{"id":"https://openalex.org/W4225490240","doi":"https://doi.org/10.1016/j.patter.2022.100451","title":"Hierarchical confounder discovery in the experiment-machine learning cycle","display_name":"Hierarchical confounder discovery in the experiment-machine learning cycle","publication_year":2022,"publication_date":"2022-02-22","ids":{"openalex":"https://openalex.org/W4225490240","doi":"https://doi.org/10.1016/j.patter.2022.100451","pmid":"https://pubmed.ncbi.nlm.nih.gov/35465234"},"language":"en","primary_location":{"id":"doi:10.1016/j.patter.2022.100451","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patter.2022.100451","pdf_url":"http://www.cell.com/article/S2666389922000241/pdf","source":{"id":"https://openalex.org/S4210198061","display_name":"Patterns","issn_l":"2666-3899","issn":["2666-3899"],"is_oa":true,"is_in_doaj":true,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Patterns","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://www.cell.com/article/S2666389922000241/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080513268","display_name":"Alex Rogozhnikov","orcid":"https://orcid.org/0000-0002-7413-9553"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Rogozhnikov","raw_affiliation_strings":["Herophilus, Inc., San Francisco, CA 94107, USA"],"affiliations":[{"raw_affiliation_string":"Herophilus, Inc., San Francisco, CA 94107, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078365445","display_name":"Pavan Ramkumar","orcid":"https://orcid.org/0000-0001-7450-0727"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pavan Ramkumar","raw_affiliation_strings":["Herophilus, Inc., San Francisco, CA 94107, USA"],"affiliations":[{"raw_affiliation_string":"Herophilus, Inc., San Francisco, CA 94107, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065642586","display_name":"Rishi Bedi","orcid":"https://orcid.org/0000-0002-4348-395X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rishi Bedi","raw_affiliation_strings":["Herophilus, Inc., San Francisco, CA 94107, USA"],"affiliations":[{"raw_affiliation_string":"Herophilus, Inc., San Francisco, CA 94107, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016124697","display_name":"Saul Kato","orcid":"https://orcid.org/0000-0003-2990-8306"},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Saul Kato","raw_affiliation_strings":["Herophilus, Inc., San Francisco, CA 94107, USA","Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA 94143, USA"],"affiliations":[{"raw_affiliation_string":"Herophilus, Inc., San Francisco, CA 94107, USA","institution_ids":[]},{"raw_affiliation_string":"Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA 94143, USA","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020984279","display_name":"G. Sean Escola","orcid":"https://orcid.org/0000-0003-0645-1964"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"G. Sean Escola","raw_affiliation_strings":["Herophilus, Inc., San Francisco, CA 94107, USA","Zuckerman Institute, Department of Psychiatry, Columbia University, New York City, NY 10032, USA"],"affiliations":[{"raw_affiliation_string":"Herophilus, Inc., San Francisco, CA 94107, USA","institution_ids":[]},{"raw_affiliation_string":"Zuckerman Institute, Department of Psychiatry, Columbia University, New York City, NY 10032, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016124697","https://openalex.org/A5020984279"],"corresponding_institution_ids":["https://openalex.org/I180670191","https://openalex.org/I78577930"],"apc_list":{"value":5200,"currency":"USD","value_usd":5200},"apc_paid":{"value":5200,"currency":"USD","value_usd":5200},"fwci":0.5281,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.77897078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":"4","first_page":"100451","last_page":"100451"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.991599977016449,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9884999990463257,"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/confounding","display_name":"Confounding","score":0.8625110983848572},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6776442527770996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6181327700614929},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47835296392440796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.465924471616745},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.44650861620903015},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.35963600873947144},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1756623089313507},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1499449610710144}],"concepts":[{"id":"https://openalex.org/C77350462","wikidata":"https://www.wikidata.org/wiki/Q1125472","display_name":"Confounding","level":2,"score":0.8625110983848572},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6776442527770996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6181327700614929},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