Search

This study leverages electronic health record data in the National COVID Cohort Collaborative’s (N3C) repository to investigate disparities in Paxlovid treatment and to emulate a target trial assessing its effectiveness in reducing COVID-19 hospitalization rates. From an eligible population of 632,822 COVID-19 patients seen at 33 clinical sites across the United States between December 23, 2021 and December 31, 2022, patients were matched across observed treatment groups, yielding an analytical sample of 410,642 patients. We estimate a 65% reduced odds of hospitalization among Paxlovid-treated patients within a 28-day follow-up period, and this effect did not vary by patient vaccination status. Notably, we observe disparities in Paxlovid treatment, with lower rates among Black and Hispanic or Latino patients, and within socially vulnerable communities. Ours is the largest study of Paxlovid’s real-world effectiveness to date, and our primary findings are consistent with previous randomized control trials and real-world studies.

Although the COVID-19 pandemic has persisted for over 2 years, reinfections with SARS-CoV-2 are not well understood. We use the electronic health record (EHR)-based study cohort from the National COVID Cohort Collaborative (N3C) as part of the NIH Researching COVID to Enhance Recovery (RECOVER) Initiative to characterize reinfection, understand development of Long COVID after reinfection, and compare severity of reinfection with initial infection. We validate previous findings of reinfection incidence (5.9%), the occurrence of most reinfections during the Omicron epoch, and evidence of multiple reinfections. We present novel findings that Long COVID diagnoses occur closer to the index date for infection or reinfection in the Omicron BA epoch. We report lower albumin levels leading up to reinfection and a statistically significant association of severity between first infection and reinfection (chi-squared value: 9446.2, p-value: 0) with a medium effect size (Cramer’s V: 0.18, DoF = 4).

Identifying individuals with a higher risk of developing severe COVID-19 outcomes will inform targeted or more intensive clinical monitoring and management. To date, there is mixed evidence regarding the impact of pre-existing autoimmune disease (AID) diagnosis and/or immunosuppressant (IS) exposure on developing severe COVID-19 outcomes.A retrospective cohort of adults diagnosed with COVID-19 was created in the National COVID Cohort Collaborative enclave. Two outcomes, life-threatening disease, and hospitalization were evaluated by using logistic regression models with and without adjustment for demographics and comorbidities.Of the 2,453,799 adults diagnosed with COVID-19, 191,520 (7.81%) had a pre-existing AID diagnosis and 278,095 (11.33%) had a pre-existing IS exposure. Logistic regression models adjusted for demographics and comorbidities demonstrated that individuals with a pre-existing AID (OR = 1.13, 95% CI 1.09 - 1.17; P< 0.001), IS (OR= 1.27, 95% CI 1.24 - 1.30; P< 0.001), or both (OR = 1.35, 95% CI 1.29 - 1.40; P< 0.001) were more likely to have a life-threatening COVID-19 disease. These results were consistent when evaluating hospitalization. A sensitivity analysis evaluating specific IS revealed that TNF inhibitors were protective against life-threatening disease (OR = 0.80, 95% CI 0.66- 0.96; P=0.017) and hospitalization (OR = 0.80, 95% CI 0.73 - 0.89; P< 0.001).Patients with pre-existing AID, exposure to IS, or both are more likely to have a life-threatening disease or hospitalization. These patients may thus require tailored monitoring and preventative measures to minimize negative consequences of COVID-19.

Long COVID, or complications arising from COVID-19 weeks after infection, has become a central concern for public health experts. The United States National Institutes of Health founded the RECOVER initiative to better understand long COVID. We used electronic health records available through the National COVID Cohort Collaborative to characterize the association between SARS-CoV-2 vaccination and long COVID diagnosis. Among patients with a COVID-19 infection between August 1, 2021 and January 31, 2022, we defined two cohorts using distinct definitions of long COVID—a clinical diagnosis (n = 47,404) or a previously described computational phenotype (n = 198,514)—to compare unvaccinated individuals to those with a complete vaccine series prior to infection. Evidence of long COVID was monitored through June or July of 2022, depending on patients’ data availability. We found that vaccination was consistently associated with lower odds and rates of long COVID clinical diagnosis and high-confidence computationally derived diagnosis after adjusting for sex, demographics, and medical history., The extent to which COVID-19 vaccination protects against long COVID is not well understood. Here, the authors use electronic health record data from the United States and find that, for people who received their vaccination prior to infection, vaccination was associated with lower incidence of long COVID.

