{"id":"https://openalex.org/W2754456784","doi":"https://doi.org/10.3233/mas-170397","title":"A new framework for prediction and variable selection for uncommon events in a large prospective cohort study","display_name":"A new framework for prediction and variable selection for uncommon events in a large prospective cohort study","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2754456784","doi":"https://doi.org/10.3233/mas-170397","mag":"2754456784","pmid":"https://pubmed.ncbi.nlm.nih.gov/29075164"},"language":"en","primary_location":{"id":"doi:10.3233/mas-170397","is_oa":false,"landing_page_url":"https://doi.org/10.3233/mas-170397","pdf_url":null,"source":{"id":"https://openalex.org/S2765066696","display_name":"Model Assisted Statistics and Applications","issn_l":"1574-1699","issn":["1574-1699","1875-9068"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Model Assisted Statistics and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5654558","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102881795","display_name":"Hye\u2010Seung Lee","orcid":"https://orcid.org/0000-0002-5194-7101"},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hye-Seung Lee","raw_affiliation_strings":["University of South Florida","Health Informatics Institute, 3650 Spectrum Blvd., Suite 100, University of South Florida, Tampa, Florida 33612"],"affiliations":[{"raw_affiliation_string":"University of South Florida","institution_ids":["https://openalex.org/I2613432"]},{"raw_affiliation_string":"Health Informatics Institute, 3650 Spectrum Blvd., Suite 100, University of South Florida, Tampa, Florida 33612","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084625995","display_name":"Jeffrey P. Krischer","orcid":"https://orcid.org/0000-0003-4526-888X"},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey P. Krischer","raw_affiliation_strings":["University of South Florida","Health Informatics Institute, 3650 Spectrum Blvd., Suite 100, University of South Florida, Tampa, Florida 33612"],"affiliations":[{"raw_affiliation_string":"University of South Florida","institution_ids":["https://openalex.org/I2613432"]},{"raw_affiliation_string":"Health Informatics Institute, 3650 Spectrum Blvd., Suite 100, University of South Florida, Tampa, Florida 33612","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102881795"],"corresponding_institution_ids":["https://openalex.org/I2613432"],"apc_list":null,"apc_paid":null,"fwci":0.1726,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56921487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"12","issue":"3","first_page":"227","last_page":"237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10351","display_name":"Liver Disease Diagnosis and Treatment","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10351","display_name":"Liver Disease Diagnosis and Treatment","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"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/T10136","display_name":"Statistical Methods and Inference","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14374","display_name":"Statistical Methods in Epidemiology","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5537645220756531},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5132114887237549},{"id":"https://openalex.org/keywords/cohort","display_name":"Cohort","score":0.5004618167877197},{"id":"https://openalex.org/keywords/prospective-cohort-study","display_name":"Prospective cohort study","score":0.4425964951515198},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.384024977684021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3294183015823364},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3249831199645996},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.2217056155204773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2092311680316925},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16439971327781677}],"concepts":[{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5537645220756531},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5132114887237549},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.5004618167877197},{"id":"https://openalex.org/C188816634","wikidata":"https://www.wikidata.org/wiki/Q2113324","display_name":"Prospective cohort study","level":2,"score":0.4425964951515198},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.384024977684021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3294183015823364},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3249831199645996},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.2217056155204773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2092311680316925},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16439971327781677},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/mas-170397","is_oa":false,"landing_page_url":"https://doi.org/10.3233/mas-170397","pdf_url":null,"source":{"id":"https://openalex.org/S2765066696","display_name":"Model