Current Electronic Health Record Research Articles

Optimizing EHR Data

Electronic health records (EHRs) contribute to quality-of-care delivery directly. With a comprehensive and effective use of EHR data, healthcare providers can create precise, personalized treatment plans and seamlessly communicate across departments. By optimizing the data in a health system, clinical engineers can improve these processes and, subsequently, patient flow. This article combines case studies and existing research to explore the challenges and opportunities in current EHR data systems, how evolving artificial intelligence tools can be used to improve data utilization, and the importance of interoperability.

Sex and Gender Variables in Data Set Creation and Data Cleaning for Inclusive and Accurate Reproductive Health Research and Quality Improvement.

Existing data is often used for reproductive research and quality improvement. Electronic health records (EHRs) with a single data field for sex and gender conflate sex assigned at birth, genotype, gender identity, and the presence of anatomic tissue and organs. This is problematic for inclusion of transgender and gender-diverse populations in research. This article discusses considerations with a single-item sex and gender variable drawn from EHR records and describes an audit to determine variable validity as a criterion for inclusion or exclusion in perinatal research. Individuals with a live birth at a large academic medical center from 2010 to 2022 were identified via electronic query, and records with male demographic information were reviewed to validate (1) the patient's date of birth and delivery date in the EHR matched the medical record number, (2) male sex and gender demographic information, and (3) male gender terms in EHR notes. All health records of male birthing individuals (n = 8) had EHR evidence of giving birth within the health system during the timeframe, and the date of birth matched the medical record number of the EHR. All had male gender in the EHR demographic information. Six patients did not have any male gender terms in available EHR notes, only female gender terms. Two records had recent notes using male gender terms. Current EHRs may not have reliable data on the gender and sex of gender-diverse individuals. A single sex and gender variable drawn from EHRs should not be used as inclusion or exclusion criteria for health research or quality improvement without additional record review. EHRs can be updated to collect more data on sex, gender identity, and other relevant variables to improve research and quality improvement.

Spatial Computing Opportunities in Biomedical Decision Support: The Atlas-EHR Vision

We consider the problem of reducing the time that healthcare professionals need to understand the patient’s medical history through the next generation of biomedical decision support. This problem is societally important because it has the potential to improve healthcare quality and patient outcomes. However, navigating electronic health records (EHR) is challenging due to high patient-doctor ratios, potentially long medical histories, urgency of treatment for some medical conditions, and patient variability. The current EHR systems provide only a longitudinal view of patient medical history, which is time-consuming to browse, and doctors often need to engage nurses, residents, and others for initial analysis. To overcome this limitation, we envision an alternative spatial representation of patient histories (e.g., electronic health records) and other biomedical data in the form of Atlas-EHR. Just like Google Maps, which allows a global, national, regional, and local view, Atlas-EHR can start with an overview of the patient’s anatomy and history before drilling down to spatially anatomical subsystems, their individual components, or subcomponents. Atlas-EHR presents a compelling opportunity for spatial computing since healthcare is almost a fifth of the US economy. However, traditional spatial computing designed for geographic use cases (e.g., navigation, land survey, and mapping) faces many hurdles in the biomedical domain. This article presents several open research questions under this theme in five broad areas of spatial computing.

Use of electronic health records to characterize patients with uncontrolled hypertension in two large health system networks