Machine learning (ML)-driven computable phenotypes are among the most challenging to share and reproduce. Despite this difficulty, the urgent public health considerations around Long COVID make it especially important to ensure the rigor and reproducibility of Long COVID phenotyping algorithms such that they can be made available to a broad audience of researchers. As part of the NIH Researching COVID to Enhance Recovery (RECOVER) Initiative, researchers with the National COVID Cohort Collaborative (N3C) devised and trained an ML-based phenotype to identify patients highly probable to have Long COVID. Supported by RECOVER, N3C and NIH’s All of Us study partnered to reproduce the output of N3C’s trained model in the All of Us data enclave, demonstrating model extensibility in multiple environments. This case study in ML-based phenotype reuse illustrates how open-source software best practices and cross-site collaboration can de-black-box phenotyping algorithms, prevent unnecessary rework, and promote open science in informatics.

Additional file 1: Supplemental methods, supplemental table 1, supplemental figures 1-3. Supplemental Methods – Description of additional methods used, including: Community detection in diagnosis analysis. network stability, age-stratified condition co-occurrence networks, and standard N3C data quality checks. Supplemental Table 1. – Demographic breakdown of all COVID-positive patients across 34 N3C sites. Supplemental Figure 1. – Uptake of U09.9 and B94.8 ICD-10_CM codes across 34 N3C sites. Supplemental Figure 2. – Common medications among patients with a U09.9 code. Supplemental Figure 3. – Common conditions among patients with a U09.9 code

Given the growing number of prediction algorithms developed to predict COVID-19 mortality, we evaluated the transportability of a mortality prediction algorithm using a multi-national network of healthcare systems. We predicted COVID-19 mortality using baseline commonly measured laboratory values and standard demographic and clinical covariates across healthcare systems, countries, and continents. Specifically, we trained a Cox regression model with nine measured laboratory test values, standard demographics at admission, and comorbidity burden pre-admission. These models were compared at site, country, and continent level. Of the 39,969 hospitalized patients with COVID-19 (68.6% male), 5717 (14.3%) died. In the Cox model, age, albumin, AST, creatine, CRP, and white blood cell count are most predictive of mortality. The baseline covariates are more predictive of mortality during the early days of COVID-19 hospitalization. Models trained at healthcare systems with larger cohort size largely retain good transportability performance when porting to different sites. The combination of routine laboratory test values at admission along with basic demographic features can predict mortality in patients hospitalized with COVID-19. Importantly, this potentially deployable model differs from prior work by demonstrating not only consistent performance but also reliable transportability across healthcare systems in the US and Europe, highlighting the generalizability of this model and the overall approach.

Healthcare datasets obtained from Electronic Health Records have proven to be extremely useful to assess associations between patients' predictors and outcomes of interest. However, these datasets often suffer from missing values in a high proportion of cases and the simple removal of these cases may introduce severe bias. For these reasons, several multiple imputation algorithms have been proposed to attempt to recover the missing information. Each algorithm presents strengths and weaknesses, and there is currently no consensus on which multiple imputation algorithms works best in a given scenario. Furthermore, the selection of each algorithm parameters and data-related modelling choices are also both crucial and challenging. In this paper, we propose a novel framework to numerically evaluate strategies for handling missing data in the context of statistical analysis, with a particular focus on multiple imputation techniques. We demonstrate the feasibility of our approach on a large cohort of type-2 diabetes patients provided by the National COVID Cohort Collaborative (N3C) Enclave, where we explored the influence of various patient characteristics on outcomes related to COVID-19. Our analysis included classic multiple imputation techniques as well as simple complete-case Inverse Probability Weighted models. The experiments presented here show that our approach could effectively highlight the most valid and performant missing-data handling strategy for our case study. Moreover, our methodology allowed us to gain an understanding of the behavior of the different models and of how it changed as we modified their parameters. Our method is general and can be applied to different research fields and on datasets containing heterogeneous types.

Additional file 1. Figures S1–S2, Tables S1–S4, and Supplemental Note 1.

