Local Electronic Health Record Research Articles

A knowledge-transfer-based approach for combining ordinal regression and medical scoring system in the early prediction of sepsis with electronic health records

Objective:The prediction of sepsis, especially early diagnosis, has received a significant attention in biomedical research. In order to improve current medical scoring system and overcome the limitations of class imbalance and sample size of local EHR (electronic health records), we propose a novel knowledge-transfer-based approach, which combines a medical scoring system and an ordinal logistic regression model. Materials and Methods:Medical scoring systems (i.e. NEWS, SIRS and QSOFA) are generally robust and useful for sepsis diagnosis. With local EHR, machine-learning-based methods have been widely used for building prediction models/methods, but they are often impacted by class imbalance and sample size. Knowledge distillation and knowledge transfer have recently been proposed as a combination approach for improving the prediction performance and model generalization. In this study, we developed a novel knowledge-transfer-based method for combining a medical scoring system (after a proposed score transformation) and an ordinal logistic regression model. We mathematically confirmed that it was equivalent to a specific form of the weighted regression. Furthermore, we theoretically explored its effectiveness in the scenario of class imbalance. Results:For the local dataset and the MIMIC-IV dataset, the VUS (the volume under the multi-dimensional ROC surface, a generalization measure of AUC-ROC for ordinal categories) of the knowledge-transfer-based model (ORNEWS) based on the NEWS scoring system were 0.384 and 0.339, respectively, while the VUS of the traditional ordinal regression model (OR) were 0.352 and 0.322, respectively. Consistent analysis results were also observed for the knowledge-transfer-based models based on the SIRS/QSOFA scoring systems in the ordinal scenarios. Additionally, the predicted probabilities and the binary classification ROC curves of the knowledge-transfer-based models indicated that this approach enhanced the predicted probabilities for the minority classes while reducing the predicted probabilities for the majority classes, which improved AUCs/VUSs on imbalanced data. Discussion:Knowledge transfer, which combines a medical scoring system and a machine-learning-based model, improves the prediction performance for early diagnosis of sepsis, especially in the scenarios of class imbalance and limited sample size.

Personalized Federated Graph Learning on Non-IID Electronic Health Records.

Understanding the latent disease patterns embedded in electronic health records (EHRs) is crucial for making precise and proactive healthcare decisions. Federated graph learning-based methods are commonly employed to extract complex disease patterns from the distributed EHRs without sharing the client-side raw data. However, the intrinsic characteristics of the distributed EHRs are typically non-independent and identically distributed (Non-IID), significantly bringing challenges related to data imbalance and leading to a notable decrease in the effectiveness of making healthcare decisions derived from the global model. To address these challenges, we introduce a novel personalized federated learning framework named PEARL, which is designed for disease prediction on Non-IID EHRs. Specifically, PEARL incorporates disease diagnostic code attention and admission record attention to extract patient embeddings from all EHRs. Then, PEARL integrates self-supervised learning into a federated learning framework to train a global model for hierarchical disease prediction. To improve the performance of the client model, we further introduce a fine-tuning scheme to personalize the global model using local EHRs. During the global model updating process, a differential privacy (DP) scheme is implemented, providing a high-level privacy guarantee. Extensive experiments conducted on the real-world MIMIC-III dataset validate the effectiveness of PEARL, demonstrating competitive results when compared with baselines.

Electronic Health Record-Oriented Knowledge Graph System for Collaborative Clinical Decision Support Using Multicenter Fragmented Medical Data: Design and Application Study.

The medical knowledge graph provides explainable decision support, helping clinicians with prompt diagnosis and treatment suggestions. However, in real-world clinical practice, patients visit different hospitals seeking various medical services, resulting in fragmented patient data across hospitals. With data security issues, data fragmentation limits the application of knowledge graphs because single-hospital data cannot provide complete evidence for generating precise decision support and comprehensive explanations. It is important to study new methods for knowledge graph systems to integrate into multicenter, information-sensitive medical environments, using fragmented patient records for decision support while maintaining data privacy and security. This study aims to propose an electronic health record (EHR)-oriented knowledge graph system for collaborative reasoning with multicenter fragmented patient medical data, all the while preserving data privacy. The study introduced an EHR knowledge graph framework and a novel collaborative reasoning process for utilizing multicenter fragmented information. The system was deployed in each hospital and used a unified semantic structure and Observational Medical Outcomes Partnership (OMOP) vocabulary to standardize the local EHR data set. The system transforms local EHR data into semantic formats and performs semantic reasoning to generate intermediate reasoning findings. The generated intermediate findings used hypernym concepts to isolate original medical data. The intermediate findings and hash-encrypted patient identities were synchronized through a blockchain network. The multicenter intermediate findings were collaborated for final reasoning and clinical decision support without gathering original EHR data. The system underwent evaluation through an application study involving the utilization of multicenter fragmented EHR data to alert non-nephrology clinicians about overlooked patients with chronic kidney disease (CKD). The study covered 1185 patients in nonnephrology departments from 3 hospitals. The patients visited at least two of the hospitals. Of these, 124 patients were identified as meeting CKD diagnosis criteria through collaborative reasoning using multicenter EHR data, whereas the data from individual hospitals alone could not facilitate the identification of CKD in these patients. The assessment by clinicians indicated that 78/91 (86%) patients were CKD positive. The proposed system was able to effectively utilize multicenter fragmented EHR data for clinical application. The application study showed the clinical benefits of the system with prompt and comprehensive decision support.

