{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T21:10:11Z","timestamp":1720905011751},"reference-count":70,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2019,3,6]],"date-time":"2019-03-06T00:00:00Z","timestamp":1551830400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Manchester Molecular Pathology Innovation Centre","award":["MR\/N00583X\/1"],"award-info":[{"award-number":["MR\/N00583X\/1"]}]},{"name":"Pacific Life Re"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Objective<\/jats:title><jats:p>We seek to quantify the mortality risk associated with mentions of medical concepts in textual electronic health records (EHRs). Recognizing mentions of named entities of relevant types (eg, conditions, symptoms, laboratory tests or behaviors) in text is a well-researched task. However, determining the level of risk associated with them is partly dependent on the textual context in which they appear, which may describe severity, temporal aspects, quantity, etc.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>To take into account that a given word appearing in the context of different risk factors (medical concepts) can make different contributions toward risk level, we propose a multitask approach, called context-aware linear modeling, which can be applied using appropriately regularized linear regression. To improve the performance for risk factors unseen in training data (eg, rare diseases), we take into account their distributional similarity to other concepts.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The evaluation is based on a corpus of 531 reports from EHRs with 99 376 risk factors rated manually by experts. While context-aware linear modeling significantly outperforms single-task models, taking into account concept similarity further improves performance, reaching the level of human annotators\u2019 agreements.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Our results show that automatic quantification of risk factors in EHRs can achieve performance comparable to human assessment, and taking into account the multitask structure of the problem and the ability to handle rare concepts is crucial for its accuracy.<\/jats:p><\/jats:sec>","DOI":"10.1093\/jamia\/ocz004","type":"journal-article","created":{"date-parts":[[2019,1,5]],"date-time":"2019-01-05T20:08:56Z","timestamp":1546718936000},"page":"537-546","source":"Crossref","is-referenced-by-count":3,"title":["Quantifying risk factors in medical reports with a context-aware linear model"],"prefix":"10.1093","volume":"26","author":[{"given":"Piotr","family":"Przyby\u0142a","sequence":"first","affiliation":[{"name":"National Centre for Text Mining, School of Computer Science, University of Manchester, Manchester, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Austin J","family":"Brockmeier","sequence":"additional","affiliation":[{"name":"National Centre for Text Mining, School of Computer Science, University of Manchester, Manchester, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sophia","family":"Ananiadou","sequence":"additional","affiliation":[{"name":"National Centre for Text Mining, School of Computer Science, University of Manchester, Manchester, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2019,3,6]]},"reference":[{"key":"2020110613061007500_ocz004-B1","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.ijmedinf.2018.03.013","article-title":"Concurrence of big data analytics and healthcare: a systematic review","volume":"114","author":"Mehta","year":"2018","journal-title":"Int J Med Inform"},{"issue":"1","key":"2020110613061007500_ocz004-B2","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1093\/jamia\/ocw042","article-title":"Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review","volume":"24","author":"Goldstein","year":"2017","journal-title":"J Am Med Inform Assoc"},{"key":"2020110613061007500_ocz004-B3","doi-asserted-by":"crossref","article-title":"Risk prediction with electronic health records: a deep learning approach","author":"Cheng","DOI":"10.1137\/1.9781611974348.49"},{"key":"2020110613061007500_ocz004-B4","doi-asserted-by":"crossref","article-title":"Improving palliative care with deep learning","author":"Avati","DOI":"10.1109\/BIBM.2017.8217669"},{"key":"2020110613061007500_ocz004-B5","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.jbi.2017.06.016","article-title":"Text