achieved higher PPVs (>80%), while ICD-only algorithms had more variable performance across settings, generally with low PPVs. Similar trends were seen in studies for other conditions, but generally lower PPVs (<65%) in general populations 20 , 54 , probably reflecting the challenges of identifying these conditions due to non-specific coding and overlap with other autoimmune conditions. Similarly, a systematic review by Crossfield et al 55 on gout also highlighted variability in methods and performance, reflecting a lack of standardisation in defining rheumatologic conditions using real-world data. Compared to these conditions, RA appears to be more accurately identified in EHRs, especially when algorithms include medication data or are supported by specialist confirmation. The accuracy of hospitalisation-based algorithms must be interpreted within the context of evolving healthcare delivery. RA hospitalisations have declined significantly over the past two decades due to earlier diagnosis, improved outpatient care, and widespread use of biologic therapies 56 – 58 . As a result, performance of algorithms using hospitalisation codes in historic data may be less representative of current patient populations. Similarly, treatment patterns have evolved, with earlier DMARD initiation, combined therapies (e.g., biologics and DMARDs) 59 – 61 , and the development of targeted-synthetic DMARDs (e.g., JAK inhibitors), which may affect the predictive value of medication-based algorithms applied to contemporary prescribing data. The transition from ICD-9 to ICD-10 introduced more specific diagnosis codes, potentially influencing algorithm performance. In this review, 62.8% of studies examined ICD-9 and 48.6% examined ICD-10 codes, reflecting variability in study periods, country-level implementation, differences in capacity to adopt new coding systems, and the use of historical data sources. Algorithms developed with ICD-9 codes may not translate directly to ICD-10 without re-validation 62 , 63 , particularly for specific or rare disease subtypes. These changes underscore the need for regular update and validation of algorithms to align with current coding systems and clinical practice. From a practical perspective, the selection of an algorithm for identifying RA or JIA should be guided by the purpose of the study and the nature of the data source. For studies aiming to evaluate treatment outcomes, assess adverse events, or conduct comparative effectiveness studies, algorithms with high specificity may be preferable to ensure the correct identification of true cases. In contrast, for surveillance or studies assessing prevalence or burden of disease, algorithms prioritising higher sensitivity may be preferable, even at lower PPV. Future research should focus on validating existing algorithms, such as the eMERGE 37 , 38 and Liao et al 34 algorithms, across diverse healthcare systems and populations. While both show consistent diagnostic accuracy in diverse settings, the generalisability of the Liao algorithm beyond academic health centres, remains uncertain. Validation using community-based data is needed to ensure broader applicability. Clear and transparent reporting of algorithm components is essential for replication, external validation, and broader implementation in different contexts. Additionally, the development and validation of algorithms using machine learning or natural language processing techniques hold promise for further improving case ascertainment, particularly in settings where structured coding is limited. 