Disagreement concerning atopic dermatitis subtypes between an English prospective cohort (ALSPAC) and linked electronic health records.

Subtypes of atopic dermatitis (AD) have been derived from the Avon Longitudinal Study of Parents and Children (ALSPAC) based on presence and severity of symptoms reported in questionnaires (Severe-Frequent, Moderate-Frequent, Moderate-Declining, Mild-Intermittent, Unaffected/Rare). Good agreement between ALSPAC and linked electronic health records (EHRs) would increase trust in the clinical validity of these subtypes and allow inferring subtypes from EHRs alone, which would enable their study in large primary care databases. 1. Explore if presence and number of AD records in EHRs agrees with AD symptom and severity reports from ALSPAC; 2. Explore if EHRs agree with ALSPAC-derived AD subtypes; 3. Construct models to classify ALSPAC-derived AD subtype using EHRs. We used data from the ALSPAC prospective cohort study from 11 timepoints until age 14 years (1991-2008), linked to local general practice EHRs. We assessed how far ALSPAC questionnaire responses and derived subtypes agreed with AD as established in EHRs using different AD definitions (e.g., diagnosis and/or prescription) and other AD-related records. We classified AD subtypes using EHRs, fitting multinomial logistic regression models tuning hyperparameters and evaluating performance in the testing set (ROC AUC, accuracy, sensitivity, and specificity). 8,828 individuals out of a total 13,898 had both been assigned an AD subtype and had linked EHRs. The number of AD-related codes in EHRs generally increased with severity of AD subtype, however not all with the Severe-Frequent subtypes had AD in EHRs, and many with the Unaffected/Rare subtype did have AD in EHRs. When predicting ALSPAC AD subtype using EHRs, the best tuned model had ROC AUC of 0.65, sensitivity of 0.29 and specificity of 0.83 (both macro averaged); when different sets of predictors were used, individuals with missing EHR coverage excluded, and subtypes combined, sensitivity was not considerably improved. ALSPAC and EHRs disagreed not just on AD subtypes, but also on whether children had AD or not. Researchers should be aware that individuals considered as having AD in one source may not be considered as having AD in another.

Making the EHR Work for You-Modifications of an Electronic Health Record System to Improve Tracking and Management of Patients Receiving Outpatient Parenteral Antibiotic Therapy.

Managing the complex needs of outpatient parenteral antibiotic therapy (OPAT) patients is challenging and time-consuming. We describe development of multimodal interventions to facilitate patient management within an Epic® (Epic Systems Corporation)-based electronic health record (EHR) platform. During 2016-2018, a multidisciplinary team created several modifications in our local EHR to improve gaps in OPAT care, including shared note templates, shared patient lists, automatically triggered notifications, and comprehensive order sets. A SmartForm was created, allowing collection of discrete, self-contained extractable data about each OPAT episode. We reviewed OPAT episodes from January 2019 through December 2022. The multimodal EHR interventions culminated in the creation of a patient report, the "OPAT Monitoring View" collating OPAT-relevant data from multiple sections of the chart onto 1 screen display. This view is accessible both within the patient chart and from multiple list-based, in-basket, and snapshot-anchored preview functions in the EHR. Implementation of the EHR bundle facilitated management of 3402 OPAT episodes from 2019 to 2022 (850 episodes/year), about 50% higher than anticipated based on 540 OPAT courses in 2016. The OPAT EHR bundle allowed efficient (<3 hours) multidisciplinary rounds for management of 130-145 patients each week, streamlining of care transitions, and increasing staff satisfaction. Bundled multimodal modifications to the local EHR increased patient care efficiency and staff satisfaction and facilitated data collection to support a large OPAT program. These modifications apply commonly available EHR functionalities to OPAT care and could be adapted to other settings with different EHR platforms.