mining applied to electronic cardiovascular procedure reports to identify patients with trileaflet aortic stenosis and coronary artery disease","volume":"72","author":"Small","year":"2017","journal-title":"J Biomed Inform"},{"key":"2020110613061007500_ocz004-B6","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.ijmedinf.2017.12.024","article-title":"Natural language processing of clinical notes for identification of critical limb ischemia","volume":"111","author":"Afzal","year":"2018","journal-title":"Int J Med Inform"},{"issue":"7","key":"2020110613061007500_ocz004-B7","doi-asserted-by":"crossref","first-page":"1125","DOI":"10.1097\/CCM.0000000000003148","article-title":"Inclusion of unstructured clinical text improves early prediction of death or prolonged ICU stay","volume":"46","author":"Weissman","year":"2018","journal-title":"Crit Care Med"},{"key":"2020110613061007500_ocz004-B8","doi-asserted-by":"crossref","first-page":"1190","DOI":"10.1177\/000313481808400736","article-title":"Predicting mortality in the surgical intensive care unit using artificial intelligence and natural language processing of physician documentation","volume":"84","author":"Parreco","year":"2018","journal-title":"Am Surg"},{"key":"2020110613061007500_ocz004-B9","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J R Stat Soc Ser B"},{"key":"2020110613061007500_ocz004-B10","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-78503-5","volume-title":"Clinical Text Mining Secondary Use of Electronic Patient Records","author":"Dalianis","year":"2018"},{"key":"2020110613061007500_ocz004-B11","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.jbi.2017.07.012","article-title":"Natural language processing systems for capturing and standardizing unstructured clinical information: a systematic review","volume":"73","author":"Kreimeyer","year":"2017","journal-title":"J Biomed Inform"},{"key":"2020110613061007500_ocz004-B12","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.jbi.2017.11.011","article-title":"Clinical information extraction applications: a literature review","volume":"77","author":"Wang","year":"2018","journal-title":"J Biomed Inform"},{"issue":"1","key":"2020110613061007500_ocz004-B13","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1136\/amiajnl-2013-002544","article-title":"Evaluating the state of the art in disorder recognition and normalization of the clinical narrative","volume":"22","author":"Pradhan","year":"2015","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"2020110613061007500_ocz004-B14","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1186\/s13326-017-0153-x","article-title":"Semantic annotation in biomedicine: the current landscape","volume":"8","author":"Jovanovi\u0107","year":"2017","journal-title":"J Biomed Semant"},{"issue":"5","key":"2020110613061007500_ocz004-B15","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1136\/amiajnl-2011-000203","article-title":"2010 i2b2\/VA challenge on concepts, assertions, and relations in clinical text","volume":"18","author":"Uzuner","year":"2011","journal-title":"J Am Med Inform Assoc"},{"issue":"11","key":"2020110613061007500_ocz004-B16","doi-asserted-by":"crossref","first-page":"e112774","DOI":"10.1371\/journal.pone.0112774","article-title":"Negation\u2019s not solved: generalizability versus optimizability in clinical natural language processing","volume":"9","author":"Wu","year":"2014","journal-title":"PLoS One"},{"key":"2020110613061007500_ocz004-B17","first-page":"321","article-title":"Hedging their mets: the use of uncertainty terms in clinical documents and its potential implications when sharing the documents with patients","volume":"2012","author":"Hanauer","year":"2012","journal-title":"AMIA Annu Symp Proc"},{"issue":"3","key":"2020110613061007500_ocz004-B18","doi-asserted-by":"crossref","first-page":"266","DOI":"10.3414\/ME15-01-0112","article-title":"Valx: a system for extracting and structuring numeric lab test comparison statements from text","volume":"55","author":"Hao","year":"2016","journal-title":"Methods Inf Med"},{"key":"2020110613061007500_ocz004-B19","doi-asserted-by":"crossref","article-title":"Extracting modifiable risk factors from narrative preventive healthcare guidelines for EHR integration","author":"Shah","DOI":"10.1109\/BIBE.2017.000-2"},{"key":"2020110613061007500_ocz004-B20","doi-asserted-by":"crossref","article-title":"Medical