{"id":"https://openalex.org/W3136255400","doi":"https://doi.org/10.1109/ichi48887.2020.9374369","title":"A Natural Language Processing Tool to Extract Quantitative Smoking Status from Clinical Narratives","display_name":"A Natural Language Processing Tool to Extract Quantitative Smoking Status from Clinical Narratives","publication_year":2020,"publication_date":"2020-11-01","ids":{"openalex":"https://openalex.org/W3136255400","doi":"https://doi.org/10.1109/ichi48887.2020.9374369","mag":"3136255400","pmid":"https://pubmed.ncbi.nlm.nih.gov/33786419"},"language":"en","primary_location":{"id":"doi:10.1109/ichi48887.2020.9374369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichi48887.2020.9374369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Healthcare Informatics (ICHI)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8006894","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103133745","display_name":"Xi Yang","orcid":"https://orcid.org/0000-0003-2981-3972"},"institutions":[{"id":"https://openalex.org/I2800717037","display_name":"University of Florida Health","ror":"https://ror.org/04tk2gy88","country_code":"US","type":"education","lineage":["https://openalex.org/I2800717037"]},{"id":"https://openalex.org/I94062374","display_name":"Florida College","ror":"https://ror.org/010bgev76","country_code":"US","type":"education","lineage":["https://openalex.org/I94062374"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xi Yang","raw_affiliation_strings":["Health Outcomes and Biomedical Informatics College of Medicine, University of Florida Gainesville, USA","Health Outcomes and Biomedical Informatics College of Medicine, University of Florida, Gainesville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Health Outcomes and Biomedical Informatics College of Medicine, University of Florida Gainesville, USA","institution_ids":["https://openalex.org/I2800717037","https://openalex.org/I94062374"]},{"raw_affiliation_string":"Health Outcomes and Biomedical Informatics College of Medicine, University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I2800717037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015108820","display_name":"Hanyuan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanyuan Yang","raw_affiliation_strings":["Computer and Information Science and Engineering College of Engineering, University of Florida Gainesville, USA","Computer and Information Science and Engineering College of Engineering, University of Florida, Gainesville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer and Information Science and Engineering College of Engineering, University of Florida Gainesville, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"Computer and Information Science and Engineering College of Engineering, University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031161176","display_name":"Tianchen Lyu","orcid":"https://orcid.org/0000-0002-0981-3847"},"institutions":[{"id":"https://openalex.org/I2800717037","display_name":"University of Florida Health","ror":"https://ror.org/04tk2gy88","country_code":"US","type":"education","lineage":["https://openalex.org/I2800717037"]},{"id":"https://openalex.org/I94062374","display_name":"Florida College","ror":"https://ror.org/010bgev76","country_code":"US","type":"education","lineage":["https://openalex.org/I94062374"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianchen Lyu","raw_affiliation_strings":["Health Outcomes and Biomedical Informatics College of Medicine, University of Florida Gainesville, USA","Health Outcomes and Biomedical Informatics College of Medicine, University of Florida, Gainesville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Health Outcomes and Biomedical Informatics College of Medicine, University of Florida Gainesville, USA","institution_ids":["https://openalex.org/I2800717037","https://openalex.org/I94062374"]},{"raw_affiliation_string":"Health Outcomes and Biomedical Informatics College of Medicine, University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I2800717037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101662378","display_name":"Shuang Yang","orcid":"https://orcid.org/0000-0002-7943-8130"},"institutions":[{"id":"https://openalex.org/I2800717037","display_name":"University of Florida Health","ror":"https://ror.org/04tk2gy88","country_code":"US","type":"education","lineage":["https://openalex.org/I2800717037"]},{"id":"https://openalex.org/I94062374","display_name":"Florida College","ror":"https://ror.org/010bgev76","country_code":"US","type":"education","lineage":["https://openalex.org/I94062374"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuang Yang","raw_affiliation_strings":["Health Outcomes and Biomedical Informatics College of Medicine, University of Florida Gainesville, USA","Health Outcomes and Biomedical Informatics College of Medicine, University of Florida, Gainesville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Health Outcomes and Biomedical Informatics College of Medicine, University of Florida Gainesville, USA","institution_ids":["https://openalex.org/I2800717037","https://openalex.org/I94062374"]},{"raw_affiliation_string":"Health