Relative bed allocation for COVID-19 patients, EHR investments, and COVID-19 mortality outcomes.

Managing flexibility in the relative bed allocation for COVID-19 and non-COVID-19 patients was a key challenge for hospitals during the COVID-19 pandemic. Based on organizational information processing theory (OIPT), we propose that the local electronic health record (EHR) systems could improve patient outcomes through improved bed allocation in the local area. In an empirical analysis of county-level weekly hospital data in the US, relative capacity of beds in hospitals with higher EHR was associated with lower 7-, 14-, and 21-day forward-looking COVID-19 death rate at the county-level. Testing for cross-state variation in non-pharmaceutical interventions along contiguous county border-pair analysis to control for spatial correlation varying between state variations in non-pharmaceutical intervention policies, 2SLS analysis using quality ratings, and using foot-traffic data at the US hospitals our findings are generally supported. The findings have implications for policymakers and stakeholders of the local healthcare supply chains and EHR systems.

Sepsis is the most frequent trigger for electrical storm in structural heart disease: results from a tertiary referral centre prospective registry

Abstract Funding Acknowledgements Type of funding sources: None. Background Electrical storm is a specific clinical presentation yielding to high morbidity and mortality. Acute development of electrical storms results from the underlying myocardial substrate, autonomic activation, and trigger factors. Main therapeutic approaches range from pharmacological to interventional treatment. Methods We enrolled in a prospective single center registry all patients admitted from March 2018 to March 2022 at our Centre who satisfied diagnostic criteria for electrical storm. Demographic, instrumental, and interventional data were obtained from local electronic health record. Results A total of 87 patients (79% male sex, mean age 72,21±10,49 years) were enrolled. Mean left ventricular ejection fraction was 37,27±11,62%. Underlying cardiomyopathy was ischemic in 57,47%; dilated cardiomyopathy in 20,69%, arrhythmogenic cardiomyopathy in 8%, other in 13,84%. A definite trigger was identified in 34 cases (39%), most frequent ones were sepsis (11 events, 32,4%), acute heart failure (6 events, 17,6%), myocardial ischemia (5 events, 14,7%), thyrotoxicosis (5 events, 14,7%), ionic disorder (4 events, 11,8%). An ICD was already implanted in 89,66% of patients, all remaining patients were implanted during index hospitalization. An ablation strategy was pursued in 65,52% of cases. Mean days from hospitalization to ablation were 7±5. Median hospital stay was 11 days (IQR 8-18). Conclusion In our single referral centre experience, in patients with electrical storm, ischemic cardiomyopathy was the dominant underlying heart disease. An identifiable trigger was found in a large cohort of patients, with sepsis being the most frequent. An ablation strategy was pursued in most cases.

