{"id":"https://openalex.org/W3001161237","doi":"https://doi.org/10.1101/2020.01.22.915397","title":"Medical data and machine learning improve power of stroke genome-wide association studies","display_name":"Medical data and machine learning improve power of stroke genome-wide association studies","publication_year":2020,"publication_date":"2020-01-23","ids":{"openalex":"https://openalex.org/W3001161237","doi":"https://doi.org/10.1101/2020.01.22.915397","mag":"3001161237"},"language":"en","primary_location":{"id":"doi:10.1101/2020.01.22.915397","doi":"https://doi.org/10.1101/2020.01.22.915397","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2020.01.22.915397","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2020/11/09/2020.01.22.915397.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2020/11/09/2020.01.22.915397.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062357855","display_name":"Phyllis Thangaraj","orcid":"https://orcid.org/0000-0003-3968-1563","observed_orcids":["https://orcid.org/0000-0003-3968-1563"]},"institutions":[{"id":"https://openalex.org/I2799503643","display_name":"Columbia University Irving Medical Center","ror":"https://ror.org/01esghr10","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799503643"]},{"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":false,"raw_author_name":"Phyllis M. Thangaraj","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University Irving Medical Center","Department of Systems Biology, Columbia University Irving Medical Center","Integrated Program in Cellular, Molecular, and Biomedical Studies, Columbia University Irving Medical Center","Department of Biomedial Informatis, Columbia University Irving Medial Center, New York, NY","Department of Systems Biology, Columia University Irving Medical Center, New York, NY","Integrted Progrm in Cellulr, Moleculr, nd Biomedicl Studies, Columbi University Irving Medicl Center, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University Irving Medical Center","institution_ids":["https://openalex.org/I2799503643"]},{"raw_affiliation_string":"Department of Systems Biology, Columbia University Irving Medical Center","institution_ids":["https://openalex.org/I2799503643"]},{"raw_affiliation_string":"Integrated Program in Cellular, Molecular, and Biomedical Studies, Columbia University Irving Medical Center","institution_ids":["https://openalex.org/I2799503643"]},{"raw_affiliation_string":"Department of Biomedial Informatis, Columbia University Irving Medial Center, New York, NY","institution_ids":["https://openalex.org/I2799503643","https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Systems Biology, Columia University Irving Medical Center, New York, NY","institution_ids":["https://openalex.org/I2799503643"]},{"raw_affiliation_string":"Integrted Progrm in Cellulr, Moleculr, nd Biomedicl Studies, Columbi University Irving Medicl Center, New York, NY","institution_ids":["https://openalex.org/I2799503643","https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061872875","display_name":"Undina Gisladottir","orcid":"https://orcid.org/0000-0001-5892-0852","observed_orcids":["https://orcid.org/0000-0001-5892-0852"]},"institutions":[{"id":"https://openalex.org/I2799503643","display_name":"Columbia University Irving Medical Center","ror":"https://ror.org/01esghr10","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799503643"]},{"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":false,"raw_author_name":"Undina Gisladottir","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University Irving Medical Center","Department of Biomedial Informatis, Columbia University Irving Medial Center, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University Irving Medical Center","institution_ids":["https://openalex.org/I2799503643"]},{"raw_affiliation_string":"Department of Biomedial Informatis, Columbia University Irving Medial Center, New York, NY","institution_ids":["https://openalex.org/I2799503643","https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086753691","display_name":"Nicholas P. Tatonetti","orcid":"https://orcid.org/0000-0002-2700-2597","observed_orcids":["https://orcid.org/0000-0002-2700-2597"]},"institutions":[{"id":"https://openalex.org/I2799503643","display_name":"Columbia University Irving Medical Center","ror":"https://ror.org/01esghr10","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799503643"]},{"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":"Nicholas P. Tatonetti","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University Irving Medical Center","Department of Medicine, Columbia University Irving Medical Center","Department of Systems Biology, Columbia University Irving Medical