{"id":"https://openalex.org/W2056795985","doi":"https://doi.org/10.1145/2003351.2003356","title":"A lung cancer outcome calculator using ensemble data mining on SEER data","display_name":"A lung cancer outcome calculator using ensemble data mining on SEER data","publication_year":2011,"publication_date":"2011-07-20","ids":{"openalex":"https://openalex.org/W2056795985","doi":"https://doi.org/10.1145/2003351.2003356","mag":"2056795985"},"language":"en","primary_location":{"id":"doi:10.1145/2003351.2003356","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2003351.2003356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Workshop on Data Mining in Bioinformatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004659592","display_name":"Ankit Agrawal","orcid":"https://orcid.org/0000-0002-5519-0302"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ankit Agrawal","raw_affiliation_strings":["Northwestern University, IL","Northwestern University, IL,"],"affiliations":[{"raw_affiliation_string":"Northwestern University, IL","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern University, IL,","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085992504","display_name":"Sanchit Misra","orcid":"https://orcid.org/0000-0001-7863-858X"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanchit Misra","raw_affiliation_strings":["Northwestern University, IL","Northwestern University, IL,"],"affiliations":[{"raw_affiliation_string":"Northwestern University, IL","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern University, IL,","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030090531","display_name":"Ramanathan Narayanan","orcid":"https://orcid.org/0000-0003-4456-5241"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramanathan Narayanan","raw_affiliation_strings":["Northwestern University, IL","Northwestern University, IL,"],"affiliations":[{"raw_affiliation_string":"Northwestern University, IL","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern University, IL,","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082617064","display_name":"Lalith Polepeddi","orcid":"https://orcid.org/0000-0003-2515-9889"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lalith Polepeddi","raw_affiliation_strings":["Northwestern University, IL","Northwestern University, IL,"],"affiliations":[{"raw_affiliation_string":"Northwestern University, IL","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern University, IL,","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074976770","display_name":"Alok Choudhary","orcid":"https://orcid.org/0000-0001-8152-6319"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alok Choudhary","raw_affiliation_strings":["Northwestern University, IL","Northwestern University, IL,"],"affiliations":[{"raw_affiliation_string":"Northwestern University, IL","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern University, IL,","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5004659592"],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":8.4089,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.97179558,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11719","display_name":"Data Quality and Management","score":0.9728000164031982,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9678000211715698,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/calculator","display_name":"Calculator","score":0.8509455919265747},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.6368503570556641},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6353452801704407},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6272807717323303},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5976787209510803},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5836722254753113},{"id":"https://openalex.org/keywords/lung-cancer","display_name":"Lung cancer","score":0.5650268793106079},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47162318229675293},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.41756346821784973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40296536684036255},{"id":"https://openalex.org/keywords/oncology","display_name":"Oncology","score":0.17447435855865479},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.16889122128486633},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15916064381599426}],"concepts":[{"id":"https://openalex.org/C2776836400","wikidata":"https://www.wikidata.org/wiki/Q31087","display_name":"Calculator","level":2,"score":0.8509455919265747},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.6368503570556641},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6353452801704407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6272807717323303},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5976787209510803},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5836722254753113},{"id":"https://openalex.org/C2776256026","wikidata":"https://www.wikidata.org/wiki/Q47912","display_name":"Lung