MP19-14 WHO RECEIVES THIRD LINE THERAPIES FOR OVERACTIVE BLADDER? TRENDS FROM DATA IN THE AUA AQUA REGISTRY

You have accessJournal of UrologyCME1 Apr 2023MP19-14 WHO RECEIVES THIRD LINE THERAPIES FOR OVERACTIVE BLADDER? TRENDS FROM DATA IN THE AUA AQUA REGISTRY Katherine Shapiro, Dora Jericevic, Max Bowman, Camille Velez Morell, Rachel Mbassa, Raymond Feng, Michelle van Kuiken, and Benjamin Brucker Katherine ShapiroKatherine Shapiro More articles by this author , Dora JericevicDora Jericevic More articles by this author , Max BowmanMax Bowman More articles by this author , Camille Velez MorellCamille Velez Morell More articles by this author , Rachel MbassaRachel Mbassa More articles by this author , Raymond FengRaymond Feng More articles by this author , Michelle van KuikenMichelle van Kuiken More articles by this author , and Benjamin BruckerBenjamin Brucker More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003244.14AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Third line therapies for Overactive Bladder (OAB) include Percutaneous Tibial Nerve Stimulation (PTNS), Sacral Neuromodulation (SNS) and OnabotulinumtoxinA bladder injections (BTX-A). The American Urologic Association (AUA) and Society for Urodynamics, Female Pelvic Medicine and Reconstructive Surgery (SUFU) have jointly developed a guideline to help manage patients with OAB. Using the AUA Quality (AQUA) registry, we aim to assess access and implementation of third line therapies. METHODS: The AQUA registry collects data from participating urologists across practice settings by direct interface with local electronic health record systems. We queried the registry for patients >18 years with a new diagnosis of OAB, urinary urgency, frequency, and urgency urinary incontinence (UUI) from 2014-2020 using ICD9 and ICD10 codes with >1 year follow up. We evaluated patients who proceeded to third line therapy by insurance type, gender, ethnicity, metropolitan status, age and medication type. We excluded patients with a diagnosis of neurogenic bladder. Multivariable regression was performed to determine the odds ratio of progression to third line therapy. Only patients who first received second line therapy prior to third line therapy were included in the analysis. RESULTS: A total of 1,401,168 patients were diagnosed with OAB during the study period. Complete data was available for 641,122 and analysis was performed specifically for this cohort. 112,021 (17.5%) patients received second line therapy with either an anticholinergic, beta-3 agonist or combination therapy. Of those, 7,487 (1.2%) received at least one third line therapy. BTX-A was the most common therapy overall (40%, 32% SNS, 28% PTNS), while PTNS was the most common third line therapy in men (35%), Asian patients (37%), patients aged >80 (40%) and patients seen in solo practitioner (46%) settings. Black and Asian race, male gender and rural setting had lower odds of progressing to third line therapy. Patients seen by providers in multi-specialty settings, single specialty settings and solo practices were approximately 3 times more likely to receive third line therapy than in an academic medical center (Table 1). CONCLUSIONS: In this study, a small percentage of patients progress from second to third line therapy. Rates varied amongst gender, race, metropolitan status and practice setting. These findings highlight opportunities to improve third line therapy implementation. Source of Funding: AUA Data Committee © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e270 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Katherine Shapiro More articles by this author Dora Jericevic More articles by this author Max Bowman More articles by this author Camille Velez Morell More articles by this author Rachel Mbassa More articles by this author Raymond Feng More articles by this author Michelle van Kuiken More articles by this author Benjamin Brucker More articles by this author Expand All Advertisement PDF downloadLoading ...

Federated electronic data capture (fEDC): Architecture and prototype

In clinical research as well as patient care, structured documentation of findings is an important task. In many cases, this is achieved by means of electronic case report forms (eCRF) using corresponding information technology systems. To avoid double data entry, eCRF systems can be integrated with electronic health records (EHR). However, when researchers from different institutions collaborate in collecting data, they often use a single joint eCRF system on the Internet. In this case, integration with EHR systems is not possible in most cases due to information security and data protection restrictions.To overcome this shortcoming, we propose a novel architecture for a federated electronic data capture system (fEDC). Four key requirements were identified for fEDC: Definitions of forms have to be available in a reliable and controlled fashion, integration with electronic health record systems must be possible, patient data should be under full local control until they are explicitly transferred for joint analysis, and the system must support data sharing principles accepted by the scientific community for both data model and data captured.With our approach, sites participating in a joint study can run their own instance of an fEDC system that complies with local standards (such as being behind a network firewall) while also being able to benefit from using identical form definitions by sharing metadata in the Operational Data Model (ODM) format published by the Clinical Data Interchange Standards Consortium (CDISC) throughout the collaboration. The fEDC architecture was validated with a working open-source prototype at five German university hospitals.The fEDC architecture provides a novel approach with the potential to significantly improve collaborative data capture: Efforts for data entry are reduced and at the same time, data quality is increased since barriers for integrating with local electronic health record systems are lowered. Further, metadata are shared and patient privacy is ensured at a high level.

Electronic health record closed-loop referral (“eReferral”) to a state tobacco quitline: a retrospective case study of primary care implementation challenges and adaptations

BackgroundHealth system change can increase the reach of evidence-based smoking cessation treatments. Proactive electronic health record (EHR)-enabled, closed-loop referral (“eReferral”) to state tobacco quitlines increases the rates at which patients who smoke accept cessation treatment. Implementing such system change poses many challenges, however, and adaptations to system contexts are often required, but are understudied. This retrospective case study identified adaptations to eReferral EHR tools and implementation strategies in two healthcare systems.MethodsIn a large clustered randomized controlled trial (C-RCT; NCT02735382) conducted in 2016–2017, 11 primary care clinics in two healthcare systems implemented quitline eReferral, starting with 1 pilot clinic per system followed by 2 phases of implementation (an experimental phase in 5–6 test clinics per system and then a system-wide dissemination phase in both systems). Adaptations were informed by stakeholder input from live trainings, follow-up calls and meetings in the first month after eReferral launch, emails, direct observation by researchers, and clinic staff survey responses. Retrospective, descriptive analysis characterized implementation strategy modifications and adaptations using the Framework for Reporting Adaptations and Modifications to Evidence-based Implementation Strategies (FRAME-IS). A pre- and post-implementation survey assessed staff ratings of eReferral acceptability and implementation barriers and facilitators.FindingsMajor modifications to closed-loop eReferral implementation strategies included aligning the eReferral initiative with other high-priority health system objectives, modifying eReferral user interfaces and training in their use, modifying eReferral workflows and associated training, and maintaining and enhancing interoperability and clinician feedback functions. The two health systems both used Epic EHRs but used different approaches to interfacing with the quitline vendor and integrating eReferral into clinician workflows. Both health systems engaged in iterative refinement of the EHR alert prompting eReferral, the eReferral order, trainings, and workflows. Staff survey comments suggested moderate acceptability of eReferral processes and identified possible targets for future modifications in eReferral, including reducing clinician burden related to EHR documentation and addressing clinicians’ negative beliefs about patient receptivity to cessation treatment.ConclusionsSystem-wide implementation of tobacco quitline eReferral in primary care outpatient clinics is feasible but requires extensive coordination across stakeholders, tailoring to local health system EHR configurations, and sensitivity to system- and clinic-specific workflows.Trial registrationwww.clinicaltrials.gov, NCT02735382. Registered on 12 August 2016.

