Search

Radiological reporting has generated large quantities of digital content within the electronic health record, which is potentially a valuable source of information for improving clinical care and supporting research. Although radiology reports are stored for communication and documentation of diagnostic imaging, harnessing their potential requires efficient and automated information extraction: they exist mainly as free-text clinical narrative, from which it is a major challenge to obtain structured data. Natural language processing (NLP) provides techniques that aid the conversion of text into a structured representation, and thus enables computers to derive meaning from human (ie, natural language) input. Used on radiology reports, NLP techniques enable automatic identification and extraction of information. By exploring the various purposes for their use, this review examines how radiology benefits from NLP. A systematic literature search identified 67 relevant publications describing NLP methods that support practical applications in radiology. This review takes a close look at the individual studies in terms of tasks (ie, the extracted information), the NLP methodology and tools used, and their application purpose and performance results. Additionally, limitations, future challenges, and requirements for advancing NLP in radiology will be discussed. (C) RSNA, 2016

Publisher's version (útgefin grein). Publisher's note: Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations., Electrocardiographic PR interval measures atrio-ventricular depolarization and conduction, and abnormal PR interval is a risk factor for atrial fibrillation and heart block. Our genome-wide association study of over 92,000 European-descent individuals identifies 44 PR interval loci (34 novel). Examination of these loci reveals known and previously not-yet-reported biological processes involved in cardiac atrial electrical activity. Genes in these loci are over-represented in cardiac disease processes including heart block and atrial fibrillation. Variants in over half of the 44 loci were associated with atrial or blood transcript expression levels, or were in high linkage disequilibrium with missense variants. Six additional loci were identified either by meta-analysis of ~105,000 African and European-descent individuals and/or by pleiotropic analyses combining PR interval with heart rate, QRS interval, and atrial fibrillation. These findings implicate developmental pathways, and identify transcription factors, ion-channel genes, and cell-junction/cell-signaling proteins in atrio-ventricular conduction, identifying potential targets for drug development., Acknowledgements per cohort are listed in Supplementary Note 2. We thank the following studies for sharing their summary level results: QRS voltage (van der Harst et al., 2016)[12], heart rate (den Hoed et al., 2013)[35], RR interval (Eijgelsheim et al., 2010)[11], atrial fibrillation (Christophersen et al., 2017[15]), and CARe-COGENT AA PR Consortium (Butler et al., 2012)[33]. We acknowledge Dr. Vinicius Tragante for his help generating the author list.