Background For some SARS-CoV-2 survivors, recovery from the acute phase of the infection has been grueling with lingering effects. Many of the symptoms characterized as the post-acute sequelae of COVID-19 (PASC) could have multiple causes or are similarly seen in non-COVID patients. Accurate identification of PASC phenotypes will be important to guide future research and help the healthcare system focus its efforts and resources on adequately controlled age- and gender-specific sequelae of a COVID-19 infection. Methods In this retrospective electronic health record (EHR) cohort study, we applied a computational framework for knowledge discovery from clinical data, MLHO, to identify phenotypes that positively associate with a past positive reverse transcription-polymerase chain reaction (RT-PCR) test for COVID-19. We evaluated the post-test phenotypes in two temporal windows at 3–6 and 6–9 months after the test and by age and gender. Data from longitudinal diagnosis records stored in EHRs from Mass General Brigham in the Boston Metropolitan Area was used for the analyses. Statistical analyses were performed on data from March 2020 to June 2021. Study participants included over 96 thousand patients who had tested positive or negative for COVID-19 and were not hospitalized. Results We identified 33 phenotypes among different age/gender cohorts or time windows that were positively associated with past SARS-CoV-2 infection. All identified phenotypes were newly recorded in patients’ medical records 2 months or longer after a COVID-19 RT-PCR test in non-hospitalized patients regardless of the test result. Among these phenotypes, a new diagnosis record for anosmia and dysgeusia (OR 2.60, 95% CI [1.94–3.46]), alopecia (OR 3.09, 95% CI [2.53–3.76]), chest pain (OR 1.27, 95% CI [1.09–1.48]), chronic fatigue syndrome (OR 2.60, 95% CI [1.22–2.10]), shortness of breath (OR 1.41, 95% CI [1.22–1.64]), pneumonia (OR 1.66, 95% CI [1.28–2.16]), and type 2 diabetes mellitus (OR 1.41, 95% CI [1.22–1.64]) is one of the most significant indicators of a past COVID-19 infection. Additionally, more new phenotypes were found with increased confidence among the cohorts who were younger than 65. Conclusions The findings of this study confirm many of the post-COVID-19 symptoms and suggest that a variety of new diagnoses, including new diabetes mellitus and neurological disorder diagnoses, are more common among those with a history of COVID-19 than those without the infection. Additionally, more than 63% of PASC phenotypes were observed in patients under 65 years of age, pointing out the importance of vaccination to minimize the risk of debilitating post-acute sequelae of COVID-19 among younger adults.

