Electronic Health Record Data Research Articles

Artificial intelligence-assisted automated heart failure detection and classification from electronic health records.

Electronic health records (EHR) linked to Digital Imaging and Communications in Medicine (DICOM), biological specimens, and deep learning (DL) algorithms could potentially improve patient care through automated case detection and surveillance. We hypothesized that by applying keyword searches to routinely stored EHR, in conjunction with AI-powered automated reading of DICOM echocardiography images and analysing biomarkers from routinely stored plasma samples, we were able to identify heart failure (HF) patients. We used EHR data between 1993 and 2021 from Tayside and Fife (~20% of the Scottish population). We implemented a keyword search strategy complemented by filtering based on International Classification of Diseases (ICD) codes and prescription data to EHR data set. We then applied DL for the automated interpretation of echocardiographic DICOM images. These methods were then integrated with the analysis of routinely stored plasma samples to identify and categorize patients into HF with reduced ejection fraction (HFrEF), HF with preserved ejection fraction (HFpEF), and controls without HF. The final diagnosis was verified through a manual review of medical records, measured natriuretic peptides in stored blood samples, and by comparing clinical outcomes among groups. In our study, we selected the patient cohort through an algorithmic workflow. This process started with 60850 EHR data and resulted in a final cohort of 578 patients, divided into 186 controls, 236 with HFpEF, and 156 with HFrEF, after excluding individuals with mismatched data or significant valvular heart disease. The analysis of baseline characteristics revealed that compared with controls, patients with HFrEF and HFpEF were generally older, had higher BMI, and showed a greater prevalence of co-morbidities such as diabetes, COPD, and CKD. Echocardiographic analysis, enhanced by DL, provided high coverage, and detailed insights into cardiac function, showing significant differences in parameters such as left ventricular diameter, ejection fraction, and myocardial strain among the groups. Clinical outcomes highlighted a higher risk of hospitalization and mortality for HF patients compared with controls, with particularly elevated risk ratios for both HFrEF and HFpEF groups. The concordance between the algorithmic selection of patients and manual validation demonstrated high accuracy, supporting the effectiveness of our approach in identifying and classifying HF subtypes, which could significantly impact future HF diagnosis and management strategies. Our study highlights the feasibility of combining keyword searches in EHR, DL automated echocardiographic interpretation, and biobank resources to identify HF subtypes.

Characterization of Post-COVID-19 Definitions and Clinical Coding Practices: Longitudinal Study.

Post-COVID-19 condition (colloquially known as "long COVID-19") characterized as postacute sequelae of SARS-CoV-2 has no universal clinical case definition. Recent efforts have focused on understanding long COVID-19 symptoms, and electronic health record (EHR) data provide a unique resource for understanding this condition. The introduction of the International Classification of Diseases, Tenth Revision (ICD-10) code U09.9 for "Post COVID-19 condition, unspecified" to identify patients with long COVID-19 has provided a method of evaluating this condition in EHRs; however, the accuracy of this code is unclear. This study aimed to characterize the utility and accuracy of the U09.9 code across 3 health care systems-the Veterans Health Administration, the Beth Israel Deaconess Medical Center, and the University of Pittsburgh Medical Center-against patients identified with long COVID-19 via a chart review by operationalizing the World Health Organization (WHO) and Centers for Disease Control and Prevention (CDC) definitions. Patients who were COVID-19 positive with either a U07.1 ICD-10 code or positive polymerase chain reaction test within these health care systems were identified for chart review. Among this cohort, we sampled patients based on two approaches: (1) with a U09.9 code and (2) without a U09.9 code but with a new onset long COVID-19-related ICD-10 code, which allows us to assess the sensitivity of the U09.9 code. To operationalize the long COVID-19 definition based on health agency guidelines, symptoms were grouped into a "core" cluster of 11 commonly reported symptoms among patients with long COVID-19 and an extended cluster that captured all other symptoms by disease domain. Patients having ≥2 symptoms persisting for ≥60 days that were new onset after their COVID-19 infection, with ≥1 symptom in the core cluster, were labeled as having long COVID-19 per chart review. The code's performance was compared across 3 health care systems and across different time periods of the pandemic. Overall, 900 patient charts were reviewed across 3 health care systems. The prevalence of long COVID-19 among the cohort with the U09.9 ICD-10 code based on the operationalized WHO definition was between 23.2% and 62.4% across these health care systems. We also evaluated a less stringent version of the WHO definition and the CDC definition and observed an increase in the prevalence of long COVID-19 at all 3 health care systems. This is one of the first studies to evaluate the U09.9 code against a clinical case definition for long COVID-19, as well as the first to apply this definition to EHR data using a chart review approach on a nationwide cohort across multiple health care systems. This chart review approach can be implemented at other EHR systems to further evaluate the utility and performance of the U09.9 code.