4.2 Limitations The studies reviewed exhibited substantial methodological variability, making direct comparisons difficult. Differences in sample size, sampling methods, settings, population, and data sources likely contributed to the high statistical heterogeneity in several analyses. Algorithm definitions varied widely, even within similar categories, highlighting a lack of standardisation in algorithm development and validation methods. Despite this, meta-analyses were feasible by grouping algorithms into broad, but conceptually coherent categories, prioritising simplicity and clinical interpretability. While many incorporated medication use, most studies grouped DMARDs as a single category, precluding an evaluation of the contribution of specific drugs or therapeutic classes to the accuracy. Several studies did not report full accuracy measures due to sampling designs, which involved evaluating only algorithm-positive cases, and thus only the PPV. The PPV depends on disease prevalence within the population being studied. Several studies selected their populations from hospital settings or rheumatologic clinics, where the prevalence of RA is likely to be higher than in the general population, potentially leading to an overestimation of the PPVs. Another source of variability may be the data used in each study and purpose for which it was originally generated, i.e., for claims/reimbursement versus clinical care. Therefore, findings should be interpreted cautiously, and ideally, validated in general populations to better understand their performance across varying levels of disease prevalence. Finally, the search focused on studies explicitly reporting diagnostic validation, potentially excluding relevant studies that addressed this in broader investigations (i.e., assessed an algorithm accuracy as an intermediate objective as part of an EHR-based study of RA outcomes). A protocol deviation was the omission of grey literature search due the nature of the review and to the expectation that relevant studies would be published primarily in peer-reviewed journals. This systematic review incorporates comprehensive and contemporary evidence from diverse geographic areas. To our knowledge, is the first systematic review to comprehensively synthesise and quantitatively analyse RA and JIA algorithm accuracy in EHRs without geographic restriction across diverse healthcare settings. It adheres to PRISMA guidelines, systematically categorised algorithms by restrictiveness to facilitate clinically meaningful comparisons, and used the QUADAS-2 tool for transparent quality assessment. 4.3 Conclusions This review highlights the variability in accuracy of algorithms used to identify RA and JIA in EHRs. Algorithms combining diagnostic codes and prescription data, particularly DMARDs, or a rheumatologist diagnosis demonstrated the highest overall performance, with a good balance of sensitivity, specificity, and PPV. Less restrictive algorithms may aid initial case identification but require refinement for specific research purposes. The choice of algorithm should be tailored to the study objective and data source. Future efforts should prioritise external validation of high-performing algorithms across diverse settings to improve standardisation and reliability in real-world data research. Data Availability This research is based on published literature. All data used in this research are already included in the article or the supplementary material. The data extraction template is available at the Open Science Framework: OSF | Data Extraction Template.xlsx . Availability of data This research is based on published literature. All data used in this research are already included in the article or the supplementary material. The data extraction template is available at the Open Science Framework: OSF | Data Extraction Template.xlsx . Acknowledgment The authors acknowledge the use of large language model to assist with English grammar and spelling during the preparation of the manuscript. Footnotes Grant/Financial support This research was funded by the Health Research Board Applied Programme Grant Awards (APRO-2023-028) scheme. Declaration of interests Authors declare no potential conflict of interests. References 1. ↵ Agarwal SK . Core management principles in rheumatoid arthritis to help guide managed care professionals . J Manag Care Pharm . 