risk information extraction based on Hidden Markov Model","author":"Xin","DOI":"10.1109\/CompComm.2016.7924809"},{"key":"2020110613061007500_ocz004-B21","doi-asserted-by":"crossref","article-title":"Risk information extraction and aggregation","author":"Deleris","DOI":"10.1007\/978-3-642-41575-3_12"},{"key":"2020110613061007500_ocz004-B22","doi-asserted-by":"crossref","first-page":"S78","DOI":"10.1016\/j.jbi.2015.05.009","article-title":"Annotating risk factors for heart disease in clinical narratives for diabetic patients","volume":"58","author":"Stubbs","year":"2015","journal-title":"J Biomed Inform"},{"issue":"e2","key":"2020110613061007500_ocz004-B23","doi-asserted-by":"crossref","first-page":"e212","DOI":"10.1136\/amiajnl-2013-001962","article-title":"Developing and evaluating an automated appendicitis risk stratification algorithm for pediatric patients in the emergency department","volume":"20","author":"Deleger","year":"2013","journal-title":"J Am Med Inform Assoc"},{"key":"2020110613061007500_ocz004-B24","article-title":"Learning many related tasks at the same time with backpropagation","author":"Caruana"},{"key":"2020110613061007500_ocz004-B25","article-title":"Solving a huge number of similar tasks: a combination of multi-task learning and a hierarchical Bayesian approach","author":"Heskes"},{"key":"2020110613061007500_ocz004-B26","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1007\/978-3-540-45167-9_41","article-title":"Exploiting task relatedness for multiple task learning","volume-title":"Learning Theory and Kernel Machines","author":"Ben-David","year":"2003"},{"issue":"1","key":"2020110613061007500_ocz004-B27","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1093\/nsr\/nwx105","article-title":"An overview of multi-task learning","volume":"5","author":"Zhang","year":"2018","journal-title":"Natl Sci Rev"},{"key":"2020110613061007500_ocz004-B28","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1613\/jair.731","article-title":"A model of inductive bias learning","volume":"12","author":"Baxter","year":"2000","journal-title":"J Artif Intell Res"},{"key":"2020110613061007500_ocz004-B29","article-title":"Deep multi-task representation learning: a tensor factorisation approach","author":"Yang","year":"2017","journal-title":"arXiv Prepr arXiv:1605.06391"},{"key":"2020110613061007500_ocz004-B30","doi-asserted-by":"crossref","article-title":"Multi-task feature and kernel selection for SVMs","author":"Jebara","DOI":"10.1145\/1015330.1015426"},{"key":"2020110613061007500_ocz004-B31","first-page":"35","article-title":"Multi-task learning for classification with dirichlet process priors","volume":"8","author":"Xue","year":"2007","journal-title":"J Mach Learn Res"},{"issue":"3","key":"2020110613061007500_ocz004-B32","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1007\/s10994-008-5050-1","article-title":"Flexible latent variable models for multi-task learning","volume":"73","author":"Zhang","year":"2008","journal-title":"Mach Learn"},{"key":"2020110613061007500_ocz004-B33","first-page":"83","article-title":"Task clustering and gating for bayesian multitask learning","volume":"4","author":"Bakker","year":"2003","journal-title":"J Mach Learn Res"},{"key":"2020110613061007500_ocz004-B34","article-title":"A convex formulation for learning task relationships in multi-task learning","author":"Zhang"},{"key":"2020110613061007500_ocz004-B35","article-title":"Learning multiple tasks with multilinear relationship networks","author":"Long"},{"key":"2020110613061007500_ocz004-B36","first-page":"615","article-title":"Learning multiple tasks with kernel methods","volume":"6","author":"Evgeniou","year":"2005","journal-title":"J Mach Learn Res"},{"key":"2020110613061007500_ocz004-B37","article-title":"Multi-task learning via conic programming","author":"Kato"},{"key":"2020110613061007500_ocz004-B38","volume-title":"Multi-task feature selection","author":"Obozinski","year":"2006"},{"key":"2020110613061007500_ocz004-B39","doi-asserted-by":"crossref","first-page":"41","DOI":"10.7551\/mitpress\/7503.003.0010","article-title":"Multi-task feature learning","volume-title":"Advances in Neural Information Processing Systems 19","author":"Argyriou","year":"2007"},{"issue":"2","key":"2020110613061007500_ocz004-B40","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1007\/s11222-008-9111-x","article-title":"Joint