{"id":"https://openalex.org/W2104092906","doi":"https://doi.org/10.1093/bioinformatics/btp605","title":"Reporting bias when using real data sets to analyze classification performance","display_name":"Reporting bias when using real data sets to analyze classification performance","publication_year":2009,"publication_date":"2009-10-21","ids":{"openalex":"https://openalex.org/W2104092906","doi":"https://doi.org/10.1093/bioinformatics/btp605","mag":"2104092906","pmid":"https://pubmed.ncbi.nlm.nih.gov/19846436"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btp605","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btp605","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/26/1/68/48851537/bioinformatics_26_1_68.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/26/1/68/48851537/bioinformatics_26_1_68.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111733816","display_name":"Mohammadmahdi R. Yousefi","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]},{"id":"https://openalex.org/I1284308235","display_name":"Translational Genomics Research Institute","ror":"https://ror.org/02hfpnk21","country_code":"US","type":"facility","lineage":["https://openalex.org/I1284308235"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohammadmahdi R. Yousefi","raw_affiliation_strings":["1 Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843 and 2 Computational Biology Division, Translational Genomics Research Institute, Phoenix, AZ 85004, USA"],"affiliations":[{"raw_affiliation_string":"1 Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843 and 2 Computational Biology Division, Translational Genomics Research Institute, Phoenix, AZ 85004, USA","institution_ids":["https://openalex.org/I1284308235","https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100559028","display_name":"Jianping Hua","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]},{"id":"https://openalex.org/I1284308235","display_name":"Translational Genomics Research Institute","ror":"https://ror.org/02hfpnk21","country_code":"US","type":"facility","lineage":["https://openalex.org/I1284308235"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianping Hua","raw_affiliation_strings":["1 Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843 and 2 Computational Biology Division, Translational Genomics Research Institute, Phoenix, AZ 85004, USA"],"affiliations":[{"raw_affiliation_string":"1 Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843 and 2 Computational Biology Division, Translational Genomics Research Institute, Phoenix, AZ 85004, USA","institution_ids":["https://openalex.org/I1284308235","https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028402481","display_name":"Chao Sima","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]},{"id":"https://openalex.org/I1284308235","display_name":"Translational Genomics Research Institute","ror":"https://ror.org/02hfpnk21","country_code":"US","type":"facility","lineage":["https://openalex.org/I1284308235"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Sima","raw_affiliation_strings":["1 Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843 and 2 Computational Biology Division, Translational Genomics Research Institute, Phoenix, AZ 85004, USA"],"affiliations":[{"raw_affiliation_string":"1 Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843 and 2 Computational Biology Division, Translational Genomics Research Institute, Phoenix, AZ 85004, USA","institution_ids":["https://openalex.org/I1284308235","https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112221423","display_name":"Edward R. Dougherty","orcid":null},"institutions":[{"id":"https://openalex.org/I1284308235","display_name":"Translational Genomics Research Institute","ror":"https://ror.org/02hfpnk21","country_code":"US","type":"facility","lineage":["https://openalex.org/I1284308235"]},{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward R. Dougherty","raw_affiliation_strings":["1 Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843 and 2 Computational Biology Division, Translational Genomics Research Institute, Phoenix, AZ 85004, USA"],"affiliations":[{"raw_affiliation_string":"1 Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843 and 2 Computational Biology Division, Translational Genomics Research Institute, Phoenix, AZ 85004, USA","institution_ids":["https://openalex.org/I1284308235","https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5111733816"],"corresponding_institution_ids":["https://openalex.org/I1284308235","https://openalex.org/I91045830"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.8772,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.85294678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"26","issue":"1","first_page":"68","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9995999932289124,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9995999932289124,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9916999936103821,"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":0.6872822642326355},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6648340225219727},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5862767696380615},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5640503764152527},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5311456918716431},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5205903053283691},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5171598792076111},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4713439643383026},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4617038369178772},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.45597705245018005},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4090900719165802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32211270928382874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6872822642326355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6648340225219727},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5862767696380615},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5640503764152527},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5311456918716431},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5205903053283691},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5171598792076111},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4713439643383026},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4617038369178772},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.45597705245018005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4090900719165802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32211270928382874},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btp605","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btp605","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/26/1/68/48851537/bioinformatics_26_1_68.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:19846436","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19846436","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":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btp605","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btp605","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/26/1/68/48851537/bioinformatics_26_1_68.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6200000047683716,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2104092906.pdf","grobid_xml":"https://content.openalex.org/works/W2104092906.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W270103414","https://openalex.org/W1972909920","https://openalex.org/W1976564639","https://openalex.org/W2067526101","https://openalex.org/W2077922582","https://openalex.org/W2097413644","https://openalex.org/W2100468749","https://openalex.org/W2101095322","https://openalex.org/W2110298216","https://openalex.org/W2110502951","https://openalex.org/W2111539174","https://openalex.org/W2120503632","https://openalex.org/W2121277505","https://openalex.org/W2138218344","https://openalex.org/W2150671673","https://openalex.org/W2155165473","https://openalex.org/W2157531738","https://openalex.org/W2160450758","https://openalex.org/W2163563958","https://openalex.org/W2163883927","https://openalex.org/W4245479598","https://openalex.org/W6683157813"],"related_works":["https://openalex.org/W2250488071","https://openalex.org/W2356150353","https://openalex.org/W2380744779","https://openalex.org/W1999647744","https://openalex.org/W2018643641","https://openalex.org/W2469878540","https://openalex.org/W2765337000","https://openalex.org/W2967867994","https://openalex.org/W2112264450","https://openalex.org/W3023858869"],"abstract_inverted_index":{"Companion":[0],"web":[1],"site":[2],"at":[3],"http://gsp.tamu.edu/Publications/supplementary/yousefi09a/":[4]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