Publisher's version (útgefin grein)., Background: Genome-wide association studies conducted on QRS duration, an electrocardiographic measurement associated with heart failure and sudden cardiac death, have led to novel biological insights into cardiac function. However, the variants identified fall predominantly in non-coding regions and their underlying mechanisms remain unclear. Results: Here, we identify putative functional coding variation associated with changes in the QRS interval duration by combining Illumina HumanExome BeadChip genotype data from 77,898 participants of European ancestry and 7695 of African descent in our discovery cohort, followed by replication in 111,874 individuals of European ancestry from the UK Biobank and deCODE cohorts. We identify ten novel loci, seven within coding regions, including ADAMTS6, significantly associated with QRS duration in gene-based analyses. ADAMTS6 encodes a secreted metalloprotease of currently unknown function. In vitro validation analysis shows that the QRS-associated variants lead to impaired ADAMTS6 secretion and loss-of function analysis in mice demonstrates a previously unappreciated role for ADAMTS6 in connexin 43 gap junction expression, which is essential for myocardial conduction. Conclusions: Our approach identifies novel coding and non-coding variants underlying ventricular depolarization and provides a possible mechanism for the ADAMTS6-associated conduction changes., Funding This work was funded by a grant to YJ from the British Heart Foundation (PG/12/38/29615). AGES: This study has been funded by NIH contracts N01-AG-1-2100 and 271201200022C, the NIA Intramural Research Program, Hjartavernd (the Icelandic Heart Association), and the Althingi (the Icelandic Parliament). The study is approved by the Icelandic National Bioethics Committee, VSN: 00–063. The researchers are indebted to the participants for their willingness to participate in the study. ARIC: The Atherosclerosis Risk in Communities Study is carried out as a collaborative study supported by National Heart, Lung, and Blood Institute contracts (HHSN268201100005C, HHSN268201100006C, HHSN268201100007C, HHSN268201100008C, HHSN268201100009C, HHSN268201100010C, HHSN268201100011C, and HHSN268201100012C), R01HL087641, R01HL59367, and R01HL086694; National Human Genome Research Institute contract U01HG004402; and National Institutes of Health contract HHSN268200625226C. The authors thank the staff and participants of the ARIC study for their important contributions. Infrastructure was partly supported by Grant Number UL1RR025005, a component of the National Institutes of Health and NIH Roadmap for Medical Research. Funding support for “Building on GWAS for NHLBI-diseases: the U.S. CHARGE consortium” was provided by the NIH through the American Recovery and Reinvestment Act of 2009 (ARRA) (5RC2HL102419). BRIGHT: The Exome Chip genotyping was funded by Wellcome Trust Strategic Awards (083948 and 085475). This work was also supported by the Medical Research Council of Great Britain (Grant no. G9521010D); and by the British Heart Foundation (Grant no. PG/02/128). AFD was supported by the British Heart Foundation (Grant nos. RG/07/005/23633 and SP/08/005/25115); and by the European Union Ingenious HyperCare Consortium: Integrated Genomics, Clinical Research, and Care in Hypertension (grant no. LSHM-C7–2006-037093). The BRIGHT study is extremely grateful to all the patients who participated in the study and the BRIGHT nursing team. We would also like to thank the Barts Genome Centre staff for their assistance with this project. CHS: This Cardiovascular Health Study (CHS) research was supported by NHLBI contracts HHSN268201800001C, HHSN268201200036C, HHSN268200800007C, N01HC55222, N01HC85079, N01HC85080, N01HC85081, N01HC85082, N01HC85083, N01HC85086; and NHLBI grants R01HL068986, U01HL080295, R01HL087652, R01HL105756, R01HL103612, R01HL120393, and U01HL130114 with additional contribution from the National Institute of Neurological Disorders and Stroke (NINDS). Additional support was provided through R01AG023629 from the National Institute on Aging (NIA). A full list of principal CHS investigators and institutions can be found at CHS-NHLBI.org. The provision of genotyping data was supported in part by the National Center for Advancing Translational Sciences, CTSI grant UL1TR001881, and the National Institute of Diabetes and Digestive and Kidney Disease Diabetes Research Center (DRC) grant DK063491 to the Southern California Diabetes Endocrinology Research Center. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. ERF: The ERF study as a part of EUROSPAN (European Special Populations Research Network) was supported by European Commission FP6 STRP grant number 018947 (LSHG-CT-2006-01947) and also received funding from the European Community’s Seventh Framework Programme (FP7/2007–2013)/grant agreement HEALTH-F4–2007-201413 by the European Commission under the programme “Quality of Life and Management of the Living Resources” of 5th Framework Programme (no. QLG2-CT-2002-01254). The ERF study was further supported by ENGAGE consortium and CMSB. High-throughput analysis of the ERF data was supported by joint grant from Netherlands Organization for Scientific Research and the Russian Foundation for Basic Research (NWO-RFBR 047.017.043). We are grateful to all study participants and their relatives, general practitioners, and neurologists for their contributions to the ERF study and to P Veraart for her help in genealogy, J Vergeer for the supervision of the laboratory work, and P Snijders for his help in data collection. FHS: The Framingham Heart Study (FHS) research reported in this article was supported by a grant from the National Heart, Lung, and Blood Institute (NHLBI), HL120393. Generation Scotland: Generation Scotland received core support from the Chief Scientist Office of the Scottish Government Health Directorates (CZD/16/6) and the Scottish Funding Council (HR03006). Genotyping of the Generation Scotland and Scottish Family Health Study samples was carried out by the Genetics Core Laboratory at the Clinical Research Facility, Edinburgh, Scotland and was funded by the UK’s Medical Research Council. GOCHA: The Genetics of Cerebral Hemorrhage with Anticoagulation was carried out as a collaborative study supported by grants R01NS073344, R01NS059727, and 5K23NS059774 from the NIH–National Institute of Neurological Disorders and Stroke (NIH-NINDS). GRAPHIC: The GRAPHIC Study was funded by the British Heart Foundation (BHF/RG/2000004). NJS and CPN are supported by the British Heart Foundation and is a NIHR Senior Investigator. This work falls under the portfolio of research supported by the NIHR Leicester Cardiovascular Biomedical Research. INGI-FVG: This study has been funded by Regione FVG (L.26.2008). INTER99: The Inter99 was initiated by Torben Jørgensen (PI), Knut Borch-Johnsen (co-PI), Hans Ibsen and Troels F. Thomsen. The steering committee comprises the former two and Charlotta Pisinger. The study was financially supported by research grants from the Danish Research Council, the Danish Centre for Health Technology Assessment, Novo Nordisk Inc., Research Foundation of Copenhagen County, Ministry of Internal Affairs and Health, the Danish Heart Foundation, the Danish Pharmaceutical Association, the Augustinus Foundation, the Ib Henriksen Foundation, the Becket Foundation, and the Danish Diabetes Association. The Novo Nordisk Foundation Center for Basic Metabolic Research is an independent Research Center at the University of Copenhagen partially funded by an unrestricted donation from the Novo Nordisk Foundation (www.metabol.ku.dk). JHS: We thank the Jackson Heart Study (JHS) participants and staff for their contributions to this work. The JHS is supported by contracts HHSN268201300046C, HHSN268201300047C, HHSN268201300048C, HHSN268201300049C, HHSN268201300050C from the National Heart, Lung, and Blood Institute and the National Institute on Minority Health and Health Disparities. Dr. Wilson is supported by U54GM115428 from the National Institute of General Medical Sciences. KORA: The KORA study was initiated and financed by the Helmholtz Zentrum München – German Research Center for Environmental Health, which is funded by the German Federal Ministry of Education and Research (BMBF) and by the State of Bavaria. Furthermore, KORA research was supported within the Munich Center of Health Sciences (MC-Health), Ludwig-Maximilians-Universität, as part of LMUinnovativ. Korcula: This work was funded by the Medical Research Council UK, The Croatian Ministry of Science, Education and Sports (grant 216–1080315-0302), the Croatian Science Foundation (grant 8875), the Centre of Excellence in Personalized health care, and the Centre of Competencies for Integrative Treatment, Prevention and Rehabilitation using TMS. LifeLines: The LifeLines Cohort Study and generation and management of GWAS genotype data for the LifeLines Cohort Study are supported by The Netherlands Organization of Scientific Research NWO (grant 175.010.2007.006), the Economic Structure Enhancing Fund (FES) of the Dutch government, the Ministry of Economic Affairs, the Ministry of Education, Culture and Science, the Ministry for Health, Welfare and Sports, the Northern Netherlands Collaboration of Provinces (SNN), the Province of Groningen, University Medical Center Groningen, the University of Groningen, Dutch Kidney Foundation, and Dutch Diabetes Research Foundation. Niek Verweij is supported by NWO-VENI (016.186.125) and Marie Sklodowska-Curie GF (call: H2020-MSCA-IF-2014, Project ID: 661395). UHP: Folkert W. Asselbergs is supported by UCL Hospitals NIHR Biomedical Research Centre. Ilonca Vaartjes is supported by a Dutch Heart Foundation grant DHF project “Facts and Figures.” MGH-CAMP: Dr. Patrick Ellinor is funded by NIH grants (2R01HL092577, 1R01HL128914, R01HL104156, and K24HL105780) and American Heart Association Established Investigator Award 13EIA14220013 (Ellinor). Dr. Steve Lubitz is funded by NIH grants K23HL114724 and a Doris Duke Charitable Foundation Clinical Scientist Development Award 2014105. NEO: The authors of the NEO study thank all individuals who participated in the Netherlands Epidemiology in Obesity study, all participating general practitioners for inviting eligible participants, and all research nurses for collection of the data. We thank the NEO study group, Pat van Beelen, Petra Noordijk, and Ingeborg de Jonge for the coordination, lab, and data management of the NEO study. We also thank Arie Maan for the analyses of the electrocardiograms. The genotyping in the NEO study was supported by the Centre National de Génotypage (Paris, France), headed by Jean-Francois Deleuze. The NEO study is supported by the participating Departments, the Division and the Board of Directors of the Leiden University Medical Center, and by the Leiden University, Research Profile Area Vascular and Regenerative Medicine. Dennis Mook-Kanamori is supported by Dutch Science Organization (ZonMW-VENI Grant 916.14.023). RS-I: The generation and management of the Illumina Exome Chip v1.0 array data for the Rotterdam Study (RS-I) was executed by the Human Genotyping Facility of the Genetic Laboratory of the Department of Internal Medicine, Erasmus MC, Rotterdam, The Netherlands. The Exome chip array dataset was funded by the Genetic Laboratory of the Department of Internal Medicine, Erasmus MC, from the Netherlands Genomics Initiative (NGI)/Netherlands Organization for Scientific Research (NWO)-sponsored Netherlands Consortium for Healthy Aging (NCHA; project nr. 050–060-810); the Netherlands Organization for Scientific Research (NWO; project number 184021007); and by the Rainbow Project (RP10; Netherlands Exome Chip Project) of the Biobanking and Biomolecular Research Infrastructure Netherlands (BBMRI-NL; www.bbmri.nl). We thank Ms. Mila Jhamai, Ms. Sarah Higgins, and Mr. Marijn Verkerk for their help in creating the exome chip database, and Carolina Medina-Gomez, MSc, Lennard Karsten, MSc, and Linda Broer PhD for QC and variant calling. Variants were called using the best practice protocol developed by Grove et al. as part of the CHARGE consortium exome chip central calling effort. The Rotterdam Study is funded by Erasmus Medical Center and Erasmus University, Rotterdam, Netherlands Organization for the Health Research and Development (ZonMw), the Research Institute for Diseases in the Elderly (RIDE), the Ministry of Education, Culture and Science, the Ministry for Health, Welfare and Sports, the European Commission (DG XII), and the Municipality of Rotterdam. The authors are grateful to the study participants, the staff from the Rotterdam Study, and the participating general practitioners and pharmacists. The work of Bruno H. Stricker is supported by grants from the Netherlands Organization for Health Research and Development (ZonMw) (Priority Medicines Elderly 113102005 to ME and DoelmatigheidsOnderzoek 80–82500–98-10208 to BHS). The work of Mark Eijgelsheim is supported by grants from the Netherlands Organization for Health Research and Development (ZonMw) (Priority Medicines Elderly 113102005 to ME and DoelmatigheidsOnderzoek 80–82500–98-10208 to BHS). SHIP: SHIP is supported by the BMBF (grants 01ZZ9603, 01ZZ0103, and 01ZZ0403) and the German Research Foundation (Deutsche Forschungsgemeinschaft [DFG]; grant GR 1912/5–1). SHIP and SHIP-TREND are part of the Community Medicine Research net (CMR) of the Ernst-Moritz-Arndt University Greifswald (EMAU) which is funded by the BMBF as well as the Ministry for Education, Science and Culture and the Ministry of Labor, Equal Opportunities, and Social Affairs of the Federal State of Mecklenburg-West Pomerania. The CMR encompasses several research projects that share data from SHIP. The EMAU is a member of the Center of Knowledge Interchange (CKI) program of the Siemens AG. SNP typing of SHIP and SHIP-TREND using the Illumina Infinium HumanExome BeadChip (version v1.0) was supported by the BMBF (grant 03Z1CN22). We thank all SHIP and SHIP-TREND participants and staff members as well as the genotyping staff involved in the generation of the SNP data. TWINSUK: TwinsUK is funded by the Wellcome Trust, Medical Research Council, European Union, the National Institute for Health Research (NIHR)-funded BioResource, Clinical Research Facility and Biomedical Research Centre based at Guy’s and St Thomas’ NHS Foundation Trust in partnership with King’s College London. UKBB: This research has been conducted using the UK Biobank Resource (application 8256 - Understanding genetic influences in the response of the cardiac electrical system to exercise) and is supported by Medical Research Council grant MR/N025083/1. We also wish to acknowledge the support of the NIHR Cardiovascular Biomedical Research Unit at Barts and Queen Mary University of London, UK. PD Lambiase acknowledges support from the UCLH Biomedicine NIHR. MO is supported by an IEF 2013 Marie Curie fellowship. JR acknowledges support from the People Programme (Marie Curie Actions) of the European Union’s Seventh Framework Programme (FP7/2007–2013) under REA grant agreement no. 608765. YFS: The Young Finns Study has been financially supported by the Academy of Finland: grants 286284, 134309 (Eye), 126925, 121584, 124282, 129378 (Salve), 117787 (Gendi), and 41071 (Skidi); the Social Insurance Institution of Finland; Competitive State Research Financing of the Expert Responsibility area of Kuopio, Tampere and Turku University Hospitals (grant X51001); Juho Vainio Foundation; Paavo Nurmi Foundation; Finnish Foundation for Cardiovascular Research; Finnish Cultural Foundation; Tampere Tuberculosis Foundation; Emil Aaltonen Foundation; Yrjö Jahnsson Foundation; Signe and Ane Gyllenberg Foundation; and Diabetes Research Foundation of Finnish Diabetes Association. The expert technical assistance in the statistical analyses by Irina Lisinen is gratefully acknowledged. Cell culture and biochemistry: Funding was provided by the National Institutes of Health (Program of Excellence in Glycoscience award HL107147 to SSA and F32AR063548 to TJM) and the David and Lindsay Morgenthaler Postdoctoral Fellowship (to TJM) and by the Allen Distinguished Investigator Program, through support made by The Paul G. Allen Frontiers Group and the American Heart Association (to SSA). Mutant mouse model: Adamts6 mutant mice were generated and further propagated and analyzed by funding provided by NIH grants HL098180 and HL132024 (to CWL) and by the Allen Distinguished Investigator Program, through support made by The Paul G. Allen Frontiers Group and the American Heart Association (to SSA).

Background: \ud Automated measurements of electrocardiographic (ECG) intervals by current-generation digital electrocardiographs are critical to computer-based ECG diagnostic statements, to serial comparison of ECGs, and to epidemiological studies of ECG findings in populations. A previous study demonstrated generally small but often significant systematic differences among 4 algorithms widely used for automated ECG in the United States and that measurement differences could be related to the degree of abnormality of the underlying tracing. Since that publication, some algorithms have been adjusted, whereas other large manufacturers of automated ECGs have asked to participate in an extension of this comparison.\ud \ud Methods: \ud Seven widely used automated algorithms for computer-based interpretation participated in this blinded study of 800 digitized ECGs provided by the Cardiac Safety Research Consortium. All tracings were different from the study of 4 algorithms reported in 2014, and the selected population was heavily weighted toward groups with known effects on the QT interval: included were 200 normal subjects, 200 normal subjects receiving moxifloxacin as part of an active control arm of thorough QT studies, 200 subjects with genetically proved long QT syndrome type 1 (LQT1), and 200 subjects with genetically proved long QT syndrome Type 2 (LQT2).\ud \ud Results: \ud For the entire population of 800 subjects, pairwise differences between algorithms for each mean interval value were clinically small, even where statistically significant, ranging from 0.2 to 3.6 milliseconds for the PR interval, 0.1 to 8.1 milliseconds for QRS duration, and 0.1 to 9.3 milliseconds for QT interval. The mean value of all paired differences among algorithms was higher in the long QT groups than in normals for both QRS duration and QT intervals. Differences in mean QRS duration ranged from 0.2 to 13.3 milliseconds in the LQT1 subjects and from 0.2 to 11.0 milliseconds in the LQT2 subjects. Differences in measured QT duration (not corrected for heart rate) ranged from 0.2 to 10.5 milliseconds in the LQT1 subjects and from 0.9 to 12.8 milliseconds in the LQT2 subjects.\ud \ud Conclusions: \ud Among current-generation computer-based electrocardiographs, clinically small but statistically significant differences exist between ECG interval measurements by individual algorithms. Measurement differences between algorithms for QRS duration and for QT interval are larger in long QT interval subjects than in normal subjects. Comparisons of population study norms should be aware of small systematic differences in interval measurements due to different algorithm methodologies, within-individual interval measurement comparisons should use comparable methods, and further attempts to harmonize interval measurement methodologies are warranted.