BackgroundImproving hypertension control is a public health priority. However, consistent identification of uncontrolled hypertension using computable definitions in electronic health records (EHR) across health systems remains uncertain.MethodsIn this retrospective cohort study, we applied two computable definitions to the EHR data to identify patients with controlled and uncontrolled hypertension and to evaluate differences in characteristics, treatment, and clinical outcomes between these patient populations. We included adult patients (≥ 18 years) with hypertension (based on either ICD-10 codes of hypertension or two elevated blood pressure [BP] measurements) receiving ambulatory care within Yale-New Haven Health System (YNHHS; a large US health system) and OneFlorida Clinical Research Consortium (OneFlorida; a Clinical Research Network comprised of 16 health systems) between October 2015 and December 2018. We identified patients with controlled and uncontrolled hypertension based on either a single BP measurement from a randomly selected visit or all BP measurements recorded between hypertension identification and the randomly selected visit).ResultsOverall, 253,207 and 182,827 adults at YNHHS and OneFlorida were identified as having hypertension. Of these patients, 83.1% at YNHHS and 76.8% at OneFlorida were identified using ICD-10-CM codes, whereas 16.9% and 23.2%, respectively, were identified using elevated BP measurements (≥ 140/90 mmHg). A total of 24.1% of patients at YNHHS and 21.6% at OneFlorida had both diagnosis code for hypertension and elevated blood pressure measurements. Uncontrolled hypertension was observed among 32.5% and 43.7% of patients at YNHHS and OneFlorida, respectively. Uncontrolled hypertension was disproportionately higher among Black patients when compared with White patients (38.9% versus 31.5% in YNHHS; p < 0.001; 49.7% versus 41.2% in OneFlorida; p < 0.001). Medication prescription for hypertension management was more common in patients with uncontrolled hypertension when compared with those with controlled hypertension (overall treatment rate: 39.3% versus 37.3% in YNHHS; p = 0.04; 42.2% versus 34.8% in OneFlorida; p < 0.001). Patients with controlled and uncontrolled hypertension had similar incidence rates of deaths, CVD events, and healthcare visits at 3, 6, 12, and 24 months. The two computable definitions generated consistent results.ConclusionsWhile the current EHR systems are not fully optimized for disease surveillance and stratification, our findings illustrate the potential of leveraging EHR data to conduct digital population surveillance in the realm of hypertension management.

Reliable generation of privacy-preserving synthetic electronic health record time series via diffusion models.

Electronic health records (EHRs) are rich sources of patient-level data, offering valuable resources for medical data analysis. However, privacy concerns often restrict access to EHRs, hindering downstream analysis. Current EHR deidentification methods are flawed and can lead to potential privacy leakage. Additionally, existing publicly available EHR databases are limited, preventing the advancement of medical research using EHR. This study aims to overcome these challenges by generating realistic and privacy-preserving synthetic EHRs time series efficiently. We introduce a new method for generating diverse and realistic synthetic EHR time series data using denoizing diffusion probabilistic models. We conducted experiments on 6 databases: Medical Information Mart for Intensive Care III and IV, the eICU Collaborative Research Database (eICU), and non-EHR datasets on Stocks and Energy. We compared our proposed method with 8 existing methods. Our results demonstrate that our approach significantly outperforms all existing methods in terms of data fidelity while requiring less training effort. Additionally, data generated by our method yield a lower discriminative accuracy compared to other baseline methods, indicating the proposed method can generate data with less privacy risk. The proposed model utilizes a mixed diffusion process to generate realistic synthetic EHR samples that protect patient privacy. This method could be useful in tackling data availability issues in the field of healthcare by reducing barrier to EHR access and supporting research in machine learning for health. The proposed diffusion model-based method can reliably and efficiently generate synthetic EHR time series, which facilitates the downstream medical data analysis. Our numerical results show the superiority of the proposed method over all other existing methods.

Re-Envisioning Electronic Health Records to Optimize Patient-Centered Cancer Care, Quality, Surveillance, and Research.

Electronic health records (EHRs) are a significant advancement over paper records. However, the full potential of EHRs for improving care quality, patient outcomes, surveillance, and research in cancer care is yet to be realized. The organic evolution of EHRs has resulted in a number of unanticipated consequences including increased time spent by clinicians interfacing with the EHR for daily workflows. Patient access to clinicians and their records has been an important advancement in patient-centered care; however, this has brought to light additional gaps and challenges in EHRs meeting these needs. A significant challenge for EHR design and physician workflows is how best to meet the complex goals and priorities of various stakeholders including providers, researchers, patients, health systems, payors, and regulatory agencies. The National Cancer Policy Forum convened a 2022 workshop, "Innovations in Electronic Health Records for Oncology Care, Research and Surveillance," to address these challenges and to facilitate collaboration across all user groups with the goal of re-envisioning EHRs that will better support shared goals of improving patient outcomes and advancing cancer care and research without overburdening clinicians with administrative tasks. Here, we summarize the current EHR ecosystem as discussed at the workshop and highlight opportunities to improve EHR contributions to oncology evidence and care.