Assisted Statistics and Applications","issn_l":"1574-1699","issn":["1574-1699","1875-9068"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Model Assisted Statistics and Applications","raw_type":"journal-article"},{"id":"pmid:29075164","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29075164","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":"Model assisted statistics and applications : an international journal","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:5654558","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5654558","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Model Assist Stat Appl","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:5654558","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5654558","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Model Assist Stat Appl","raw_type":"Text"},"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W154377515","https://openalex.org/W1541370058","https://openalex.org/W1567191158","https://openalex.org/W1587722274","https://openalex.org/W1707852223","https://openalex.org/W1773554468","https://openalex.org/W1970792239","https://openalex.org/W2005526508","https://openalex.org/W2006481870","https://openalex.org/W2018144913","https://openalex.org/W2043478128","https://openalex.org/W2044379334","https://openalex.org/W2045005627","https://openalex.org/W2046385294","https://openalex.org/W2052825782","https://openalex.org/W2064186732","https://openalex.org/W2070230130","https://openalex.org/W2084164487","https://openalex.org/W2097360283","https://openalex.org/W2099237778","https://openalex.org/W2101707180","https://openalex.org/W2119910794","https://openalex.org/W2127570288","https://openalex.org/W2135046866","https://openalex.org/W2141704883","https://openalex.org/W2148154452","https://openalex.org/W2150290224","https://openalex.org/W2152575748","https://openalex.org/W2154063392","https://openalex.org/W2562162676","https://openalex.org/W2911964244","https://openalex.org/W2952332227","https://openalex.org/W3099478002","https://openalex.org/W3105543546","https://openalex.org/W4246767508","https://openalex.org/W4294541781","https://openalex.org/W6638215274"],"related_works":["https://openalex.org/W4205762803","https://openalex.org/W2535856026","https://openalex.org/W2265065644","https://openalex.org/W1922851888","https://openalex.org/W2134699697","https://openalex.org/W2549677424","https://openalex.org/W2322875716","https://openalex.org/W2468698815","https://openalex.org/W2383516975","https://openalex.org/W2374878784"],"abstract_inverted_index":{"When":[0,45],"prediction":[1,11,107,130],"is":[2,13,17,65,86,103,109,136,175],"a":[3,24,50,60,79,90,106,167,170,185],"goal,":[4],"validation":[5],"utilizing":[6],"data":[7,16,162],"outside":[8],"of":[9,59,81,122,127,143],"the":[10,57,69,82,94,116,120,128,133,141,144],"effort":[12],"desirable.":[14],"Typically,":[15],"split":[18],"into":[19],"two":[20],"parts:":[21],"one":[22,27],"for":[23,28,147,160,169],"development":[25],"and":[26,105],"validation.":[29,148],"But":[30],"this":[31,84],"approach":[32],"becomes":[33],"less":[34],"attractive":[35],"when":[36],"predicting":[37,46],"uncommon":[38,47],"events,":[39],"as":[40,164,166],"it":[41],"substantially":[42],"reduces":[43],"power.":[44],"events":[48],"within":[49],"large":[51,186],"prospective":[52,187],"cohort":[53,71,96,135,145,188],"study,":[54],"we":[55,151],"propose":[56,152],"use":[58],"nested":[61],"case-control":[62,117,134],"design,":[63],"which":[64],"an":[66,153,178],"alternative":[67],"to":[68,88,93,138],"full":[70,95],"analysis.":[72,97],"By":[73],"including":[74],"all":[75],"cases":[76],"but":[77],"only":[78],"subset":[80],"non-cases,":[83],"design":[85],"expected":[87],"produce":[89],"result":[91],"similar":[92],"In":[98,149],"our":[99],"framework,":[100],"variable":[101,155,182],"selection":[102,156,183],"conducted":[104],"model":[108,131],"fit":[110],"on":[111],"those":[112],"selected":[113],"variables":[114],"in":[115,132,140,184],"cohort.":[118],"Then,":[119],"fraction":[121],"true":[123],"negative":[124],"predictions":[125],"(specificity)":[126],"fitted":[129],"compared":[137],"that":[139],"rest":[142],"(non-cases)":[146],"addition,":[150],"iterative":[154],"using":[157],"random":[158],"forest":[159],"missing":[161],"imputation,":[163],"well":[165],"strategy":[168],"valid":[171],"classification.":[172],"Our":[173],"framework":[174],"illustrated":[176],"with":[177],"application":[179],"featuring":[180],"high-dimensional":[181],"study.":[189]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}