Outcomes and Biomedical Informatics College of Medicine, University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I2800717037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052505769","display_name":"Yi Guo","orcid":"https://orcid.org/0000-0003-0587-4105"},"institutions":[{"id":"https://openalex.org/I2800717037","display_name":"University of Florida Health","ror":"https://ror.org/04tk2gy88","country_code":"US","type":"education","lineage":["https://openalex.org/I2800717037"]},{"id":"https://openalex.org/I94062374","display_name":"Florida College","ror":"https://ror.org/010bgev76","country_code":"US","type":"education","lineage":["https://openalex.org/I94062374"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Guo","raw_affiliation_strings":["Health Outcomes and Biomedical Informatics College of Medicine, University of Florida Gainesville, USA","Health Outcomes and Biomedical Informatics College of Medicine, University of Florida, Gainesville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Health Outcomes and Biomedical Informatics College of Medicine, University of Florida Gainesville, USA","institution_ids":["https://openalex.org/I2800717037","https://openalex.org/I94062374"]},{"raw_affiliation_string":"Health Outcomes and Biomedical Informatics College of Medicine, University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I2800717037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030951014","display_name":"Jiang Bian","orcid":"https://orcid.org/0000-0002-2238-5429"},"institutions":[{"id":"https://openalex.org/I2800717037","display_name":"University of Florida Health","ror":"https://ror.org/04tk2gy88","country_code":"US","type":"education","lineage":["https://openalex.org/I2800717037"]},{"id":"https://openalex.org/I94062374","display_name":"Florida College","ror":"https://ror.org/010bgev76","country_code":"US","type":"education","lineage":["https://openalex.org/I94062374"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiang Bian","raw_affiliation_strings":["Health Outcomes and Biomedical Informatics College of Medicine, University of Florida Gainesville, USA","Health Outcomes and Biomedical Informatics College of Medicine, University of Florida, Gainesville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Health Outcomes and Biomedical Informatics College of Medicine, University of Florida Gainesville, USA","institution_ids":["https://openalex.org/I2800717037","https://openalex.org/I94062374"]},{"raw_affiliation_string":"Health Outcomes and Biomedical Informatics College of Medicine, University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I2800717037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084072550","display_name":"Hua Xu","orcid":"https://orcid.org/0000-0002-5274-4672"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hua Xu","raw_affiliation_strings":["School of Biomedical Informatics, University of Texas Health Science Center at Houston Houston, USA","School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Informatics, University of Texas Health Science Center at Houston Houston, USA","institution_ids":["https://openalex.org/I919571938"]},{"raw_affiliation_string":"School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010253402","display_name":"Yonghui Wu","orcid":"https://orcid.org/0000-0002-6780-6135"},"institutions":[{"id":"https://openalex.org/I2800717037","display_name":"University of Florida Health","ror":"https://ror.org/04tk2gy88","country_code":"US","type":"education","lineage":["https://openalex.org/I2800717037"]},{"id":"https://openalex.org/I94062374","display_name":"Florida College","ror":"https://ror.org/010bgev76","country_code":"US","type":"education","lineage":["https://openalex.org/I94062374"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonghui Wu","raw_affiliation_strings":["Health Outcomes and Biomedical Informatics College of Medicine, University of Florida Gainesville, USA","Health Outcomes and Biomedical Informatics College of Medicine, University of Florida, Gainesville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Health Outcomes and Biomedical Informatics College of Medicine, University of Florida Gainesville, USA","institution_ids":["https://openalex.org/I2800717037","https://openalex.org/I94062374"]},{"raw_affiliation_string":"Health Outcomes and Biomedical Informatics College of Medicine, University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I2800717037"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.3608,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.97916667,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"2020","issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9940999746322632,"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":0.9940999746322632,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9670000076293945,"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/T10028","display_name":"Topic Modeling","score":0.9646999835968018,"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/natural-language-processing","display_name":"Natural