An Electronic Health Record Model for Predicting Risk of Hepatic Fibrosis in Primary Care Patients.

One challenge for primary care providers caring for patients with nonalcoholic fatty liver disease is to identify those at the highest risk for clinically significant liver disease. To derive a risk stratification tool using variables from structured electronic health record (EHR) data for use in populations which are disproportionately affected with obesity and diabetes. We used data from 344 participants who underwent Fibroscan examination to measure liver fat and liver stiffness measurement [LSM]. Using two approaches, multivariable logistic regression and random forest classification, we assessed risk factors for any hepatic fibrosis (LSM > 7kPa) and significant hepatic fibrosis (> 8kPa). Possible predictors included data from the EHR for age, gender, diabetes, hypertension, FIB-4, body mass index (BMI), LDL, HDL, and triglycerides. Of 344 patients (56.4% women), 34 had any hepatic fibrosis, and 15 significant hepatic fibrosis. Three variables (BMI, FIB-4, diabetes) were identified from both approaches. When we used variable cut-offs defined by Youden's index, the final model predicting any hepatic fibrosis had an AUC of 0.75 (95% CI 0.67-0.84), NPV of 91.5% and PPV of 40.0%. The final model with variable categories based on standard clinical thresholds (i.e., BMI ≥ 30kg/m2; FIB-4 ≥ 1.45) had lower discriminatory ability (AUC 0.65), but higher PPV (50.0%) and similar NPV (91.3%). We observed similar findings for predicting significant hepatic fibrosis. Our results demonstrate that standard thresholds for clinical risk factors/biomarkers may need to be modified for greater discriminatory ability among populations with high prevalence of obesity and diabetes.

Computable phenotype for diagnostic error: developing the data schema for application of symptom-disease pair analysis of diagnostic error (SPADE).

Diagnostic errors are the leading cause of preventable harm in clinical practice. Implementable tools to quantify and target this problem are needed. To address this gap, we aimed to generalize the Symptom-Disease Pair Analysis of Diagnostic Error (SPADE) framework by developing its computable phenotype and then demonstrated how that schema could be applied in multiple clinical contexts. We created an information model for the SPADE processes, then mapped data fields from electronic health records (EHR) and claims data in use to that model to create the SPADE information model (intention) and the SPADE computable phenotype (extension). Later we validated the computable phenotype and tested it in four case studies in three different health systems to demonstrate its utility. We mapped and tested the SPADE computable phenotype in three different sites using four different case studies. We showed that data fields to compute an SPADE base measure are fully available in the EHR Data Warehouse for extraction and can operationalize the SPADE framework from provider and/or insurer perspective, and they could be implemented on numerous health systems for future work in monitor misdiagnosis-related harms. Data for the SPADE base measure is readily available in EHR and administrative claims. The method of data extraction is potentially universally applicable, and the data extracted is conveniently available within a network system. Further study is needed to validate the computable phenotype across different settings with different data infrastructures.

Individual Trajectories of Specialist Substance Use Disorder and Mental Health Treatment Utilization Among Young Adults With Substance Use Problems: A Cohort Study

Objective The aim of the study was to identify groups of young adults with distinct longitudinal patterns of use of treatment for substance use disorders and mental health (MH) problems and to investigate potential explanatory factors for different patterns of treatment use over time, including sociodemographic factors. Methods The sample consisted of 447 young adults aged 16–29 years who entered long-term residential substance use disorder treatment facilities in Norway from 2011 to 2016. In this study, we obtained data collected by the Norwegian Patient Registry and Statistics Norway. These data were linked with the electronic health record data of the substance use disorder treatment facilities from which the participants were recruited. Growth mixture modeling was performed. The identified groups were further compared using analysis of variance or χ 2 test. Results Four groups of participants for total treatment use, substance use disorder treatment use, and MH treatment use were identified. Most participants from the overall sample were classified as members of a group characterized by a low and stable pattern of treatment use over time. A group with a high and stable pattern of treatment use was identified in total and MH treatment use. The proportion of participants with higher levels of substance use disorder treatment use at the end of the study period than at the beginning was larger (35%) than in the case of MH treatment use (14.2%). Younger age was associated with a decreasing pattern of MH treatment use and with an increasing pattern of substance use disorder treatment use over time. There were larger proportions of female participants in groups with a stable high use of MH treatment and in groups with an initially increasing trend of substance use disorder treatment use. Findings revealed that most participants across the identified groups were recipients of welfare benefits, had low educational attainment, and were not working. Conclusions Results demonstrated significant variation in trajectories of treatment use among young adults with substance use disorder. Differences in treatment use could indicate differences in symptom severity and complexity. In this study, treatment use was associated with socioeconomic factors, sex, and age. Integrative approaches, including interagency and interdisciplinary collaboration, will often be necessary to sufficiently address the multidimensionality of substance use disorder.

