{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/extraction-of-evidence-tables-from-abstracts","title":"Extraction of evidence tables from abstracts of randomized clinical trials using a maximum entropy classifier and global constraints","arxiv_id":"1509.05209","date":"2015-09-17","proceeding":null,"authors":["Antonio Trenta","Anthony Hunter","Sebastian Riedel"],"abstract":"Systematic use of the published results of randomized clinical trials is\nincreasingly important in evidence-based medicine. In order to collate and\nanalyze the results from potentially numerous trials, evidence tables are used\nto represent trials concerning a set of interventions of interest. An evidence\ntable has columns for the patient group, for each of the interventions being\ncompared, for the criterion for the comparison (e.g. proportion who survived\nafter 5 years from treatment), and for each of the results. Currently, it is a\nlabour-intensive activity to read each published paper and extract the\ninformation for each field in an evidence table. There have been some NLP\nstudies investigating how some of the features from papers can be extracted, or\nat least the relevant sentences identified. However, there is a lack of an NLP\nsystem for the systematic extraction of each item of information required for\nan evidence table. We address this need by a combination of a maximum entropy\nclassifier, and integer linear programming. We use the later to handle\nconstraints on what is an acceptable classification of the features to be\nextracted. With experimental results, we demonstrate substantial advantages in\nusing global constraints (such as the features describing the patient group,\nand the interventions, must occur before the features describing the results of\nthe comparison).","url_abs":"http://arxiv.org/abs/1509.05209v1","url_pdf":"http://arxiv.org/pdf/1509.05209v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"extraction-of-evidence-tables-from-abstracts","repo_url":"https://github.com/antoniotre86/IERCT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"extraction-of-evidence-tables-from-abstracts","repo_url":"https://github.com/jetsunwhitton/rct-art","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}