Speech Recognition Technology for Nursing Charting: A Literature Review.

This literature review explores the impact of Speech Recognition Technology (SRT) on nursing documentation within electronic health records (EHR). A search across PubMed, CINAHL, and Google Scholar identified 156 studies, with seven meeting the inclusion criteria. These studies investigated the impact of SRT on documentation time, accuracy, and user satisfaction. Findings suggest SRT, particularly when integrated with artificial intelligence can speed up documentation by up to 15%. However, challenges remain in its implementation in real-world clinical settings and existing EHR workflows. Future studies should focus on developing SRT systems that process conversational nursing assessments and integrate into current EHRs.

Evaluation of technical approaches for real-time data transfer from electronic health record systems

Background and ObjectiveReal-time data (RTD) are data that are delivered immediately after creation. The key feature of RTD is low delivery latency. Information systems in health care are extremely time-sensitive and their building block is the electronic health record (EHR). Real-time data from EHRs play an important role to support decision-making, analytics and coordination of care. This is well mentioned in the literature, but the process has not yet been described, providing reference implementations and testing. Real-time data delivery can technically be achieved using several methods. The objective of this work is to evaluate the performance of different transfer methods of RTD from EHRs by measuring delivery latency. MethodsIn our work we used four approaches to transfer RTD from EHRs: REST hooks, WebSocket notifications, reverse proxy and database triggers. We deployed a Fast Health Interoperability Resources (FHIR) server as it is one of the most widely used EHR standard. For the reference implementations we used Python and Golang. Delivery latency was selected as performance metric, derived by subtracting the timestamp of the EHR resource creation from the timestamp of the EHR resource receipt in millisecond. The data was analyzed using descriptive statistics, cumulative distribution function (CDF), Kruskal-Wallis and post-hoc tests. ResultsThe database trigger approach had the best mean delivery latency 13.52±5.56 ms, followed by the reverse proxy 14.43±4.58 ms, REST hooks 19.26±5.76 ms and WebSocket 27.32±9.44 ms. The reverse proxy showed a tighter range of the values and lower variability. There were significant differences in the latencies between all pairs of approaches, except for reverse proxy and database trigger. ConclusionReal-time data transfer is vital for the development of robust and innovative healthcare applications. Properties of current EHR systems as a data source predefine the approaches for transfer. In our work for the first time the performance of RTD transfer from the EHRs with reference implementations is measured and evaluated. We found that database triggers achieve lowest delivery latency. Reverse proxy performed slightly slower, but offered more stability, followed by REST hooks and WebSocket notifications.

Blockchain Technology for Integrating Electronic Records of Digital Healthcare System

Background: In most healthcare facilities, the shift from paper-based medical records to electronic health records (EHRs) has taken place. However, there are issues with credibility, management, and secure data storage with the existing EHR systems. In the healthcare industry, interoperability and user control over personal data are also major challenges. Block chain technology has become a potent tool that can provide immutability, security, and user control over records that are saved; yet, its potential usage in EHR systems is still not well understood. Objectives: This research attempts to close this knowledge gap by developing an EHR framework that is built on blockchain technology and is compatible with many national and international EHR standards, including HL7 and HIPAA. Methods: In order to investigate the state of the art in the field of EHRs, including blockchain-based EHR implementations, a systematic literature review is the study approach used. Results: The report analyzes numerous national and international EHR standards, identifies the interoperability needs based on these standards, and outlines the interoperability challenges in the current blockchain-based EHR frameworks. Without the requirement for centralized systems, the suggested framework can give the healthcare industry safer ways to exchange health information while also offering the features of immutability, security, and user control over stored records. Conclusion: This work contributes to the understanding of Blockchain technology's potential application in EHR frameworks and offers an interoperable Blockchain-based EHR framework that can meet the requirements outlined in multiple national and international EHR standards.