Video-Assisted vs Robotic-Assisted Lung Lobectomies for Operating Room Resource Utilization and Patient Outcomes

With increased use of robots, there is an inadequate understanding of minimally invasive modalities' time costs. This study evaluates the operative durations of robotic-assisted vs video-assisted lung lobectomies. To compare resource utilization, specifically operative time, between video-assisted and robotic-assisted thoracoscopic lung lobectomies. This retrospective cohort study evaluated patients aged 18 to 90 years who underwent minimally invasive (robotic-assisted or video-assisted) lung lobectomy from January 1, 2020, to December 31, 2022, with 90 days' follow-up after surgery. The study included multicenter electronic health record data from 21 hospitals within an integrated health care system in Northern California. Thoracic surgery was regionalized to 4 centers with 14 board-certified general thoracic surgeons. Robotic-assisted or video-assisted lung lobectomy. The primary outcome was operative duration (cut to close) in minutes. Secondary outcomes were length of stay, 30-day readmission, and 90-day mortality. Comparisons between video-assisted and robotic-assisted lobectomies were generated using the Wilcoxon rank sum test for continuous variables and the χ2 test for categorical variables. The average treatment effects were estimated with augmented inverse probability treatment weighting (AIPTW). Patient and surgeon covariates were adjusted for and included patient demographics, comorbidities, and case complexity (age, sex, race and ethnicity, neighborhood deprivation index, body mass index, Charlson Comorbidity Index score, nonelective hospitalizations, emergency department visits, a validated laboratory derangement score, a validated institutional comorbidity score, a surgeon-designated complexity indicator, and a procedural code count), and a primary surgeon-specific indicator. The study included 1088 patients (median age, 70.1 years [IQR, 63.3-75.8 years]; 704 [64.7%] female), of whom 446 (41.0%) underwent robotic-assisted and 642 (59.0%) underwent video-assisted lobectomy. The median unadjusted operative duration was 172.0 minutes (IQR, 128.0-226.0 minutes). After AIPTW, there was less than a 10% difference in all covariates between groups, and operative duration was a median 20.6 minutes (95% CI, 12.9-28.2 minutes; P < .001) longer for robotic-assisted compared with video-assisted lobectomies. There was no difference in adjusted secondary patient outcomes, specifically for length of stay (0.3 days; 95% CI, -0.3 to 0.8 days; P = .11) or risk of 30-day readmission (adjusted odds ratio, 1.29; 95% CI, 0.84-1.98; P = .13). The unadjusted 90-day mortality rate (1.3% [n = 14]) was too low for the AIPTW modeling process. In this cohort study, there was no difference in patient outcomes between modalities, but operative duration was longer in robotic-assisted compared with video-assisted lung lobectomy. Given that this elevated operative duration is additive when applied systematically, increased consideration of appropriate patient selection for robotic-assisted lung lobectomy is needed to improve resource utilization.

Regulatory Issues in Electronic Health Records for Adolescent HIV Research: Strategies and Lessons Learned.

Electronic health records (EHRs) are a cost-effective approach to provide the necessary foundations for clinical trial research. The ability to use EHRs in real-world clinical settings allows for pragmatic approaches to intervention studies with the emerging adult HIV population within these settings; however, the regulatory components related to the use of EHR data in multisite clinical trials poses unique challenges that researchers may find themselves unprepared to address, which may result in delays in study implementation and adversely impact study timelines, and risk noncompliance with established guidance. As part of the larger Adolescent Trials Network (ATN) for HIV/AIDS Interventions Protocol 162b (ATN 162b) study that evaluated clinical-level outcomes of an intervention including HIV treatment and pre-exposure prophylaxis services to improve retention within the emerging adult HIV population, the objective of this study is to highlight the regulatory process and challenges in the implementation of a multisite pragmatic trial using EHRs to assist future researchers conducting similar studies in navigating the often time-consuming regulatory process and ensure compliance with adherence to study timelines and compliance with institutional and sponsor guidelines. Eight sites were engaged in research activities, with 4 sites selected from participant recruitment venues as part of the ATN, who participated in the intervention and data extraction activities, and an additional 4 sites were engaged in data management and analysis. The ATN 162b protocol team worked with site personnel to establish the necessary regulatory infrastructure to collect EHR data to evaluate retention in care and viral suppression, as well as para-data on the intervention component to assess the feasibility and acceptability of the mobile health intervention. Methods to develop this infrastructure included site-specific training activities and the development of both institutional reliance and data use agreements. Due to variations in site-specific activities, and the associated regulatory implications, the study team used a phased approach with the data extraction sites as phase 1 and intervention sites as phase 2. This phased approach was intended to address the unique regulatory needs of all participating sites to ensure that all sites were properly onboarded and all regulatory components were in place. Across all sites, the regulatory process spanned 6 months for the 4 data extraction and intervention sites, and up to 10 months for the data management and analysis sites. The process for engaging in multisite clinical trial studies using EHR data is a multistep, collaborative effort that requires proper advanced planning from the proposal stage to adequately implement the necessary training and infrastructure. Planning, training, and understanding the various regulatory aspects, including the necessity of data use agreements, reliance agreements, external institutional review board review, and engagement with clinical sites, are foremost considerations to ensure successful implementation and adherence to pragmatic trial timelines and outcomes.