2011 ; 17 : S03 – 8 . OpenUrl PubMed 2. ↵ Abramowicz S , Kim S , Prahalad S , et al. Juvenile arthritis: current concepts in terminology, etiopathogenesis, diagnosis, and management . Int J Oral Maxillofac Surg . 2016 ; 45 : 801 – 812 . OpenUrl PubMed 3. ↵ Hochberg MC . Adult and juvenile rheumatoid arthritis: current epidemiologic concepts . Epidemiol Rev . 1981 ; 3 : 27 – 44 . OpenUrl PubMed Web of Science 4. ↵ Sangha O . Epidemiology of rheumatic diseases . Rheumatology (Oxford) . 2000 ; 39 : 3 – 12 . OpenUrl CrossRef PubMed Web of Science 5. ↵ Vinet E , Chakravarty EF , Simard JF , et al. Use of administrative databases to assess reproductive health issues in rheumatic diseases . Rheumatic Disease Clinics of North America . 2018 ; 44 : 327 – 336 . OpenUrl PubMed 6. ↵ Schneeweiss S , Avorn J . A review of uses of health care utilization databases for epidemiologic research on therapeutics . J Clin Epidemiol . 2005 ; 58 : 323 – 337 . OpenUrl CrossRef PubMed Web of Science 7. ↵ De Coster C , Quan H , Finlayson A , et al. Identifying priorities in methodological research using ICD-9-CM and ICD-10 administrative data: report from an international consortium . BMC Health Serv Res . 2006 ; 6 : 77 . OpenUrl CrossRef PubMed 8. ↵ Benchimol EI , Manuel DG , To T , et al. Development and use of reporting guidelines for assessing the quality of validation studies of health administrative data . J Clin Epidemiol . 2011 ; 64 : 821 – 829 . OpenUrl CrossRef PubMed 9. ↵ Widdifield J , Bombardier C , Bernatsky S , et al. An administrative data validation study of the accuracy of algorithms for identifying rheumatoid arthritis: the influence of the reference standard on algorithm performance . BMC Musculoskelet Disord . 2014 ; 15 : 216 . OpenUrl CrossRef PubMed 10. ↵ Kim SY , Servi A , Polinski JM , et al. Validation of rheumatoid arthritis diagnoses in health care utilization data . Arthritis Res Ther . 2011 ; 13 : R32 . OpenUrl CrossRef PubMed 11. ↵ Carrara G , Scirè CA , Zambon A , et al. A validation study of a new classification algorithm to identify rheumatoid arthritis using administrative health databases: case–control and cohort diagnostic accuracy studies. Results from the RECord linkage on rheumatic diseases study of the Italian society for rheumatology . BMJ Open . 2015 ; 5 : e006029 . OpenUrl Abstract / FREE Full Text 12. ↵ Chung CP , Rohan P , Krishnaswami S , et al. A systematic review of validated methods for identifying patients with rheumatoid arthritis using administrative or claims data . Vaccine . 2013 ; 31 : K41 – 61 . OpenUrl CrossRef PubMed Web of Science 13. ↵ Carnahan RM , Moores KG . Mini-Sentinel’s systematic reviews of validated methods for identifying health outcomes using administrative and claims data: methods and lessons learned . Pharmacoepidemiol Drug Saf . 2012 ; 21 : 82 – 89 . OpenUrl PubMed 14. ↵ Salameh JP , Bossuyt PM , McGrath TA , et al. Preferred reporting items for systematic review and meta-analysis of diagnostic test accuracy studies (PRISMA-DTA): explanation, elaboration, and checklist . The BMJ . 2020 ; 370 : m2632 . OpenUrl 15. ↵ Widdifield J , Labrecque J , Lix L , et al. Systematic review and critical appraisal of validation studies to identify rheumatic diseases in health administrative databases . Arthritis Care Res (Hoboken ). 