Background: Electrical conduction from the cardiac sinoatrial node to the ventricles is critical for normal heart function. Genome-wide association studies have identified more than a dozen common genetic loci that are associated with PR interval. However, it is unclear whether rare and low-frequency variants also contribute to PR interval heritability. Methods: We performed large-scale meta-analyses of the PR interval that included 83 367 participants of European ancestry and 9436 of African ancestry. We examined both common and rare variants associated with the PR interval. Results: We identified 31 genetic loci that were significantly associated with PR interval after Bonferroni correction ( P −6 ), including 11 novel loci that have not been reported previously. Many of these loci are involved in heart morphogenesis. In gene-based analysis, we found that multiple rare variants at MYH6 ( P =5.9×10 −11 ) and SCN5A ( P =1.1×10 −7 ) were associated with PR interval. SCN5A locus also was implicated in the common variant analysis, whereas MYH6 was a novel locus. Conclusions: We identified common variants at 11 novel loci and rare variants within 2 gene regions that were significantly associated with PR interval. Our findings provide novel insights to the current understanding of atrioventricular conduction, which is critical for cardiac activity and an important determinant of health.

Background Electrocardiographic measures of left ventricular hypertrophy (LVH) are used as predictors of cardiovascular risk. We combined linkage and association analyses to discover novel rare genetic variants involved in three such measures and two principal components derived from them. Methods The study was conducted among participants from the Erasmus Rucphen Family Study (ERF), a Dutch family-based sample from the southwestern Netherlands. Variance components linkage analyses were performed using Merlin. Regions of interest (LOD > 1.9) were fine-mapped using microarray and exome sequence data. Results We observed one significant LOD score for the second principal component on chromosome 15 (LOD score = 3.01) and 12 suggestive LOD scores. Several loci contained variants identified in GWAS for these traits; however, these did not explain the linkage peaks, nor did other common variants. Exome sequence data identified two associated variants after multiple testing corrections were applied. Conclusions We did not find common SNPs explaining these linkage signals. Exome sequencing uncovered a relatively rare variant in MAPK3K11 on chromosome 11 (MAF = 0.01) that helped account for the suggestive linkage peak observed for the first principal component. Conditional analysis revealed a drop in LOD from 2.01 to 0.88 for MAP3K11, suggesting that this variant may partially explain the linkage signal at this chromosomal location. MAP3K11 is related to the JNK pathway and is a pro-apoptotic kinase that plays an important role in the induction of cardiomyocyte apoptosis in various pathologies, including LVH. Electronic supplementary material The online version of this article (10.1186/s12920-018-0339-9) contains supplementary material, which is available to authorized users.

MotivationGenome-wide association studies have had great success in identifying human genetic variants associated with disease, disease risk factors, and other biomedical phenotypes. Many variants are associated with multiple traits, even after correction for trait-trait correlation. Discovering subsets of variants associated with a shared subset of phenotypes could help reveal disease mechanisms, suggest new therapeutic options, and increase the power to detect additional variants with similar pattern of associations. Here we introduce two methods based on a Bayesian framework, SNP And Pleiotropic PHenotype Organization (SAPPHO), one modeling independent phenotypes (SAPPHO-I) and the other incorporating a full phenotype covariance structure (SAPPHO-C). These two methods learn patterns of pleiotropy from genotype and phenotype data, using identified associations to discover additional associations with shared patterns.ResultsThe SAPPHO methods, along with other recent approaches for pleiotropic association tests, were assessed using data from the Atherosclerotic Risk in Communities (ARIC) study of 8,000 individuals, whose gold-standard associations were provided by meta-analysis of 40,000 to 100,000 individuals from the CHARGE consortium. Using power to detect gold-standard associations at genome-wide significance (0.05 family-wise error rate) as a metric, SAPPHO performed best. The SAPPHO methods were also uniquely able to select the most significant variants in a parsimonious model, excluding other less likely variants within a linkage disequilibrium block. For meta-analysis, the SAPPHO methods implement summary modes that use sufficient statistics rather than full phenotype and genotype data. Meta-analysis applied to CHARGE detected 16 additional associations to the gold-standard loci, as well as 124 novel loci, at 0.05 false discovery rate. Reasons for the superior performance were explored by performing simulations over a range of scenarios describing different genetic architectures. With SAPPHO we were able to learn genetic structures that were hidden using the traditional univariate tests.Availabilityhttps://bitbucket.org/baderlab/fast/wiki/Home. SAPPHO software is available under the GNU General Public License, v2.

Sulfonylureas, a commonly-used class of medication used to treat type 2 diabetes, have been associated with an increased risk of cardiovascular disease. Their effects on QT interval duration and related electrocardiographic phenotypes are potential mechanisms for this adverse effect. In eleven ethnically diverse cohorts that included 71 857 European, African American, and Hispanic/Latino ancestry individuals with repeated measures of medication use and electrocardiogram (ECG) measurements, we conducted a pharmacogenomic genome-wide association study of sulfonylurea use and three ECG phenotypes: QT, JT, and QRS intervals. In ancestry-specific meta-analyses, 8 novel pharmacogenomic loci met the threshold for genome-wide significance (P < 5 x 10−8), and a pharmacokinetic variant in CYP2C9 (rs1057910) that has been associated with sulfonylurea-related treatment effects and other adverse drug reactions in previous studies was replicated. Additional research is needed to replicate the novel findings and to understand their biological basis.

Electrocardiographic PR interval measures atrial and atrioventricular depolarization and conduction, and abnormal PR interval is a risk factor for atrial fibrillation and heart block. We performed a genome-wide association study in over 92,000 individuals of European descent and identified 44 loci associated with PR interval (34 novel). Examination of the 44 loci revealed known and novel biological processes involved in cardiac atrial electrical activity, and genes in these loci were highly over-represented in several cardiac disease processes. Nearly half of the 61 independent index variants in the 44 loci were associated with atrial or blood transcript expression levels, or were in high linkage disequilibrium with one or more missense variants. Cardiac regulatory regions of the genome as measured by cardiac DNA hypersensitivity sites were enriched for variants associated with PR interval, compared to non-cardiac regulatory regions. Joint analyses combining PR interval with heart rate, QRS interval, and atrial fibrillation identified additional new pleiotropic loci. The majority of associations discovered in European-descent populations were also present in African-American populations. Meta-analysis examining over 105,000 individuals of African and European descent identified additional novel PR loci. These additional analyses identified another 13 novel loci. Together, these findings underscore the power of GWAS to extend knowledge of the molecular underpinnings of clinical processes.

Background QT interval, measured through a standard ECG, captures the time it takes for the cardiac ventricles to depolarize and repolarize. JT interval is the component of the QT interval that reflects ventricular repolarization alone. Prolonged QT interval has been linked to higher risk of sudden cardiac arrest. Methods and Results We performed an ExomeChip-wide analysis for both QT and JT intervals, including 209 449 variants, both common and rare, in 17 341 genes from the Illumina Infinium HumanExome BeadChip. We identified 10 loci that modulate QT and JT interval duration that have not been previously reported in the literature using single-variant statistical models in a meta-analysis of 95 626 individuals from 23 cohorts (comprised 83 884 European ancestry individuals, 9610 blacks, 1382 Hispanics, and 750 Asians). This brings the total number of ventricular repolarization associated loci to 45. In addition, our approach of using coding variants has highlighted the role of 17 specific genes for involvement in ventricular repolarization, 7 of which are in novel loci. Conclusions Our analyses show a role for myocyte internal structure and interconnections in modulating QT interval duration, adding to previous known roles of potassium, sodium, and calcium ion regulation, as well as autonomic control. We anticipate that these discoveries will open new paths to the goal of making novel remedies for the prevention of lethal ventricular arrhythmias and sudden cardiac arrest.