Abstract PO2-17-05: Pharmacy fills but not baseline distress or other clinical factors can identify those at high risk for early adjuvant endocrine therapy discontinuation

Abstract Background Completion of the recommended 5-10 year course of adjuvant endocrine therapy (AET) course is low, and few risk factors for discontinuation have been identified. We examined factors associated with early AET discontinuation in a large cohort with patient-reported outcomes (PROs) and other measures routinely used in clinical care at four sites within an academic health system's multidisciplinary cancer center. Methods We examined postmenopausal women with stage I-III hormone-receptor positive breast cancer identified using the registry at an academic multidisciplinary cancer center 2014-19 who received a prescription for AET, and followed them for up to 5 years. Breast cancer extent of disease and treatments, Elixhauser comorbidity index, medication number and sociodemographic characteristics (age, race/ethnicity, insurance, area deprivation index of zip code of residence) were abstracted from the electronic health record (EHR). PRO measures included the Distress Thermometer (DT, scored 0-10) and its associated problem list (39 yes/no questions), and the Patient Health Questionnaire-9 (depression), all administered routinely as part of clinical care between diagnosis date and start of AET. If &amp;gt;1 PRO performed during that time, the measure closest to AET start was used. DT was dichotomized using the clinically accepted score of 4 as the threshold for severe distress, as was Patient Health Questionnaire-9 (PHQ-9) depression ( &amp;gt;5). AET prescription information included both prescription date from the EHR, and prescription fills assessed using an all-payer pharmacy data source. AET was defined as discontinued (d/c) when no prescription had been filled at any pharmacy for at least 90 days. We used nonparametric hypotheses test for two-samples (d/c vs. no d/c) as well as Kaplan-Meier product-limit time-to-event analyses with censoring for recurrence, death, or change of provider, and advanced machine learning to examine the association of these variables with discontinuation prior to five years. 54 curated covariates were examined in all, corresponding to a Bonferroni statistical significance p-value threshold of 0.001 to control type I error. Sensitivity analyses were performed to 1)use alternative date of DT (closest to diagnosis date) and 2)to examine d/c defined as 180 days. Results Among the cohort of 985 women (74% stage I, 25% Elixhauser comorbidity score &amp;gt;2), 36.9% had a DT &amp;gt;4, and 6.7% a PHQ-9 &amp;gt;5. The cohort had a median followup time of 954 days, and during followup 291 women ( 29.5) % discontinued before completion of the 5-year course or censoring for death, change to a provider outside the system or study end date in 2021. Over 40% of women who stopped filling prescriptions never had their prescriptions discontinued by their physician in the EHR. None of the examined variables including those for Distress and PL, PHQ-9 and measures of extent of disease, cancer treatments, medication number and sociodemographic characteristics were associated with early discontinuation. Results were similar in analyses using the DT date closest to diagnosis or a 180-day prescription fill gap. We also used advanced machine learning with respect to time to event discontinuation had similar results. Conclusions. Clinically available EHR data including two PRO measures were not reliable predictors of early discontinuation. However, many women who had discontinued still had orders for AET in the EHR, suggesting that their physicians were unaware that they had stopped filling prescriptions. Future work should examine whether routine monitoring of prescription fills might be enlisted to identify these women and assist with education, supportive care or other assistance to restart. Citation Format: Joan Neuner, Rodney Sparapani, Jacob Tiegs, Vaia Makris, Melinda Stolley, Sailaja Kamaraju, Bradley Crotty, Kathryn Flynn. Pharmacy fills but not baseline distress or other clinical factors can identify those at high risk for early adjuvant endocrine therapy discontinuation [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO2-17-05.

A Quantitative Bias Analysis Approach to Informative Presence Bias in Electronic Health Records.

Accurate outcome and exposure ascertainment in electronic health record (EHR) data, referred to as EHR phenotyping, relies on the completeness and accuracy of EHR data for each individual. However, some individuals, such as those with a greater comorbidity burden, visit the health care system more frequently and thus have more complete data, compared with others. Ignoring such dependence of exposure and outcome misclassification on visit frequency can bias estimates of associations in EHR analysis. We developed a framework for describing the structure of outcome and exposure misclassification due to informative visit processes in EHR data and assessed the utility of a quantitative bias analysis approach to adjusting for bias induced by informative visit patterns. Using simulations, we found that this method produced unbiased estimates across all informative visit structures, if the phenotype sensitivity and specificity were correctly specified. We applied this method in an example where the association between diabetes and progression-free survival in metastatic breast cancer patients may be subject to informative presence bias. The quantitative bias analysis approach allowed us to evaluate robustness of results to informative presence bias and indicated that findings were unlikely to change across a range of plausible values for phenotype sensitivity and specificity. Researchers using EHR data should carefully consider the informative visit structure reflected in their data and use appropriate approaches such as the quantitative bias analysis approach described here to evaluate robustness of study findings.