47835296392440796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.465924471616745},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.44650861620903015},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.35963600873947144},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1756623089313507},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1499449610710144},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.patter.2022.100451","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patter.2022.100451","pdf_url":"http://www.cell.com/article/S2666389922000241/pdf","source":{"id":"https://openalex.org/S4210198061","display_name":"Patterns","issn_l":"2666-3899","issn":["2666-3899"],"is_oa":true,"is_in_doaj":true,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Patterns","raw_type":"journal-article"},{"id":"pmid:35465234","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35465234","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":"Patterns (New York, N.Y.)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9024009","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9024009","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Patterns (N Y)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1016/j.patter.2022.100451","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patter.2022.100451","pdf_url":"http://www.cell.com/article/S2666389922000241/pdf","source":{"id":"https://openalex.org/S4210198061","display_name":"Patterns","issn_l":"2666-3899","issn":["2666-3899"],"is_oa":true,"is_in_doaj":true,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Patterns","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225490240.pdf","grobid_xml":"https://content.openalex.org/works/W4225490240.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1972978214","https://openalex.org/W2005335622","https://openalex.org/W2099720176","https://openalex.org/W2557738935","https://openalex.org/W2566843361","https://openalex.org/W2617652967","https://openalex.org/W2772246530","https://openalex.org/W2788633781","https://openalex.org/W2803094965","https://openalex.org/W2811374795","https://openalex.org/W2883480695","https://openalex.org/W2889326414","https://openalex.org/W2964231736","https://openalex.org/W2968103140","https://openalex.org/W2968231730","https://openalex.org/W2999737340","https://openalex.org/W3046863270","https://openalex.org/W3080122543","https://openalex.org/W3098677849","https://openalex.org/W3099661382","https://openalex.org/W3104508774","https://openalex.org/W3109762849","https://openalex.org/W4235762696","https://openalex.org/W6748182698","https://openalex.org/W6752428614","https://openalex.org/W6781615156"],"related_works":["https://openalex.org/W2994176440","https://openalex.org/W2510575233","https://openalex.org/W2481749367","https://openalex.org/W830718730","https://openalex.org/W2495367848","https://openalex.org/W2793477322","https://openalex.org/W4236720793","https://openalex.org/W1992228662","https://openalex.org/W4246786946","https://openalex.org/W2503931704"],"abstract_inverted_index":{"The":[0],"promise":[1],"of":[2,39,58,98,115],"machine":[3],"learning":[4],"(ML)":[5],"to":[6,20,34,37,123,143],"extract":[7],"insights":[8],"from":[9],"high-dimensional":[10],"datasets":[11,47],"is":[12],"tempered":[13],"by":[14],"confounding":[15,59],"variables.":[16],"It":[17],"behooves":[18],"scientists":[19],"determine":[21],"if":[22],"a":[23,69,106,129],"model":[24],"has":[25],"extracted":[26],"the":[27,56,74,96],"desired":[28],"information":[29],"or":[30],"instead":[31],"fallen":[32],"prey":[33],"bias.":[35],"Due":[36],"features":[38],"natural":[40],"phenomena":[41],"and":[42,61,86,142],"experimental":[43,116],"design":[44],"constraints,":[45],"bioscience":[46],"are":[48],"often":[49],"organized":[50],"in":[51,83,128,139,147],"nested":[52],"hierarchies":[53],"that":[54,78,91],"obfuscate":[55],"origins":[57],"effects":[60,82,97,114],"render":[62],"confounder":[63,81,145],"amelioration":[64],"methods":[65,103],"ineffective.":[66],"We":[67,89,118],"propose":[68],"non-parametric":[70],"statistical":[71],"method":[72],"called":[73],"rank-to-group":[75],"(RTG)":[76],"score":[77],"identifies":[79],"hierarchical":[80,99],"raw":[84],"data":[85],"ML-derived":[87],"embeddings.":[88],"show":[90],"RTG":[92,121],"scores":[93,122],"correctly":[94],"assign":[95],"confounders":[100],"when":[101],"linear":[102],"fail.":[104],"In":[105],"public":[107],"biomedical":[108],"image":[109],"dataset,":[110],"we":[111],"discover":[112,124],"unreported":[113],"design.":[117],"then":[119],"use":[120],"crossmodal":[125],"correlated":[126],"variability":[127],"multi-phenotypic":[130],"biological":[131],"dataset.":[132],"This":[133],"approach":[134],"should":[135],"be":[136],"generally":[137],"useful":[138],"experiment-analysis":[140],"cycles":[141],"ensure":[144],"robustness":[146],"ML":[148],"models.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}