Social Determinants of Health Data Availability for Patients with Eye Conditions.

Purpose:To quantify and characterize social determinants of health (SDoH) data coverage using single-center electronic health records (EHRs) and the National Institutes of Health All of Us research program.Design:Retrospective cohort study from June 2014 through June 2021.Participants:Adults 18 years of age or older with a diagnosis of diabetic retinopathy, glaucoma, cataracts, or age-related macular degeneration.Methods:For All of Us, research participants completed online survey forms as part of a nationwide prospective cohort study. In local EHRs, patients were selected based on diagnosis codes.Main Outcome Measures:Social determinants of health data coverage, characterized by the proportion of each disease cohort with available data regarding demographics and socioeconomic factors.Results:In All of Us, we identified 23 806 unique adult patients, of whom 2246 had a diagnosis of diabetic retinopathy, 13 448 had a diagnosis of glaucoma, 6634 had a diagnosis of cataracts, and 1478 had a diagnosis of age-related macular degeneration. Survey completion rates were high (99.5%–100%) across all cohorts for demographic information, overall health, income, education, and lifestyle. However, health care access (12.7%–29.4%), housing (0.7%–1.1%), social isolation (0.2%–0.3%), and food security (0–0.1%) showed significantly lower response rates. In local EHRs, we identified 80 548 adult patients, of whom 6616 had a diagnosis of diabetic retinopathy, 26 793 had a diagnosis of glaucoma, 40 427 had a diagnosis of cataracts, and 6712 had a diagnosis of age-related macular degeneration. High data coverage was found across all cohorts for variables related to tobacco use (82.84%–89.07%), alcohol use (77.45%–83.66%), and intravenous drug use (84.76%–93.14%). However, low data coverage (< 50% completion) was found for all other variables, including education, finances, social isolation, stress, physical activity, food insecurity, and transportation. We used chi-square testing to assess whether the data coverage varied across different disease cohorts and found that all fields varied significantly (P < 0.001).Conclusions:The limited and highly variable data coverage in both local EHRs and All of Us highlights the need for researchers and providers to develop SDoH data collection strategies and to assemble complete datasets.

A Phenotyping Algorithm to Identify People With HIV in Electronic Health Record Data (HIV-Phen): Development and Evaluation Study.

BackgroundIdentification of people with HIV from electronic health record (EHR) data is an essential first step in the study of important HIV outcomes, such as risk assessment. This task has been historically performed via manual chart review, but the increased availability of large clinical data sets has led to the emergence of phenotyping algorithms to automate this process. Existing algorithms for identifying people with HIV rely on a combination of International Classification of Disease codes and laboratory tests or closely mimic clinical testing guidelines for HIV diagnosis. However, we found that existing algorithms in the literature missed a significant proportion of people with HIV in our data.ObjectiveThe aim of this study is to develop and evaluate HIV-Phen, an updated criteria-based HIV phenotyping algorithm.MethodsWe developed an algorithm using HIV-specific laboratory tests and medications and compared it with previously published algorithms in national and local data sets to identify cohorts of people with HIV. Cohort demographics were compared with those reported in the national and local surveillance data. Chart reviews were performed on a subsample of patients from the local database to calculate the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the algorithm.ResultsOur new algorithm identified substantially more people with HIV in both national (up to an 85.75% increase) and local (up to an 83.20% increase) EHR databases than the previously published algorithms. The demographic characteristics of people with HIV identified using our algorithm were similar to those reported in national and local HIV surveillance data. Our algorithm demonstrated improved sensitivity over existing algorithms (98% vs 56%-92%) while maintaining a similar overall accuracy (96% vs 80%-96%).ConclusionsWe developed and evaluated an updated criteria-based phenotyping algorithm for identifying people with HIV in EHR data that demonstrates improved sensitivity over existing algorithms.

