Recombinant Zoster Vaccination Among US Veterans Receiving Immunosuppressive Medications.

This cross-sectional study investigates rates of recombinant zoster vaccination among US veterans receiving immunosuppressive medications before and after expanded indications for younger adults who are immunocompromised.

Agreement of Medication Information Derived From EHR Data Compared to Medicare Insurance Claims: An Analysis of Biologic Disease-Modifying Antirheumatic Drugs.

PURPOSE: Few studies have reported the agreement between medication information derived from ambulatory EHR data compared to administrative claims for high-cost specialty drugs. We used data from a national EHR-enabled registry, the Rheumatology Informatics System for Effectiveness (RISE), with linked Medicare claims in a population of patients with rheumatoid arthritis (RA) to investigate variations in agreement for different biologic disease-modifying agents (bDMARDs) between two data sources (RISE EHR data vs. Medicare claims), categorized by drug, route of administration, and patient insurance factors (dual eligibility). METHODS: Patients ≥ 65 years old, with ≥ 2 visits in RISE with RA ICD codes ≥ 30 days apart, and continuous enrollment in Medicare Parts B and D in 2017-2018 were included. We classified patients as bDMARD users or nonusers in Medicare claims or EHR data in 2018, and we calculated sensitivity, specificity, positive predicted value (PPV), and negative predicted value (NPV) of EHR data for identifying bDMARD users, using Medicare as the reference standard. We also calculated these metrics after stratifying by clinic-administered (Part B) versus. pharmacy-dispensed (Part D) bDMARDs and by patient dual-eligibility. RESULTS: A total of 26 097 patients were included in the study. Using Medicare claims as the reference standard, EHR data had a sensitivity of 75.0%-90.8% for identifying patients with the same medication and route. PPV for Part B bDMARDs was higher compared with Part D bDMARDs (range 94.3%-97.3% vs. 51.0%-69.6%). We observed higher PPVs for Part D bDMARDs among patients who were dual-eligible (range 82.4%-95.1%). CONCLUSION: The risk of misclassification of drug exposure based on EHR data sources alone is small for Medicare Part B bDMARDs but could be as high as 50% for Part D bDMARDs, in particular for patients who are not dually eligible for Medicare and Medicaid.

Validating claims-based algorithms for a systemic lupus erythematosus diagnosis in Medicare data for informed use of the Lupus Index: a tool for geospatial research.

OBJECTIVE: This study aimed to validate claims-based algorithms for identifying SLE and lupus nephritis (LN) in Medicare data, enhancing the use of the Lupus Index for geospatial research on SLE prevalence and outcomes. METHODS: We retrospectively evaluated the performance of rule-based algorithms using the International Classification of Diseases, 10th Revision (ICD-10) codes to identify SLE and LN in a well-defined prospective longitudinal cohort of patients with and without SLE from a South Carolina registry and rheumatology outpatient clinics. The analysis included comparison of algorithms based on Medicare fee-for-service claims data to these rigorously phenotyped populations. The primary classification for SLE cases was based on the American College of Rheumatology and Systemic Lupus Erythematosus International Collaborating Clinics criteria for SLE and LN. Algorithms were based on the number of ICD-10 codes with and without a 30-day separation in the observation period, including all of 2016-2018. RESULTS: The algorithm using two ICD-10 codes for SLE, with or without a 30-day separation, showed the best overall performance. For LN, specific ICD-10 codes outperformed combinations of SLE and renal/proteinuria codes that were found in ICD-9. CONCLUSIONS: The findings of this study highlight the performance of specific ICD-10 code algorithms in identifying SLE and LN cases within Medicare data, providing a valuable tool for informing use of the Lupus Index. This index allows for improved geographical targeting of clinical resources, health disparity studies and clinical trial site selection. The study underscores the importance of algorithm selection based on research objectives, recommending more specific algorithms for precise tasks like clinical trial site identification and less specific ones for broader applications such as health disparities research.

Limitations in Activities of Daily Living among Individuals with Systemic Lupus Erythematosus.