2013 ; 65 : 1490 – 1503 . OpenUrl PubMed 16. ↵ McPheeters ML , Sathe NA , Jerome RN , et al. Methods for systematic reviews of administrative database studies capturing health outcomes of interest . Vaccine . 2013 ; 31 : K2 – 6 . OpenUrl CrossRef PubMed 17. ↵ Cohen JF , Korevaar DA , Altman DG , et al. STARD 2015 guidelines for reporting diagnostic accuracy studies: explanation and elaboration . BMJ Open . 2016 ; 14 : e012799 . OpenUrl 18. ↵ Nelson DE , Holtzman D , Bolen J , et al. Reliability and validity of measures from the behavioral risk factor surveillance system (BRFSS) . Soz Praventivmed . 2001 ; 46 : S3 – 42 . OpenUrl CrossRef PubMed Web of Science 19. ↵ Deeks J , Bossuyt P , Gatsonis C Reitsma H , Rutjes A , Whiting P , Vlassov V , Leeflang M , Deeks J. Chapter 9: Assessing methodological quality . In: Deeks J , Bossuyt P , Gatsonis C , editors. Cochrane Handbook of Systematic Reviews of Diagnostic Test Accuracy . Version 1.0. The Cochrane Collaboration ; 2009 . p. 1 - 24 . 20. ↵ Shrestha S , Dave AJ , Losina E , et al. Diagnostic accuracy of administrative data algorithms in the diagnosis of osteoarthritis: a systematic review . BMC Med Inform Decis Mak . 2016 ; 16 : 82 . OpenUrl PubMed 21. ↵ Deeks JJ , Bossuyt PM , Gatsonics C Macaskill P , Gatsonis C , Deeks J , Harbord R , Takwoingi Y. Chapter 10: Analysing and presenting results . In Deeks JJ , Bossuyt PM , Gatsonics C , editors. Cochrane Handbook for Systematic Reviews of Diagnostic Test Accuracy . Version 1.0. The Cochrane Collaboration ; 2010 . p. 1 – 61 . 22. Deeks JJ , Bossuyt PM , Leeflang MM , Takwoingi Y Takwoingi Y , Dendukuri N , Schiller I , Rucker G , Jones HE , Partlett C , Macaskill P. Supplementary material 1 to chapter 10: code for undertaking meta-analysis . In Deeks JJ , Bossuyt PM , Leeflang MM , Takwoingi Y , editors. Cochrane Handbook for Systematic Reviews of Diagnostic Test Accuracy . Version 2.0. Cochrane ; 2023 . p. 1 – 83 . 23. ↵ Barker TH , Migliavaca CB , Stein C , et al. Conducting proportional meta-analysis in different types of systematic reviews: a guide for synthesisers of evidence . BMC Med Res Methodol . 2021 ; 21 : 189 . OpenUrl CrossRef PubMed 24. ↵ Cho SK , Sung YK , Choi CB , et al. Development of an algorithm for identifying rheumatoid arthritis in the Korean national health insurance claims database . Rheumatol Int . 2013 ; 33 : 2985 – 2992 . OpenUrl PubMed 25. ↵ Curtis JR , Xie F , Chen L , et al. Evaluation of a methodologic approach to define an inception cohort of rheumatoid arthritis patients using administrative data . Arthritis Care Res (Hoboken ). 2018 ; 70 : 1541 – 1545 . OpenUrl PubMed 26. ↵ Fowles JB , Lawthers AG , Weiner JP , et al. Agreement between diagnosis in physicians’ medical records and Medicare part B claims data . Health Care Financ Rev . 1995 ; 16 : 189 – 199 . OpenUrl PubMed 27. ↵ Losina E , Barrett J , Baron JA , et al. Accuracy of Medicare claims data for rheumatologic diagnoses in total hip replacement recipients . J Clin Epidemiol . 2003 ; 56 : 515 – 519 . OpenUrl CrossRef PubMed Web of Science 28. ↵ Widdifield J , Bernatsky S , Paterson JM , et al. Accuracy of Canadian health administrative databases in identifying patients with rheumatoid arthritis: a validation study using the medical records of rheumatologists . Arthritis Care Res (Hoboken ). 2013 ; 65 : 1582 – 1591 . OpenUrl PubMed 29. ↵ Allebeck P , Ljungstrorn K , Allander E . Rheumatoid Arthritis in a medical information system: how valid is the diagnosis? Scand J Soc Med . 1983 ; 11 : 27 – 32 . OpenUrl PubMed Web of Science 30. ↵ Linauskas A , Overvad K , Johansen MB , et al. Positive predictive value of first-time rheumatoid arthritis diagnoses and their serological subtypes in the Danish national patient registry . Clin Epidemiol . 