An Efficient Secure Sharing of Electronic Health Records Using IoT-Based Hyperledger Blockchain

Electronic Health Record (EHR) systems are a valuable and effective tool for exchanging medical information about patients between hospitals and other significant healthcare sector stakeholders in order to improve patient diagnosis and treatment around the world. Nevertheless, the majority of the hospital infrastructures that are now in place lack the proper security, trusted access control, and management of privacy and confidentiality concerns that the current EHR systems are supposed to provide. Goal. For various EHR systems, this research proposes a Blockchain-enabled Hyperledger Fabric Architecture as a solution to this delicate issue. The three steps of the suggested system are the secure upload phase, the secure download phase, and authentication. Patient registration, login, and verification make up the authentication step. The administrator grants authorization to read, edit, delete, or revoke the files following user details verification. In the secure upload phase, feature extraction is carried out first, and then a hashed access policy is created from the extracted feature. Next, the hash value is stored in an IoT-based Hyperledger blockchain. The uploaded EHR files are additionally encrypted before being stored on the cloud server. In the secure download step, the physician uses a hashed access policy to send the request to the cloud and decrypts the corresponding files. The experimental findings demonstrate that the system outperformed cutting-edge techniques. The proposed Modified Key Policy Attribute-Based Encryption performs better for the remaining 10 to 25 mb file sizes. This IoT framework compares MKP-ABE with certain efficiency indicators, such as encryption, decryption period, protection level analysis and encrypted memory use, resource use on decryption, upload time, and transfer time, which are present in the KP-ABE, the ECC, RSA, and AES. Here, the IoT device suggested requires 4008 ms for data encryption and 4138 ms for the data decryption.

A mixed-methods examination of the acceptability of, CareMOBI, a dementia-focused mhealth app, among primary care providers.

CareMOBI (mhealth for Organization to Bolster Interconnectedness) is a user-centered mobile application that supports secure communication between adult day health centers, primary care providers, and family caregivers. The aim of this study was to examine the acceptability of CareMOBI in the primary care setting and identify factors contributing to the likelihood of adoption among primary care providers. We used a mixed-methods concurrent triangulation design. We, first, collected quantitative data using the Technology Acceptance Model questionnaire. Follow-up interview questions allowed participants to elaborate on their experience interacting with CareMOBI. We developed an informational matrix based on major themes within the Technology Acceptance Model (ease of use, value in clinical care, fit within existing workflows, and likelihood of adoption) in which qualitative data were embedded and compared. Our sample included 10 primary care providers. Participants rated CareMOBI high in ease of use (M = 6.71 out of 7), value in clinical care (M = 6.79), and likelihood of adoption (M = 6.71). They found specific functions of CareMOBI helpful, including the summary of health progress and the patient profile. In contrast, participants reported the lowest score for the fit of CareMOBI within existing workflows (M = 5.52). Qualitative feedback attributed this score to concerns over the lack of interoperability between CareMOBI in its current form and electronic health record systems used in the primary care setting. Providers found CareMOBI valuable and easy to use, and there was a high likelihood of eventual adoption. However, apprehensions regarding workflow and electronic health records integration arose, which the team will have to consider as they move forward to the next phase of the application's development.

Design Principles for the Interface of an Automated Medical Reporting System: a User Study in Preoperative Screening

This paper presents a qualitative design science study into the interface of an Automated Medical Reporting (AMR) system in order to establish user-centered design principles. AMR has been proposed as a solution to conquer the administrative burden in healthcare to improve patient-doctor contact. In order to expand this vision by including interface design principles without overlooking the usability aspects, a case study was performed within the preoperative screening department of an academic hospital. In this research, the current screening procedures were investigated by a task analysis, a heuristic evaluation of the current Electronic Health Record system, and stakeholder interviews. The preoperative screenings analysis and the findings of the interviews were translated into design choices. Based on these design choices and IT expert feedback, a treatment design in the form of a high-fidelity prototype of an AMR system for preoperative screenings was developed. This treatment was evaluated by conducting think-aloud sessions and a focus group. Based on the evaluations, ten elementary design principles were formulated for the AMR system interface, which have been categorized into four themes: (1) system status visibility, (2) care provider control, (3) consultation traceability, and (4) patient privacy. We also experienced that medical specialists find it hard to envision the future of their workflow using an AMR system, and that many individual preferences exist.