Center","Department of Biomedial Informatis, Columbia University Irving Medial Center, New York, NY","Department of Meicine, Columbia University Irving Meical Center, New York, NY","Department of Systems Biology, Columia University Irving Medical Center, New York, NY"],"raw_orcid":"https://orcid.org/0000-0002-2700-2597","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University Irving Medical Center","institution_ids":["https://openalex.org/I2799503643"]},{"raw_affiliation_string":"Department of Medicine, Columbia University Irving Medical Center","institution_ids":["https://openalex.org/I2799503643"]},{"raw_affiliation_string":"Department of Systems Biology, Columbia University Irving Medical Center","institution_ids":["https://openalex.org/I2799503643"]},{"raw_affiliation_string":"Department of Biomedial Informatis, Columbia University Irving Medial Center, New York, NY","institution_ids":["https://openalex.org/I2799503643","https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Meicine, Columbia University Irving Meical Center, New York, NY","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Systems Biology, Columia University Irving Medical Center, New York, NY","institution_ids":["https://openalex.org/I2799503643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086753691"],"corresponding_institution_ids":["https://openalex.org/I2799503643","https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T13648","display_name":"Cerebrovascular and genetic disorders","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11468","display_name":"Genetic Mapping and Diversity in Plants and Animals","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/stroke","display_name":"stroke","score":0.8629999756813049},{"id":"https://openalex.org/keywords/genome-wide-association-study","display_name":"genome-wide association study","score":0.8700000047683716},{"id":"https://openalex.org/keywords/electronic-health-records","display_name":"electronic health records","score":0.6990000009536743},{"id":"https://openalex.org/keywords/phenotyping","display_name":"phenotyping","score":0.6079999804496765},{"id":"https://openalex.org/keywords/disease-probability","display_name":"disease probability","score":0.5210000276565552},{"id":"https://openalex.org/keywords/abcg8","display_name":"ABCG8","score":0.8360000252723694},{"id":"https://openalex.org/keywords/intracerebral-hemorrhage","display_name":"intracerebral hemorrhage","score":1.0},{"id":"https://openalex.org/keywords/study-power","display_name":"study power","score":0.4740000069141388},{"id":"https://openalex.org/keywords/uk-biobank","display_name":"UK Biobank","score":0.6320000290870667}],"concepts":[{"id":"https://openalex.org/C116567970","wikidata":"https://www.wikidata.org/wiki/Q864217","display_name":"Biobank","level":2,"score":0.9179046154022217},{"id":"https://openalex.org/C106208931","wikidata":"https://www.wikidata.org/wiki/Q1098876","display_name":"Genome-wide association study","level":5,"score":0.7918716669082642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5291638374328613},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.4980032444000244},{"id":"https://openalex.org/C106934330","wikidata":"https://www.wikidata.org/wiki/Q1971873","display_name":"Trait","level":2,"score":0.43281567096710205},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.4263894855976105},{"id":"https://openalex.org/C186413461","wikidata":"https://www.wikidata.org/wiki/Q744727","display_name":"Genetic association","level":5,"score":0.4219704866409302},{"id":"https://openalex.org/C2780645631","wikidata":"https://www.wikidata.org/wiki/Q671554","display_name":"Stroke (engine)","level":2,"score":0.4142112135887146},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.37756308913230896},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35799330472946167},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2478058934211731},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23433324694633484},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.13493412733078003},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.13377317786216736},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13204440474510193},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.11365196108818054},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10535275936126709},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.10116761922836304},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1101/2020.01.22.915397","doi":"https://doi.org/10.1101/2020.01.22.915397","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2020.01.22.915397","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2020/11/09/2020.01.22.915397.