Purpose: Prolonged ventricular repolarization (measured as heart-rate corrected QT (QTc) prolongation or JT-interval prolongation) is a risk factor for ventricular arrhythmias and can be drug-induced. Drugs can be classified as having known or possible QTc-prolonging properties. Regulatory agencies recommend avoiding concomitant use of multiple QTc-prolonging drugs, but evidence is lacking to what degree ventricular repolarization is influenced by concomitant use of these drugs. Methods: Within a population-based cohort of persons aged 45years and older, with up to five electrocardiograms recorded per participant between 1991 and 2010, we used generalised estimating equations to study the association between concomitant use of multiple QTc-prolonging drugs and repolarization duration. Results: The study population consisted of 13009 participants with 26908 electrocardiograms. With the addition of a second or third QTc-prolonging drug there was no substantial increase in QTc and JT interval and no increased risk of a prolonged QTc interval, compared to use of one QTc-prolonging drug. There was a large difference between the effect of one known or one possible QTc-prolonging drugs on QTc interval: 15ms for known, and 3ms for possible QTc-prolonging drugs. Conclusions: In this study, the added prolongation in users of two or three QTc-prolonging drugs on QTc was small. There was a large difference in QTc prolongation between known and possible QTc-prolonging drugs. Further research in larger or high-risk populations is needed to establish whether it is safe to use multiple QTc-prolonging drugs concomitantly to prevent that the current advice might unnecessarily withhold beneficial drugs from patients.

textabstractAims Selective serotonin re-uptake inhibitors (SSRIs), specifically citalopram and escitalopram, are thought to cause QTc prolongation, although studies have shown contradictory results. Nevertheless, a maximum citalopram dosage of 20 mg in high risk patients (e.g. >60 years of age) is recommended. We aimed to investigate the association between use of (individual) SSRIs and QTc in a population-based study in older adults. Methods This study, which was part of the prospective Rotterdam Study (period 1991-2012), included participants with up to five electrocardiograms (ECGs). We used linear mixed models to compare QTcF (QT corrected according to Fridericia) measured during use of individual SSRIs with QTcF measured during non-use of any antidepressant. For citalopram, analyses were additionally restricted to a maximum dosage of 20 mg in participants aged 60 years and older. Results We included 12 589 participants with a total of 26 620 ECGs of which 436 ECGs were made during SSRI use. The mean QTcF was similar during use of any drugs from the SSRI class and during non-use. After stratifying to individual SSRIs, ECGs recorded during use of citalopram had the longest QTc compared with ECGs recorded during non-use (+12.8 ms, 90% CI 7.5, 18.2). This result remained similar in the analysis comprising participants aged 60 years and older with a maximum prescribed daily dosage of 20 mg citalopram. Conclusions Although no SSRI class effect was observed, use of citalopram was associated with a longer QTcF, even after considering the recommended restrictions. Other SSRIs may not give a clinically relevant QTcF prolongation.

A prolonged heart rate corrected QT interval (QTc) increases the risk of sudden cardiac death. Some methods of heart rate correction (notably Bazett) overestimate QTc in people with high heart rates. Studies suggest that tricyclic antidepressants (TCAs) can prolong the QTc and increase heart rate. Therefore, we aimed to study whether TCA-induced QTc prolongation is a false-positive observation due to overestimation at high heart rates. For this, we included 12,734 participants from the prospective population-based Rotterdam Study, with a total of 27,068 electrocardiograms (ECGs), of which, 331 during TCA use. Associations between use of TCAs, QTc, and heart rate were studied with linear repeated measurement analyses. QT was corrected for heart rate according to Bazett (QTc(Bazett)), Fridericia (QTc(Fridericia)), or a correction based on regression coefficients obtained from the Rotterdam Study data (QTc(Statistical)). On ECGs recorded during TCA use, QTc(Bazett) was 6.5 milliseconds (95% confidence interval, 4.0-9.0) longer, and heart rate was 5.8 beats per minute (95% confidence interval, 4.7-6.9) faster than during nonuse. QTc(Fridericia) and QTc(Statistical) were not statistically significantly longer during TCA use than during nonuse. Furthermore, QTc(Bazett) was similar for ECGs recorded during TCA use and nonuse after statistical adjustment for heart rate. According to our results, TCA use does not seem to be associated with QTc prolongation. Therefore, the current advice of regulatory authorities to restrict the use of these drugs and to do regular checkups of the QTc may need to be revised. Other formulas, like Fridericia's, might be preferred.

Objective To create a multilingual gold-standard corpus for biomedical concept recognition. Materials and methods We selected text units from different parallel corpora (Medline abstract titles, drug labels, biomedical patent claims) in English, French, German, Spanish, and Dutch. Three annotators per language independently annotated the biomedical concepts, based on a subset of the Unified Medical Language System and covering a wide range of semantic groups. To reduce the annotation workload, automatically generated preannotations were provided. Individual annotations were automatically harmonized and then adjudicated, and cross-language consistency checks were carried out to arrive at the final annotations. Results The number of final annotations was 5530. Inter-annotator agreement scores indicate good agreement (median F-score 0.79), and are similar to those between individual annotators and the gold standard. The automatically generated harmonized annotation set for each language performed equally well as the best annotator for that language. Discussion The use of automatic preannotations, harmonized annotations, and parallel corpora helped to keep the manual annotation efforts manageable. The inter-annotator agreement scores provide a reference standard for gauging the performance of automatic annotation techniques. Conclusion To our knowledge, this is the first gold-standard corpus for biomedical concept recognition in languages other than English. Other distinguishing features are the wide variety of semantic groups that are being covered, and the diversity of text genres that were annotated.

Background A prolonged heart rate-corrected QT (QTc) interval is a well-known risk indicator for sudden cardiac death (SCD) and a contraindication for drugs with potentially arrhythmogenic adverse effects. Objective We aimed to study the consistency of QTc interval prolongation and whether a consistent QTc interval prolongation correlates differently with SCD than does an inconsistently prolonged QTc interval. Methods We used a population-based cohort study of persons 55 years and older. We excluded participants using QTc-prolonging drugs or with bundle branch block. The QT interval was corrected for heart rate using Bazett and Fridericia formulas. Using a Cox regression model, we assessed the association between QTc interval prolongation consistency and the occurrence of SCD. Results A total of 3484 participants had electrocardiograms (ECGs) recorded on 2 consecutive visits. In 96%-98% of participants with a normal QTc interval on the first ECG, the QTc interval remained normal, but only in 27%-35% of those with a prolonged QTc interval, the QTc interval was prolonged on the second ECG after a median of 1.8 years. A consistently prolonged QTc interval was associated with an increased risk of SCD as compared with a consistently normal QTc interval (Bazett: hazard ratio 2.23; 95% confidence interval 1.17-4.24, Fridericia: hazard ratio 6.67; 95% confidence interval 2.96-15.06). A prolonged QTc interval preceded or followed by a normal QTc interval was not significantly associated with an increased risk of SCD. Conclusion Persons with an inconsistently prolonged QTc interval did not have a higher risk of SCD than those with a consistently normal QTc interval. Persons with a consistently prolonged QTc interval did have a higher risk of SCD. Our results suggest that repeated measurements of the QTc interval could enhance risk stratification.

Introduction There is growing interest in whether social media can capture patient-generated information relevant for medicines safety surveillance that cannot be found in traditional sources. Objective The aim of this study was to evaluate the potential contribution of mining social media networks for medicines safety surveillance using the following associations as case studies: (1) rosiglitazone and cardiovascular events (i.e. stroke and myocardial infarction); and (2) human papilloma virus (HPV) vaccine and infertility. Methods We collected publicly accessible, English-language posts on Facebook, Google+, and Twitter until September 2014. Data were queried for co-occurrence of keywords related to the drug/vaccine and event of interest within a post. Messages were analysed with respect to geographical distribution, context, linking to other web content, and author’s assertion regarding the supposed association. Results A total of 2537 posts related to rosiglitazone/cardiovascular events and 2236 posts related to HPV vaccine/infertility were retrieved, with the majority of posts representing data from Twitter (98 and 85 %, respectively) and originating from users in the US. Approximately 21 % of rosiglitazone-related posts and 84 % of HPV vaccine-related posts referenced other web pages, mostly news items, law firms’ websites, or blogs. Assertion analysis predominantly showed affirmation of the association of rosiglitazone/cardiovascular events (72 %; n = 1821) and of HPV vaccine/infertility (79 %; n = 1758). Only ten posts described personal accounts of rosiglitazone/cardiovascular adverse event experiences, and nine posts described HPV vaccine problems related to infertility. Conclusions Publicly available data from the considered social media networks were sparse and largely untrackable for the purpose of providing early clues of safety concerns regarding the prespecified case studies. Further research investigating other case studies and exploring other social media platforms are necessary to further characterise the usefulness of social media for safety surveillance. Electronic supplementary material The online version of this article (doi:10.1007/s40264-015-0333-5) contains supplementary material, which is available to authorized users.

The transformation of recorded electrocardiographic leads (source leads) into leads that are wanted but were not recorded (target leads) has many practical applications. In general, two transformation methods are put to use, a purely statistical one and a model-based one. They are briefly reviewed and compared. Lead transformations were first used in the early nineteen-sixties to transform the component leads of one vectorcardiographic lead system into those of another. Since then, the use of lead transformations has proliferated and they are currently applied for a variety of purposes. Lead transformations can be grouped according to the source and target leads that are involved. A few applications of lead transformations from the different groups are presented, with a focus on the practicality of the application. The validity and value of the dipole approximation in relation to lead transformations is discussed. (C) 2015 Published by Elsevier Inc.

Nature Communications 8: Article number: 15805 (2017); Published: 14 June 2017; Updated: 2 August 2017 In Supplementary Fig. 10 of this Article, images for panels a and b were inadvertently omitted. The correct version of Supplementary Fig. 10 is provided as Supplementary Information associated withthis Erratum.

Resting heart rate is a heritable trait, and an increase in heart rate is associated with increased mortality risk. Genome-wide association study analyses have found loci associated with resting heart rate, at the time of our study these loci explained 0.9% of the variation. This study aims to discover new genetic loci associated with heart rate from Exome Chip meta-analyses.\ud \ud Heart rate was measured from either elecrtrocardiograms or pulse recordings. We meta-analysed heart rate association results from 104 452 European-ancestry individuals from 30 cohorts, genotyped using the Exome Chip. Twenty-four variants were selected for follow-up in an independent dataset (UK Biobank, N = 134 251). Conditional and gene-based testing was undertaken, and variants were investigated with bioinformatics methods.\ud \ud We discovered five novel heart rate loci, and one new independent low-frequency non-synonymous variant in an established heart rate locus (KIAA1755). Lead variants in four of the novel loci are non-synonymous variants in the genes C10orf71, DALDR3, TESK2 and SEC31B. The variant at SEC31B is significantly associated with SEC31B expression in heart and tibial nerve tissue. Further candidate genes were detected from long-range regulatory chromatin interactions in heart tissue (SCD, SLF2 and MAPK8). We observed significant enrichment in DNase I hypersensitive sites in fetal heart and lung. Moreover, enrichment was seen for the first time in human neuronal progenitor cells (derived from embryonic stem cells) and fetal muscle samples by including our novel variants.\ud \ud Our findings advance the knowledge of the genetic architecture of heart rate, and indicate new candidate genes for follow-up functional studies.

