{"id":"https://openalex.org/W4399368797","doi":"https://doi.org/10.1093/bioinformatics/btae341","title":"Improving the performance and interpretability on medical datasets using graphical ensemble feature selection","display_name":"Improving the performance and interpretability on medical datasets using graphical ensemble feature selection","publication_year":2024,"publication_date":"2024-05-24","ids":{"openalex":"https://openalex.org/W4399368797","doi":"https://doi.org/10.1093/bioinformatics/btae341"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btae341","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae341","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae341/58108007/btae341.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae341/58108007/btae341.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070081715","display_name":"Enzo Battistella","orcid":"https://orcid.org/0000-0001-7053-5666"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Enzo Battistella","raw_affiliation_strings":["Network Science Institute, Northeastern University , Boston, MA 02115, United States"],"affiliations":[{"raw_affiliation_string":"Network Science Institute, Northeastern University , Boston, MA 02115, United States","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104670364","display_name":"Dina Ghiassian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dina Ghiassian","raw_affiliation_strings":["Scipher Medicine , Waltham, MA 02453, United States"],"affiliations":[{"raw_affiliation_string":"Scipher Medicine , Waltham, MA 02453, United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038976962","display_name":"Albert-\u0139aszl\u00f3 Barab\u00e1si","orcid":"https://orcid.org/0000-0002-4028-3522"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"id":"https://openalex.org/I1283280774","display_name":"Brigham and Women's Hospital","ror":"https://ror.org/04b6nzv94","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283280774","https://openalex.org/I48633490"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Albert-L\u00e1szl\u00f3 Barab\u00e1si","raw_affiliation_strings":["Department of Data and Network Science, Central Eastern University , Budapest 1051, Hungary","Department of Medicine, Brigham and Women\u2019s Hospital, Harvard Medical School , Boston, MA 02115, United States","Network Science Institute, Northeastern University , Boston, MA 02115, United States"],"affiliations":[{"raw_affiliation_string":"Department of Data and Network Science, Central Eastern University , Budapest 1051, Hungary","institution_ids":[]},{"raw_affiliation_string":"Department of Medicine, Brigham and Women\u2019s Hospital, Harvard Medical School , Boston, MA 02115, United States","institution_ids":["https://openalex.org/I1283280774","https://openalex.org/I136199984"]},{"raw_affiliation_string":"Network Science Institute, Northeastern University , Boston, MA 02115, United States","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070081715"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.4307,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80848519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"40","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.998199999332428,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.998199999332428,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9944999814033508,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8200585842132568},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7723023295402527},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7498165965080261},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7131085991859436},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7097247838973999},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.6124411821365356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5986440181732178},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5258921980857849},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.5075634717941284},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4453830122947693},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43163496255874634},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4205482602119446},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.41139835119247437},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.11081317067146301},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.11058929562568665}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8200585842132568},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7723023295402527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7498165965080261},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7131085991859436},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7097247838973999},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.6124411821365356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5986440181732178},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5258921980857849},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.5075634717941284},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4453830122947693},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43163496255874634},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4205482602119446},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.41139835119247437},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.11081317067146301},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.11058929562568665},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btae341","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae341","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae341/58108007/btae341.