A qualitative exploration of barriers to efficient and effective structured medication reviews in primary care: Findings from the DynAIRx study.

Structured medication reviews (SMRs), introduced in the United Kingdom (UK) in 2020, aim to enhance shared decision-making in medication optimisation, particularly for patients with multimorbidity and polypharmacy. Despite its potential, there is limited empirical evidence on the implementation of SMRs, and the challenges faced in the process. This study is part of a larger DynAIRx (Artificial Intelligence for dynamic prescribing optimisation and care integration in multimorbidity) project which aims to introduce Artificial Intelligence (AI) to SMRs and develop machine learning models and visualisation tools for patients with multimorbidity. Here, we explore how SMRs are currently undertaken and what barriers are experienced by those involved in them. Qualitative focus groups and semi-structured interviews took place between 2022-2023. Six focus groups were conducted with doctors, pharmacists and clinical pharmacologists (n = 21), and three patient focus groups with patients with multimorbidity (n = 13). Five semi-structured interviews were held with 2 pharmacists, 1 trainee doctor, 1 policy-maker and 1 psychiatrist. Transcripts were analysed using thematic analysis. Two key themes limiting the effectiveness of SMRs in clinical practice were identified: 'Medication Reviews in Practice' and 'Medication-related Challenges'. Participants noted limitations to the efficient and effectiveness of SMRs in practice including the scarcity of digital tools for identifying and prioritising patients for SMRs; organisational and patient-related challenges in inviting patients for SMRs and ensuring they attend; the time-intensive nature of SMRs, the need for multiple appointments and shared decision-making; the impact of the healthcare context on SMR delivery; poor communication and data sharing issues between primary and secondary care; difficulties in managing mental health medications and specific challenges associated with anticholinergic medication. SMRs are complex, time consuming and medication optimisation may require multiple follow-up appointments to enable a comprehensive review. There is a need for a prescribing support system to identify, prioritise and reduce the time needed to understand the patient journey when dealing with large volumes of disparate clinical information in electronic health records. However, monitoring the effects of medication optimisation changes with a feedback loop can be challenging to establish and maintain using current electronic health record systems.

Pre-pandemic assessment: a decade of progress in electronic health record adoption among U.S. hospitals.

As the COVID-19 pandemic loomed, the adoption of electronic health records (EHRs) in US hospitals became a pivotal concern. This study provides a pre-pandemic assessment, highlighting a decade of progress in EHR adoption from 2009 to 2019, with the last available survey conducted from January to June of 2020. It delves into the current EHR adoption rates, variations across different hospital categories, the influence of major vendors, and the challenges in implementing these systems. The study found that basic EHR adoption surged from 6.6% to 81.2%, while comprehensive systems increased from 3.6% to 63.2%. Despite this growth, the findings point to enduring disparities among hospitals, a concentrated market share by 6 vendors (90%), and significant concerns regarding maintenance costs. These insights provide an invaluable snapshot of the state of EHR adoption at the brink of the pandemic, serving as a benchmark to assess hospitals' readiness to utilize digital infrastructure in health care. The conclusions underscore the necessity for strategic policy interventions to encourage a competitive landscape and guarantee equitable access, ultimately strengthening the health care system's responsiveness to global health crises such as COVID-19.