OBJECTIVE: We aimed to estimate the burden and identify potential correlates of limitations in activities of daily living (ADLs) among persons with systemic lupus erythematosus (SLE). METHODS: Individuals with SLE were recruited from a population-based cohort (10/2019-5/2022) and reported their ability to independently perform various instrumental ADLs (IADLs) and basic ADLs (BADLs) via survey. Limitations were defined as having at least some difficulty performing at least one of the IADLs or BADLs. Descriptive statistics were calculated, and associations [adjusted odds ratios (aORs)] of various participant characteristics with IADL and BADL limitations were assessed with logistic regression adjusting for age, sex, and race. RESULTS: The mean age of the 436 participants was 46.2 years; most were female (91.7%) and Black (82.8%). More than half (56.2%) reported limitations in IADLs, most commonly housekeeping (50.7%), laundry (37.2%), and shopping (33.0%); 43.8% reported limitations in independently performing BADLs, most commonly transferring (26.6%), bathing (25.3%), dressing (24.4%), and continence (22.0%). Higher disease activity (≥ vs.

Patient perceptions of an electronic-health-record-based rheumatoid arthritis outcomes dashboard: a mixed-methods study.

BACKGROUND: Outcome measures are crucial to support a treat-to-target approach to rheumatoid arthritis (RA) care, yet their integration into clinical practice remains inconsistent. We developed an Electronic Heath Record-integrated, patient-facing side-car application to display RA outcomes (disease activity, functional status, pain scores), medications, and lab results during clinical visits ("RA PRO Dashboard"). The study aimed to evaluate patient perceptions and attitudes towards the implementation of a novel patient-facing dashboard during clinical visits using a mixed-methods approach. METHODS: RA patients whose clinicians used the dashboard at least once during their clinical visit were invited to complete a survey regarding its usefulness in care. We also conducted semi-structured interviews with a subset of patients to assess their perceptions of the dashboard. The interviews were transcribed verbatim and analyzed thematically using deductive and inductive techniques. Emerging themes and subthemes were organized into four domains of the Ecological Model of Health. RESULTS: Out of 173 survey respondents, 79% were interested in seeing the dashboard again at a future visit, 71% felt it improved their understanding of their disease, and 65% believed it helped with decision-making about their RA care. Many patients reported that the dashboard helped them discuss their RA symptoms (76%) and medications (72%) with their clinician. Interviews with 29 RA patients revealed 10 key themes: the dashboard was perceived as a valuable visual tool that improved patients' understanding of RA outcome measures, enhanced their involvement in care, and increased their trust in clinicians and the clinic. Common reported limitations included concerns about reliability of RA outcome questionnaires for some RA patients and inconsistent collection and explanation of these measures by clinicians. CONCLUSIONS: In both the quantitative and qualitative components of the study, patients reported that the dashboard improved their understanding of their RA, enhanced patient-clinician communication, supported shared decision-making, and increased patient engagement in care. These findings support the use of dashboards or similar data visualization tools in RA care and can be used in future interventions to address challenges in data collection and patient education.

Low socioeconomic status and female sex are associated with worse functional status in axial spondyloarthritis.