Effect of Electronic Health Record Reminders for Routine Immunizations and Immunizations Needed for Chronic Medical Conditions.

Immunization reminders in electronic health records (EHR) provide clinical decision support (CDS) that can reduce missed immunization opportunities. Little is known about using CDS rules from a regional immunization information system (IIS) to power local EHR immunization reminders. This study aimed to assess the impact of EHR reminders using regional IIS CDS-provided rules on receipt of immunizations in a low-income, urban population for both routine immunizations and those recommended for patients with chronic medical conditions (CMCs). We built an EHR-based immunization reminder using the open-source resource used by the New York City IIS in which we overlaid logic regarding immunizations needed for CMCs. Using a randomized cluster-cross-over pragmatic clinical trial in four academic-affiliated clinics, we compared captured immunization opportunities during patient visits when the reminder was "on" versus "off" for the primary immunization series, school-age boosters, and adolescents. We also assessed coverage of CMC-specific immunizations. Up-to-date immunization was measured by end of quarter. Rates were compared using chi square tests. Overall, 15,343 unique patients were seen for 26,647 visits. The alert significantly impacted captured opportunities to complete the primary series in both well-child and acute care visits (57.6% on vs. 54.3% off, p = 0.001, and 15.3% on vs. 10.1% off, p = 0.02, respectively), among most age groups, and several immunization types. Captured opportunities for CMC-specific immunizations remained low regardless of alert status. The alert did not have an effect on up-to-date immunization overall (89.1 vs. 88.3%). CDS in this population improved captured immunization opportunities. Baseline high rates may have blunted an up-to-date population effect. Converting Centers for Disease Control and Prevention (CDC) rules to generate sufficiently sensitive and specific alerts for CMC-specific immunizations proved challenging, and the alert did not have an impact on CMC-specific immunizations, potentially highlighting need for more work in this area.

The Dutch Data Warehouse, a multicenter and full-admission electronic health records database for critically ill COVID-19 patients

BackgroundThe Coronavirus disease 2019 (COVID-19) pandemic has underlined the urgent need for reliable, multicenter, and full-admission intensive care data to advance our understanding of the course of the disease and investigate potential treatment strategies. In this study, we present the Dutch Data Warehouse (DDW), the first multicenter electronic health record (EHR) database with full-admission data from critically ill COVID-19 patients.MethodsA nation-wide data sharing collaboration was launched at the beginning of the pandemic in March 2020. All hospitals in the Netherlands were asked to participate and share pseudonymized EHR data from adult critically ill COVID-19 patients. Data included patient demographics, clinical observations, administered medication, laboratory determinations, and data from vital sign monitors and life support devices. Data sharing agreements were signed with participating hospitals before any data transfers took place. Data were extracted from the local EHRs with prespecified queries and combined into a staging dataset through an extract–transform–load (ETL) pipeline. In the consecutive processing pipeline, data were mapped to a common concept vocabulary and enriched with derived concepts. Data validation was a continuous process throughout the project. All participating hospitals have access to the DDW. Within legal and ethical boundaries, data are available to clinicians and researchers.ResultsOut of the 81 intensive care units in the Netherlands, 66 participated in the collaboration, 47 have signed the data sharing agreement, and 35 have shared their data. Data from 25 hospitals have passed through the ETL and processing pipeline. Currently, 3464 patients are included in the DDW, both from wave 1 and wave 2 in the Netherlands. More than 200 million clinical data points are available. Overall ICU mortality was 24.4%. Respiratory and hemodynamic parameters were most frequently measured throughout a patient's stay. For each patient, all administered medication and their daily fluid balance were available. Missing data are reported for each descriptive.ConclusionsIn this study, we show that EHR data from critically ill COVID-19 patients may be lawfully collected and can be combined into a data warehouse. These initiatives are indispensable to advance medical data science in the field of intensive care medicine.