Nursing assessments of women with hypertensive disorders during labor in an academic medical center in Mississippi: a best practice implementation project

The objective of this project was to promote evidence-based practices regarding the nursing assessment of pregnant women with hypertensive disorders admitted to the intrapartum unit. Hypertension during pregnancy has been associated with adverse maternal and fetal outcomes. Ongoing evaluation and nursing care are key in the prevention of complications resulting from hypertensive disorders in pregnancy. The implementation of this best practice project was guided by the JBI Model of Evidence-based Healthcare and used the JBI Practical Application of Clinical Evidence System and Getting Research into Practice audit and feedback strategy to promote evidence-based practices regarding the nursing assessment of pregnant women with hypertensive disorders admitted to an intrapartum unit. Eight audit criteria that were representative of best-practice recommendations for nursing assessment of pregnant women with hypertensive disorders were used. A baseline audit was conducted, followed by the implementation of multiple strategies that were determined by the key stakeholders. The project was finalized with a follow-up audit to determine a change in compliance with best-practice recommendations. Baseline audits revealed an average 45% compliance rate with the eight best practice audit criteria. An on-site simulation event, which included a nursing assessment of normal and abnormal lung sounds along with the hands-on practice of deep tendon reflexes, was provided by project members. Evidence-based assessment guidelines were presented and reviewed with all participants. Input from the nursing staff was gathered regarding current documentation practices and electronic health record accessibility. As a result, an electronic health record change was requested, and improvements in nursing practice were observed for five of the eight audit criteria. Follow-up audits revealed an average compliance rate of 73% for all eight audit criteria, a 28% improvement. Continuing nursing education and ongoing competency refreshers can affect the quality of client care and outcomes by offering occasions to improve or strengthen clinical expertise and proficiency. For this project, the simulation training event improved nursing staff compliance with best practices.

Assessing the accuracy of electronic health record gender identity and REaL data at an academic medical center

BackgroundCollection of accurate patient race, ethnicity, preferred language (REaL) and gender identity in the electronic health record (EHR) is essential for equitable and inclusive care. Misidentification of these factors limits quality measurement of health outcomes in at-risk populations. Therefore, the aim of our study was to assess the accuracy of REaL and gender identity data at our institution.MethodsA survey was administered to 117 random patients, selected from prior day admissions at a large academic medical center in urban central New York. Patients (or guardians) self-reported REaL and gender identity data, selecting from current EHR options. Variables were coded for the presence or absence of a difference from data recorded in the EHR.ResultsRace was misreported in the EHR for 13% of patients and ethnicity for 6%. For most White and Black patients, race was concordant. However, self-identified data for all multiracial patients were discordant with the EHR. Most Non-Hispanic patients had ethnicity correctly documented. Some Hispanic patients were misidentified. There was a significant association between reporting both a race and an ethnicity which differed from the EHR on chi square analysis (P < 0.001). Of those who reported an alternative ethnicity, 71.4% also reported an alternative race. Gender identity was missing for most patients and 11% of the gender-identity entries present in the EHR were discordant with the patient’s self-identity. Preferred language was 100% concordant with the EHR.ConclusionsAt an academic medical center, multiracial and Hispanic patients were more likely to have their demographics misreported in the EHR, and gender identity data were largely missing. Healthcare systems need strategies that support accurate collection of patients’ self-reported ReAL and gender identity data to improve the future ability to identify and address healthcare disparities.

Parkinson's disease diagnosis codes are insufficiently accurate for electronic health record research and differ by race

