Diverse Electronic Health Record Research Articles

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.

Abstract 12687: Evaluating a Coronary Artery Disease Polygenic Risk Score Screening Strategy in a Diverse Patient Cohort at UCLA

Introduction: Recent efforts to predict and mitigate coronary artery disease (CAD) risk have incorporated polygenic risk scores (PGS). Few studies examine the clinical impact of these PGS screening strategies or quantify their performance in clinical terms. Here we estimate the number needed to screen (NNS) of a PGS screening strategy for CAD based using a diverse electronic health record (EHR) linked biobank at UCLA Health. Methods: We leveraged longitudinal EHR data to conduct a synthetic trial. We assumed PGS screening was performed on 6/1/2013 for patients established prior to 1/1/2013 or 6 months into follow time if established later. Patients with preexisting cardiovascular disease or strong statin indications (LDL > 190, diabetes or already on statins) are excluded. Patients with PGS scores in the top 5% of their genetic ancestry groupings (European, East Asian, African, Hispanic) are assumed to have been started on statins for the median 6.9 years of follow up. CAD diagnosis during follow up time was determined by ICD codes. NNS to prevent one CV event is calculated from cohort size and events assuming a statin number needed to treat of 50. Results: Of 33,789 adults, 17,074 were low risk and eligible for PGS screening (35% male with a mean age of 44). NNS to detect one CAD diagnosis was 351, 359, 814, 159 in the European, Hispanic, East Asian and African ancestry groups and NNS to prevent one cardiovascular event was 17,550, 17,950, 40,700, 7,950 respectively. Conclusion: Although PGS accuracy is lower in African ancestry individuals as compared to Europeans, the clinical utility of this PGS-based screening is highest in African ancestries due to increased baseline rates of disease in the African genetic ancestry grouping. Our results demonstrate that PGS accuracy is distinct from clinical utility of PGS-based strategies. Evaluation of screening strategies rather than accuracy alone will be required before PGS screening implementation.

Contrastive learning improves critical event prediction in COVID-19 patients

SummaryDeep learning (DL) models typically require large-scale, balanced training data to be robust, generalizable, and effective in the context of healthcare. This has been a major issue for developing DL models for the coronavirus disease 2019 (COVID-19) pandemic, where data are highly class imbalanced. Conventional approaches in DL use cross-entropy loss (CEL), which often suffers from poor margin classification. We show that contrastive loss (CL) improves the performance of CEL, especially in imbalanced electronic health records (EHR) data for COVID-19 analyses. We use a diverse EHR dataset to predict three outcomes: mortality, intubation, and intensive care unit (ICU) transfer in hospitalized COVID-19 patients over multiple time windows. To compare the performance of CEL and CL, models are tested on the full dataset and a restricted dataset. CL models consistently outperform CEL models, with differences ranging from 0.04 to 0.15 for area under the precision and recall curve (AUPRC) and 0.05 to 0.1 for area under the receiver-operating characteristic curve (AUROC).

Quantifying the Burden of Viral Sepsis During the Coronavirus Disease 2019 Pandemic and Beyond.

Quantifying the Burden of Viral Sepsis During the Coronavirus Disease 2019 Pandemic and Beyond.

Exome-wide evaluation of rare coding variants using electronic health records identifies new gene-phenotype associations.

The clinical impact of rare loss-of-function variants has yet to be determined for most genes. Integration of DNA sequencing data with electronic health records (EHRs) could enhance our understanding of the contribution of rare genetic variation to human disease1. By leveraging 10,900 whole-exome sequences linked to EHR data in the Penn Medicine Biobank, we addressed the association of the cumulative effects of rare predicted loss-of-function variants for each individual gene on human disease on an exome-wide scale, as assessed using a set of diverse EHR phenotypes. After discovering 97 genes with exome-by-phenome-wide significant phenotype associations (P < 10-6), we replicated 26 of these in the Penn Medicine Biobank, as well as in three other medical biobanks and the population-based UK Biobank. Of these 26 genes, five had associations that have been previously reported and represented positive controls, whereas 21 had phenotype associations not previously reported, among which were genes implicated in glaucoma, aortic ectasia, diabetes mellitus, muscular dystrophy and hearing loss. These findings show the value of aggregating rare predicted loss-of-function variants into 'gene burdens' for identifying new gene-disease associations using EHR phenotypes in a medical biobank. We suggest that application of this approach to even larger numbers of individuals will provide the statistical power required to uncover unexplored relationships between rare genetic variation and disease phenotypes.