covariate selection and joint subspace selection for multiple classification problems","volume":"20","author":"Obozinski","year":"2010","journal-title":"Stat Comput"},{"issue":"1","key":"2020110613061007500_ocz004-B41","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1111\/j.1467-9868.2005.00532.x","article-title":"Model selection and estimation in regression with grouped variables","volume":"68","author":"Yuan","year":"2006","journal-title":"J R Stat Soc B Stat Method"},{"key":"2020110613061007500_ocz004-B42","doi-asserted-by":"crossref","article-title":"A high-performance semi-supervised learning method for text chunking","author":"Ando","DOI":"10.3115\/1219840.1219841"},{"key":"2020110613061007500_ocz004-B43","first-page":"1817","article-title":"A framework for learning predictive structures from multiple tasks and unlabeled data","volume":"6","author":"Ando","year":"2005","journal-title":"J Mach Learn Res"},{"key":"2020110613061007500_ocz004-B44","doi-asserted-by":"crossref","article-title":"Uncovering shared structures in multiclass classification","author":"Amit","DOI":"10.1145\/1273496.1273499"},{"issue":"3","key":"2020110613061007500_ocz004-B45","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/s10994-007-5040-8","article-title":"Convex multi-task feature learning","volume":"73","author":"Argyriou","year":"2008","journal-title":"Mach Learn"},{"issue":"6","key":"2020110613061007500_ocz004-B46","doi-asserted-by":"crossref","first-page":"3465","DOI":"10.1137\/090763184","article-title":"Trace norm regularization: reformulations, algorithms, and multi-task learning","volume":"20","author":"Pong","year":"2010","journal-title":"SIAM J Optim"},{"key":"2020110613061007500_ocz004-B47","doi-asserted-by":"crossref","first-page":"1025","DOI":"10.1109\/TPAMI.2012.189","article-title":"A convex formulation for learning a shared predictive structure from multiple tasks","volume":"35","author":"Chen","year":"2013","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"2020110613061007500_ocz004-B48","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1145\/2086737.2086742","article-title":"Learning incoherent sparse and low-rank patterns from multiple tasks","volume":"5","author":"Chen","year":"2012","journal-title":"ACM Trans Knowl Discov Data"},{"key":"2020110613061007500_ocz004-B49","first-page":"964","article-title":"A dirty model for multi-task learning","volume-title":"Advances in Neural Information Processing Systems 23","author":"Jalali","year":"2010"},{"key":"2020110613061007500_ocz004-B50","article-title":"Variable selection and task grouping for multi-task learning","author":"Jeong","year":"2018","journal-title":"arXiv Prepr arXiv:1802.04676"},{"key":"2020110613061007500_ocz004-B51","doi-asserted-by":"crossref","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci Data"},{"key":"2020110613061007500_ocz004-B52","article-title":"BRAT\u202f: a web-based tool for NLP-assisted text annotation","author":"Stenetorp"},{"issue":"3","key":"2020110613061007500_ocz004-B53","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1136\/jamia.2009.002733","article-title":"An overview of MetaMap: historical perspective and recent advances","volume":"17","author":"Aronson","year":"2010","journal-title":"J Am Med Inform Assoc"},{"key":"2020110613061007500_ocz004-B54","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1093\/jamia\/ocw177","article-title":"MetaMap Lite: an evaluation of a new Java implementation of MetaMap","volume":"42","author":"Demner-Fushman","year":"2017","journal-title":"J Am Med Inform Assoc"},{"key":"2020110613061007500_ocz004-B55","article-title":"Clinical concept embeddings learned from massive sources of medical data","author":"Beam","year":"2018","journal-title":"arXiv:1804.01486"},{"issue":"5","key":"2020110613061007500_ocz004-B56","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1016\/j.jbi.2009.05.002","article-title":"ConText: an algorithm for determining negation, experiencer, and temporal status from clinical reports","volume":"42","author":"Harkema","year":"2009","journal-title":"J Biomed Inform"},{"key":"2020110613061007500_ocz004-B57","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v033.i01","article-title":"Regularization paths for generalized linear models via coordinate