OBJECTIVE: We determined whether socioeconomic status (SES) and sex are associated with functional status (FS) in axial spondyloarthritis (axSpA). METHODS: We conducted a cohort study of patients with axSpA in the Rheumatology Informatics System for Effectiveness (RISE) registry. We performed cross-sectional and longitudinal analyses of FS through the Multi-Dimensional Health Assessment Questionnaire (MDHAQ) using GEE models. Area Deprivation Index (ADI) was used as an SES proxy. The cross-sectional analysis tested for a linear trend across ADI quintiles for MDHAQ. The longitudinal analysis' outcome was functional decline. We reported predictive margins and assessed for interaction with sex. In the longitudinal analysis, we reported odds of functional decline. RESULTS: In the cross-sectional analysis (N=5,658) mean (SD) age was 53.8 years (15.2), 55.8% were female, and 71.4% were non-Hispanic White. Average (SD) MDHAQ was 1.6 (2.0) in men vs. 2.1 (2.2) in women. Predicted mean MDHAQ score was 2.2 (95%CI 1.8-2.7) for the lowest ADI quintile and 1.8 (95%CI 1.4-2.1) for the highest. Women had lower FS compared to men across quintiles. In the longitudinal analysis (N= 2,341) the proportion with FS decline was 14.3% (95% CI 7.6%-25.5%) for the lowest SES quintile compared to 9.6% (95% CI 5.2%-17.1%) for the highest. Women had 1.7 (95%CI 1.3-2.2) times higher odds of functional decline compared to men. There was no interaction with sex. CONCLUSIONS: In this large sample of axSpA patients, those with lower SES had worse FS and functional decline. Women had worse FS than men, initially and over time.

Initiation of glucocorticoids before entering rheumatology care associates with long-term glucocorticoid use in older adults with early rheumatoid arthritis: A joint analysis of Medicare and the Rheumatology Informatics System for Effectiveness (RISE) data.

OBJECTIVE: To assess relationships between the timing of glucocorticoid (GC) initiation, entrance into rheumatology care, and the duration of GC use in older adults with early rheumatoid arthritis (eRA) in the U.S. METHODS: Data from the Rheumatology Informatics System for Effectiveness (RISE) registry and Medicare (2016-2018) were linked. Patients with ≥2 RA ICD codes in RISE were included; the first being the index date which signaled entrance into rheumatology care. GC initiation (between 3 months before to 6 months after the index date) and continuous GC use up to 12 months after the index date were captured using Medicare claims. Cox proportional hazards models with adjustment for confounders assessed differences in the duration of GC use for patients initiating GCs before versus after the index date. Average daily GC doses were estimated. RESULTS: 1,733 patients (67 % female; mean age 76 ± 6 years) were included. 41 % initiated GCs, on average 16 ± 58 days before entering rheumatologic care. The mean duration of GC use was 157 days (95 %-CI 143 to 170). GC initiation before rheumatologic care was associated with longer GC use, even after adjustment for confounders (hazard ratio 0.61; 95 %-CI [0.51 to 0.74]). For patients using GCs for ≥3 months, average daily GC doses were <5 mg/d prednisone equivalent. CONCLUSION: GCs are regularly used in eRA and most often initiated before patients enter rheumatology care. Long-term, low-dose GC use is common and associated with initiation before rheumatology care. Earlier referral to rheumatology might reduce GC exposure among U.S. patients with eRA.

Leveraging the Consolidated Framework for Implementation Research (CFIR) to Develop the American College of Rheumatology's Toolkit for Implementation of Rheumatoid Arthritis Outcome Measures in Clinical Practice: A Qualitative Study.

OBJECTIVE: Despite the recognized benefits of collecting rheumatoid arthritis (RA) outcomes measures, their use in routine care is inconsistent. Using the Consolidated Framework for Implementation Research (CFIR), we conducted semi-structured interviews with United States rheumatologists and practice personnel to assess workflows, opportunities, and challenges in collecting RA outcome measures. Using insights from interviews, we developed the RA Measures Toolkit to enhance their utilization in clinical practice. METHODS: We invited 138 RISE registry practices and 5 academic medical centers with ≥ 30 patients eligible for RA outcome measures to participate in the study. Practices were classified based on their performance in quality payment programs. Recorded interviews were transcribed verbatim and analyzed thematically using deductive and inductive techniques. The findings were used to create the RA Measures Toolkit. RESULTS: We conducted 20 interviews with 38 participants across 20 practices. Key themes within the CFIR domains highlighted the challenges and best practices in RA outcome measure collection and included: 1) Process: the variability in practices' use of RA outcome measures and the importance of streamlined workflows, 2) Intervention: challenges of integrating PROs into electronic health records (EHRs), and 3) Individual characteristics: importance of clinic culture around quality improvement. Using this data, we developed the RA Toolkit, a multimedia online resource, featuring guidelines, best practices, and educational resources to improve the efficiency of current workflows and to enhance patient care. CONCLUSION: This study identifies critical gaps in the collection of RA outcome measures in U.S. rheumatology practices and provides actionable recommendations and resources to address challenges via the RA Toolkit.