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1101/2020.01.22.915397","doi":"https://doi.org/10.1101/2020.01.22.915397","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2020.01.22.915397","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2020/11/09/2020.01.22.915397.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"score":0.9763000011444092,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3001161237.pdf","grobid_xml":"https://content.openalex.org/works/W3001161237.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W48750798","https://openalex.org/W66857733","https://openalex.org/W1500506047","https://openalex.org/W1976751364","https://openalex.org/W2016202952","https://openalex.org/W2018025378","https://openalex.org/W2024901100","https://openalex.org/W2039508086","https://openalex.org/W2041467022","https://openalex.org/W2057913811","https://openalex.org/W2070082005","https://openalex.org/W2076907924","https://openalex.org/W2092087640","https://openalex.org/W2099085143","https://openalex.org/W2104355263","https://openalex.org/W2115335486","https://openalex.org/W2119924680","https://openalex.org/W2123152121","https://openalex.org/W2142771980","https://openalex.org/W2152885121","https://openalex.org/W2153118028","https://openalex.org/W2153860431","https://openalex.org/W2164988677","https://openalex.org/W2171079026","https://openalex.org/W2181523240","https://openalex.org/W2234310594","https://openalex.org/W2238851414","https://openalex.org/W2331834241","https://openalex.org/W2345621280","https://openalex.org/W2416382276","https://openalex.org/W2466965730","https://openalex.org/W2575618123","https://openalex.org/W2785925223","https://openalex.org/W2791863121","https://openalex.org/W2794409974","https://openalex.org/W2798750837","https://openalex.org/W2804842126","https://openalex.org/W2867709400","https://openalex.org/W2883622734","https://openalex.org/W2884743521","https://openalex.org/W2895486342","https://openalex.org/W2899096266","https://openalex.org/W2901303766","https://openalex.org/W2910949799","https://openalex.org/W2950099124","https://openalex.org/W2952226016","https://openalex.org/W2969978363","https://openalex.org/W2976223633","https://openalex.org/W2982537709","https://openalex.org/W2990677574","https://openalex.org/W2995302941","https://openalex.org/W3015900446","https://openalex.org/W3111073730"],"related_works":["https://openalex.org/W3009864517","https://openalex.org/W4404117190","https://openalex.org/W2159062914","https://openalex.org/W3111073730","https://openalex.org/W3015900446","https://openalex.org/W2736452443","https://openalex.org/W4225910238","https://openalex.org/W4406993171","https://openalex.org/W4404061721","https://openalex.org/W7073596146"],"abstract_inverted_index":{"Abstract":[0],"Genome-wide":[1],"association":[2],"studies":[3,39],"(GWAS)":[4],"may":[5],"require":[6],"enrollment":[7],"of":[8,12,22,84,104,154],"up":[9],"to":[10,14,31,73,150],"millions":[11],"participants":[13],"power":[15,153],"variant":[16,128],"discovery.":[17],"This":[18],"requires":[19],"manual":[20],"curation":[21],"cases":[23,60,107],"and":[24,61,124],"controls":[25],"with":[26,132],"large-scale":[27],"collaborations.":[28],"Biobanks":[29],"connected":[30],"electronic":[32],"health":[33],"records":[34],"(EHR)":[35],"can":[36],"facilitate":[37],"these":[38],"by":[40,76],"using":[41,94],"data":[42],"from":[43],"clinical":[44],"care":[45],"systems,":[46,54],"like":[47],"billing":[48],"diagnosis":[49],"codes,":[50],"as":[51,97],"phenotypes.":[52],"These":[53],"however,":[55],"do":[56],"not":[57],"define":[58],"adjudicated":[59],"controls.":[62],"We":[63,89],"developed":[64],"QTPhenProxy,":[65],"a":[66,80,82,92,98,126],"machine":[67],"learning":[68],"model":[69],"that":[70,139],"adds":[71],"nuance":[72],"cohort":[74,81],"classification":[75],"assigning":[77],"everyone":[78],"in":[79,122,129,135,141],"probability":[83],"having":[85],"the":[86,95,109,136,142,152],"study":[87],"disease.":[88],"then":[90],"ran":[91],"GWAS":[93],"probabilities":[96],"quantitative":[99],"trait.":[100],"With":[101],"an":[102],"order":[103],"magnitude":[105],"fewer":[106],"than":[108],"largest":[110],"stroke":[111,123],"GWAS,":[112],"our":[113],"method":[114],"outperformed":[115],"previous":[116],"methods":[117],"at":[118],"replicating":[119],"known":[120],"variants":[121],"discovered":[125],"novel":[127],"ABCG8":[130],"associated":[131],"intracerebral":[133],"hemorrhage":[134],"UK":[137],"Biobank":[138],"replicated":[140],"MEGASTROKE":[143],"GWA":[144],"meta-analysis.":[145],"QTPhenProxy":[146],"expands":[147],"traditional":[148],"phenotyping":[149],"improve":[151],"GWAS.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2020-01-30T00:00:00"}