{"id":"https://openalex.org/W1995616412","doi":"https://doi.org/10.1016/s1386-5056(02)00057-6","title":"Evaluating and reducing the effect of data corruption when applying bag of words approaches to medical records","display_name":"Evaluating and reducing the effect of data corruption when applying bag of words approaches to medical records","publication_year":2002,"publication_date":"2002-12-01","ids":{"openalex":"https://openalex.org/W1995616412","doi":"https://doi.org/10.1016/s1386-5056(02)00057-6","mag":"1995616412","pmid":"https://pubmed.ncbi.nlm.nih.gov/12460633"},"language":"en","primary_location":{"id":"doi:10.1016/s1386-5056(02)00057-6","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s1386-5056(02)00057-6","pdf_url":null,"source":{"id":"https://openalex.org/S53142634","display_name":"International Journal of Medical Informatics","issn_l":"1386-5056","issn":["1386-5056","1872-8243"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Medical Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5042384742","display_name":"Patrick Ruch","orcid":"https://orcid.org/0000-0002-3374-2962"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I4210106256","display_name":"University Hospital of Geneva","ror":"https://ror.org/01m1pv723","country_code":"CH","type":"healthcare","lineage":["https://openalex.org/I4210106256"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"P Ruch","raw_affiliation_strings":["Theoretical Computer Science Laboratory, Swiss Federal Institute of Technology, Lausanne, Switzerland. patrick.ruch@epfl.ch","Medical Informatics Division, University Hospital of Geneva, Geneva, Switzerland","Theoretical Computer Science Laboratory, Swiss Federal Institute of Technology, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Theoretical Computer Science Laboratory, Swiss Federal Institute of Technology, Lausanne, Switzerland. patrick.ruch@epfl.ch","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Medical Informatics Division, University Hospital of Geneva, Geneva, Switzerland","institution_ids":["https://openalex.org/I4210106256"]},{"raw_affiliation_string":"Theoretical Computer Science Laboratory, Swiss Federal Institute of Technology, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074689150","display_name":"Robert Baud","orcid":"https://orcid.org/0009-0002-1709-0439"},"institutions":[{"id":"https://openalex.org/I4210106256","display_name":"University Hospital of Geneva","ror":"https://ror.org/01m1pv723","country_code":"CH","type":"healthcare","lineage":["https://openalex.org/I4210106256"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"R Baud","raw_affiliation_strings":["Medical Informatics Division, University Hospital of Geneva, Geneva, Switzerland"],"affiliations":[{"raw_affiliation_string":"Medical Informatics Division, University Hospital of Geneva, Geneva, Switzerland","institution_ids":["https://openalex.org/I4210106256"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002030006","display_name":"Antoine Geissb\u00fchler","orcid":"https://orcid.org/0000-0001-5039-3373"},"institutions":[{"id":"https://openalex.org/I4210106256","display_name":"University Hospital of Geneva","ror":"https://ror.org/01m1pv723","country_code":"CH","type":"healthcare","lineage":["https://openalex.org/I4210106256"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"A Geissb\u00fchler","raw_affiliation_strings":["Medical Informatics Division, University Hospital of Geneva, Geneva, Switzerland"],"affiliations":[{"raw_affiliation_string":"Medical Informatics Division, University Hospital of Geneva, Geneva, Switzerland","institution_ids":["https://openalex.org/I4210106256"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042384742"],"corresponding_institution_ids":["https://openalex.org/I4210106256","https://openalex.org/I5124864"],"apc_list":{"value":3210,"currency":"USD","value_usd":3210},"apc_paid":null,"fwci":3.4273,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.92713294,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"67","issue":"1-3","first_page":"75","last_page":"83"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9983999729156494,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.995199978351593,"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/computer-science","display_name":"Computer science","score":0.7265845537185669},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.6672825813293457},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6465523838996887},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6399644017219543},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6279668211936951},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5281028151512146},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.4459303021430969},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.23373162746429443},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08172494173049927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7265845537185669},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.6672825813293457},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6465523838996887},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6399644017219543},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6279668211936951},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5281028151512146},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.4459303021430969},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.23373162746429443},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08172494173049927},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D005544","descriptor_name":"Forecasting","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005544","descriptor_name":"Forecasting","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005544","descriptor_name":"Forecasting","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008037","descriptor_name":"Linguistics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008037","descriptor_name":"Linguistics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008037","descriptor_name":"Linguistics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016347","descriptor_name":"Medical Records Systems, Computerized","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016347","descriptor_name":"Medical Records Systems, Computerized","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016347","descriptor_name":"Medical Records Systems, Computerized","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1016/s1386-5056(02)00057-6","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s1386-5056(02)00057-6","pdf_url":null,"source":{"id":"https://openalex.org/S53142634","display_name":"International Journal of Medical Informatics","issn_l":"1386-5056","issn":["1386-5056","1872-8243"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Medical Informatics","raw_type":"journal-article"},{"id":"pmid:12460633","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12460633","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":"International journal of medical informatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W19235523","https://openalex.org/W26772505","https://openalex.org/W101490221","https://openalex.org/W116908793","https://openalex.org/W182831726","https://openalex.org/W1482504747","https://openalex.org/W1557757161","https://openalex.org/W1574862351","https://openalex.org/W1576520375","https://openalex.org/W1587754947","https://openalex.org/W1687182314","https://openalex.org/W1765388594","https://openalex.org/W1956559956","https://openalex.org/W1978394996","https://openalex.org/W2005422315","https://openalex.org/W2006997130","https://openalex.org/W2010595692","https://openalex.org/W2036370897","https://openalex.org/W2043909051","https://openalex.org/W2082359793","https://openalex.org/W2085763602","https://openalex.org/W2103090613","https://openalex.org/W2111192396","https://openalex.org/W2115159360","https://openalex.org/W2158505321","https://openalex.org/W2161377381","https://openalex.org/W2162462731","https://openalex.org/W2325227998","https://openalex.org/W2484978994","https://openalex.org/W3041351009","https://openalex.org/W4231862806","https://openalex.org/W6637377479","https://openalex.org/W6675519746","https://openalex.org/W6677875524","https://openalex.org/W6812747060"],"related_works":["https://openalex.org/W2161008081","https://openalex.org/W2100947578","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W1479704461","https://openalex.org/W4281569536","https://openalex.org/W2171473894","https://openalex.org/W2741230576","https://openalex.org/W2372355498","https://openalex.org/W1441686524"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