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11187494","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11187494","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11187494/pdf/btae341.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:https://openresearch.ceu.edu:20.500.14018/27978","is_oa":true,"landing_page_url":"https://www.scopus.com/pages/publications/85196688503","pdf_url":null,"source":{"id":"https://openalex.org/S4306401981","display_name":"Open Research (Auckland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39854758","host_organization_name":"Auckland University of Technology","host_organization_lineage":["https://openalex.org/I39854758"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"6","raw_type":"Journal article"},{"id":"pmh:oai:openresearch.ceu.edu:20.500.14018/27978","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.14018/27978","pdf_url":null,"source":{"id":"https://openalex.org/S4306401981","display_name":"Open Research (Auckland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39854758","host_organization_name":"Auckland University of Technology","host_organization_lineage":["https://openalex.org/I39854758"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"6","raw_type":"Journal article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btae341","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae341","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae341/58108007/btae341.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399368797.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1526787720","https://openalex.org/W1600604896","https://openalex.org/W1992018127","https://openalex.org/W2062533676","https://openalex.org/W2116341502","https://openalex.org/W2116868464","https://openalex.org/W2131885284","https://openalex.org/W2131888517","https://openalex.org/W2134029774","https://openalex.org/W2162162988","https://openalex.org/W2167101736","https://openalex.org/W2213612645","https://openalex.org/W2260771218","https://openalex.org/W2329659234","https://openalex.org/W2470861207","https://openalex.org/W2772211527","https://openalex.org/W2796207838","https://openalex.org/W2796408191","https://openalex.org/W2942807971","https://openalex.org/W2948009788","https://openalex.org/W2949158494","https://openalex.org/W2955219525","https://openalex.org/W2980962597","https://openalex.org/W2998216295","https://openalex.org/W2999580660","https://openalex.org/W3004127313","https://openalex.org/W3041913137","https://openalex.org/W3046918297","https://openalex.org/W3093455605","https://openalex.org/W3093854333","https://openalex.org/W3094165960","https://openalex.org/W3203526420","https://openalex.org/W3210087576","https://openalex.org/W3211044167","https://openalex.org/W4286587612","https://openalex.org/W4306405846","https://openalex.org/W4366276659","https://openalex.org/W4388041411","https://openalex.org/W6635873800","https://openalex.org/W6692628530","https://openalex.org/W6701881206","https://openalex.org/W6762227895","https://openalex.org/W6772654164","https://openalex.org/W6846876409","https://openalex.org/W6862688848","https://openalex.org/W7066667914"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W2905433371","https://openalex.org/W3009056573","https://openalex.org/W4297676672","https://openalex.org/W2922073769","https://openalex.org/W4295122168","https://openalex.org/W3155717344","https://openalex.org/W1770458422","https://openalex.org/W1038900426"],"abstract_inverted_index":{"Abstract":[0],"Motivation":[1],"A":[2],"major":[3],"hindrance":[4],"towards":[5],"using":[6],"Machine":[7],"Learning":[8],"(ML)":[9],"on":[10,90,106,122,128],"medical":[11,169],"datasets":[12],"is":[13],"the":[14,36,43,59,80,85,113,134,141,146,156,168],"discrepancy":[15],"between":[16,159],"a":[17,71],"large":[18],"number":[19],"of":[20,84,171],"variables":[21],"and":[22,82,145,174],"small":[23],"sample":[24],"sizes.":[25],"While":[26],"multiple":[27],"feature":[28,74],"selection":[29,45,75],"techniques":[30,41],"have":[31],"been":[32],"proposed":[33],"to":[34,51,57,78,131,140],"avoid":[35],"resulting":[37],"overfitting,":[38],"overall":[39],"ensemble":[40,73],"offer":[42],"best":[44],"robustness.":[46],"Yet,":[47],"current":[48],"methods":[49,115],"designed":[50,77],"combine":[52],"different":[53],"algorithms":[54],"generally":[55],"fail":[56],"leverage":[58],"dependencies":[60],"identified":[61],"by":[62,116],"their":[63],"components.":[64],"Here,":[65],"we":[66,93,162],"propose":[67],"Graphical":[68],"Ensembling":[69],"(GE),":[70],"graph-theory-based":[72],"technique":[76],"improve":[79,167],"stability":[81],"relevance":[83],"selected":[86,102,135],"features.":[87,103,124],"Results":[88],"Relying":[89],"four":[91],"datasets,":[92],"show":[94,132],"that":[95,133,164],"GE":[96,111,165],"increases":[97],"classification":[98],"performance":[99],"with":[100],"fewer":[101,123],"For":[104],"example,":[105],"rheumatoid":[107],"arthritis":[108],"patient":[109],"stratification,":[110],"outperforms":[112],"baseline":[114],"9%":[117],"Balanced":[118],"Accuracy":[119],"while":[120],"relying":[121],"We":[125],"use":[126],"data":[127],"sub-cellular":[129],"networks":[130],"features":[136],"(proteins)":[137],"are":[138,150],"closer":[139],"known":[142],"disease":[143],"genes,":[144],"uncovered":[147],"biological":[148,160],"mechanisms":[149],"more":[151],"diversified.":[152],"By":[153],"successfully":[154],"tackling":[155],"complex":[157],"correlations":[158],"variables,":[161],"anticipate":[163],"will":[166],"applications":[170],"ML.":[172],"Availability":[173],"implementation":[175],"https://github.com/ebattistella/auto_machine_learning.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}