2018 ; 10 : 1709 – 1720 . OpenUrl PubMed 31. ↵ Pedersen M , Klarlund M , Jacobsen S , et al. Validity of rheumatoid arthritis diagnoses in the Danish national patient registry . Eur J Epidemiol . 2004 ; 19 : 1097 – 1103 . OpenUrl CrossRef PubMed Web of Science 32. ↵ Carroll RJ , Thompson WK , Eyler AE , et al. Portability of an algorithm to identify rheumatoid arthritis in electronic health records . J Am Med Inform Assoc . 2012 ; 19 : e162 – 169 . OpenUrl CrossRef PubMed 33. ↵ Huang S , Huang J , Cai T , et al. Impact of ICD10 and secular changes on electronic medical record rheumatoid arthritis algorithms . Rheumatology (United Kingdom ). 2020 ; 59 : 3759 – 3766 . OpenUrl 34. ↵ Liao KP , Cai T , Gainer V , et al. Electronic medical records for discovery research in rheumatoid arthritis . Arthritis Care Res (Hoboken) . 2010 ; 62 : 1120 – 1127 . OpenUrl CrossRef PubMed 35. ↵ Peterson HM , Vela KL , Barnado A , et al. Developing electronic health record algorithms that accurately identify patients with juvenile idiopathic arthritis . Semin Arthritis Rheum . 2023 ; 59 : 152167 . OpenUrl PubMed 36. ↵ Wei WQ , Teixeira PL , Mo H , et al. Combining billing codes, clinical notes, and medications from electronic health records provides superior phenotyping performance . J Am Med Inform Assoc . 2016 ; 23 : e20 – 27 . OpenUrl CrossRef PubMed 37. ↵ Zheng HW , Ranganath VK , Perry LC , et al. Evaluation of an automated phenotyping algorithm for rheumatoid arthritis . J Biomed Inform . 2022 ; 135 : 104214 . OpenUrl PubMed 38. ↵ Kronzer VL , Wang L , Liu H , et al. Investigating the impact of disease and health record duration on the eMERGE algorithm for rheumatoid arthritis . J Am Med Inform Assoc . 2020 ; 27 : 601 – 605 . OpenUrl PubMed 39. ↵ Harrold LR , Salman C , Shoor S , et al. Incidence and prevalence of juvenile idiopathic arthritis among children in a managed care population, 1996-2009 . Journal of Rheumatology . 2013 ; 40 : 1218 – 1225 . OpenUrl Abstract / FREE Full Text 40. ↵ Ibfelt EH , Sørensen J , Jensen DV , et al. Validity and completeness of rheumatoid arthritis diagnoses in the nationwide DANBIO clinical register and the Danish national patient registry . Clin Epidemiol . 2017 ; 9 : 627 – 632 . OpenUrl CrossRef 41. ↵ Katz JN , Barrett J , Liang MH , et al. Sensitivity and positive predictive value of Medicare part B physician claims for rheumatologic diagnoses and procedures . Arthritis Rheum . 1997 ; 40 : 1594 – 1600 . OpenUrl CrossRef PubMed Web of Science 42. ↵ Paltta J , Heikkilä HK , Pirilä L , et al. The validity of rheumatoid arthritis diagnoses in Finnish biobanks . Scand J Rheumatol . 2023 ; 52 : 1 – 9 . OpenUrl PubMed 43. ↵ Waldenlind K , Eriksson JK , Grewin B , et al. Validation of the rheumatoid arthritis diagnosis in the Swedish national patient register: a cohort study from Stockholm County . BMC Musculoskelet Disord . 2014 ; 15 : 432 . OpenUrl CrossRef PubMed 44. ↵ Hanly JG , Thompson K , Skedgel C . The use of administrative health care databases to identify patients with rheumatoid arthritis . Open Access Rheumatol . 2015 ; 7 : 69 – 75 . OpenUrl PubMed 45. ↵ Shiff NJ , Oen K , Rabbani R , et al. Validation of administrative case ascertainment algorithms for chronic childhood arthritis in Manitoba, Canada . Rheumatol Int . 2017 ; 37 : 1575 – 1584 . OpenUrl PubMed 46. ↵ Stringer E , Bernatsky S . Validity of juvenile idiopathic arthritis diagnoses using administrative health data . Rheumatol Int . 2015 ; 35 : 575 – 579 . OpenUrl PubMed 47. ↵ Thomas SL , Edwards CJ , Smeeth L , et al. How accurate are diagnoses for rheumatoid arthritis and juvenile idiopathic arthritis in the general practice research database? Arthritis Care Res (Hoboken ). 