language processing","score":0.694892406463623},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.6453290581703186},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6412433385848999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6246187090873718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5588393807411194},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.5475850105285645},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4874301254749298},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.44616052508354187},{"id":"https://openalex.org/keywords/lung-cancer-screening","display_name":"Lung cancer screening","score":0.4148064851760864},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.40920767188072205},{"id":"https://openalex.org/keywords/lung-cancer","display_name":"Lung cancer","score":0.37189751863479614},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3375563621520996},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15584000945091248},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.12828731536865234}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.694892406463623},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.6453290581703186},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6412433385848999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6246187090873718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5588393807411194},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.5475850105285645},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4874301254749298},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.44616052508354187},{"id":"https://openalex.org/C2777405583","wikidata":"https://www.wikidata.org/wiki/Q6704277","display_name":"Lung cancer screening","level":3,"score":0.4148064851760864},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.40920767188072205},{"id":"https://openalex.org/C2776256026","wikidata":"https://www.wikidata.org/wiki/Q47912","display_name":"Lung cancer","level":2,"score":0.37189751863479614},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3375563621520996},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15584000945091248},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.12828731536865234},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ichi48887.2020.9374369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichi48887.2020.9374369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Healthcare Informatics (ICHI)","raw_type":"proceedings-article"},{"id":"pmid:33786419","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33786419","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8006894","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8006894","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc (IEEE Int Conf Healthc Inform)","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:8006894","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8006894","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc (IEEE Int Conf Healthc Inform)","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/3"}],"awards":[{"id":"https://openalex.org/G579819645","display_name":null,"funder_award_id":"R01-CA246418","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"}],"funders":[{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W191029809","https://openalex.org/W2053154970","https://openalex.org/W2146089916","https://openalex.org/W2769851464","https://openalex.org/W6607779907"],"related_works":["https://openalex.org/W2890029653","https://openalex.org/W2123376283","https://openalex.org/W2950278309","https://openalex.org/W2060192418","https://openalex.org/W2014385108","https://openalex.org/W2066874075","https://openalex.org/W2792951589","https://openalex.org/W3208882810","https://openalex.org/W3168794733","https://openalex.org/W1772447446"],"abstract_inverted_index":{"This":[0],"study":[1],"presents":[2],"a":[3,35,59,69,73],"natural":[4],"language":[5],"processing":[6],"(NLP)":[7],"tool":[8],"to":[9],"extract":[10],"quantitative":[11],"smoking":[12],"information":[13],"(e.g.,":[14],"Pack-Year,":[15],"Quit":[16],"Year,":[17,19],"Smoking":[18],"and":[20,27,53,72,76,105,109],"Pack":[21],"per":[22],"Day)":[23],"from":[24,41],"clinical":[25,39],"notes":[26,40,67],"standardized":[28],"them":[29],"into":[30,68],"Pack-Year":[31],"unit.":[32],"We":[33,63],"annotated":[34],"corpus":[36],"of":[37,103],"200":[38,66],"patients":[42],"who":[43],"had":[44],"low-dose":[45],"CT":[46],"imaging":[47],"procedures":[48],"for":[49,107],"lung":[50],"cancer":[51],"screening":[52],"developed":[54,77],"an":[55],"NLP":[56,79,96],"system":[57,80,97],"using":[58,82],"two-layer":[60],"rule-engine":[61],"structure.":[62],"divided":[64],"the":[65,78,83,90,99],"training":[70,84],"set":[71,75,92],"test":[74,91],"only":[81],"set.":[85],"The":[86],"experimental":[87],"results":[88],"on":[89],"showed":[93],"that":[94],"our":[95],"achieved":[98],"best":[100],"F1":[101],"scores":[102],"0.963":[104],"0.946":[106],"lenient":[108],"strict":[110],"evaluation,":[111],"respectively.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