Concordance Between Electronic Health Record-Recorded Race and Ethnicity and Patient Report in Emergency Department Patients

We assessed the concordance of patient-reported race and ethnicity for emergency department (ED) patients compared with what was recorded in the electronic health record. We conducted a single-center, prospective, observational study of 744 ED patients (English- and/or Spanish-speaking), asking them to describe their race and ethnicity. We compared the distributions of ethnicity and race between patient-reported and electronic health record data using McNemar's test. We calculated percent agreement and Cohen's kappa, with 95% confidence intervals (CI), for the concordance of patient-reported race and ethnicity with electronic health record data. Of 744 ED patients, 731 participants who completed the survey reported their ethnicity, resulting in 98.2% of electronic health records obtained ethnicities matched self-reported data (kappa= 0.95; 95% CI: 0.92 to 0.98). For those who self-reported as Hispanic, only 92.3% agreement was observed between the self-reported and electronic health record values. For all patients who had race recorded, 85.4% agreement was observed (kappa= 0.75; 95% CI 0.71 to 0.79). High rates of agreement were observed for Black or African American patients (98.7%) and White patients (96.6%), with low rates for those who identified as "More than one race" (22.9%) or "Other" race (1.8%). In the subset of Hispanic patients, low rates of agreement (25.0%) were observed for race (kappa= 0.10; 95% CI 0.01 to 0.19). Documentation discordance regarding race and ethnicity exists between electronic health records and self-reported data for our ED patients, particularly for ethnically Hispanic and Latino/a patients. Future efforts should focus on ensuring that demographic information in the electronic health record is accurately collected.

The landscape of real-world evidence of rituximab utilization and clinical outcomes in patients with cancer, rheumatoid arthritis, and multiple sclerosis: A scoping review.

Rituximab (RTX) is an anti-CD20 monoclonal antibody that is used to treat various conditions in cancer, rheumatoid arthritis (RA), and multiple sclerosis (MS). Although RTX has been used in the United States for almost 3 decades, questions remain regarding its real-world utilization and effectiveness. To describe the state of observational research and real-world evidence evaluating RTX in oncology, RA, and off-label use in MS. A broad search was conducted in MEDLINE, Embase, and CINAHL covering the period of January 2010 to June 2022. Two reviewers independently screened all identified records for each disease category (cancer, RA, MS) beginning with title review, followed by abstract, and full-text review to identify relevant publications to include in the final analysis. Data were extracted and summarized for each disease based on overall trends, similarities, and differences across included studies and stratified by disease state. A total of 260 studies met eligibility criteria, with 79 studies for the RA cohort, 144 for cancer, and 37 for MS. Across all disease cohorts, most studies (n = 189; 72.7%) were retrospective. 171 (65.8%) studies used hospital or electronic health record data as their data source and 65 (23.2%) used registry databases. Most studies (n = 153; 58.8%) assessed the effectiveness of RTX measured by disease-specific endpoints, followed by safety (n = 60; 23.1%), treatment patterns (n = 32; 12.3%), and descriptive analyses assessing treatment adherence and economic burden of disease (n = 16; 6.2%). Although safety was not the primary outcome for most studies, the majority of studies across all disease states still reported some form of safety measure. Conclusive statements on RTX's benefit varied across disease states, with MS having the most (n = 30; 81.1%) studies suggesting the drug's positive benefit. There were limited studies assessing RTX use, associated economic burden, and biosimilar switching. The findings underscore the need for health care providers to better understand the treatment landscape and utilization of RTX, particularly in terms of patient selection, timing of initiation, and long-term outcomes. Real-world evidence can help support health care decisions and treatment using rituximab.

Drivers of Variation in Opioid Prescribing after Common Surgical Procedures in a Large Multihospital Healthcare System.