Cell-Specific Transposable Element and Gene Expression Analysis Across Systemic Lupus Erythematosus Phenotypes.

OBJECTIVE: There is an established yet unexplained link between interferon (IFN) and systemic lupus erythematosus (SLE). The expression of sequences derived from transposable elements (TEs) may contribute to SLE phenotypes, specifically production of type I IFNs and generation of autoantibodies. METHODS: We profiled cell-sorted RNA-sequencing data (CD4+ T cells, CD14+ monocytes, CD19+ B cells, and natural killer cells) from peripheral blood mononuclear cells of 120 patients with SLE and quantified TE expression identifying 27,135 TEs. We tested for differential TE expression across 10 SLE phenotypes, including autoantibody production and disease activity. RESULTS: We found 731 differentially expressed (DE) TEs across all SLE phenotypes that were mostly cell specific and phenotype specific. DE TEs were enriched for specific families and open reading frames of viral genes encoded in TE sequences. Increased expression of DE TEs was associated with genes involved in antiviral activity, such as LY6E, ISG15, and TRIM22, and pathways such as IFN signaling. CONCLUSION: These findings suggest that expression of TEs contributes to activation of SLE-related mechanisms in a cell-specific manner, which can impact disease diagnostics and therapeutics.

Patterns of Infliximab Biosimilar Uptake for Medicare, Medicaid, and Private Insurance from 2016 to 2022.

OBJECTIVE: Biosimilars have the potential to reduce spending on biologic drugs, yet uptake has been slower than anticipated. We investigated how successive introductions of infliximab biosimilars influenced their adoption by major US insurance providers. METHODS: Data came from the Rheumatology Informatics System for Effectiveness, a national registry with electronic health records from more than 1,100 US rheumatologists. All infliximab administrations (bio-originator or biosimilar) to patients aged ≥18 years from April 2016 to September 2022 were included. We used an interrupted time series to model the effect of each infliximab biosimilar release (infliximab-dyyb, November 2016; infliximab-adba, July 2017; and infliximab-axxq, July 2020) on uptake across Medicare, Medicaid, and private insurers. RESULTS: With the first and second biosimilar releases, biosimilar uptake rose slowly, with average annual increases of ≤5% from 2016 to June 2020 (Medicare 3.2%, Medicaid 5.2%, and private insurance 1.8%). With the third biosimilar release in July 2020, the average annual increase reached 13% for Medicaid and 16.4% for private insurance but remained low for Medicare (5.6%). By September 2022, uptake was higher for Medicaid (43.8%) and private insurance (38.5%) than for Medicare (24%). CONCLUSION: Our results have two key findings for policy makers. First, our results suggest that one or two biosimilars may not generate enough competition to speed adoption rates for biosimilars. Second, Medicare, which covers most patients receiving biologics nationally, had slow adoption rates even after the third biosimilar was introduced. Policy levers to speed adoption among Medicare beneficiaries are needed.

Development and application of Breadth-Depth-Context (BDC), a conceptual framework for measuring technology engagement with a qualified clinical data registry.