A genome-first approach to aggregating rare genetic variants in LMNA for association with electronic health record phenotypes

Purpose“Genome-first” approaches, in which genetic sequencing is agnostically linked to associated phenotypes, can enhance our understanding of rare variants’ contributions to disease. Loss-of-function variants in LMNA cause a range of rare diseases, including cardiomyopathy. MethodsWe leveraged exome sequencing from 11,451 unselected individuals in the Penn Medicine Biobank to associate rare variants in LMNA with diverse electronic health record (EHR)–derived phenotypes. We used Rare Exome Variant Ensemble Learner (REVEL) to annotate rare missense variants, clustered predicted deleterious and loss-of-function variants into a “gene burden” (N = 72 individuals), and performed a phenome-wide association study (PheWAS). Major findings were replicated in DiscovEHR. ResultsThe LMNA gene burden was significantly associated with primary cardiomyopathy (p = 1.78E-11) and cardiac conduction disorders (p = 5.27E-07). Most patients had not been clinically diagnosed with LMNA cardiomyopathy. We also noted an association with chronic kidney disease (p = 1.13E-06). Regression analyses on echocardiography and serum labs revealed that LMNA variant carriers had dilated cardiomyopathy and primary renal disease. ConclusionPathogenic LMNA variants are an underdiagnosed cause of cardiomyopathy. We also find that LMNA loss of function may be a primary cause of renal disease. Finally, we show the value of aggregating rare, annotated variants into a gene burden and using PheWAS to identify novel ontologies for pleiotropic human genes.

Developing Phenotypes from Electronic Health Records for Chronic Disease Surveillance

ObjectiveTo utilize clinical data in Electronic Health Records (EHRs) to develop chronic disease phenotypes appropriate for conducting population health surveillance.IntroductionChronic diseases, including hypertension, type 2 diabetes mellitus (diabetes), obesity, and hyperlipidemia, are some of the leading causes of morbidity and mortality in the United States. Monitoring disease prevalence guides public health programs and policies that help prevent this burden. EHRs can supplement traditional sources of chronic disease surveillance, such as health surveys and administrative claims datasets, by offering near real-time data, large sample sizes, and a rich source of clinical data. However, few studies have provided clear, consistent EHR phenotypes that were developed to inform population health surveillance.MethodsRetrospective EHR data were obtained for patients seen at New York University Langone Health in 2017 (n=1,397,446). To better estimate chronic disease burden among New York City (NYC) adults, the patient population was limited to NYC residents aged 20 or older, who were seen in the ambulatory primary care setting (n=153,653). Rule-based algorithms for identifying patients with hypertension, statin-eligibility, diabetes, and obesity were developed based on a combination of diagnostic codes, lab results or vitals, and relevant prescriptions. We compared the performance of our metric definitions to selected phenotypes from the literature using percent agreement and Cohen’s kappa. Patients with discordant disease classifications between the two sets of definitions were analyzed through natural language processing (NLP) on the patients’ 2017 medical notes using a support vector machine model. Statin-eligibility is a novel phenotype and therefore did not have a comparable definition in the literature. Sensitivity analyses were conducted to determine how disease burden changed under alternative rules for each metric.ResultsOf 153,653 adult ambulatory care patients in 2017, an estimated 53.7% had hypertension, 12.4% had diabetes, 27.8% were obese, and 30.0% were statin-eligible under our proposed definitions. The estimated prevalence of hypertension increased from 28.1% to 53.7% when diagnostic codes were supplemented with blood pressure measurements and anti-hypertensive medications, while the estimated prevalence of diabetes increased less than one percentage point with inclusion of diabetes-related medications and elevated A1C measurements. There was high agreement between our obesity (94.5% agreement, k=0.86) and diabetes (96.2% agreement, k=0.81) definitions and selected definitions from the literature and moderate agreement between the hypertension definitions (74.8% agreement, k=0.41). NLP classification of discordant cases had greater alignment with the classification results of our definitions for both hypertension (78.0% agreement) and diabetes (71.2% agreement) but did not show strong agreement with either obesity algorithm. Sensitivity analyses did not have large impacts on prevalence estimates for any of the indicators, with all estimates within two percentage points of the final algorithms.ConclusionsOur proposed rule-based phenotypes using prescriptions, labs, and vitals improved ascertainment of conditions beyond diagnostic codes and were robust to modifications per sensitivity analyses. Results from our algorithms were highly consistent with standard phenotypes from the literature and may improve case capture for surveillance purposes. These algorithms can be replicated across diverse EHR networks and can be weighted to generate population prevalence estimates.

