{"id":"https://openalex.org/W4205250588","doi":"https://doi.org/10.1145/3493700.3493773","title":"Data Science and Natural Language Processing to Extract Information in Clinical Domain","display_name":"Data Science and Natural Language Processing to Extract Information in Clinical Domain","publication_year":2022,"publication_date":"2022-01-07","ids":{"openalex":"https://openalex.org/W4205250588","doi":"https://doi.org/10.1145/3493700.3493773"},"language":"en","primary_location":{"id":"doi:10.1145/3493700.3493773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493700.3493773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050525772","display_name":"V. G. Vinod Vydiswaran","orcid":"https://orcid.org/0000-0002-3122-1936"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"V.G.Vinod Vydiswaran","raw_affiliation_strings":["University of Michigan, US"],"affiliations":[{"raw_affiliation_string":"University of Michigan, US","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051163444","display_name":"Xinyan Zhao","orcid":"https://orcid.org/0000-0002-1970-031X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyan Zhao","raw_affiliation_strings":["University of Michigan, US"],"affiliations":[{"raw_affiliation_string":"University of Michigan, US","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028581235","display_name":"Deahan Yu","orcid":"https://orcid.org/0000-0001-7263-078X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deahan Yu","raw_affiliation_strings":["University of Michigan, US"],"affiliations":[{"raw_affiliation_string":"University of Michigan, US","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050525772"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.3431,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.53287556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"352","last_page":"353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/jargon","display_name":"Jargon","score":0.8020851612091064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7269538640975952},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6082445979118347},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5751940011978149},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.5158511996269226},{"id":"https://openalex.org/keywords/electronic-health-record","display_name":"Electronic health record","score":0.48747706413269043},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.47549471259117126},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4703379273414612},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.4484519958496094},{"id":"https://openalex.org/keywords/medical-information","display_name":"Medical information","score":0.4459204077720642},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3746577501296997},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3727415204048157},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.21602573990821838},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20900830626487732},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.16811701655387878}],"concepts":[{"id":"https://openalex.org/C2777611551","wikidata":"https://www.wikidata.org/wiki/Q17951","display_name":"Jargon","level":2,"score":0.8020851612091064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269538640975952},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6082445979118347},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5751940011978149},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.5158511996269226},{"id":"https://openalex.org/C3020144179","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic health record","level":3,"score":0.48747706413269043},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.47549471259117126},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4703379273414612},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.4484519958496094},{"id":"https://openalex.org/C3019150057","wikidata":"https://www.wikidata.org/wiki/Q92779279","display_name":"Medical information","level":2,"score":0.4459204077720642},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3746577501296997},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3727415204048157},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.21602573990821838},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20900830626487732},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.16811701655387878},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3493700.3493773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493700.3493773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1964625659","https://openalex.org/W2002514548","https://openalex.org/W2146089916","https://openalex.org/W2159636537","https://openalex.org/W2169818249","https://openalex.org/W2784089855","https://openalex.org/W3102881428"],"related_works":["https://openalex.org/W187932805","https://openalex.org/W4392490004","https://openalex.org/W1641026212","https://openalex.org/W4402738807","https://openalex.org/W2911982698","https://openalex.org/W2323588885","https://openalex.org/W3047677938","https://openalex.org/W2087134418","https://openalex.org/W2078646730","https://openalex.org/W4312053962"],"abstract_inverted_index":{"In":[0],"the":[1],"past":[2],"decade,":[3],"massive":[4],"amounts":[5],"of":[6],"clinical":[7,81],"data":[8,96],"have":[9],"been":[10],"made":[11],"available":[12],"in":[13,16],"computable":[14],"form":[15],"electronic":[17],"health":[18,54],"record":[19,71],"(EHR)":[20],"systems":[21,65],"and":[22,47,77,90],"social":[23,94],"media.":[24],"To":[25],"benefit":[26],"from":[27,103],"these":[28],"large-scale":[29],"data,":[30],"we":[31],"need":[32],"to":[33,61,70],"extract":[34],"relevant":[35],"information,":[36,86],"which":[37,87],"remains":[38],"challenging.":[39],"Clinical":[40],"narratives":[41,82],"often":[42,101],"contain":[43,83],"abbreviations,":[44],"medical":[45],"terms,":[46],"other":[48],"jargon":[49],"that":[50],"are":[51],"easy":[52],"for":[53,58],"professionals,":[55],"but":[56],"challenging":[57],"automated":[59],"approaches":[60],"disambiguate.":[62],"Many":[63],"EHR":[64],"use":[66],"non-standard":[67],"document":[68],"structures":[69],"critical":[72],"information":[73],"about":[74],"medications,":[75],"diagnoses,":[76],"potential":[78],"complications.":[79],"Finally,":[80],"sensitive":[84],"patient":[85],"raises":[88],"privacy":[89],"security":[91],"concerns.":[92],"Additionally,":[93],"media":[95],"with":[97],"such":[98],"as":[99],"tweets":[100],"suffer":[102],"high":[104],"language":[105],"variance.":[106]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}