Objectives: Despite the proliferation of dashboards that display performance data derived from Qualified Clinical Data Registries (QCDR), the degree to which clinicians and practices engage with such dashboards has not been well described. We aimed to develop a conceptual framework for assessing user engagement with dashboard technology and to demonstrate its application to a rheumatology QCDR. Materials and Methods: We developed the BDC (Breadth-Depth-Context) framework, which included concepts of breadth (derived from dashboard sessions), depth (derived from dashboard actions), and context (derived from practice characteristics). We demonstrated its application via user log data from the American College of Rheumatology's Rheumatology Informatics System for Effectiveness (RISE) registry to define engagement profiles and characterize practice-level factors associated with different profiles. Results: We applied the BDC framework to 213 ambulatory practices from the RISE registry in 2020-2021, and classified practices into 4 engagement profiles: not engaged (8%), minimally engaged (39%), moderately engaged (34%), and most engaged (19%). Practices with more patients and with specific electronic health record vendors (eClinicalWorks and eMDs) had a higher likelihood of being in the most engaged group, even after adjusting for other factors. Discussion: We developed the BDC framework to characterize user engagement with a registry dashboard and demonstrated its use in a specialty QCDR. The application of the BDC framework revealed a wide range of breadth and depth of use and that specific contextual factors were associated with nature of engagement. Conclusion: Going forward, the BDC framework can be used to study engagement with similar dashboards.

Transcobalamin receptor antibodies in autoimmune vitamin B12 central deficiency.

Vitamin B12 is critical for hematopoiesis and myelination. Deficiency can cause neurologic deficits including loss of coordination and cognitive decline. However, diagnosis relies on measurement of vitamin B12 in the blood, which may not accurately reflect the concentration in the brain. Using programmable phage display, we identified an autoantibody targeting the transcobalamin receptor (CD320) in a patient with progressive tremor, ataxia, and scanning speech. Anti-CD320 impaired cellular uptake of cobalamin (B12) in vitro by depleting its target from the cell surface. Despite a normal serum concentration, B12 was nearly undetectable in her cerebrospinal fluid (CSF). Immunosuppressive treatment and high-dose systemic B12 supplementation were associated with increased B12 in the CSF and clinical improvement. Optofluidic screening enabled isolation of a patient-derived monoclonal antibody that impaired B12 transport across an in vitro model of the blood-brain barrier (BBB). Autoantibodies targeting the same epitope of CD320 were identified in seven other patients with neurologic deficits of unknown etiology, 6% of healthy controls, and 21.4% of a cohort of patients with neuropsychiatric lupus. In 132 paired serum and CSF samples, detection of anti-CD320 in the blood predicted B12 deficiency in the brain. However, these individuals did not display any hematologic signs of B12 deficiency despite systemic CD320 impairment. Using a genome-wide CRISPR screen, we found that the low-density lipoprotein receptor serves as an alternative B12 uptake pathway in hematopoietic cells. These findings dissect the tissue specificity of B12 transport and elucidate an autoimmune neurologic condition that may be amenable to immunomodulatory treatment and nutritional supplementation.

Structuring medication signeturs as a language regression task: comparison of zero- and few-shot GPT with fine-tuned models.

Importance: Electronic health record textual sources such as medication signeturs (sigs) contain valuable information that is not always available in structured form. Commonly processed through manual annotation, this repetitive and time-consuming task could be fully automated using large language models (LLMs). While most sigs include simple instructions, some include complex patterns. Objectives: We aimed to compare the performance of GPT-3.5 and GPT-4 with smaller fine-tuned models (ClinicalBERT, BlueBERT) in extracting the average daily dose of 2 immunomodulating medications with frequent complex sigs: hydroxychloroquine, and prednisone. Methods: Using manually annotated sigs as the gold standard, we compared the performance of these models in 702 hydroxychloroquine and 22 104 prednisone prescriptions. Results: GPT-4 vastly outperformed all other models for this task at any level of in-context learning. With 100 in-context examples, the model correctly annotates 94% of hydroxychloroquine and 95% of prednisone sigs to within 1 significant digit. Error analysis conducted by 2 additional manual annotators on annotator-model disagreements suggests that the vast majority of disagreements are model errors. Many model errors relate to ambiguous sigs on which there was also frequent annotator disagreement. Discussion: Paired with minimal manual annotation, GPT-4 achieved excellent performance for language regression of complex medication sigs and vastly outperforms GPT-3.5, ClinicalBERT, and BlueBERT. However, the number of in-context examples needed to reach maximum performance was similar to GPT-3.5. Conclusion: LLMs show great potential to rapidly extract structured data from sigs in no-code fashion for clinical and research applications.