Made available in DSpace on 2022-04-29T08:35:59Z (GMT). No. of bitstreams: 0 Previous issue date: 2021-12-01 Division of Intramural Research, National Institute of Allergy and Infectious Diseases Division of Microbiology and Infectious Diseases, National Institute of Allergy and Infectious Diseases National Institute of Allergy and Infectious Diseases National Center for Advancing Translational Sciences National Heart, Lung, and Blood Institute National Institute of Environmental Health Sciences U.S. National Library of Medicine National Institute of Neurological Disorders and Stroke Division of Cancer Prevention, National Cancer Institute Neurological complications worsen outcomes in COVID-19. To define the prevalence of neurological conditions among hospitalized patients with a positive SARS-CoV-2 reverse transcription polymerase chain reaction test in geographically diverse multinational populations during early pandemic, we used electronic health records (EHR) from 338 participating hospitals across 6 countries and 3 continents (January–September 2020) for a cross-sectional analysis. We assessed the frequency of International Classification of Disease code of neurological conditions by countries, healthcare systems, time before and after admission for COVID-19 and COVID-19 severity. Among 35,177 hospitalized patients with SARS-CoV-2 infection, there was an increase in the proportion with disorders of consciousness (5.8%, 95% confidence interval [CI] 3.7–7.8%, pFDR < 0.001) and unspecified disorders of the brain (8.1%, 5.7–10.5%, pFDR < 0.001) when compared to the pre-admission proportion. During hospitalization, the relative risk of disorders of consciousness (22%, 19–25%), cerebrovascular diseases (24%, 13–35%), nontraumatic intracranial hemorrhage (34%, 20–50%), encephalitis and/or myelitis (37%, 17–60%) and myopathy (72%, 67–77%) were higher for patients with severe COVID-19 when compared to those who never experienced severe COVID-19. Leveraging a multinational network to capture standardized EHR data, we highlighted the increased prevalence of central and peripheral neurological phenotypes in patients hospitalized with COVID-19, particularly among those with severe disease. Department of Biostatistics Epidemiology and Informatics University of Pennsylvania Perelman School of Medicine Department of Biomedical Informatics Harvard Medical School Department of Neurology University of Pittsburgh, Biomedical Science Tower 3, Suite 7014, 3501 5th Avenue Department of Pediatrics Wake Forest School of Medicine Department of Critical Care National University Health Systems Department of Preventive Medicine Northwestern University Department of Biomedical Informatics University of Pittsburgh Department of Surgery National University Health Systems Department of Internal Medicine University of Kansas Medical Center Data Analytics Center University of Pennsylvania Health System Department of Computational Medicine and Bioinformatics University of Michigan Department of Biomedical Informatics University of Kentucky Department of Legal Economic and Social Sciences University Magna Graecia of Catanzaro Health Catalyst INC. Department of Surgery ASST Pavia Lombardia Region Health System Clinical Research Unit of Botucatu Medical School São Paulo State University Pediatric Emergency Department Hôpital Necker-Enfants Malades Assistance Publique-Hôpitaux de Paris National Center for Infectious Diseases Tan Tock Seng Hospital Departments of Biomedical Informatics Pediatrics Cincinnati Children’s Hospital Medical Center University of Cincinnati Department of Pediatrics Medical University of South Carolina Department of Surgery St. Luke’s University Health Network Department of Medicine David Geffen School of Medicine at UCLA UOC Ricerca Innovazione e Brand Reputation ASST Papa Giovanni XXIII Department of Electrical Computer and Biomedical Engineering University of Pavia IT Department Innovation & Data APHP Greater Paris University Hospital I.T. Department ASST Pavia Health Informatics Hospital Universitario, 12 de Octubre Strategy and Transformation Department APHP Greater Paris University Hospital Faculty of Medicine and Medical Center University of Freiburg Digital Research Informatics and Virtual Environments (DRIVE), Great Ormond Street Hospital for Children Scientific Direction IRCCS Ca’ Granda Ospedale Maggiore Policlinico di Milano North Carolina Translational and Clinical Sciences (NC TraCS) Institute University of North Carolina BIOMERIS (BIOMedical Research Informatics Solutions) Department of Biomedical Informatics HEGP APHP Greater Paris University Hospital Department of Medical and Surgical Sciences Data Analytics Research Center University Magna Graecia of Catanzaro Department of Anesthesia St. Luke’s University Health Network Université Paris-Saclay Inria CEA INRIA Sophia-Antipolis–ZENITH Team LIRMM Computational Health Informatics Program Boston Children’s Hospital Department of Internal Medicine University of Kentucky Unit of Internal Medicine and Endocrinology Istituti Clinici Scientifici Maugeri SpA SB IRCCS Department of Internal Medicine and Therapeutics University of Pavia Informatics Institute University of Alabama at Birmingham IAM Unit Bordeaux University Hospital/ERIAS-Inserm U1219 BPH Biomedical Informatics Center Medical University of South Carolina Clinical Research Informatics Boston Children’s Hospital Department of Biomedical and Health Informatics Children’s Hospital of Philadelphia SED/SIERRA Inria Centre de Paris Health Information Technology & Services University of Michigan Internal Medicine Department Botucatu Medical School São Paulo State University Heinrich-Lanz-Center for Digital Health University Medicine Mannheim Heidelberg University Department of Anesthesiology Critical Care and Pain Medicine Boston Children’s Hospital Department of Learning Health Sciences University of Michigan Medical School MSHI Medical University of South Carolina Department of Medicine Massachusetts General Hospital Division of Human Genetics Department of Pediatrics The Children’s Hospital of Philadelphia Center for Medical Information and Communication Technology University Hospital Renaissance Computing Institute/Department of Computer Science University of North Carolina Clinical Research Unit Saint Antoine Hospital APHP Greater Paris University Hospital Clevy.io Department of Biostatistics Harvard T.H. Chan School of Public Health VA Informatics and Computing Infrastructure VA Salt Lake City Health Care System MICHR Informatics University of Michigan Laboratory of Informatics and Systems Engineering for Clinical Research Istituti Clinici Scientifici Maugeri SpA SB IRCCS Harvard Catalyst Harvard Medical School Clinical Research Unit Paris Saclay APHP Greater Paris University Hospital Department of Anesthesiology and Critical Care Children’s Hospital of Philadelphia VA Informatics and Computing Infrastructure Tennessee Valley Healthcare System Veterans Affairs Medical Center École Normale Supérieure PSL Université Paris BIG-ARC The University of Texas Health Science Center at Houston School of Biomedical Informatics Pediatric Infectious Disease Department Hospital Universitario, 12 de Octubre Department of Infectious Diseases Great Ormond Street Hospital for Children Department of Neurology Massachusetts General Hospital Internal Medicine Department of Botucatu Medical School São Paulo State University Department of Pediatrics Boston Children’s Hospital Center for Biomedical Informatics Wake Forest School of Medicine Department of Medical Informatics University of Erlangen-Nürnberg Department of Veterans Affairs Office of Research and Development Biomedical Data Science Lab ITACA Institute Universitat Politècnica de València Nurse Department of FMB-Medicine School of Botucatu Management Engineering ASST Pavia Lombardia Region Health System Department of Anesthesiology University Hospital Erlangen FAU Erlangen-Nürnberg Critical Care Medicine Department of Medicine St. Luke’s University Health Network Department of Medicine National University Hospital Department of Information Management Chang Gung University Clinical & Translational Science Institute Medical College of Wisconsin Montréal Neurological Institute McGill University SequeL Inria Lille Respiratory Department ICS S Maugeri IRCCS Department of Health Management and Informatics University of Missouri Department of Oncology ASST Papa Giovanni XXIII Clinical Research Unit of Botucatu Medical School São Paulo State University Internal Medicine Department Botucatu Medical School São Paulo State University Internal Medicine Department of Botucatu Medical School São Paulo State University Division of Intramural Research, National Institute of Allergy and Infectious Diseases: AI11679 Division of Microbiology and Infectious Diseases, National Institute of Allergy and Infectious Diseases: AI11679 National Institute of Allergy and Infectious Diseases: AI11679 National Center for Advancing Translational Sciences: CTSA Award #UL1TR001878 National Center for Advancing Translational Sciences: CTSA Award #UL1TR002366 National Heart, Lung, and Blood Institute: K23HL148394 National Institute of Environmental Health Sciences: P30ES017885 U.S. National Library of Medicine: R01LM012095 National Institute of Neurological Disorders and Stroke: R01NS098023 Division of Cancer Prevention, National Cancer Institute: U24CA210967 National Center for Advancing Translational Sciences: UL1TR001420 National Center for Advancing Translational Sciences: UL1TR001857