Reduced cardiac vagal control reflected in low heart rate variability (HRV) is associated with greater risks for cardiac morbidity and mortality. In two-stage meta-analyses of genome-wide association studies for three HRV traits in up to 53,174 individuals of European ancestry, we detect 17 genome-wide significant SNPs in eight loci. HRV SNPs tag non-synonymous SNPs (in NDUFA11 and KIAA1755), expression quantitative trait loci (eQTLs) (influencing GNG11, RGS6 and NEO1), or are located in genes preferentially expressed in the sinoatrial node (GNG11, RGS6 and HCN4). Genetic risk scores account for 0.9 to 2.6% of the HRV variance. Significant genetic correlation is found for HRV with heart rate (−0.74, Heart rate variability (HRV) describes the individual variation in cardiac cycle duration and is a measure of vagal control of heart rate. Here, the authors identify seventeen single-nucleotide polymorphisms associated with HRV, lending new insight into the vagal regulation of heart rhythm.

Background Increased heart rate and a prolonged QT interval are important risk factors for cardiovascular morbidity and mortality, and can be influenced by the use of various medications, including tricyclic/tetracyclic antidepressants (TCAs). We aim to identify genetic loci that modify the association between TCA use and RR and QT intervals. Methods and results We conducted race/ethnic-specific genome-wide interaction analyses (with HapMap phase II imputed reference panel imputation) of TCAs and resting RR and QT intervals in cohorts of European (n=45 706; n=1417 TCA users), African (n=10 235; n=296 TCA users) and Hispanic/Latino (n=13 808; n=147 TCA users) ancestry, adjusted for clinical covariates. Among the populations of European ancestry, two genome-wide significant loci were identified for RR interval: rs6737205 in BRE (β=56.3, p interaction =3.9e −9 ) and rs9830388 in UBE2E2 (β=25.2, p interaction =1.7e −8 ). In Hispanic/Latino cohorts, rs2291477 in TGFBR3 significantly modified the association between TCAs and QT intervals (β=9.3, p interaction =2.55e −8 ). In the meta-analyses of the other ethnicities, these loci either were excluded from the meta-analyses (as part of quality control), or their effects did not reach the level of nominal statistical significance (p interaction >0.05). No new variants were identified in these ethnicities. No additional loci were identified after inverse-variance-weighted meta-analysis of the three ancestries. Conclusions Among Europeans, TCA interactions with variants in BRE and UBE2E2 were identified in relation to RR intervals. Among Hispanic/Latinos, variants in TGFBR3 modified the relation between TCAs and QT intervals. Future studies are required to confirm our results.

Aims To determine the interaction between HRV and inflammation and their association with cardiovascular/all-cause mortality in the general population. Methods and results Subjects of the CARLA study ( n = 1671; 778 women, 893 men, 45–83 years of age) were observed for an average follow-up period of 8.8 years (226 deaths, 70 cardiovascular deaths). Heart rate variability parameters were calculated from 5-min segments of 20-min resting electrocardiograms. High-sensitivity C-reactive protein (hsCRP), interleukin-6 (IL-6), and soluble tumour necrosis factor-alpha receptor type 1 (sTNF-R1) were measured as inflammation parameters. The HRV parameters determined included the standard deviation of normal-to-normal intervals (SDNN), the root-mean-square of successive normal-interval differences (RMSSD), the low- and high-frequency (HF) power, the ratio of both, and non-linear parameters [Poincare plot (SD1, SD2, SD1/SD2), short-term detrended fluctuation analysis]. We estimated hazard ratios by using covariate-adjusted Cox regression for cardiovascular and all-cause mortality incorporating an interaction term of HRV/inflammation parameters. Relative excess risk due to interactions (RERIs) were computed. We found an interaction effect of sTNF-R1 with SDNN (RERI: 0.5; 99% confidence interval (CI): 0.1–1.0), and a weaker effect with RMSSD (RERI: 0.4; 99% CI: 0.0–0.9) and HF (RERI: 0.4; 99% CI: 0.0–0.9) with respect to cardiovascular mortality on an additive scale after covariate adjustment. Neither IL-6 nor hsCRP showed a significant interaction with the HRV parameters. Conclusion A change in TNF-α levels or the autonomic nervous system influences the mortality risk through both entities simultaneously. Thus, TNF-α and HRV need to be considered when predicating mortality.

Background— The P wave on an ECG is a measure of atrial electric function, and its characteristics may serve as predictors for atrial arrhythmias. Increased mean P-wave duration and P-wave terminal force traditionally have been used as markers for left atrial enlargement, and both have been associated with increased risk of atrial fibrillation. Here, we explore the genetic basis of P-wave morphology through meta-analysis of genome-wide association study results for P-wave duration and P-wave terminal force from 12 cohort studies. Methods and Results— We included 44 456 individuals, of which 6778 (16%) were of African ancestry. Genotyping, imputation, and genome-wide association study were performed at each study site. Summary-level results were meta-analyzed centrally using inverse-variance weighting. In meta-analyses of P-wave duration, we identified 6 significant ( P − 8 ) novel loci and replicated a prior association with S CN10A. We identified 3 loci at SCN5A , TBX5 , and CAV1/CAV2 that were jointly associated with the PR interval, PR segment, and P-wave duration. We identified 6 novel loci in meta-analysis of P-wave terminal force. Four of the identified genetic loci were significantly associated with gene expression in 329 left atrial samples. Finally, we observed that some of the loci associated with the P wave were linked to overall atrial conduction, whereas others identified distinct phases of atrial conduction. Conclusions— We have identified 6 novel genetic loci associated with P-wave duration and 6 novel loci associated with P-wave terminal force. Future studies of these loci may aid in identifying new targets for drugs that may modify atrial conduction or treat atrial arrhythmias.

textabstractBackground Increased variability of beat-to-beat QT-interval durations on the electrocardiogram (ECG) has been associated with increased risk for fatal and non-fatal cardiac events. However, techniques for the measurement of QT variability (QTV) have not been validated since a gold standard is not available. In this study, we propose a validation method and illustrate its use for the validation of two automatic QTV measurement techniques. Methods Our method generates artificial standard 12-lead ECGs based on the averaged P-QRS-T complexes from a variety of existing ECG signals, with simulated intrinsic (QT interval) and extrinsic (noise, baseline wander, signal length) variations. We quantified QTV by a commonly used measure, short-term QT variability (STV). Using 28,800 simulated ECGs, we assessed the performance of a conventional QTV measurement algorithm, resembling a manual QTV measurement approach, and a more advanced algorithm based on fiducial segment averaging (FSA). Results The results for the conventional algorithm show considerable median absolute differences between the simulated and estimated STV. For the highest noise level, median differences were 4±6 ms in the absence of QTV. Increasing signal length generally yields more accurate STV estimates, but the difference in performance between 30 or 60 beats is small. The FSA algorithm proved to be very accurate, with most median absolute differences less than 0.5 ms, even for the highest levels of disturbance. Conclusions Artificially constructed ECGs with a variety of disturbances allow validation of QTV measurement procedures. The FSA algorithm provides highly accurate STV estimates under varying signal conditions, and performs much better than traditional beat-by-beat analysis. The fully automatic operation of the FSA algorithm enables STV measurement in large sets of ECGs.

The QT interval, an electrocardiographic measure reflecting myocardial repolarization, is a heritable trait. QT prolongation is a risk factor for ventricular arrhythmias and sudden cardiac death (SCD) and could indicate the presence of the potentially lethal mendelian long-QT syndrome (LQTS). Using a genome-wide association and replication study in up to 100,000 individuals, we identified 35 common variant loci associated with QT interval that collectively explain similar to 8-10% of QT-interval variation and highlight the importance of calcium regulation in myocardial repolarization. Rare variant analysis of 6 new QT interval-associated loci in 298 unrelated probands with LQTS identified coding variants not found in controls but of uncertain causality and therefore requiring validation. Several newly identified loci encode proteins that physically interact with other recognized repolarization proteins. Our integration of common variant association, expression and orthogonal protein-protein interaction screens provides new insights into cardiac electrophysiology and identifies new candidate genes for ventricular arrhythmias, LQTS and SCD.

