{"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/guided-deep-list-automating-the-generation-of","title":"Guided Deep List: Automating the Generation of Epidemiological Line Lists from Open Sources","arxiv_id":"1702.06663","date":"2017-02-22","proceeding":null,"authors":["Saurav Ghosh","Prithwish Chakraborty","Bryan L. Lewis","Maimuna S. Majumder","Emily Cohn","John S. Brownstein","Madhav V. Marathe","Naren Ramakrishnan"],"abstract":"Real-time monitoring and responses to emerging public health threats rely on\nthe availability of timely surveillance data. During the early stages of an\nepidemic, the ready availability of line lists with detailed tabular\ninformation about laboratory-confirmed cases can assist epidemiologists in\nmaking reliable inferences and forecasts. Such inferences are crucial to\nunderstand the epidemiology of a specific disease early enough to stop or\ncontrol the outbreak. However, construction of such line lists requires\nconsiderable human supervision and therefore, difficult to generate in\nreal-time. In this paper, we motivate Guided Deep List, the first tool for\nbuilding automated line lists (in near real-time) from open source reports of\nemerging disease outbreaks. Specifically, we focus on deriving epidemiological\ncharacteristics of an emerging disease and the affected population from reports\nof illness. Guided Deep List uses distributed vector representations (ala\nword2vec) to discover a set of indicators for each line list feature. This\ndiscovery of indicators is followed by the use of dependency parsing based\ntechniques for final extraction in tabular form. We evaluate the performance of\nGuided Deep List against a human annotated line list provided by HealthMap\ncorresponding to MERS outbreaks in Saudi Arabia. We demonstrate that Guided\nDeep List extracts line list features with increased accuracy compared to a\nbaseline method. We further show how these automatically extracted line list\nfeatures can be used for making epidemiological inferences, such as inferring\ndemographics and symptoms-to-hospitalization period of affected individuals.","url_abs":"http://arxiv.org/abs/1702.06663v1","url_pdf":"http://arxiv.org/pdf/1702.06663v1.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":"guided-deep-list-automating-the-generation-of","repo_url":"https://github.com/sauravcsvt/KDD_linelisting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"epidemiology","task_name":"Epidemiology"}],"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}