{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T19:33:49Z","timestamp":1785008029561,"version":"3.55.0"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"23","license":[{"start":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T00:00:00Z","timestamp":1665619200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2021ZD0113302"],"award-info":[{"award-number":["2021ZD0113302"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206079"],"award-info":[{"award-number":["62206079"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,11,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>With the rapid development of precision medicine, a large amount of health data (such as electronic health records, gene sequencing, medical images, etc.) has been produced. It encourages more and more interest in data-driven insight discovery from these data. A reasonable way to verify the derived insights is by checking evidence from biomedical literature. However, manual verification is inefficient and not scalable. Therefore, an intelligent technique is necessary to solve this problem.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>This article introduces a framework for biomedical evidence engineering, addressing this problem more effectively. The framework consists of a biomedical literature retrieval module and an evidence extraction module. The retrieval module ensembles several methods and achieves state-of-the-art performance in biomedical literature retrieval. A BERT-based evidence extraction model is proposed to extract evidence from literature in response to queries. Moreover, we create a dataset with 1 million examples of biomedical evidence, 10\u00a0000 of which are manually annotated.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Datasets are available at https:\/\/github.com\/SendongZhao.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btac675","type":"journal-article","created":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T15:43:10Z","timestamp":1665675790000},"page":"5270-5278","source":"Crossref","is-referenced-by-count":7,"title":["Biomedical evidence engineering for data-driven discovery"],"prefix":"10.1093","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4676-1812","authenticated-orcid":false,"given":"Sendong","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Computer Science, College of Computer Science and Technology, Harbin Institute of Technology, Harbin 10065 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1377-1106","authenticated-orcid":false,"given":"Aobo","family":"Wang","sequence":"additional","affiliation":[{"name":"Research School of Finance, Actuarial Studies and Statistics, College of Business and Economics, Australian National University, Canberra, ACT 2600 , Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Computer Science, College of Computer Science and Technology, Harbin Institute of Technology, Harbin 10065 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences, Weill Medical College, Cornell University , New York, NY 14853, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,10,13]]},"reference":[{"key":"2023012806254297300_btac675-B1","article-title":"Query focused abstractive summarization: incorporating query relevance, multi-document coverage, and summary length constraints into seq2seq models","author":"Baumel","year":"2018"},{"key":"2023012806254297300_btac675-B2","article-title":"AttSum: joint learning of focusing and summarization with neural attention","author":"Cao","year":"2016"},{"key":"2023012806254297300_btac675-B3","first-page":"335","author":"Carbonell","year":"1998"},{"key":"2023012806254297300_btac675-B4","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"2023012806254297300_btac675-B5","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1056\/NEJMoa012512","article-title":"Reduction in the incidence of type 2 diabetes with lifestyle intervention or metformin","volume":"346","author":"Diabetes Prevention Program Research Group","year":"2002","journal-title":"N. Engl. J. Med"},{"key":"2023012806254297300_btac675-B6","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1613\/jair.1523","article-title":"LexRank: graph-based lexical centrality as salience in text summarization","volume":"22","author":"Erkan","year":"2004","journal-title":"JAIR"},{"key":"2023012806254297300_btac675-B7","first-page":"961","author":"Feigenblat","year":"2017"},{"key":"2023012806254297300_btac675-B8","author":"Galley","year":"2006"},{"key":"2023012806254297300_btac675-B9","first-page":"149","article-title":"PheKnow7Cloud: a tool for evaluating high-throughput phenotype candidates