This cohort study aims to describe international hospitalization trends and key epidemiological and clinical features of children and youth with COVID-19., Key Points Question What are international trends in hospitalizations for children and youth with SARS-CoV-2, and what are the epidemiological and clinical features of these patients? Findings This cohort study of 671 children and youth found discrete surges in hospitalizations with variable trends and timing across countries. Common complications included cardiac arrhythmias and viral pneumonia, and laboratory findings included elevations in markers of inflammation and abnormalities of coagulation; few children and youth were treated with medications directed specifically at SARS-CoV-2. Meaning These findings suggest large-scale informatics-based approaches used to incorporate electronic health record data across health care systems can provide an efficient source of information to monitor disease activity and define epidemiological and clinical features of pediatric patients hospitalized with SARS-CoV-2 infections., Importance Additional sources of pediatric epidemiological and clinical data are needed to efficiently study COVID-19 in children and youth and inform infection prevention and clinical treatment of pediatric patients. Objective To describe international hospitalization trends and key epidemiological and clinical features of children and youth with COVID-19. Design, Setting, and Participants This retrospective cohort study included pediatric patients hospitalized between February 2 and October 10, 2020. Patient-level electronic health record (EHR) data were collected across 27 hospitals in France, Germany, Spain, Singapore, the UK, and the US. Patients younger than 21 years who tested positive for COVID-19 and were hospitalized at an institution participating in the Consortium for Clinical Characterization of COVID-19 by EHR were included in the study. Main Outcomes and Measures Patient characteristics, clinical features, and medication use. Results There were 347 males (52%; 95% CI, 48.5-55.3) and 324 females (48%; 95% CI, 44.4-51.3) in this study’s cohort. There was a bimodal age distribution, with the greatest proportion of patients in the 0- to 2-year (199 patients [30%]) and 12- to 17-year (170 patients [25%]) age range. Trends in hospitalizations for 671 children and youth found discrete surges with variable timing across 6 countries. Data from this cohort mirrored national-level pediatric hospitalization trends for most countries with available data, with peaks in hospitalizations during the initial spring surge occurring within 23 days in the national-level and 4CE data. A total of 27 364 laboratory values for 16 laboratory tests were analyzed, with mean values indicating elevations in markers of inflammation (C-reactive protein, 83 mg/L; 95% CI, 53-112 mg/L; ferritin, 417 ng/mL; 95% CI, 228-607 ng/mL; and procalcitonin, 1.45 ng/mL; 95% CI, 0.13-2.77 ng/mL). Abnormalities in coagulation were also evident (D-dimer, 0.78 ug/mL; 95% CI, 0.35-1.21 ug/mL; and fibrinogen, 477 mg/dL; 95% CI, 385-569 mg/dL). Cardiac troponin, when checked (n = 59), was elevated (0.032 ng/mL; 95% CI, 0.000-0.080 ng/mL). Common complications included cardiac arrhythmias (15.0%; 95% CI, 8.1%-21.7%), viral pneumonia (13.3%; 95% CI, 6.5%-20.1%), and respiratory failure (10.5%; 95% CI, 5.8%-15.3%). Few children were treated with COVID-19–directed medications. Conclusions and Relevance This study of EHRs of children and youth hospitalized for COVID-19 in 6 countries demonstrated variability in hospitalization trends across countries and identified common complications and laboratory abnormalities in children and youth with COVID-19 infection. Large-scale informatics-based approaches to integrate and analyze data across health care systems complement methods of disease surveillance and advance understanding of epidemiological and clinical features associated with COVID-19 in children and youth.