2008 ; 59 : 1314 – 1321 . OpenUrl 48. ↵ Nanji JA , Choi M , Ferrari R , et al. Time to consultation and disease-modifying antirheumatic drug treatment of patients with rheumatoid arthritis - Northern Alberta perspective . Journal of Rheumatology . 2012 ; 39 : 707 – 711 . OpenUrl Abstract / FREE Full Text 49. ↵ Ng B , Aslam F , Petersen NJ , et al. Identification of rheumatoid arthritis patients using an administrative database: a veterans affairs study . Arthritis Care Res (Hoboken ). 2012 ; 64 : 1490 – 1496 . OpenUrl PubMed 50. ↵ Singh JA , Holmgren AR , Noorbaloochi S . Accuracy of veterans administration databases for a diagnosis of rheumatoid arthritis . Arthritis Care Res (Hoboken ). 2004 ; 51 : 952 – 957 . OpenUrl 51. ↵ Almutairi K , Inderjeeth C , Preen DB , et al. The accuracy of administrative health data for identifying patients with rheumatoid arthritis: a retrospective validation study using medical records in western Australia . Rheumatol Int . 2021 ; 41 : 741 – 750 . OpenUrl PubMed 52. ↵ Kubota K , Yoshizawa M , Takahashi S , et al. The validity of the claims-based definition of rheumatoid arthritis evaluated in 64 hospitals in Japan . BMC Musculoskelet Disord . 2021 ; 22 : 373 . OpenUrl PubMed 53. ↵ Convertino I , Cazzato M , Giometto S , et al. Validation of algorithms for selecting rheumatoid arthritis patients in the Tuscan healthcare administrative databases . Sci Rep . 2021 ; 11 : 20314 . OpenUrl PubMed 54. ↵ Moores KG , Sathe NA . A systematic review of validated methods for identifying systemic lupus erythematosus (SLE) using administrative or claims data . Vaccine . 2013 ; 31 : K62 – 73 . OpenUrl CrossRef PubMed Web of Science 55. ↵ Crossfield SSR , Lai LYH , Kingsbury SR , et al. Variation in methods, results and reporting in electronic health record-based studies evaluating routine care in gout: a systematic review . PLoS One . 2019 ; 14 : e0224272 . OpenUrl PubMed 56. ↵ Iyer P , Gao Y , Field EH , et al. Trends in hospitalization rates, major causes of hospitalization, and in-hospital mortality in rheumatoid arthritis in the United States from 2000 to 2014 . ACR Open Rheumatol . 2020 ; 2 : 715 – 724 . OpenUrl PubMed 57. Rai SK , Aviña-Zubieta JA , McCormick N , et al. Trends in gout and rheumatoid arthritis hospitalizations in Canada from 2000 to 2011 . Arthritis Care Res (Hoboken ). 2017 ; 69 : 758 – 762 . OpenUrl CrossRef PubMed 58. ↵ Kiadaliri AA , Englund M. Temporal trends and regional disparity in rheumatoid arthritis and gout hospitalizations in Sweden, 1998–2015 . Clin Rheumatol . 2018 ; 37 : 825 – 830 . OpenUrl PubMed 59. ↵ Aletaha D , Smolen JS . The Rheumatoid arthritis patient in the clinic: comparing more than 1300 consecutive DMARD courses . Rheumatology (Oxford ). 2002 ; 41 : 1367 – 1374 . OpenUrl CrossRef PubMed Web of Science 60. Betts KA , Griffith J , Ganguli A , et al. Economic burden and treatment patterns of cycling between conventional synthetic disease-modifying antirheumatic drugs among biologic-treated patients with rheumatoid arthritis . Clin Ther . 2016 ; 38 : 1205 – 1216 . OpenUrl PubMed 61. ↵ Kim G , Barner JC , Rascati K , et al. Examining time to initiation of biologic disease-modifying antirheumatic drugs and medication adherence and persistence among Texas Medicaid recipients with rheumatoid arthritis . Clin Ther . 2016 ; 38 : 646 – 654 . OpenUrl PubMed 62. ↵ Simeone JC , Liu X , Bhagnani T , et al. Comparison of ICD-9-CM to ICD-10-CM crosswalks derived by physician and clinical coder vs. automated methods . Perspect Health Inf Manag . 2021 ; 18 : 1e . OpenUrl 63. ↵ Nam YH , Mendelsohn AB , Panozzo CA , et al. Health outcomes coding trends in the US food and drug administration’s sentinel system during transition to international classification of diseases-10 coding system: A brief review . Pharmacoepidemiol Drug Saf . 