Misuse of prescription opioids is a well-established contributor to the United States opioid epidemic. The primary objective of this study was to identify which level of care delivery (i.e. patient, prescriber, or hospital) produced the most unwarranted variation in opioid prescribing after common surgical procedures. Electronic health record (EHR) data from a large multihospital healthcare system was used in conjunction with random-effect models to examine variation in opioid prescribing practices following similar inpatient and outpatient surgical procedures between October 2019 and September 2021. Unwarranted variation was conceptualized as variation resulting from prescriber behavior unsupported by evidence. Covariates identified as drivers of warranted variation included characteristics known to influence pain levels or patient safety. All other model variables, including prescriber specialty and patient race, ethnicity, and insurance status were characterized as potential drivers of unwarranted variation. Among 25,188 procedures with an opioid prescription at hospital discharge, 53.5% exceeded guideline recommendations, corresponding to 13,228 patients receiving the equivalent of >140,000 excess 5mg oxycodone tablets following surgical procedures. Prescribing variation was primarily driven by prescriber-level factors, with approximately half of the total variation in morphine milligram equivalents (MMEs) prescribed observed at the prescriber level and not explained by any measured variables. Unwarranted covariates associated with higher prescribed opioid quantity included non-Hispanic black race, Medicare insurance, smoking history, later hospital discharge times, and prescription by a surgeon rather than a hospitalist or primary care provider. Given the large proportion of unexplained variation observed at the provider level, targeting prescribers through education and training may be an effective strategy for reducing postoperative opioid prescribing.

Variations in Using Diagnosis Codes for Defining Age-Related Macular Degeneration Cohorts

Data harmonization is vital for secondary electronic health record data analysis, especially when combining data from multiple sources. Currently, there is a gap in knowledge as to how studies identify cohorts of patients with age-related macular degeneration (AMD), a leading cause of blindness. We hypothesize that there is variation in using medical condition codes to define cohorts of AMD patients that can lead to either the under- or overrepresentation of such cohorts. This study identified articles studying AMD using the International Classification of Diseases (ICD-9, ICD-9-CM, ICD-10, and ICD-10-CM). The data elements reviewed included the year of publication; dataset origin (Veterans Affairs, registry, national or commercial claims database, and institutional EHR); total number of subjects; and ICD codes used. A total of thirty-seven articles were reviewed. Six (16%) articles used cohort definitions from two ICD terminologies. The Medicare database was the most used dataset (14, 38%), and there was a noted increase in the use of other datasets in the last few years. We identified substantial variation in the use of ICD codes for AMD. For the studies that used ICD-10 terminologies, 7 (out of 9, 78%) defined the AMD codes correctly, whereas, for the studies that used ICD-9 and 9-CM terminologies, only 2 (out of 30, 7%) defined and utilized the appropriate AMD codes (p = 0.0001). Of the 43 cohort definitions used from 37 articles, 31 (72%) had missing or incomplete AMD codes used, and only 9 (21%) used the exact codes. Additionally, 13 articles (35%) captured ICD codes that were not within the scope of AMD diagnosis. Efforts to standardize data are needed to provide a reproducible research output.

Hyperkalemia Recurrence Following Medical Nutrition Therapy in Patients with Stage3-4 Chronic Kidney Disease: The REVOLUTIONIZEI Real-World Study.

The REVOLUTIONIZEI study aimed to characterize the relationships between medical nutrition therapy (MNT) and hyperkalemia recurrence in patients with stage3-4 chronic kidney disease (CKD) and hyperkalemia who received MNT in real-world clinical practice. This observational cohort study used de-identified electronic health record data from patients aged ≥18years with stage3-4 CKD who received MNT between January 2019 and October 2022 and had hyperkalemia (serum potassium >5.0mmol/L) within 30days before MNT. Patients were followed for 6months or until the first censoring event (death, prescription of outpatient potassium binder, or study end). The primary outcome was the percentage of patients with ≥1hyperkalemia recurrence during follow-up. Secondary outcomes included the number of hyperkalemia recurrences per patient, time to each recurrence, and hyperkalemia-related healthcare resource utilization. Exploratory outcomes included all-cause healthcare resource utilization and mortality. The final cohort comprised 2048 patients; 1503 (73.4%) patients remained uncensored after 6months. During the 6-month follow-up period, 56.0% of patients had ≥1hyperkalemia recurrence and 37.4% had ≥1 recurrence within the first month. Patients with ≥1hyperkalemia recurrence during follow-up had a mean ± standard deviation (SD) of 2.6 ± 2.2 recurrences. The mean ± SD time to first hyperkalemia recurrence was 45 ± 46days; the time between recurrences decreased with subsequent episodes. Hyperkalemia-related hospitalizations and emergency department visits were recorded for 13.7% and 1.5% of patients, respectively. Sensitivity analyses showed that results were consistent across patient subgroups, including those with comorbid heart failure and patients receiving renin-angiotensin-aldosterone system inhibitor therapy at baseline. Most patients with stage3-4 CKD had hyperkalemia recurrence, and MNT alone was inadequate to prevent recurrence. These patients may require additional long-term treatment, such as novel potassium binders, to maintain normokalemia and prevent hyperkalemia recurrence following MNT. Infographic available for this article. INFOGRAPHIC.

Validation of new medication use algorithms as proxies for worsening disease activity in patients with juvenile idiopathic arthritis.