ObjectiveCoronavirus disease 2019 (COVID-19) poses societal challenges that require expeditious data and knowledge sharing. Though organizational clinical data are abundant, these are largely inaccessible to outside researchers. Statistical, machine learning, and causal analyses are most successful with large-scale data beyond what is available in any given organization. Here, we introduce the National COVID Cohort Collaborative (N3C), an open science community focused on analyzing patient-level data from many centers.Materials and methodsThe Clinical and Translational Science Award Program and scientific community created N3C to overcome technical, regulatory, policy, and governance barriers to sharing and harmonizing individual-level clinical data. We developed solutions to extract, aggregate, and harmonize data across organizations and data models, and created a secure data enclave to enable efficient, transparent, and reproducible collaborative analytics.ResultsOrganized in inclusive workstreams, we created legal agreements and governance for organizations and researchers; data extraction scripts to identify and ingest positive, negative, and possible COVID-19 cases; a data quality assurance and harmonization pipeline to create a single harmonized dataset; population of the secure data enclave with data, machine learning, and statistical analytics tools; dissemination mechanisms; and a synthetic data pilot to democratize data access.ConclusionsThe N3C has demonstrated that a multisite collaborative learning health network can overcome barriers to rapidly build a scalable infrastructure incorporating multiorganizational clinical data for COVID-19 analytics. We expect this effort to save lives by enabling rapid collaboration among clinicians, researchers, and data scientists to identify treatments and specialized care and thereby reduce the immediate and long-term impacts of COVID-19.

While we pay attention to the latest advances in clinical natural language processing (NLP), we can notice some resistance in the clinical and translational research community to adopt NLP models due to limited transparency, interpretability, and usability. In this study, we proposed an open natural language processing development framework. We evaluated it through the implementation of NLP algorithms for the National COVID Cohort Collaborative (N3C). Based on the interests in information extraction from COVID-19 related clinical notes, our work includes 1) an open data annotation process using COVID-19 signs and symptoms as the use case, 2) a community-driven ruleset composing platform, and 3) a synthetic text data generation workflow to generate texts for information extraction tasks without involving human subjects. The corpora were derived from texts from three different institutions (Mayo Clinic, University of Kentucky, University of Minnesota). The gold standard annotations were tested with a single institution's (Mayo) ruleset. This resulted in performances of 0.876, 0.706, and 0.694 in F-scores for Mayo, Minnesota, and Kentucky test datasets, respectively. The study as a consortium effort of the N3C NLP subgroup demonstrates the feasibility of creating a federated NLP algorithm development and benchmarking platform to enhance multi-institution clinical NLP study and adoption. Although we use COVID-19 as a use case in this effort, our framework is general enough to be applied to other domains of interest in clinical NLP., Comment: update on contents