2021 ; 30 : 838 – 842 . OpenUrl PubMed 64. Sugiyama N , Kinjo M , Jinno S , et al. Validation of claims-based algorithms for rheumatoid arthritis in Japan: Results from the VALIDATE-J study . Int J Rheum Dis . 2024 ; 27 : e15001 . OpenUrl PubMed 65. Zhou SM , Fernandez-Gutierrez F , Kennedy J , et al. Defining disease phenotypes in primary care electronic health records by a machine learning approach: a case study in identifying rheumatoid arthritis . PLoS One . 2016 ; 11 : e0154515 . OpenUrl CrossRef PubMed View the discussion thread. Back to top Previous Next Posted June 30, 2025. Download PDF Supplementary Material Data/Code Email Thank you for your interest in spreading the word about medRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following Accuracy of diagnostic codes and algorithms used to identify rheumatoid arthritis and juvenile idiopathic arthritis in electronic health records: systematic review and meta-analysis Message Subject (Your Name) has forwarded a page to you from medRxiv Message Body (Your Name) thought you would like to see this page from the medRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share Accuracy of diagnostic codes and algorithms used to identify rheumatoid arthritis and juvenile idiopathic arthritis in electronic health records: systematic review and meta-analysis Constanza Saka-Herrán , Jessica Bennett , Yara Alkabti , Muhammad Fatir , Barbara Clyne , Caroline McCarthy , Gráinne Tynan , Nikki Dunne , Michelle Flood , Eoghan McCarthy , Frank Moriarty medRxiv 2025.06.30.25330552; doi: https://doi.org/10.1101/2025.06.30.25330552 Share This Article: Copy Citation Tools Accuracy of diagnostic codes and algorithms used to identify rheumatoid arthritis and juvenile idiopathic arthritis in electronic health records: systematic review and meta-analysis Constanza Saka-Herrán , Jessica Bennett , Yara Alkabti , Muhammad Fatir , Barbara Clyne , Caroline McCarthy , Gráinne Tynan , Nikki Dunne , Michelle Flood , Eoghan McCarthy , Frank Moriarty medRxiv 2025.06.30.25330552; doi: https://doi.org/10.1101/2025.06.30.25330552 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Rheumatology Subject Areas All Articles Addiction Medicine (567) Allergy and Immunology (863) Anesthesia (297) Cardiovascular Medicine (4411) Dentistry and Oral Medicine (443) Dermatology (380) Emergency Medicine (606) Endocrinology (including Diabetes Mellitus and Metabolic Disease) (1505) Epidemiology (15205) Forensic Medicine (30) Gastroenterology (1119) Genetic and Genomic Medicine (6574) Geriatric Medicine (666) Health Economics (994) Health Informatics (4511) Health Policy (1365) Health Systems and Quality Improvement (1608) Hematology (537) HIV/AIDS (1263) Infectious Diseases (except HIV/AIDS) (15903) Intensive Care and Critical Care Medicine (1103) Medical Education (620) Medical Ethics (144) Nephrology (666) Neurology (6573) Nursing (345) Nutrition (998) Obstetrics and Gynecology (1139) Occupational and Environmental Health (954) Oncology (3319) Ophthalmology (968) Orthopedics (369) Otolaryngology (420) Pain Medicine (435) Palliative Medicine (129) Pathology (662) Pediatrics (1689) Pharmacology and Therapeutics (691) Primary Care Research (710) Psychiatry and Clinical Psychology (5422) Public and Global Health (9205) Radiology and Imaging (2191) Rehabilitation Medicine and Physical Therapy (1367) Respiratory Medicine (1191) Rheumatology (593) Sexual and Reproductive Health (709) Sports Medicine (529) Surgery (709) Toxicology (99) Transplantation (288) Urology (265) (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9feab4053adadfa9',t:'MTc3OTI3MzQxNg=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();