cancer","level":2,"score":0.5650268793106079},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47162318229675293},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.41756346821784973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40296536684036255},{"id":"https://openalex.org/C143998085","wikidata":"https://www.wikidata.org/wiki/Q162555","display_name":"Oncology","level":1,"score":0.17447435855865479},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.16889122128486633},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15916064381599426},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2003351.2003356","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2003351.2003356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Workshop on Data Mining in Bioinformatics","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.600.5301","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.600.5301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.rpi.edu/~zaki/Workshops/BIOKDD11/doc/biokdd2011_Ankit.Agrawal.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"awards":[{"id":"https://openalex.org/G2101386667","display_name":null,"funder_award_id":"DE-FG02-08ER25848","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2851448297","display_name":null,"funder_award_id":"CNS-0551639IIS-0536994IIS-0905205","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"},{"id":"https://openalex.org/G6878061678","display_name":null,"funder_award_id":"OCI-0724599","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G776663208","display_name":null,"funder_award_id":"CCF-0621443","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"},{"id":"https://openalex.org/G8345836828","display_name":null,"funder_award_id":"CNS-0551639IIS-0536994IIS-0905205","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G8670585632","display_name":null,"funder_award_id":"DE-FC02-07ER25808","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"},{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"},{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W185853634","https://openalex.org/W1493775511","https://openalex.org/W1495061682","https://openalex.org/W1554663460","https://openalex.org/W1570448133","https://openalex.org/W1608292140","https://openalex.org/W1881647329","https://openalex.org/W1964526617","https://openalex.org/W1973448749","https://openalex.org/W1979118614","https://openalex.org/W1983024255","https://openalex.org/W2007922827","https://openalex.org/W2024046085","https://openalex.org/W2086811040","https://openalex.org/W2102083998","https://openalex.org/W2104873924","https://openalex.org/W2105809105","https://openalex.org/W2109688168","https://openalex.org/W2113242816","https://openalex.org/W2125055259","https://openalex.org/W2133914847","https://openalex.org/W2133990480","https://openalex.org/W2149214723","https://openalex.org/W2151713352","https://openalex.org/W2153635508","https://openalex.org/W2156909104","https://openalex.org/W2246514367","https://openalex.org/W2260087768","https://openalex.org/W2412930843","https://openalex.org/W2911964244","https://openalex.org/W2966207845","https://openalex.org/W3142144633","https://openalex.org/W4206535445","https://openalex.org/W4297832830"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"We":[0],"analyze":[1],"the":[2,8,12,40,59,88,99,151,155],"lung":[3,21,108,162],"cancer":[4,22,109,163],"data":[5,24,52,61,65],"available":[6,174],"from":[7],"SEER":[9],"program":[10],"with":[11,63],"aim":[13],"of":[14,34,39,75,94,115,129,137,154,158,170],"developing":[15],"accurate":[16],"survival":[17],"prediction":[18,90],"models":[19],"for":[20,112,131],"using":[23,143],"mining":[25,53,66],"techniques.":[26],"Carefully":[27],"designed":[28],"preprocessing":[29],"steps":[30],"resulted":[31],"in":[32,87,92],"removal/modification/splitting":[33],"several":[35],"attributes,":[36],"and":[37,68,81,96,126],"2":[38,124],"11":[41],"derived":[42],"attributes":[43,139],"were":[44,56],"found":[45,84],"to":[46,85,149],"have":[47,104],"significant":[48],"predictive":[49,152],"power.":[50],"Several":[51],"classification":[54],"techniques":[55],"used":[57],"on":[58],"preprocessed":[60],"along":[62],"various":[64],"optimizations":[67],"validations.":[69],"In":[70],"our":[71],"experiments,":[72],"ensemble":[73],"voting":[74],"five":[76],"decision":[77],"tree":[78],"based":[79],"classifiers":[80],"meta-classifiers":[82],"was":[83,140],"result":[86,169],"best":[89],"performance":[91],"terms":[93],"accuracy":[95],"area":[97],"under":[98],"ROC":[100],"curve.":[101],"Further,":[102],"we":[103],"developed":[105,166],"an":[106],"on-line":[107,161],"outcome":[110,164],"calculator":[111,165],"estimating":[113],"risk":[114],"mortality":[116],"after":[117],"6":[118],"months,":[119,121],"9":[120],"1":[122],"year,":[123,125],"5":[127],"years":[128],"diagnosis,":[130],"which":[132],"a":[133,168],"smaller":[134],"non-redundant":[135],"subset":[136],"13":[138],"carefully":[141],"selected":[142],"attribute":[144],"selection":[145],"techniques,":[146],"while":[147],"trying":[148],"retain":[150],"power":[153],"original":[156],"set":[157],"attributes.":[159],"The":[160],"as":[167],"this":[171],"study":[172],"is":[173],"at":[175],"http://info.eecs.northwestern.edu:8080/LungCancerOutcome-Calculator/":[176]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}