PurposeThe Electronic Medical Record Search Engine (EMERSE) is a software tool built to aid research spanning cohort discovery, population health, and data abstraction for clinical trials. EMERSE is now live at three academic medical centers, with additional sites currently working on implementation. In this report, we describe how EMERSE has been used to support cancer research based on a variety of metrics.MethodsWe identified peer-reviewed publications that used EMERSE through online searches as well as through direct e-mails to users based on audit logs. These logs were also used to summarize use at each of the three sites. Search terms for two of the sites were characterized using the natural language processing tool MetaMap to determine to which semantic types the terms could be mapped.ResultsWe identified a total of 326 peer-reviewed publications that used EMERSE through August 2019, although this is likely an underestimation of the true total based on the use log analysis. Oncology-related research comprised nearly one third (n = 105; 32.2%) of all research output. The use logs showed that EMERSE had been used by multiple people at each site (nearly 3,500 across all three) who had collectively logged into the system > 100,000 times. Many user-entered search queries could not be mapped to a semantic type, but the most common semantic type for terms that did match was "disease or syndrome," followed by "pharmacologic substance."ConclusionEMERSE has been shown to be a valuable tool for supporting cancer research. It has been successfully deployed at other sites, despite some implementation challenges unique to each deployment environment.

Electronic health record (EHR)-based computable phenotypes are algorithms used to identify individuals or populations with clinical conditions or events of interest within a clinical data repository. Due to a lack of EHR data standardization, computable phenotypes can be semantically ambiguous and difficult to share across institutions. In this research, I propose a new computable phenotyping methodological framework based on semantic web technologies, specifically ontologies, the Resource Description Framework (RDF) data format, triplestores, and Web Ontology Language (OWL) reasoning. My hypothesis is that storing and analyzing clinical data using these technologies can begin to address the critical issues of semantic ambiguity and lack of interoperability in the context of computable phenotyping. To test this hypothesis, I compared the performance of two variants of two computable phenotypes (for depression and rheumatoid arthritis, respectively). The first variant of each phenotype used a list of ICD-10-CM codes to define the condition; the second variant used ontology concepts from SNOMED and the Human Phenotype Ontology (HPO). After executing each variant of each phenotype against a clinical data repository, I compared the patients matched in each case to see where the different variants overlapped and diverged. Both the ontologies and the clinical data were stored in an RDF triplestore to allow me to assess the interoperability advantages of the RDF format for clinical data. All tested methods successfully identified cohorts in the data store, with differing rates of overlap and divergence between variants. Depending on the phenotyping use case, SNOMED and HPO’s ability to more broadly define many conditions due to complex relationships between their concepts may be seen as an advantage or a disadvantage. I also found that RDF triplestores do indeed provide interoperability advantages, despite being far less commonly used in clinical data applications than relational databases. Despite the fact that these methods and technologies are not “one-size-fits-all,” the experimental results are encouraging enough for them to (1) be put into practice in combination with existing phenotyping methods or (2) be used on their own for particularly well-suited use cases.

Presentation to the International Society of Environmental Epidemiology 2020 Virtual Meeting (ISEE) August 2020

Electronic Health Record (EHR) systems typically define laboratory test results using the Laboratory Observation Identifier Names and Codes (LOINC) and can transmit them using Fast Healthcare Interoperability Resource (FHIR) standards. LOINC has not yet been semantically integrated with computational resources for phenotype analysis. Here, we provide a method for mapping LOINC-encoded laboratory test results transmitted in FHIR standards to the Human Phenotype Ontology (HPO) terms. We annotated the medical implications of 2421 commonly used laboratory tests with HPO terms. Using these annotations, a software assesses laboratory test results and converts each into an HPO term. We validated our approach with EHR data from 15,681 patients with respiratory complaints and identified known biomarkers for asthma. Finally, we provide a freely available SMART on FHIR application that can be used within EHR systems. Our approach allows reusing readily available laboratory tests in EHR for deep phenotyping and using the hierarchical structure of HPO for association studies with medical outcomes and genomics.