descent","volume":"33","author":"Friedman","year":"2010","journal-title":"J Stat Softw"},{"key":"2020110613061007500_ocz004-B58","doi-asserted-by":"crossref","article-title":"An accelerated gradient method for trace norm minimization","author":"Ji","DOI":"10.1145\/1553374.1553434"},{"issue":"3\u20134","key":"2020110613061007500_ocz004-B59","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1007\/s00180-013-0440-7","article-title":"Sparse trace norm regularization","volume":"29","author":"Chen","year":"2014","journal-title":"Comput Stat"},{"issue":"R2","key":"2020110613061007500_ocz004-B60","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1051\/m2an\/197509R200411","article-title":"On the approximation of a class of nonlinear Dirichlet problems by a penalty-duality method and finite elements of order\u00a0one","volume":"9","author":"Glowinski","year":"1975","journal-title":"Rairo Analyse Num\u00e9rique"},{"issue":"1","key":"2020110613061007500_ocz004-B61","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/0898-1221(76)90003-1","article-title":"A dual algorithm for the solution of nonlinear variational problems via finite element approximation","volume":"2","author":"Gabay","year":"1976","journal-title":"Comput Math with Appl"},{"issue":"1\u20133","key":"2020110613061007500_ocz004-B62","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1007\/BF01581204","article-title":"On the Douglas\u2013Rachford splitting method and the proximal point algorithm for maximal monotone operators","volume":"55","author":"Eckstein","year":"1992","journal-title":"Math Program"},{"key":"2020110613061007500_ocz004-B63","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/978-1-4419-9569-8_10","article-title":"Proximal splitting methods in signal processing","volume-title":"Fixed-Point Algorithms for Inverse Problems in Science and Engineering","author":"Combettes","year":"2011"},{"issue":"1","key":"2020110613061007500_ocz004-B64","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000016","article-title":"Distributed optimization and statistical learning via the alternating direction method of multipliers","volume":"3","author":"Boyd","year":"2010","journal-title":"FNT Mach Learn"},{"issue":"5","key":"2020110613061007500_ocz004-B65","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1080\/00107510500052444","article-title":"Power laws, Pareto distributions and Zipf\u2019s law","volume":"46","author":"Newman","year":"2005","journal-title":"Contemp Phys"},{"key":"2020110613061007500_ocz004-B66","unstructured":"Morgan W . Statistical Hypothesis Tests for NLP; 2006. https:\/\/cs.stanford.edu\/people\/wmorgan\/sigtest.pdf. Accessed August 5, 2018."},{"issue":"14","key":"2020110613061007500_ocz004-B67","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1002\/sim.4484","article-title":"L1 penalized continuation ratio models for ordinal response prediction using high-dimensional datasets","volume":"31","author":"Archer","year":"2012","journal-title":"Stat Med"},{"key":"2020110613061007500_ocz004-B68","doi-asserted-by":"crossref","article-title":"Proactive learning for named entity recognition","author":"Li","DOI":"10.18653\/v1\/W17-2314"},{"key":"2020110613061007500_ocz004-B69","doi-asserted-by":"crossref","article-title":"APLenty: annotation tool for creating high-quality datasets using active and proactive learning","author":"Nghiem","DOI":"10.18653\/v1\/D18-2019"},{"issue":"S3","key":"2020110613061007500_ocz004-B70","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1007\/s11606-013-2455-8","article-title":"Bringing big data to personalized healthcare: a patient-centered framework","volume":"28","author":"Chawla","year":"2013","journal-title":"J Gen Intern Med"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/26\/6\/537\/34153430\/ocz004.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/26\/6\/537\/34153430\/ocz004.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T20:56:32Z","timestamp":1720904192000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/26\/6\/537\/5370307"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,6]]},"references-count":70,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2019,3,6]]},"published-print":{"date-parts":[[2019,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocz004","relation":{},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,6]]},"published":{"date-parts":[[2019,3,6]]}}}