Security and Privacy-Preserving Challenges of e-Health Solutions in Cloud Computing

A systematic and comprehensive review of security and privacy-preserving challenges in e-health solutions indicates various privacy preserving approaches to ensure privacy and security of electronic health records (EHRs) in the cloud. This paper highlights the research challenges and directions concerning cyber security to build a comprehensive security model for EHR. We carry an intensive study in the IEEE, Science Direct, Google Scholar, PubMed, and ACM for papers on EHR approach published between 2000 and 2018 and summarized them in terms of the architecture types as well as evaluation strategies. We surveyed, investigated, and reviewed various aspects of several articles and identified the following tasks: 1) EHR security and privacy; 2) security and privacy requirements of e-health data in the cloud; 3) EHR cloud architecture, and; 4) diverse EHR cryptographic and non-cryptographic approaches. We also discuss some crucial issues and the ample opportunities for advanced research related to security and privacy of EHRs. Since big data provide a great mine of information and knowledge in e-Health applications, serious privacy and security challenges that require immediate attention exist. Studies must focus on efficient comprehensive security mechanisms for EHR and also explore techniques to maintain the integrity and confidentiality of patients’ information.

Treatment patterns, duration and outcomes of pemetrexed maintenance therapy in patients with advanced NSCLC in a real-world setting

Objectives: In patients with non-squamous non-small-cell lung cancer (NSCLC), maintenance therapy regimens, including pemetrexed, have been shown to prolong overall survival (OS) and progression-free survival (PFS). The purpose of this study was to describe real-world maintenance use of pemetrexed and associated outcomes in patients with advanced NSCLC.Methods: This was a retrospective, observational study that used longitudinal, demographically and geographically diverse electronic health record data in the United States. Eligible patients were adults with advanced non-squamous NSCLC who had received maintenance treatment with pemetrexed monotherapy or pemetrexed plus bevacizumab. Descriptive statistics were used to describe the patient population and multivariable logistic regression was used to identify the factors associated with duration of maintenance therapy. Kaplan–Meier curves and Cox regression models were used for time-to-event analysis.Results: Patients receiving pemetrexed maintenance therapy were treated with either pemetrexed monotherapy (66.0%) or pemetrexed plus bevacizumab (34.0%). Carboplatin and pemetrexed (37.9%) or carboplatin, pemetrexed and bevacizumab (36.1%) were the most commonly used first-line therapies observed. The majority (84.9%) of these maintenance patients responded to first-line therapy. The median duration of maintenance therapy was 6.0 months for pemetrexed and bevacizumab and 4.1 months for pemetrexed monotherapy. The median OS from the start of first-line therapy of the total study cohort was 21.5 months (95% CI 20.0, 22.9).Conclusion: Real-world effectiveness of pemetrexed maintenance therapy is similar to that observed in published randomized controlled trials, confirming a role for pemetrexed maintenance in eligible patients in clinical practice.

Abstract P3-17-03: Concordance of real world progression free survival (PFS) on endocrine therapy as first line treatment for metastatic breast cancer using electronic health record with proper quality control versus conventional PFS from a phase 3 trial

Abstract Background: There is growing interest to assess treatment effect with clinical endpoints that are reflective of real world clinical practice based on data systemically collected from the electronic health record (EHR). This study compared real world PFS (rwPFS) among a cohort of female patients (pts) treated with letrozole (LET) monotherapy as first-line therapy for metastatic breast cancer (MBC) in routine clinical practice to PFS using RECIST criteria from the LET alone cohort in a randomized clinical trial (PALOMA-2). Methods: For rwPFS, assessments were based on clinician notes, radiological reports, and pathological reports available in the EHR. Data were extracted from the EHR using technology-enabled abstraction; relevant documents were presented to trained human experts and data were entered into an electronic interface mimicking a case report form, with centralized management and quality controls. The patient cohort was derived from a large, longitudinal, demographically and geographically diverse EHR database of pts receiving cancer care at U.S. community-based and academic clinics (Flatiron Health); pts were all females who began treatment with LET for MBC as first-line treatment between January 1, 2011 and September 30, 2015. PFS in the clinical trial used a conventional definition based on RECIST; data were from the Pfizer clinical study PALOMA-2 database; 222 post-menopausal women in the LET alone arm met pre-specified inclusion/exclusion criteria and assessment intervals with enhanced data collection as previously detailed (Finn, NEJM 2016). All data were de-identified. Propensity score matching using a nearest neighbor algorithm with caliper=0.10 (maximum difference in propensity scores for a match) was performed to assess the consistency between the two approaches to PFS assessment. Kaplan-Meier estimates of median rwPFS/PFS are reported. Results: 107 pts met eligibility criteria from the EHR subset. Pts were younger and had less extensive disease in the PALOMA 2 cohort: The mean age was 60.6 vs 68.6 years and the proportion stage IV at diagnosis was 32.4% versus 39.3% in the LET alone cohort in PALOMA-2 compared to the EHR cohort, respectively. Propensity matching with caliper=0.10 based on age, stage at diagnosis and # of disease sites identified 79 pts from each cohort. Summary of Progression-Free Survival in Matched Data Using Propensity Score Matching Method (Kaplan-Meier estimates) rwPFSRECIST PFSSourceFlatironPALOMA-2Unmatched results N (pts)107222median PFS (months)18.714.595% Confidence Interval(14.6, 24.1)(12.9, 17.1)Matching with Caliper (=0.10) N (pts)7979median PFS (months)18.519.295% Confidence Interval(13.7, 24.1)(13.7, not estimated) Conclusion: This analysis showed concordance between rwPFS and RECIST-based PFS for LET-treated MBC matched pts using a caliper=0.10 in the first line setting. Clinically meaningful information on treatment effect could be derived from a rwPFS assessment based on EHR data abstraction that incorporates proper quality controls. Impact: These data increase confidence in the use of rwPFS as a primary outcome in real-world studies. Citation Format: Bartlett CH, Mardekian J, Cotter M, Huang X, Zhang Z, Parrinello CM, Abernethy AP, Koehler M. Concordance of real world progression free survival (PFS) on endocrine therapy as first line treatment for metastatic breast cancer using electronic health record with proper quality control versus conventional PFS from a phase 3 trial [abstract]. In: Proceedings of the 2017 San Antonio Breast Cancer Symposium; 2017 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2018;78(4 Suppl):Abstract nr P3-17-03.