Red blood cell (RBC) alloimmunization is a significant clinical complication of sickle cell disease (SCD). It can lead to difficulty with cross-matching for future transfusions and may sometimes trigger life-threatening delayed hemolytic transfusion reactions. We conducted a retrospective study to explore the association of clinical complications and age of RBC with alloimmunization in patients with SCD followed at a single institution from 2005 to 2012. One hundred and sixty six patients with a total of 488 RBC transfusions were evaluated. Nineteen patients (11%) developed new alloantibodies following blood transfusions during the period of review. The median age of RBC units was 20 days (interquartile range: 14-27 days). RBC antibody formation was significantly associated with the age of RBC units (P = 0.002), with a hazard ratio of 3.5 (95% CI: 1.71-7.11) for a RBC unit that was 7 days old and 9.8 (95% CI: 2.66-35.97) for a unit that was 35 days old, 28 days after the blood transfusion. No association was observed between RBC alloimmunization and acute vaso-occlusive complications. Although increased echocardiography-derived tricuspid regurgitant jet velocity (TRV) was associated with the presence of RBC alloantibodies (P = 0.02), TRV was not significantly associated with alloimmunization when adjusted for patient age and number of transfused RBC units. Our study suggests that RBC antibody formation is significantly associated with older age of RBCs at the time of transfusion. Prospective studies in patients with SCD are required to confirm this finding.

The use of administrative databases to conduct population-based studies of eosinophilic esophagitis (EoE) in the United States is limited because it is unknown whether the International Classification of Diseases, Ninth Revision (ICD-9) code for EoE, 530.13, accurately identifies those who truly have the disease. The aim of this retrospective study was to validate the ICD-9 code for identifying cases of EoE in administrative data. Confirmed cases of EoE as per consensus guidelines (symptoms of esophageal dysfunction and ≥15 eosinophils per high-power field on biopsy after 8 weeks of twice daily proton pump inhibitor therapy) were identified in the University of North Carolina (UNC) EoE Clinicopathologic Database from 2008 to 2010; 2008 was the first year in which the 530.13 code was approved. Using the Carolina Data Warehouse, the administrative database for patients seen in the UNC system, all diagnostic and procedure codes were obtained for these cases. Then, with the EoE cases as the reference standard, we re-queried the Carolina Data Warehouse over the same time frame for all patients seen in the system (n=308,372) and calculated the sensitivity and specificity of the ICD-9 code 530.13 as a case definition of EoE. To attempt to refine the case definition, we added procedural codes in an iterative fashion to optimize sensitivity and specificity, and restricted our analysis to privately insured patients. We also conducted a sensitivity analysis with 2011 data to identify trends in the operating parameters of the code. We identified 226 cases of EoE at UNC to serve as the reference standard. The ICD-9 code 530.13 yielded a sensitivity of 37% (83/226; 95% confidence interval: 31-43%) and specificity of 99% (308,111/308,146; 95% confidence interval: 98-100%). These operating parameters were not substantially altered if the case definition required a procedure code for endoscopy or if cases were limited to those with commercial insurance. However, in 2011, the sensitivity of the code had increased to 61%, while the specificity remained at 99%. The ICD-9 code for EoE, 530.13, had excellent specificity for identifying cases of EoE in administrative data, although this high specificity was achieved at an academic center. Additionally, the sensitivity of the code appears to be increasing over time, and the threshold at which it will stabilize is not known. While use of this administrative code will still miss a number of cases, those identified in this manner are highly likely to have the disease.

While the need for health information is a seemingly universal concept, comfort using computers and the Internet is not. Yet studies have shown that users within a large range of years of computer experience search the Internet for health information (“e-health information”) at ever-increasing rates. The purpose of the current study is to discover how a searcher’s attitudes toward and self-perception of their computer and Internet competence affect his or her e-health information-seeking behaviors. An online survey was distributed with questions that served to measure participants’ computer and Internet anxiety, as well as questions pertaining to their e-health attitudes and search behaviors. Participants’ anxiety levels had a statistically significant effect on participants’ (1) feeling that their e-health searches are generally successful (or unsuccessful), (2) satisfaction with the information obtained, and (3) tendency to share e-health information with a health care provider.

Additional file 1: Supplementary Table 1. ICEES integrated feature variable tables (v1.0.0, v2.0.0): variable names, descriptions, and binning strategy.*

Additional file 1: Supplementary Table 1. ICEES integrated feature variable tables (v1.0.0, v2.0.0): variable names, descriptions, and binning strategy.*