To facilitate claims-based research on populations with juvenile idiopathic arthritis (JIA), we sought to validate an algorithm of new medication use as a proxy for worsening JIA disease activity. Using electronic health record data from three pediatric centers, we defined new JIA medication use as (re)initiation of disease-modifying antirheumatic drugs or glucocorticoids (oral or intra-articular). Data were collected from 201 randomly selected subjects with (101) or without (100) new medication use. We assessed the positive predictive value (PPV) and negative predictive value (NPV) based on a reference standard of documented worsening of JIA disease activity. The algorithm was refined to optimize test characteristics. Overall, the medication-based algorithm had suboptimal performance in representing worsening JIA disease activity (PPV 69.3%, NPV 77.1%). However, algorithm performance improved for definitions specifying longer times after JIA diagnosis (≥1-year post-diagnosis: PPV 82.9%, NPV 80.0%) or after initiation of prior JIA treatment (≥1-year post-treatment: PPV 89.7%, NPV 80.0%). An algorithm for new JIA medication use appears to be a reasonable proxy for worsening JIA disease activity, particularly when specifying new use ≥1 year since initiating a prior JIA medication. This algorithm will be valuable for conducting research on JIA populations within administrative claims databases.

Dysphagia Is an Underrecognized Risk Factor for Viral Pneumonia Severity.

The aim of this study was to examine the role of pre-existing dysphagia as a risk factor for COVID-19 severity among adults ≥50years of age presenting to the emergency department (ED). This was a retrospective cohort study that used electronic health record data from two Midwestern EDs in the same health care system. The sample included patients ≥50years of age who tested positive for SARS-COV-2 during an ED visit between March 15, 2020 and November 19, 2020. Patients were dichotomized based on documented history of dysphagia. The primary outcome was the highest World Health Organization COVID-19 clinical severity score within 30-days of ED arrival. Patients with a score of <4 were classified as non-severe whereas a score ≥4 was considered severe. Chi-square tests were used to assess differences in clinical severity scores between patients with and without dysphagia. A logistic regression model was created to estimate the odds of a severe COVID-19 clinical score. The sample included 126 patients without dysphagia and 40 patients with dysphagia. Patients with a history of dysphagia were more likely to develop severe COVID-19 disease compared to patients without (65.0% vs. 41.3%, p = 0.015). In multivariable analysis, patients with preexisting dysphagia (OR 2.38, 95% CI: 1.05-5.42; p = 0.038) and diabetes (OR 2.42 95% CI: 1.15-5.30; p = 0.021) had significantly increased odds of developing severe COVID-19. This study showed that a pre-existing diagnosis of dysphagia was independently associated with COVID-19 severity in adults ≥50years of age.

Costs of care trajectories of people with dementia compared with matched controls. Longitudinal analysis of linked health and administrative data.

To provide insight into the health and social care costs during the disease trajectory in persons with dementia and the impact of institutionalization and death on healthcare costs compared with matched persons without dementia. Electronic health record data from family physicians were linked with national administrative databases to estimate costs of primary care, medication, secondary care, mental care, home care and institutional care for people with dementia and matched persons from the year before the recorded dementia diagnosis until death or a maximum of 4years after the diagnosis. Total mean health and social care costs among persons with dementia increased substantially during the disease trajectory, mainly due to institutional care costs. For people who remained living in the community, mean health and social care costs are higher for people with dementia than for those without dementia, while for those who are admitted to a long-term care facility, mean health and social care costs are higher for people without dementia than for those with dementia. The steep rise in health and social care costs across the dementia care trajectory is mainly due to increasing costs for institutional care. For those remaining in the community, home care costs and hospital care costs were the main cost drivers. Future research should adopt a societal perspective to investigate the influence of including social costs.

Real-world utilization, patient characteristics, and treatment patterns among men with localized prostate cancer tested with the 17-gene genomic prostate score® (GPSTM) assay.

Descriptive study focusing on real-world utilization and characteristics of men with prostate cancer tested with the 17-gene Genomic Prostate Score® (GPS™) assay by linking administrative claims and electronic health record (EHR) data with GPS results. This retrospective, observational cohort study (January 1, 2013 to December 31, 2020) included men aged 40-80 years with localized prostate cancer claims, continuous enrollment in Optum's Integrated Claims data set, ≥1 day of EHR clinical activity, and a GPS result. Men were classified as undergoing definitive therapy (DT) (prostatectomy, radiation, or focal therapy) or active surveillance (AS). AS and DT distribution were analyzed across GPS results, National Comprehensive Cancer Network® (NCCN®) risk, and race. Costs were assessed 6 months after the first GPS result (index); clinical outcomes and AS persistence were assessed during the variable follow-up. All variables were analyzed descriptively. Of 834 men, 650 (77.9%) underwent AS and 184 (22.1%) DT. Most men had Quan-Charlson comorbidity scores of 1-2 and a tumor stage of T1c (index). The most common Gleason patterns were 3 + 3 (79.6%) (AS cohort) and 3 + 4 (55.9%) (DT cohort). The mean (standard deviation) GPS results at index were 23.2 (11.3) (AS) and 30.9 (12.9) (DT). AS decreased with increasing GPS result and NCCN risk. Differences between races were minimal. Total costs were substantially higher in the DT cohort. Most men with GPS-tested localized prostate cancer underwent AS, indicating the GPS result can inform clinical management. Decreasing AS with increasing GPS result and NCCN risk suggests the GPS complements NCCN risk stratification.