Motivation: Knowledge of drug–drug interactions (DDIs) is crucial for health-care professionals to avoid adverse effects when co-administering drugs to patients. As most newly discovered DDIs are made available through scientific publications, automatic DDI extraction is highly relevant. Results: We propose a novel feature-based approach to extract DDIs from text. Our approach consists of three steps. First, we apply text preprocessing to convert input sentences from a given dataset into structured representations. Second, we map each candidate DDI pair from that dataset into a suitable syntactic structure. Based on that, a novel set of features is used to generate feature vectors for these candidate DDI pairs. Third, the obtained feature vectors are used to train a support vector machine (SVM) classifier. When evaluated on two DDI extraction challenge test datasets from 2011 and 2013, our system achieves F-scores of 71.1% and 83.5%, respectively, outperforming any state-of-the-art DDI extraction system. Availability and implementation: The source code is available for academic use at http://www.biosemantics.org/uploads/DDI.zip Contact: q.bui@erasmusmc.nl

Unrecognized myocardial infarction (MI) is frequent in the general population. Its prognosis is reported to be at least as unpropitious as that of recognized MI, particularly in men. However, contemporary data with long follow-up are lacking. The aims of this study were to investigate the long-term prognosis of unrecognized MI with respect to all-cause and cause-specific mortality and to investigate possible differences in prognosis by gender. In the population-based Rotterdam Study (2,672 men and 3,862 women), the presence of unrecognized MI and recognized MI was determined at baseline (1990 to 1993). The cohort was followed for nearly 2 decades for all-cause and cause-specific mortality. During 82,268 patient-years of follow-up (median 15.6 years) 3,412 patients died (1,300 from cardiovascular causes). Men and women with recognized and unrecognized MIs had increased total mortality rates compared with those without MIs. Hazard ratios (HRs) for men and women were 1.57 (95% confidence interval [CI] 1.36 to 1.81) and 1.89 (95% CI 1.56 to 2.30) for recognized MI and 1.72 (95% CI 1.43 to 2.07) and 1.36(95% CI 1.14 to 1.61) for unrecognized MI. Unrecognized MI was associated with increased risks for cardiovascular mortality (men: HR 2.19, 95% CI 1.66 to 2.91; women: HR 1.36, 95% CI 1.03 to 1.81) and noncardiovascular mortality (men: HR 1.47, 95% CI 1.14 to 1.89; women: Ha 1.39, 95% CI 1.10 to 1.75). In conclusion, the long-term prognosis of patients with unrecognized MIs is worse compared with those without MIs and applies not only to cardiovascular mortality but also to noncardiovascular mortality. In men, the prognosis is as unfavorable as that of patients with recognized MIs. (C) 2014 Elsevier Inc. All rights reserved.

Introduction: To establish an up-to-date and comprehensive set of normal values for the clinically current measurements in the adult ECG, covering all ages for both sexes.Methods: The study population included 13,354 individuals, taken from four population studies in The Netherlands, ranging in age from 16 to 90 years (55% men) and cardiologically healthy by commonly accepted criteria. Standard 12-lead ECGs were available for all participants. The ECGs were processed by a well-validated computer program. Normal limits were taken as the 2nd and 98th percentiles of the measurement distribution per age group.Results: Our study corroborates many findings of previous studies, but also provides more differentiated results, in particular for the older age groups. Age trends were apparent for the QTc interval, QRS axis, and indices of left ventricular hypertrophy. Amplitudes in the left precordial leads showed a substantial increase in the older age groups for women, but not for men. Sex-dependent differences were apparent for most ECG parameters. All results are available on the Website www.normalecg.org, both in tabular and in graphical format.Conclusions: We determined age- and sex-dependent normal values of the adult ECG. Our study distinguishes itself from other studies by the large size of the study population, comprising both sexes, the broad range of ages, and the exhaustive set of measurements. Our results emphasize that most diagnostic ECG criteria should be age- and sex-specific. (C) 2014 Elsevier Inc. All rights reserved.

textabstractBackground Propensity score (PS) methods are commonly used to control for confounding in comparative effectiveness studies. Electronic health records (EHRs) contain much unstructured data that could be used as proxies for potential confounding factors. The goal of this study was to assess whether the unstructured information can also be used to construct PS models that would allow to properly deal with confounding. We used an example of coxibs (Cox-2 inhibitors) vs. traditional NSAIDs and the risk of upper gastro-intestinal bleeding as example, since this association is often confounded due to channeling of coxibs to patients at higher risk of upper gastro-intestinal bleeding. Methods In a cohort study of new users of nonsteroidal anti-inflammatory drugs (NSAIDs) from the Dutch Integrated Primary Care Information (IPCI) database, we identified all patients who experienced an upper gastrointestinal bleeding (UGIB). We used a large-scale regularized regression to fit two PS models using all structured and unstructured information in the EHR. We calculated hazard ratios (HRs) to estimate the risk of UGIB among selective cyclo-oxygenase-2 (COX-2) inhibitor users compared to nonselective NSAID (nsNSAID) users. Results The crude hazard ratio of UGIB for COX-2 inhibitors compared to nsNSAIDs was 0.50 (95% confidence interval 0.18–1.36). Matching only on age resulted in an HR of 0.36 (0.11–1.16), and of 0.35 (0.11–1.11) when further adjusted for sex. Matching on PS only, the first model yielded an HR of 0.42 (0.13–1.38), which reduced to 0.35 (0.96–1.25) when adjusted for age and sex. The second model resulted in an HR of 0.42 (0.13–1.39), which dropped to 0.31 (0.09–1.08) after adjustment for age and sex. Conclusions PS models can be created using unstructured information in EHRs. An incremental benefit was observed by matching on PS over traditional matching and adjustment for covariates.

Background Atrial fibrillation is the most common sustained arrhythmia in the elderly. Serum potassium is associated with ventricular arrhythmias and cardiac arrest. Little is known about the association of serum potassium with atrial fibrillation. The objective of this study was to investigate the association of serum potassium and the risk of atrial fibrillation in a population based setting. Methods The study was performed within the prospective population-based Rotterdam Study. The study population consisted of 4059 participants without atrial fibrillation at baseline for whom baseline levels of serum potassium were measured. Atrial fibrillation was ascertained from centre visit ECG assessments as well as medical records. Results During a mean follow up of 11.8years (SD=5.2yr), 474 participants developed atrial fibrillation. Participants with hypokalemia ( Conclusions In this study low serum levels of potassium were associated with a higher risk of atrial fibrillation.

Background and objective: In order for computers to extract useful information from unstructured text, a concept normalization system is needed to link relevant concepts in a text to sources that contain further information about the concept. Popular concept normalization tools in the biomedical field are dictionarybased. In this study we investigate the usefulness of natural language processing (NLP) as an adjunct to dictionary-based concept normalization. Methods: We compared the performance of two biomedical concept normalization systems, MetaMap and Peregrine, on the Arizona Disease Corpus, with and without the use of a rule-based NLP module. Performance was assessed for exact and inexact boundary matching of the system annotations with those of the gold standard and for concept identifier matching. Results: Without the NLP module, MetaMap and Peregrine attained F-scores of 61.0% and 63.9%, respectively, for exact boundary matching, and 55.1% and 56.9% for concept identifier matching. With the aid of the NLP module, the F-scores of MetaMap and Peregrine improved to 73.3% and 78.0% for boundary matching, and to 66.2% and 69.8% for concept identifier matching. For inexact boundary matching, performances further increased to 85.5% and 85.4%, and to 73.6% and 73.3% for concept identifier matching. Conclusions: We have shown the added value of NLP for the recognition and normalization of diseases with MetaMap and Peregrine. The NLP module is general and can be applied in combination with any concept normalization system. Whether its use for concept types other than disease is equally advantageous remains to be investigated.

Purpose The aim of this study was to assess the impact of automatically detected adverse event signals from text and open-source data on the prediction of drug label changes. Methods Open-source adverse effect data were collected from FAERS, Yellow Cards and SIDER databases. A shallow linguistic relation extraction system (JSRE) was applied for extraction of adverse effects from MEDLINE case reports. Statistical approach was applied on the extracted datasets for signal detection and subsequent prediction of label changes issued for 29 drugs by the UK Regulatory Authority in 2009. Results 76% of drug label changes were automatically predicted. Out of these, 6% of drug label changes were detected only by text mining. JSRE enabled precise identification of four adverse drug events from MEDLINE that were undetectable otherwise. Conclusions Changes in drug labels can be predicted automatically using data and text mining techniques. Text mining technology is mature and well-placed to support the pharmacovigilance tasks. Copyright © 2013 John Wiley & Sons, Ltd.

Purpose Most electronic health record databases contain unstructured free-text narratives, which cannot be easily analyzed. Case-detection algorithms are usually created manually and often rely only on using coded information such as International Classification of Diseases version 9 codes. We applied a machine-learning approach to generate and evaluate an automated case-detection algorithm that uses both free-text and coded information to identify asthma cases. Methods The Integrated Primary Care Information (IPCI) database was searched for potential asthma patients aged 5–18 years using a broad query on asthma-related codes, drugs, and free text. A training set of 5032 patients was created by manually annotating the potential patients as definite, probable, or doubtful asthma cases or non-asthma cases. The rule-learning program RIPPER was then used to generate algorithms to distinguish cases from non-cases. An over-sampling method was used to balance the performance of the automated algorithm to meet our study requirements. Performance of the automated algorithm was evaluated against the manually annotated set. Results The selected algorithm yielded a positive predictive value (PPV) of 0.66, sensitivity of 0.98, and specificity of 0.95 when identifying only definite asthma cases; a PPV of 0.82, sensitivity of 0.96, and specificity of 0.90 when identifying both definite and probable asthma cases; and a PPV of 0.57, sensitivity of 0.95, and specificity of 0.67 for the scenario identifying definite, probable, and doubtful asthma cases. Conclusions The automated algorithm shows good performance in detecting cases of asthma utilizing both free-text and coded data. This algorithm will facilitate large-scale studies of asthma in the IPCI database. Copyright © 2013 John Wiley & Sons, Ltd.

Background— An elevated resting heart rate is associated with rehospitalization for heart failure and is a modifiable risk factor in heart failure patients. We aimed to examine the association between resting heart rate and incident heart failure in a population-based cohort study of healthy adults without pre-existing overt heart disease. Methods and Results— We studied 4768 men and women aged ≥55 years from the population-based Rotterdam Study. We excluded participants with prevalent heart failure, coronary heart disease, pacemaker, atrial fibrillation, atrioventricular block, and those using β-blockers or calcium channel blockers. We used extended Cox models allowing for time-dependent variation of resting heart rate along follow-up. During a median of 14.6 years of follow-up, 656 participants developed heart failure. The risk of heart failure was higher in men with higher resting heart rate. For each increment of 10 beats per minute, the multivariable adjusted hazard ratios in men were 1.16 (95% confidence interval, 1.05–1.28; P =0.005) in the time-fixed heart rate model and 1.13 (95% confidence interval, 1.02–1.25; P =0.017) in the time-dependent heart rate model. The association could not be demonstrated in women ( P for interaction=0.004). Censoring participants for incident coronary heart disease or using time-dependent models to account for the use of β-blockers or calcium channel blockers during follow-up did not alter the results. Conclusions— Baseline or persistent higher resting heart rate is an independent risk factor for the development of heart failure in healthy older men in the general population.