Proton Pump Inhibitor Use and Bone Health in Patients With Rheumatic Diseases: A Cross-Sectional Study.

OBJECTIVE: To assess the effect of proton pump inhibitor (PPI) use on bone mineral density (BMD) and bone microarchitecture as measured by the trabecular bone score (TBS) in patients with inflammatory rheumatic and musculoskeletal diseases (iRMDs). METHODS: Cross-sectional data from a prospective single-center cohort (2015 to 2022) of patients with iRMDs were used to evaluate 3 co-primary outcomes: BMD of the left femoral neck and the lumbar spine (as T-scores) and the TBS. Inverse probability weighting adjusted for numerous confounders including age, sex, body mass index, current and cumulative glucocorticoid (GC) dose, C-reactive protein levels, disability, and others. Analyses were based on general linear models, following a prespecified statistical analysis plan. RESULTS: The study included 1495 patients (75% women; mean age, 62.6±13.1 years; 49% and 63% with regular PPI and GC use, respectively). The PPI users had lower BMD at both spine (adjusted contrast -0.25; 95% CI, -0.47 to -0.04; P=.02) and femoral neck (-0.17 [-0.35 to 0.01]; P=.07). Differences between PPI users and nonusers were statistically significant only in patients concurrently using GCs at more than 7.5 mg/d prednisone equivalent. The TBS was similar in PPI users and nonusers (adjusted contrast, 0.00 [-0.04 to 0.04]; P=.97). CONCLUSION: Our results suggest that PPIs lead to a loss of BMD rather than an impairment of bone microarchitecture in patients with iRMDs. The negative association between PPI use and BMD appears to be dependent on concurrent GC use. Clinicians should carefully review the indication for PPI use in patients with iRMDs, especially in those receiving higher dose GCs.

Positive psychosocial factors may protect against perceived stress in people with systemic lupus erythematosus with and without trauma history.

OBJECTIVE: Trauma history is associated with SLE onset and worse patient-reported outcomes; perceived stress is associated with greater SLE disease activity. Stress perceptions vary in response to life events and may be influenced by psychosocial factors. In an SLE cohort, we examined whether stressful events associated with perceived stress, whether psychosocial factors affected perceived stress, and whether these relationships varied by prior trauma exposure. METHODS: This is a cross-sectional analysis of data from the California Lupus Epidemiology Study, an adult SLE cohort. Multivariable linear regression analyses controlling for age, gender, educational attainment, income, SLE damage, comorbid conditions, glucocorticoids ≥7.5 mg/day and depression examined associations of recent stressful events (Life Events Inventory) and positive (resilience, self-efficacy, emotional support) and negative (social isolation) psychosocial factors with perceived stress. Analyses were stratified by lifetime trauma history (Brief Trauma Questionnaire (BTQ)) and by adverse childhood experiences (ACEs) in a subset. RESULTS: Among 242 individuals with SLE, a greater number of recent stressful events was associated with greater perceived stress (beta (95% CI)=0.20 (0.07 to 0.33), p=0.003). Positive psychosocial factor score representing resilience, self-efficacy and emotional support was associated with lower perceived stress when accounting for number of stressful events (-0.67 (-0.94 to -0.40), p<0.0001); social isolation was associated with higher stress (0.20 (0.14 to 0.25), p<0.0001). In analyses stratified by BTQ trauma and ACEs, associations of psychosocial factors and perceived stress were similar between groups. However, the number of recent stressful events was significantly associated with perceived stress only for people with BTQ trauma (0.17 (0.05 to 0.29), p=0.0077) and ACEs (0.37 (0.15 to 0.58), p=0.0011). CONCLUSION: Enhancing positive and lessening negative psychosocial factors may mitigate deleterious perceived stress, which may improve outcomes in SLE, even among individuals with a history of prior trauma who may be more vulnerable to recent stressful events.

Using the technology acceptance model to assess clinician perceptions and experiences with a rheumatoid arthritis outcomes dashboard: qualitative study.