Endobronchial Intubation to Facilitate Extraluminal Bronchial Blocker Placement in Young Children: A Retrospective Case Series

Extraluminal bronchial blocker placement has become a well-accepted approach to one-lung ventilation in young children. In some cases, technical issues with placement may require alternative approaches to correct bronchial blocker positioning. The primary aim of this study was to review the authors' experience with using endobronchial intubation to facilitate extraluminal bronchial blocker placement in young children. Single-center case series of pediatric patients undergoing thoracic surgery and one-lung ventilation using a bronchial blocker. Tertiary academic medical center. Pediatric patients < three years of age undergoing thoracic surgery and one-lung ventilation who underwent bronchial blocker placement using endobronchial intubation to facilitate blocker placement. In all patients, the bronchial blocker was inserted through a selectively mainstemmed endotracheal tube to facilitate blocker positioning. No interventions were performed. Fifteen patients were identified after a query of the local electronic health record. There were five right-sided and ten left-sided placements in this cohort. Bronchial blocker placement was successful in 14 of 15 patients using endobronchial intubation to facilitate bronchial blocker placement. In one patient, the bronchial blocker was discovered in the nonsurgical bronchus, following placement with this technique. The bronchial blocker was repositioned manually into the desired mainstem bronchus prior to lateral positioning. Mainstem intubation can be used to facilitate bronchial blocker placement in young children and represents an alternative approach to extraluminal bronchial blocker placement.

The Development and Use of an EHR-Linked Database for Glomerular Disease Research and Quality Initiatives

Background and Objective: The use of electronic health record (EHR) data can facilitate efficient research and quality initiatives. The imprecision of ICD-10 codes for kidney diagnoses has been an obstacle to discrete data-defined diagnoses in the EHR. This manuscript describes the Kidney Research Network (KRN) registry and database that provide an example of a prospective, real-world data glomerular disease registry for research and quality initiatives. Methods: KRN is a multicenter collaboration of patients, physicians, and scientists across diverse health-care settings with a focus on improving treatment options and outcomes for patients with glomerular disease. The registry and data warehouse amasses retrospective and prospective data including EHR, active research study, completed clinical trials, patient reported outcomes, and other relevant data. Following consent, participating sites enter the patient into KRN and provide a physician-confirmed primary kidney diagnosis. Kidney biopsy reports are redacted and uploaded. Site programmers extract local EHR data including demographics, insurance type, zip code, diagnoses, encounters, laboratories, procedures, medications, dialysis/transplant status, vitals, and vital status monthly. Participating sites transform data to conform to a common data model prior to submitting to the Data Analysis and Coordinating Center (DACC). The DACC stores and reviews each site’s EHR data for quality before loading into the KRN database. Results: As of January 2021, 1,192 patients have enrolled in the registry. The database has been utilized for research, clinical trial design, clinical trial end point validation, and supported quality initiatives. The data also support a dashboard allowing enrolling sites to assist with clinical trial enrollment and population health initiatives. Conclusion: A multicenter registry using EHR data, following physician- and biopsy-confirmed glomerular disease diagnosis, can be established and used effectively for research and quality initiatives. This design provides an example which may be readily replicated for other rare or common disease endeavors.

Abstract 14052: Differences in Pediatric Cholesterol Screening Rates Between Family Medicine and Pediatrics Correlate With Conflicting Guidelines

Introduction: In 2011, the National Heart, Lung, and Blood Institute released pediatric cardiovascular guidelines, recommending universal cholesterol screening between ages 9-11 and 17-21 years. This guideline conflicts with other organizations, notably the 2016 United States Preventative Services Task Force (USPSTF) statement which did not endorse universal screening. Our institution has utilized educational tools and electronic health record (EHR) modifications to encourage pediatric cholesterol screening. Hypothesis: Changes in pediatric lipid screening rates within a single institution correlate with release of national guidelines, as well as local educational tools and EHR modifications. Methods: Order placement was defined as ordering a high-density lipoprotein cholesterol level in a patient 9-21 years with ≥ 1 well visit in prior 3 years. Order placement rate (OPR) was calculated per month using 3 months’ moving average smoothing and analyzed based on date and specialty of ordering clinician. Timing of educational tools, EHR modifications, and national guideline release were analyzed for changes in OPR. Results: A total of 36,756 visits from 2010-2019 with 21,239 orders were analyzed. Total OPR was 57.8%. Prior to 2011 guideline, pediatrician (P) OPR was 41% (95% CI: 36-47%) and 9% (7-10%) for family medicine (FM). OPR increased in the 12 months after 2011 guideline, educational initiatives, and EHR changes for P (80%, 95% CI: 76-83%) and FM (21%, 95% CI: 19-25%) . Both P and FM had lower rates after 2016, with greater decrease for FM (p&lt;0.001 for all). Conclusions: OPR was higher in P than FM, with largest OPR changes correlating with release of guidelines. Larger positive changes in OPR were seen in P compared to FM after 2011 guideline, and larger decrease in OPR in FM compared to P correlating with 2016 USPSTF statement release. Conflicting guidelines may contribute to lower overall OPR as well as different screening rates for children cared for by P and FM.