Patients with chronic obstructive pulmonary disease (COPD) are at increased risk of cardiovascular disease. Electrocardiography (ECG) carries information about cardiac disease and prognosis, but studies comparing ECG characteristics between patients with and without COPD are lacking. We related ECG characteristics of patients with COPD, to ECG characteristics of patients without COPD, and determined whether ECG abnormalities are related to COPD severity. A cross-sectional study was conducted within a cohort of 243 COPD patients, aged 65 years or older. All patients underwent extensive examinations, including resting 12-lead ECG and pulmonary function tests. The reference group (n = 293) was a sample from the general population, also aged 65 or older, without COPD. Abnormal ECGs were more prevalent in COPD patients (50%) than in patients without COPD (36%, p = 0.054). Conduction abnormalities were the most common ECG abnormality in COPD patients (28%) being significantly more prevalent than in patients without COPD (11%, p < 0.001). The mean heart rate was higher in COPD patients (72 bpm (SD 14)) compared to controls (65 bpm (SD 13), p < 0.001), and QTc prolongation was less frequent in COPD patients (9% versus 14%, p = 0.01). The prevalence of ECG abnormalities increased with severity of pulmonary obstruction. ECG abnormalities, especially conduction abnormalities are common in COPD patients, and the prevalence of ECG abnormalities increases with severity of COPD. This underlines the importance of an integrated-care approach for COPD patients, paying attention to early detection of unrecognized coexisting cardiac disorders.

Purpose Pharmacovigilance methods have advanced greatly during the last decades, making post-market drug assessment an essential drug evaluation component. These methods mainly rely on the use of spontaneous reporting systems and health information databases to collect expertise from huge amounts of real-world reports. The EU-ADR Web Platform was built to further facilitate accessing, monitoring and exploring these data, enabling an in-depth analysis of adverse drug reactions risks. Methods The EU-ADR Web Platform exploits the wealth of data collected within a large-scale European initiative, the EU-ADR project. Millions of electronic health records, provided by national health agencies, are mined for specific drug events, which are correlated with literature, protein and pathway data, resulting in a rich drug–event dataset. Next, advanced distributed computing methods are tailored to coordinate the execution of data-mining and statistical analysis tasks. This permits obtaining a ranked drug–event list, removing spurious entries and highlighting relationships with high risk potential. Results The EU-ADR Web Platform is an open workspace for the integrated analysis of pharmacovigilance datasets. Using this software, researchers can access a variety of tools provided by distinct partners in a single centralized environment. Besides performing standalone drug–event assessments, they can also control the pipeline for an improved batch analysis of custom datasets. Drug–event pairs can be substantiated and statistically analysed within the platform's innovative working environment. Conclusions A pioneering workspace that helps in explaining the biological path of adverse drug reactions was developed within the EU-ADR project consortium. This tool, targeted at the pharmacovigilance community, is available online at https://bioinformatics.ua.pt/euadr/. Copyright © 2012 John Wiley & Sons, Ltd.

Background Alterations in autonomic nervous function are common in hemodialysis (HD) patients. Sympathetic as well as parasympathetic activation may be associated with immune and inflammatory responses. We intended to confirm a role of autonomous dysregulation for inflammation in HD patients. Methods 30 HD patients (including 15 diabetics) and 15 healthy controls were studied for heart rate variability (HRV) using 5 min ECG recordings. Heart rate variability was estimated by time-domain parameters (the standard deviation of the RR intervals (SDNN) and the percentage of pairs of adjacent RR intervals differing by >50 ms (pNN50)) and frequency-domain-analysis (high- and low-frequency variation of RR intervals, HF and LF). Inflammation was detected as serum C-reactive Protein (CRP), IL-6 and circulating monocyte subpopulation numbers. Immune cells were characterized by ACh receptor expression. Results Patients differed from controls in terms of age (68.0 [14.8] yrs vs. 58.0 [13.0] yrs, p

Background Assessment of drug and vaccine effects by combining information from different healthcare databases in the European Union requires extensive efforts in the harmonization of codes as different vocabularies are being used across countries. In this paper, we present a web application called CodeMapper, which assists in the mapping of case definitions to codes from different vocabularies, while keeping a transparent record of the complete mapping process. Methods CodeMapper builds upon coding vocabularies contained in the Metathesaurus of the Unified Medical Language System. The mapping approach consists of three phases. First, medical concepts are automatically identified in a free-text case definition. Second, the user revises the set of medical concepts by adding or removing concepts, or expanding them to related concepts that are more general or more specific. Finally, the selected concepts are projected to codes from the targeted coding vocabularies. We evaluated the application by comparing codes that were automatically generated from case definitions by applying CodeMapper's concept identification and successive concept expansion, with reference codes that were manually created in a previous epidemiological study. Results Automated concept identification alone had a sensitivity of 0.246 and positive predictive value (PPV) of 0.420 for reproducing the reference codes. Three successive steps of concept expansion increased sensitivity to 0.953 and PPV to 0.616. Conclusions Automatic concept identification in the case definition alone was insufficient to reproduce the reference codes, but CodeMapper's operations for concept expansion provide an effective, efficient, and transparent way for reproducing the reference codes.

Background Public confidence in an immunization programme is a pivotal determinant of the programme’s success. The mining of social media is increasingly employed to provide insight into the public’s sentiment. This research further explores the value of monitoring social media to understand public sentiment about an international vaccination programme. Objective To gain insight into international public discussion on the paediatric pentavalent vaccine (DTP-HepB-Hib) programme by analysing Twitter messages. Methods Using a multilingual search, we retrospectively collected all public Twitter messages mentioning the DTP-HepB-Hib vaccine from July 2006 until May 2015. We analysed message characteristics by frequency of referencing other websites, type of websites, and geographic focus of the discussion. In addition, a sample of messages was manually annotated for positive or negative message tone. Results We retrieved 5771 messages. Only 3.1% of the messages were reactions to other messages, and 86.6% referred to websites, mostly news sites (70.7%), other social media (9.8%), and health-information sites (9.5%). Country mentions were identified in 70.4% of the messages, of which India (35.4%), Indonesia (18.3%), and Vietnam (13.9%) were the most prevalent. In the annotated sample, 63% of the messages showed a positive or neutral sentiment about DTP-HepB-Hib. Peaks in negative and positive messages could be related to country-specific programme events. Conclusions Public messages about DTP-HepB-Hib were characterized by little interaction between tweeters, and by frequent referencing of websites and other information links. Twitter messages can indirectly reflect the public’s opinion about major events in the debates about the DTP-HepB-Hib vaccine.

BackgroundTricyclic antidepressants (TCAs) and selective serotonin reuptake inhibitors (SSRIs) may be associated with lower heart rate variability (HRV), a condition associated with increased mortality risk. We aimed to investigate the association between TCAs, SSRIs and HRV in a population-based study.MethodIn the prospective Rotterdam Study cohort, up to five electrocardiograms (ECGs) per participant were recorded (1991–2012). Two HRV variables were studied based on 10-s ECG recordings: standard deviation of normal-to-normal RR intervals (SDNN) and root mean square of successive RR interval differences (RMSSD). We compared the HRV on ECGs recorded during use of antidepressants with the HRV on ECGs recorded during non-use of any antidepressant. Additionally, we analysed the change in HRV on consecutive ECGs. Those who started or stopped using antidepressants before the second ECG were compared with non-users on two ECGs.ResultsWe included 23 647 ECGs from 11 729 participants (59% women, mean age 64.6 years at baseline). Compared to ECGs recorded during non-use of antidepressants (n = 22 971), SDNN and RMSSD were lower in ECGs recorded during use of TCAs (n = 296) and SSRIs (n = 380). Participants who started using TCAs before the second ECG had a decrease in HRV and those who stopped had an increase in HRV compared to consistent non-users (p < 0.001). Starting or stopping SSRIs was not associated with HRV changes.ConclusionTCAs were associated with a lower HRV in all analyses, indicating a real drug effect. For SSRIs the results are mixed, indicating a weaker association, possibly due to other factors.

High-throughput experimental methods such as medical sequencing and genome-wide association studies (GWAS) identify increasingly large numbers of potential relations between genetic variants and diseases. Both biological complexity (millions of potential gene-disease associations) and the accelerating rate of data production necessitate computational approaches to prioritize and rationalize potential gene-disease relations. Here, we use concept profile technology to expose from the biomedical literature both explicitly stated gene-disease relations (the explicitome) and a much larger set of implied gene-disease associations (the implicitome). Implicit relations are largely unknown to, or are even unintended by the original authors, but they vastly extend the reach of existing biomedical knowledge for identification and interpretation of gene-disease associations. The implicitome can be used in conjunction with experimental data resources to rationalize both known and novel associations. We demonstrate the usefulness of the implicitome by rationalizing known and novel gene-disease associations, including those from GWAS. To facilitate the re-use of implicit gene-disease associations, we publish our data in compliance with FAIR Data Publishing recommendations [https://www.force11.org/group/fairgroup] using nanopublications. An online tool (http://knowledge.bio) is available to explore established and potential gene-disease associations in the context of other biomedical relations.