Predictive modeling of initiation and delayed mental health contact for depression

BackgroundDepression is prevalent among Operation Enduring Freedom and Operation Iraqi Freedom (OEF/OIF) Veterans, yet rates of Veteran mental health care utilization remain modest. The current study examined: factors in electronic health records (EHR) associated with lack of treatment initiation and treatment delay; the accuracy of regression and machine learning models to predict initiation of treatment.MethodsWe obtained data from the VA Corporate Data Warehouse (CDW). EHR data were extracted for 127,423 Veterans who deployed to Iraq/Afghanistan after 9/11 with a positive depression screen and a first depression diagnosis between 2001 and 2021. We also obtained 12-month pre-diagnosis and post-diagnosis patient data. Retrospective cohort analysis was employed to test if predictors can reliably differentiate patients who initiated, delayed, or received no mental health treatment associated with their depression diagnosis.Results108,457 Veterans with depression, initiated depression-related care (55,492 Veterans delayed treatment beyond one month). Those who were male, without VA disability benefits, with a mild depression diagnosis, and had a history of psychotherapy were less likely to initiate treatment. Among those who initiated care, those with single and mild depression episodes at baseline, with either PTSD or who lacked comorbidities were more likely to delay treatment for depression. A history of mental health treatment, of an anxiety disorder, and a positive depression screen were each related to faster treatment initiation. Classification of patients was modest (ROC AUC = 0.59 95%CI = 0.586–0.602; machine learning F-measure = 0.46).ConclusionsHaving VA disability benefits was the strongest predictor of treatment initiation after a depression diagnosis and a history of mental health treatment was the strongest predictor of delayed initiation of treatment. The complexity of the relationship between VA benefits and history of mental health care with treatment initiation after a depression diagnosis is further discussed. Modest classification accuracy with currently known predictors suggests the need to identify additional predictors of successful depression management.

Semantic Interoperability of Electronic Health Records: Systematic Review of Alternative Approaches for Enhancing Patient Information Availability.

Semantic interoperability facilitates the exchange of and access to health data that are being documented in electronic health records (EHRs) with various semantic features. The main goals of semantic interoperability development entail patient data availability and use in diverse EHRs without a loss of meaning. Internationally, current initiatives aim to enhance semantic development of EHR data and, consequently, the availability of patient data. Interoperability between health information systems is among the core goals of the European Health Data Space regulation proposal and the World Health Organization's Global Strategy on Digital Health 2020-2025. To achieve integrated health data ecosystems, stakeholders need to overcome challenges of implementing semantic interoperability elements. To research the available scientific evidence on semantic interoperability development, we defined the following research questions: What are the key elements of and approaches for building semantic interoperability integrated in EHRs? What kinds of goals are driving the development? and What kinds of clinical benefits are perceived following this development? Our research questions focused on key aspects and approaches for semantic interoperability and on possible clinical and semantic benefits of these choices in the context of EHRs. Therefore, we performed a systematic literature review in PubMed by defining our study framework based on previous research. Our analysis consisted of 14 studies where data models, ontologies, terminologies, classifications, and standards were applied for building interoperability. All articles reported clinical benefits of the selected approach to enhancing semantic interoperability. We identified 3 main categories: increasing the availability of data for clinicians (n=6, 43%), increasing the quality of care (n=4, 29%), and enhancing clinical data use and reuse for varied purposes (n=4, 29%). Regarding semantic development goals, data harmonization and developing semantic interoperability between different EHRs was the largest category (n=8, 57%). Enhancing health data quality through standardization (n=5, 36%) and developing EHR-integrated tools based on interoperable data (n=1, 7%) were the other identified categories. The results were closely coupled with the need to build usable and computable data out of heterogeneous medical information that is accessible through various EHRs and databases (eg, registers). When heading toward semantic harmonization of clinical data, more experiences and analyses are needed to assess how applicable the chosen solutions are for semantic interoperability of health care data. Instead of promoting a single approach, semantic interoperability should be assessed through several levels of semantic requirements A dual model or multimodel approach is possibly usable to address different semantic interoperability issues during development. The objectives of semantic interoperability are to be achieved in diffuse and disconnected clinical care environments. Therefore, approaches for enhancing clinical data availability should be well prepared, thought out, and justified to meet economically sustainable and long-term outcomes.