using online medical literature","volume":"2017","author":"Henderson","year":"2017","journal-title":"AMIA Summits Transl. Sci. Proc"},{"key":"2023012806254297300_btac675-B10","doi-asserted-by":"crossref","first-page":"e164","DOI":"10.2196\/jmir.9610","article-title":"Phenotype instance verification and evaluation tool (PIVET): a scaled phenotype evidence generation framework using web-based medical literature","volume":"20","author":"Henderson","year":"2018","journal-title":"J. Med. Internet Res"},{"key":"2023012806254297300_btac675-B11","doi-asserted-by":"crossref","first-page":"1556","DOI":"10.3389\/fphys.2019.01556","article-title":"Could heat therapy be an effective treatment for Alzheimerat and Parkinsonat and apy beA narrative review","volume":"10","author":"Hunt","year":"2020","journal-title":"Front. Physiol"},{"key":"2023012806254297300_btac675-B12","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"2023012806254297300_btac675-B13","article-title":"BERT: a review of applications in natural language processing and understanding","author":"Koroteev","year":"2021"},{"key":"2023012806254297300_btac675-B14","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: pre-trained biomedical language representation model for biomedical text mining","author":"Lee","year":"2019"},{"key":"2023012806254297300_btac675-B15","first-page":"1004","author":"Li","year":"2013"},{"key":"2023012806254297300_btac675-B16","first-page":"912","author":"Lin","year":"2010"},{"key":"2023012806254297300_btac675-B17","first-page":"265","article-title":"Medical subject headings (MeSH)","volume":"88","author":"Lipscomb","year":"2000","journal-title":"Bull. Med. Libr. Assoc"},{"key":"2023012806254297300_btac675-B18","doi-asserted-by":"crossref","DOI":"10.3115\/1118108.1118117","article-title":"NLTK: the natural language toolkit","author":"Loper","year":"2002"},{"key":"2023012806254297300_btac675-B19","first-page":"557","author":"McDonald","year":"2007"},{"key":"2023012806254297300_btac675-B20","first-page":"77","author":"Mohan","year":"2018"},{"key":"2023012806254297300_btac675-B21","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.ipm.2010.03.005","article-title":"Applying regression models to query-focused multi-document summarization","volume":"47","author":"Ouyang","year":"2011","journal-title":"Inf. Process. Manag"},{"key":"2023012806254297300_btac675-B22","article-title":"Understanding the behaviors of BERT in ranking","author":"Qiao","year":"2019"},{"key":"2023012806254297300_btac675-B23","first-page":"207","author":"Rau","year":"2022"},{"key":"2023012806254297300_btac675-B24","first-page":"95","author":"Ren","year":"2017"},{"key":"2023012806254297300_btac675-B25","first-page":"109","article-title":"Okapi at TREC-3","volume":"109","author":"Robertson","year":"1995","journal-title":"Nist Special Publication Sp"},{"key":"2023012806254297300_btac675-B26","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1093\/bib\/bbz042","article-title":"Graph convolutional networks for computational drug development and discovery","volume":"21","author":"Sun","year":"2020","journal-title":"Brief. Bioinform"},{"key":"2023012806254297300_btac675-B27","first-page":"296","author":"Thakur","year":"2021"},{"key":"2023012806254297300_btac675-B28","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"2023012806254297300_btac675-B29","author":"Wan","year":"2009"},{"key":"2023012806254297300_btac675-B30","author":"Zhao","year":"2019"},{"key":"2023012806254297300_btac675-B31","first-page":"149","author":"Zhao","year":"2019"},{"key":"2023012806254297300_btac675-B32","first-page":"817","author":"Zhao","year":"2019"},{"key":"2023012806254297300_btac675-B33","doi-asserted-by":"crossref","first-page":"bbaa057","DOI":"10.1093\/bib\/bbaa057","article-title":"Recent advances in biomedical literature mining","volume":"22","author":"Zhao","year":"2021","journal-title":"Brief. Bioinform"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac675\/46755741\/btac675.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/23\/5270\/48942579\/btac675.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/23\/5270\/48942579\/btac675.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T07:48:48Z","timestamp":1674892128000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/38\/23\/5270\/6760230"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,10,13]]},"references-count":33,"journal-issue":{"issue":"23","published-print":{"date-parts":[[2022,11,30]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac675","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,12,1]]},"published":{"date-parts":[[2022,10,13]]}}}