Aims To assess the value of cardiac structure/function in predicting heart rate variability (HRV) and the possibly predictive value of HRV on cardiac parameters. Methods and results Baseline and 4-year follow-up data from the population-based CARLA cohort were used (790 men, 646 women, aged 45-83 years at baseline and 50-87 years at follow-up). Echocardiographic and HRV recordings were performed at baseline and at follow-up. Linear regression models with a quadratic term were used. Crude and covariate adjusted estimates were calculated. Missing values were imputed by means of multiple imputation. Heart rate variability measures taken into account consisted of linear time and frequency domain [standard deviation of normal-to-normal intervals (SDNN), high-frequency power (HF), low-frequency power (LF), LF/HF ratio] and non-linear measures [detrended fluctuation analysis (DFA1), SD1, SD2, SD1/SD2 ratio]. Echocardiographic parameters considered were ventricular mass index, diastolic interventricular septum thickness, left ventricular diastolic dimension, left atrial dimension systolic (LADS), and ejection fraction (Teichholz). A negative quadratic relation between baseline LADS and change in SDNN and HF was observed. The maximum HF and SDNN change (an increase of roughly 0.02%) was predicted at LADS of 3.72 and 3.57 cm, respectively, while the majority of subjects experienced a decrease in HRV. There was no association between further echocardiographic parameters and change in HRV, and there was no evidence of a predictive value of HRV in the prediction of changes in cardiac structure. Conclusion In the general population, LADS predicts 4-year alteration in SDNN and HF non-linearly. Because of the novelty of the result, analyses should be replicated in other populations.

We describe the development of a chemical entity recognition system and its application in the CHEMDNER-patent track of BioCreative 2015. This community challenge includes a Chemical Entity Mention in Patents (CEMP) recognition task and a Chemical Passage Detection (CPD) classification task. We addressed both tasks by an ensemble system that combines a dictionary-based approach with a statistical one. For this purpose the performance of several lexical resources was assessed using Peregrine, our open-source indexing engine. We combined our dictionary-based results on the patent corpus with the results of tmChem, a chemical recognizer using a conditional random field classifier. To improve the performance of tmChem, we utilized three additional features, viz. part-of-speech tags, lemmas and word-vector clusters. When evaluated on the training data, our final system obtained an F-score of 85.21% for the CEMP task, and an accuracy of 91.53% for the CPD task. On the test set, the best system ranked sixth among 21 teams for CEMP with an F-score of 86.82%, and second among nine teams for CPD with an accuracy of 94.23%. The differences in performance between the best ensemble system and the statistical system separately were small.Database URL: http://biosemantics.org/chemdner-patents.

We describe our approach to the chemical–disease relation (CDR) task in the BioCreative V challenge. The CDR task consists of two subtasks: automatic disease-named entity recognition and normalization (DNER), and extraction of chemical-induced diseases (CIDs) from Medline abstracts. For the DNER subtask, we used our concept recognition tool Peregrine, in combination with several optimization steps. For the CID subtask, our system, which we named RELigator, was trained on a rich feature set, comprising features derived from a graph database containing prior knowledge about chemicals and diseases, and linguistic and statistical features derived from the abstracts in the CDR training corpus. We describe the systems that were developed and present evaluation results for both subtasks on the CDR test set. For DNER, our Peregrine system reached an F-score of 0.757. For CID, the system achieved an F-score of 0.526, which ranked second among 18 participating teams. Several post-challenge modifications of the systems resulted in substantially improved F-scores (0.828 for DNER and 0.602 for CID). RELigator is available as a web service at http://biosemantics.org/index.php/software/religator.

We describe the development of a concept recognition system for French documents and its application in task 1b of the 2015 CLEF eHealth challenge. This community challenge included recognition of entities in a French medical corpus, normalization of the recognized entities, and normalization of entity mentions that had been manually annotated. Normalization had to be based on the Unified Medical Language System (UMLS). We addressed all three subtasks by a dictionary-based approach using Peregrine, our open-source indexing engine. To increase the coverage of our initial French terminology, we explored the use of two automatic translators, Google Translate and Microsoft Translator, to translate English UMLS terms into French. The corpus consisted of 1665 titles of French Medline abstracts and 6 French drug labels of the European Medicines Agency (EMEA). The corpus was manually annotated with concepts from the UMLS, and split in an equally-sized training and test set. The best performance on the training set was obtained with a terminology that contained the intersection of the translated terms in combination with several post-processing steps to reduce the number of false-positive detections. When evaluated on the test set, our system achieved F-scores of 0.756 and 0.665 for entity recognition on the EMEA documents and Medline titles, respectively. For subsequent entity normalization, the F-scores were 0.711 and 0.587. Entity normalization given the manually annotated entity mentions resulted in F-scores of 0.872 and 0.671. Our system obtained the highest F-scores among the systems that participated in the challenge.

Hepatic steatosis (HS) affects up to 35% of adults in the general population. Atrial fibrillation (AF) is the most prevalent sustained arrhythmia and has a substantial impact on healthcare costs. We analyzed cross-sectional associations of HS and serum liver enzyme levels with prevalent AF in a general population sample.We analyzed data from 3090 women and men, aged 20-81 years, from the population-based Study of Health in Pomerania. HS was determined by ultrasonography. Serum levels of alanine aminotransferase (ALT), aspartate aminotransferase (AST) and gamma-glutamyltranspeptidase (GGT) were measured photometrically. AF was determined by automatic electrocardiographic analysis software.The prevalences of HS and AF were 30.3% and 1.49%, respectively. ALT, AST and GGT showed a positive linear association with the risk of prevalent AF, after multivariable adjustment. The adjusted odds ratios for AF per 1-standard deviation increment in log-transformed serum liver enzyme levels were 1.65 (95% confidence interval [CI]: 1.16 to 2.35; p = 0.006) for ALT, 1.47 (95%CI: 1.07 to 2.02; p = 0.017) for AST and 2.17 (95%CI: 1.64 to 2.87; p0.001) for GGT. In contrast, ultrasonographic HS was not associated with AF.Our findings indicate that moderately elevated serum liver enzymes, but not sonographic liver hyperechogenicity, were associated with increased AF prevalence in the general adult population. The hepatic release of increased levels of serum liver enzymes might be accompanied by higher levels of pro-inflammatory, pro-coagulant and pro-fibronogenic mediators that might lead to structural and electrical remodeling of the atrium resulting in the development and persistence of AF.

Graphical abstractDisplay Omitted HighlightsÂ? The 100 abstracts contain relations between drug, disorder, and targets annotated by three annotators. Â? Computer entity and relationship annotations can be corrected with a web-based tool in an easy way. Â? Entity (73.2-79.2%) and relation (68.5-86.7%) annotations agree with the consensus. Â? Given annotator agreement helps to understand annotation variability and text-mining systems. Corpora with specific entities and relationships annotated are essential to train and evaluate text-mining systems that are developed to extract specific structured information from a large corpus. In this paper we describe an approach where a named-entity recognition system produces a first annotation and annotators revise this annotation using a web-based interface. The agreement figures achieved show that the inter-annotator agreement is much better than the agreement with the system provided annotations. The corpus has been annotated for drugs, disorders, genes and their inter-relationships. For each of the drug-disorder, drug-target, and target-disorder relations three experts have annotated a set of 100 abstracts. These annotated relationships will be used to train and evaluate text-mining software to capture these relationships in texts.

Graphical abstractDisplay Omitted Highlights? An ensemble system performs substantially better than the best individual system. ? Combination of the individual systems by a simple voting scheme is straightforward. ? An ensemble system allows the balancing of precision versus recall. ? The ensemble system is freely available, extensible, integrable, and retainable. Recognition of medical concepts is a basic step in information extraction from clinical records. We wished to improve on the performance of a variety of concept recognition systems by combining their individual results.We selected two dictionary-based systems and five statistical-based systems that were trained to annotate medical problems, tests, and treatments in clinical records. Manually annotated clinical records for training and testing were made available through the 2010 i2b2/VA (Informatics for Integrating Biology and the Bedside) challenge. Results of individual systems were combined by a simple voting scheme. The statistical systems were trained on a set of 349 records. Performance (precision, recall, F-score) was assessed on a test set of 477 records, using varying voting thresholds.The combined annotation system achieved a best F-score of 82.2% (recall 81.2%, precision 83.3%) on the test set, a score that ranks third among 22 participants in the i2b2/VA concept annotation task. The ensemble system had better precision and recall than any of the individual systems, yielding an F-score that is 4.6% point higher than the best single system. Changing the voting threshold offered a simple way to obtain a system with high precision (and moderate recall) or one with high recall (and moderate precision).The ensemble-based approach is straightforward and allows the balancing of precision versus recall of the combined system. The ensemble system is freely available and can easily be extended, integrated in other systems, and retrained.

Text chunking is an essential pre-processing step in information extraction systems. No comparative studies of chunking systems, including sentence splitting, tokenization and part-of-speech tagging, are available for the biomedical domain. We compared the usability (ease of integration, speed, trainability) and performance of six state-of-the-art chunkers for the biomedical domain, and combined the chunker results in order to improve chunking performance. We investigated six frequently used chunkers: GATE chunker, Genia Tagger, Lingpipe, MetaMap, OpenNLP, and Yamcha. All chunkers were integrated into the Unstructured Information Management Architecture framework. The GENIA Treebank corpus was used for training and testing. Performance was assessed for noun-phrase and verb-phrase chunking. For both noun-phrase chunking and verb-phrase chunking, OpenNLP performed best (F-scores 89.7% and 95.7%, respectively), but differences with Genia Tagger and Yamcha were small. With respect to usability. Lingpipe and OpenNLP scored best. When combining the results of the chunkers by a simple voting scheme, the F-score of the combined system improved by 3.1 percentage point for noun phrases and 0.6 percentage point for verb phrases as compared to the best single chunker. Changing the voting threshold offered a simple way to obtain a system with high precision (and moderate recall) or high recall (and moderate precision). This study is the first to compare the performance of the whole chunking pipeline, and to combine different existing chunking systems. Several chunkers showed good performance, but OpenNLP scored best both in performance and usability. The combination of chunker results by a simple voting scheme can further improve performance and allows for different precision-recall settings. (c) 2010 Elsevier Inc. All rights reserved.