BackgroundThere are no evidence-based guidelines for data cleaning of electronic health record (EHR) databases in Parkinson's disease (PD). Previous filtering criteria have primarily used the 9th International Statistical Classification of Diseases and Related Health Problems (ICD) with variable accuracy for true PD cases. Prior studies have not excluded atypical or drug-induced parkinsonism, and little is known about differences in accuracy by race. ObjectiveTo determine if excluding parkinsonism diagnoses improves accuracy of ICD-9 and -10 PD diagnosis codes. MethodsWe included ≥2 instances of an ICD-9 and/or −10 code for PD. We removed any records with at least one code indicating atypical or drug-induced parkinsonism first in all races, and then in Non-Hispanic White and Black patients. We manually reviewed 100 randomly selected charts per group before and after filtering, and performed a test of proportion (null hypothesis 0.5) for confirmed PD. Results5633 records had ≥2 instances of a PD code. 2833 remained after filtering. The rate of true PD cases was low before and after filtering to remove parkinsonism codes (0.55 vs. 0.51, p = 0.84). Accuracy was lowest in Black patients before filtering (0.48, p = 0.69), but filtering had a greater (though modest) impact on accuracy (0.68, p < 0.001). ConclusionsThere was inadequate accuracy of PD diagnosis codes in the largest study of ICD-9 and -10 codes. Accuracy was lowest in Black patients but improved the most with removing other parkinsonism codes. This highlights the limitations of using current real-world EHR data in PD research and need for further study.

Concordance between electronic health record-recorded race/ethnicity and parental report in hospitalized children.

Electronic health records (EHRs) have become an important repository for patient race and ethnicity. Misclassification could negatively affect efforts to monitor and reduce health disparities and structural discrimination. We assessed the concordance of parental reports of race/ethnicity for their hospitalized children with EHR-documenteddemographics. We also aimed to describe parents' preferences on how race/ethnicity should be captured in the hospital's EHR. From December 2021 to May 2022, we conducted a single-center cross-sectional survey of parents of hospitalized children asking to describe their child's race/ethnicity and compared these responses to the race/ethnicity documented in the EHR. Concordance was analyzed with a kappa statistic (κ). Additionally, we queried respondents about their awareness of and preferences for race/ethnicity documentation. Of the 275 participants surveyed (79% response rate), there was 69% agreement (κ = 0.56) for race and 80% agreement (κ = 0.63) for ethnicity between parent report and EHR documentation. Sixty-eight parents (21%) felt that the designated categories poorly represent their child's race/ethnicity. Twenty-two (8%) were uncomfortable with their child's race/ethnicity being displayed on the hospital's EHR. Eighty-nine (32%) preferred a more comprehensive list of race/ethnicity categories. Nonconcordance between EHR-recorded race/ethnicity and parental report exists in the EHR for our hospitalized patients, which has implications for describing patient populations and for understanding racial and ethnic disparities. Current EHR categories may be limited in their ability to capture the complexity of these constructs. Future efforts should focus on ensuring that demographic information in the EHR is accurately collected and appropriately reflects families' preferences.

Research Priorities to Support Women Veterans' Reproductive Health and Health Care Within a Learning Health Care System.

Research Priorities to Support Women Veterans' Reproductive Health and Health Care Within a Learning Health Care System.

An EHR Data Quality Evaluation Approach Based on Medical Knowledge and Text Matching

Introduction: Recently, medical artificial intelligence based on Electronic Health Records (EHR) is a significant research field, and EHR data has been widely used in clinical decision support systems and medical diagnosis systems. However, because EHR are used to record the patient's disease information and are not primarily designed for research and discovery, the utility of EHR for research will be hindered by data quality problems. Therefore, it is a meaningful and challenging task to evaluate the data quality of EHR before they are used in medical artificial intelligence. Most of the current EHR data quality evaluation methods are based on some conventional evaluation indicators, and rarely consider the introduction of clinical evidence.Materials and methods: we propose an EHR data quality evaluation approach based on clinical evidence and a deep text matching model. First, based on the medical knowledge of the particular disease, we establish the list of standard clinical evidence descriptions including typical symptoms and special signs, etc. Then we find the relevant clinical evidence from the EHR based on the text matching model, and finally evaluate the quality of the EHR based on the quantity and quality of the relevant clinical evidence found.Results: The experimental results of more than 1,000 EHR for two types of diseases show that our approach can effectively distinguish high-quality EHR from low-quality EHR, and the high-quality EHR found generally contains sufficient and consistent information related to disease diagnosis.Conclusions: Experiments results on a real-world dataset demonstrate the effectiveness of our EHR data quality evaluation approach based on medical knowledge and text matching.