{"id":"https://openalex.org/W4281715628","doi":"https://doi.org/10.3233/shti220151","title":"A Sample Size Extractor for RCT Reports","display_name":"A Sample Size Extractor for RCT Reports","publication_year":2022,"publication_date":"2022-06-06","ids":{"openalex":"https://openalex.org/W4281715628","doi":"https://doi.org/10.3233/shti220151","pmid":"https://pubmed.ncbi.nlm.nih.gov/35673090"},"language":"en","primary_location":{"id":"doi:10.3233/shti220151","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti220151","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI220151","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI220151","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055803756","display_name":"Fengyang Lin","orcid":null},"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":"Fengyang Lin","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University, New York, NY, United States","Department of Biomedical Informatics, Columbia University, New York, NY, United States,"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University, New York, NY, United States","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University, New York, NY, United States,","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458789","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0002-1975-1272"},"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":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University, New York, NY, United States","Department of Biomedical Informatics, Columbia University, New York, NY, United States,"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University, New York, NY, United States","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University, New York, NY, United States,","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065683663","display_name":"Paul Moon","orcid":"https://orcid.org/0000-0003-2788-8719"},"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":false,"raw_author_name":"Paul Moon","raw_affiliation_strings":["College of Physicians and Surgeons: Institute of Human Nutrition, Columbia University, New York, NY, United States"],"affiliations":[{"raw_affiliation_string":"College of Physicians and Surgeons: Institute of Human Nutrition, Columbia University, New York, NY, United States","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009604048","display_name":"Chunhua Weng","orcid":"https://orcid.org/0000-0002-9624-0214"},"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":false,"raw_author_name":"Chunhua Weng","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University, New York, NY, United States","Department of Biomedical Informatics, Columbia University, New York, NY, United States,"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University, New York, NY, United States","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University, New York, NY, United States,","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055803756"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":1.3692,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82583104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"290","issue":null,"first_page":"617","last_page":"621"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9871000051498413,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9871000051498413,"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":0.9613999724388123,"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/T10028","display_name":"Topic Modeling","score":0.9584000110626221,"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/transfer-of-learning","display_name":"Transfer of learning","score":0.7047837972640991},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.6815473437309265},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.6750215291976929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6154477000236511},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5940486192703247},{"id":"https://openalex.org/keywords/randomized-controlled-trial","display_name":"Randomized controlled trial","score":0.5876385569572449},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.580001950263977},{"id":"https://openalex.org/keywords/coronavirus-disease-2019","display_name":"Coronavirus disease 2019 (COVID-19)","score":0.5638716816902161},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4727638363838196},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.45255082845687866},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.4359571039676666},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.41076621413230896},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3797379732131958},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35277336835861206},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33710506558418274},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20414039492607117},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.13557732105255127},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07118469476699829}],"concepts":[{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7047837972640991},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.6815473437309265},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.6750215291976929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6154477000236511},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5940486192703247},{"id":"https://openalex.org/C168563851","wikidata":"https://www.wikidata.org/wiki/Q1436668","display_name":"Randomized controlled trial","level":2,"score":0.5876385569572449},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.580001950263977},{"id":"https://openalex.org/C3008058167","wikidata":"https://www.wikidata.org/wiki/Q84263196","display_name":"Coronavirus disease 2019 (COVID-19)","level":4,"score":0.5638716816902161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4727638363838196},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.45255082845687866},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.4359571039676666},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.41076621413230896},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3797379732131958},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35277336835861206},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33710506558418274},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20414039492607117},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.13557732105255127},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07118469476699829},{"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/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.0},{"id":"https://openalex.org/C141071460","wikidata":"https://www.wikidata.org/wiki/Q40821","display_name":"Surgery","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C524204448","wikidata":"https://www.wikidata.org/wiki/Q788926","display_name":"Infectious disease (medical specialty)","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000453","qualifier_name":"epidemiology","is_major_topic":true},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000453","qualifier_name":"epidemiology","is_major_topic":true},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000453","qualifier_name":"epidemiology","is_major_topic":true},{"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":"D009323","descriptor_name":"Natural Language Processing","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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016032","descriptor_name":"Randomized Controlled Trials as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016032","descriptor_name":"Randomized Controlled Trials as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016032","descriptor_name":"Randomized Controlled Trials as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018401","descriptor_name":"Sample Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018401","descriptor_name":"Sample Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018401","descriptor_name":"Sample Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti220151","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti220151","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI220151","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:35673090","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35673090","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":"Studies in health technology and informatics","raw_type":null}],"best_oa_location":{"id":"doi:10.3233/shti220151","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti220151","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI220151","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G5922379911","display_name":null,"funder_award_id":"5R01LM009886-11","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G6091063704","display_name":null,"funder_award_id":"R01LM009886-11","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G6819462749","display_name":null,"funder_award_id":"5R01LM009886","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G682085659","display_name":null,"funder_award_id":"R01LM009886","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281715628.pdf","grobid_xml":"https://content.openalex.org/works/W4281715628.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W8550301","https://openalex.org/W1800049145","https://openalex.org/W2038287973","https://openalex.org/W2108696783","https://openalex.org/W2111722073","https://openalex.org/W2150054350","https://openalex.org/W2166734247","https://openalex.org/W2170216666","https://openalex.org/W2527896214","https://openalex.org/W2791189172","https://openalex.org/W2964179635","https://openalex.org/W2980993994","https://openalex.org/W3022300756","https://openalex.org/W3027335960"],"related_works":["https://openalex.org/W3082848404","https://openalex.org/W1979583797","https://openalex.org/W2016864125","https://openalex.org/W2372254676","https://openalex.org/W2793679056","https://openalex.org/W3145050838","https://openalex.org/W4293088233","https://openalex.org/W2080135837","https://openalex.org/W4295705264","https://openalex.org/W2791025012"],"abstract_inverted_index":{"Sample":[0],"size":[1,22,127],"is":[2],"an":[3,65],"important":[4],"indicator":[5],"of":[6,9,27,60,69],"the":[7,49,72,79,98,125],"power":[8],"randomized":[10],"controlled":[11],"trials":[12],"(RCTs).":[13],"In":[14],"this":[15],"paper,":[16],"we":[17,51],"designed":[18],"a":[19,25,56],"total":[20,104],"sample":[21,105,126],"extractor":[23,102],"using":[24,81],"combination":[26],"syntactic":[28],"and":[29,33,41,76,108,130],"machine":[30],"learning":[31,54,123],"methods,":[32],"evaluated":[34],"it":[35],"on":[36,71,78,90,134],"300":[37],"Covid-19":[38],"abstracts":[39,45],"(Covid-Set)":[40],"100":[42],"generic":[43],"RCT":[44],"(General-Set).":[46],"To":[47],"improve":[48],"performance,":[50],"applied":[52],"transfer":[53,117,122],"from":[55],"large":[57],"public":[58],"corpus":[59],"annotated":[61],"abstracts.":[62],"We":[63,119],"achieved":[64],"average":[66],"F1":[67,85,110],"score":[68],"0.73":[70],"Covid-Set":[73],"testing":[74],"set,":[75],"0.60":[77],"General-Set":[80],"exact":[82],"matches.":[83],"The":[84],"scores":[86,111],"for":[87],"loose":[88],"matches":[89],"both":[91],"datasets":[92],"were":[93],"over":[94],"0.74.":[95],"Compared":[96],"with":[97],"state-of-the-art":[99],"tool,":[100],"our":[101],"reports":[103],"sizes":[106],"directly":[107],"improved":[109,124],"by":[112],"at":[113],"least":[114],"4%":[115],"without":[116],"learning.":[118],"demonstrated":[120],"that":[121],"extraction":[128],"accuracy":[129],"minimized":[131],"human":[132],"labor":[133],"annotations.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}