CER Hub: An informatics platform for conducting comparative effectiveness research using multi-institutional, heterogeneous, electronic clinical data

ObjectivesComparative effectiveness research (CER) requires the capture and analysis of data from disparate sources, often from a variety of institutions with diverse electronic health record (EHR) implementations. In this paper we describe the CER Hub, a web-based informatics platform for developing and conducting research studies that combine comprehensive electronic clinical data from multiple health care organizations. MethodsThe CER Hub platform implements a data processing pipeline that employs informatics standards for data representation and web-based tools for developing study-specific data processing applications, providing standardized access to the patient-centric electronic health record (EHR) across organizations. ResultsThe CER Hub is being used to conduct two CER studies utilizing data from six geographically distributed and demographically diverse health systems. These foundational studies address the effectiveness of medications for controlling asthma and the effectiveness of smoking cessation services delivered in primary care. DiscussionThe CER Hub includes four key capabilities: the ability to process and analyze both free-text and coded clinical data in the EHR; a data processing environment supported by distributed data and study governance processes; a clinical data-interchange format for facilitating standardized extraction of clinical data from EHRs; and a library of shareable clinical data processing applications. ConclusionCER requires coordinated and scalable methods for extracting, aggregating, and analyzing complex, multi-institutional clinical data. By offering a range of informatics tools integrated into a framework for conducting studies using EHR data, the CER Hub provides a solution to the challenges of multi-institutional research using electronic medical record data.

Normalization and standardization of electronic health records for high-throughput phenotyping: the SHARPn consortium.

To develop scalable informatics infrastructure for normalization of both structured and unstructured electronic health record (EHR) data into a unified, concept-based model for high-throughput phenotype extraction. Software tools and applications were developed to extract information from EHRs. Representative and convenience samples of both structured and unstructured data from two EHR systems-Mayo Clinic and Intermountain Healthcare-were used for development and validation. Extracted information was standardized and normalized to meaningful use (MU) conformant terminology and value set standards using Clinical Element Models (CEMs). These resources were used to demonstrate semi-automatic execution of MU clinical-quality measures modeled using the Quality Data Model (QDM) and an open-source rules engine. Using CEMs and open-source natural language processing and terminology services engines-namely, Apache clinical Text Analysis and Knowledge Extraction System (cTAKES) and Common Terminology Services (CTS2)-we developed a data-normalization platform that ensures data security, end-to-end connectivity, and reliable data flow within and across institutions. We demonstrated the applicability of this platform by executing a QDM-based MU quality measure that determines the percentage of patients between 18 and 75 years with diabetes whose most recent low-density lipoprotein cholesterol test result during the measurement year was <100 mg/dL on a randomly selected cohort of 273 Mayo Clinic patients. The platform identified 21 and 18 patients for the denominator and numerator of the quality measure, respectively. Validation results indicate that all identified patients meet the QDM-based criteria. End-to-end automated systems for extracting clinical information from diverse EHR systems require extensive use of standardized vocabularies and terminologies, as well as robust information models for storing, discovering, and processing that information. This study demonstrates the application of modular and open-source resources for enabling secondary use of EHR data through normalization into standards-based, comparable, and consistent format for high-throughput phenotyping to identify patient cohorts.

The Progression of Electronic Health Records and Implications for Psychiatry

The Progression of Electronic Health Records and Implications for Psychiatry