BACKGROUND: Improving shared decision-making using a treat-to-target approach, including the use of clinical outcome measures, is important to providing high quality care for rheumatoid arthritis (RA). We developed an Electronic Health Record (EHR) integrated, patient-facing sidecar dashboard application that displays RA outcomes, medications, and lab results for use during clinical visits ("RA PRO dashboard"). The purpose of this study was to assess clinician perceptions and experiences using the dashboard in a university rheumatology clinic. METHODS: We conducted focus group (FG) discussions with clinicians who had access to the dashboard as part of a randomized, stepped-wedge pragmatic trial. FGs explored clinician perceptions towards the usability, acceptability, and usefulness of the dashboard. FG data were analyzed thematically using deductive and inductive techniques; generated themes were categorized into the domains of the Technology Acceptance Model (TAM). RESULTS: 3 FG discussions were conducted with a total of 13 clinicians. Overall, clinicians were enthusiastic about the dashboard and expressed the usefulness of visualizing RA outcome trajectories in a graphical format for motivating patients, enhancing patient understanding of their RA outcomes, and improving communication about medications. Major themes that emerged from the FG analysis as barriers to using the dashboard included inconsistent collection of RA outcomes leading to sparse data in the dashboard and concerns about explaining RA outcomes, especially to patients with fibromyalgia. Other challenges included time constraints and technical difficulties refreshing the dashboard to display real-time data. Methods for integrating the dashboard into the visit varied: some clinicians used the dashboard at the beginning of the visit as they documented RA outcomes; others used it at the end to justify changes to therapy; and a few shared it only with stable patients. CONCLUSIONS: The study provides valuable insights into clinicians' perceptions and experiences with the RA PRO dashboard. The dashboard showed promise in enhancing patient-clinician communication, shared decision-making, and overall acceptance among clinicians. Addressing challenges related to data collection, education, and tailoring dashboard use to specific patient populations will be crucial for maximizing its potential impact on RA care. Further research and ongoing improvements in dashboard design and implementation are warranted to ensure its successful integration into routine clinical practice.

Development and validation of a risk scoring system to identify patients with lupus nephritis in electronic health record data.

OBJECTIVE: Accurate identification of lupus nephritis (LN) cases is essential for patient management, research and public health initiatives. However, LN diagnosis codes in electronic health records (EHRs) are underused, hindering efficient identification. We investigated the current performance of International Classification of Diseases (ICD) codes, 9th and 10th editions (ICD9/10), for identifying prevalent LN, and developed scoring systems to increase identification of LN that are adaptable to settings with and without LN ICD codes. METHODS: Training and test sets derived from EHR data from a large health system. An external set comprised data from the EHR of a second large health system. Adults with ICD9/10 codes for SLE were included. LN cases were ascertained through manual chart reviews conducted by rheumatologists. Two definitions of LN were used: strict (definite LN) and inclusive (definite, potential or diagnostic uncertainty). Gradient boosting models including structured EHR fields were used for predictor selection. Two logistic regression-based scoring systems were developed ('LN-Code' included LN ICD codes and 'LN-No Code' did not), calibrated and validated using standard performance metrics. RESULTS: A total of 4152 patients from University of California San Francisco Medical Center and 370 patients from Zuckerberg San Francisco General Hospital and Trauma Center met the eligibility criteria. Mean age was 50 years, 87% were female. LN diagnosis codes demonstrated low sensitivity (43-73%) but high specificity (92-97%). LN-Code achieved an area under the curve (AUC) of 0.93 and a sensitivity of 0.88 for identifying LN using the inclusive definition. LN-No Code reached an AUC of 0.91 and a sensitivity of 0.95 (0.97 for the strict definition). Both scoring systems had good external validity, calibration and performance across racial and ethnic groups. CONCLUSIONS: This study quantified the underutilisation of LN diagnosis codes in EHRs and introduced two adaptable scoring systems to enhance LN identification. Further validation in diverse healthcare settings is essential to ensure their broader applicability.