Significant Management Variability of Urethral stricture Disease in United States: Data from the AUA Quality (AQUA) Registry

ObjectiveTo determine the degree of contemporary practice variation for the treatment of urethral stricture disease (USD) given repeated endoscopic management yields poor long-term success. Materials and MethodsThe AUA Quality (AQUA) Registry collects data from participating urologists across practice settings by direct interface with local electronic health record systems. We identified procedures used for USD using Current Procedural Terminology (CPT) and International Statistical Classification of Diseases (ICD-9/-10) codes. We assessed the association between patient and provider factors and repeated endoscopic treatment using generalized linear models. Provider details were derived from AUA Census. ResultsWe identified 20,640 male patients with USD treated surgically in AQUA from 2014-2018. The patients were cared for by 1343 providers at 171 practices, 95% of these community-based. Among patients with USD who had treatment, 20,101(97.9%) underwent endoscopic management. 6218(31%) underwent repeated endoscopic treatment during the study period. Urethroplasty was performed in 539(2.6%) patients. Median patient age at first procedure for endoscopic surgery vs. urethroplasty was 73 vs. 39 years old, respectively (p<0.001). At the practice level, significant variation in rates of repeated endoscopic management was noted. Patients of older age (OR=1.08, 95%CI: 1.06-1.11 for ages ≥80) and patients with a bladder cancer diagnosis (OR=1.17, 95%CI: 1.15-1.20) had higher odds of receiving repeated endoscopic management. Increasing practitioner age was also associated with increased odds of repeated endoscopic management. (OR=1.13, 95%CI: 1.11- 1.16, for practitioners ≥64). ConclusionsRepeated endoscopic management for USD is overused. The utilization of endoscopic management is variable across practices and frequently guideline-discordant, presenting an opportunity for quality improvement.

Real-world implementation of precision psychiatry: Transdiagnostic risk calculator for the automatic detection of individuals at-risk of psychosis

BackgroundRisk estimation models integrated into Electronic Health Records (EHRs) can deliver innovative approaches in psychiatry, but clinicians' endorsement and their real-world usability are unknown. This study aimed to investigate the real-world feasibility of implementing an individualised, transdiagnostic risk calculator to automatically screen EHRs and detect individuals at-risk for psychosis. MethodsFeasibility implementation study encompassing an in-vitro phase (March 2018 to May 2018) and in-vivo phase (May 2018 to April 2019). The in-vitro phase addressed implementation barriers and embedded the risk calculator (predictors: age, gender, ethnicity, index cluster diagnosis, age*gender) into the local EHR. The in-vivo phase investigated the real-world feasibility of screening individuals accessing secondary mental healthcare at the South London and Maudsley NHS Trust. The primary outcome was adherence of clinicians to automatic EHR screening, defined by the proportion of clinicians who responded to alerts from the risk calculator, over those contacted. ResultsIn-vitro phase: implementation barriers were identified/overcome with clinician and service user engagement, and the calculator was successfully integrated into the local EHR through the CogStack platform. In-vivo phase: 3722 individuals were automatically screened and 115 were detected. Clinician adherence was 74% without outreach and 85% with outreach. One-third of clinicians responded to the first email (37.1%) or phone calls (33.7%). Among those detected, cumulative risk of developing psychosis was 12% at six-month follow-up. ConclusionThis is the first implementation study suggesting that combining precision psychiatry and EHR methods to improve detection of individuals with emerging psychosis is feasible. Future psychiatric implementation research is urgently needed.

Resident Identified Violations of Usability Heuristic Principles in Local Electronic Health Records

Difficulties with the electronic health record (EHR) are known to be associated with high physician burnout. Usability studies can evaluate and identify usability issues with the EHR at the end user level. This study was conducted to determine physician perspectives and usability issues of local EHR systems. Survey and focus group methodology were employed. Participants were resident physicians who were members of a resident council in the Midwest. Survey data collected included demographics and perceptions. Focus group data included participants identification of usability principle violations and potential impact to end user. There were 15 survey respondents (across 11 residency programs) who reported use of three different EHR systems: Cerner®, Meditech, and Computerized Patient Record System (CPRS). Satisfaction was greatest with Cerner® as well as most reported level of experience. Focus group respondents reported a variety of usability violations which lead to provider confusion, increased time, alert fatigue, and potential patient safety issues. Violations of usability principles can result in disruption of physician workflow processes and lead to increased documentation time as well as fatigue. These issues have been associated with increased provider burnout. Continuous usability assessments should be conducted at the end user level to promote the development of more effective and efficient EHR interface designs.