{"id":"https://openalex.org/W2169055991","doi":"https://doi.org/10.1109/bigdata.2013.6691752","title":"Colon cancer survival prediction using ensemble data mining on SEER data","display_name":"Colon cancer survival prediction using ensemble data mining on SEER data","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2169055991","doi":"https://doi.org/10.1109/bigdata.2013.6691752","mag":"2169055991"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2013.6691752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","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/A5052511736","display_name":"Reda Al-Bahrani","orcid":"https://orcid.org/0000-0002-1528-0792"},"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":"Reda Al-Bahrani","raw_affiliation_strings":["Dept. of Electrical Engg. and Computer Science, Northwestern University, Evanston, IL, US"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engg. and Computer Science, Northwestern University, Evanston, IL, US","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","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":false,"raw_author_name":"Ankit Agrawal","raw_affiliation_strings":["Dept. of Electrical Engg. and Computer Science, Northwestern University, Evanston, IL, US"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engg. and Computer Science, Northwestern University, Evanston, IL, US","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":["Dept. of Electrical Engg. and Computer Science, Northwestern University, Evanston, IL, US"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engg. and Computer Science, Northwestern University, Evanston, IL, US","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052511736"],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":7.52,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.9693336,"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":"9","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9864000082015991,"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":0.9864000082015991,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9805999994277954,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9796000123023987,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7617650032043457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6561930179595947},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5783816576004028},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5555849671363831},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5296748876571655},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5026557445526123},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.49298593401908875},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46435120701789856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4366455078125},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.4262315630912781},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40607672929763794},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3310297727584839}],"concepts":[{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7617650032043457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6561930179595947},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5783816576004028},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5555849671363831},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5296748876571655},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5026557445526123},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.49298593401908875},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46435120701789856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4366455078125},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.4262315630912781},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40607672929763794},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3310297727584839},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2013.6691752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.414.1100","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.414.1100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cucis.ece.northwestern.edu/publications/pdf/AlAgr13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W185853634","https://openalex.org/W430011295","https://openalex.org/W1493775511","https://openalex.org/W1495061682","https://openalex.org/W1504694836","https://openalex.org/W1554663460","https://openalex.org/W1570448133","https://openalex.org/W1859701809","https://openalex.org/W1881647329","https://openalex.org/W1964526617","https://openalex.org/W1973448749","https://openalex.org/W1979118614","https://openalex.org/W1983024255","https://openalex.org/W1991733344","https://openalex.org/W2007922827","https://openalex.org/W2024046085","https://openalex.org/W2056795985","https://openalex.org/W2086811040","https://openalex.org/W2101032959","https://openalex.org/W2102083998","https://openalex.org/W2104873924","https://openalex.org/W2105809105","https://openalex.org/W2109688168","https://openalex.org/W2112076978","https://openalex.org/W2113242816","https://openalex.org/W2125055259","https://openalex.org/W2133914847","https://openalex.org/W2133990480","https://openalex.org/W2148143831","https://openalex.org/W2149214723","https://openalex.org/W2151713352","https://openalex.org/W2153635508","https://openalex.org/W2155653793","https://openalex.org/W2156909104","https://openalex.org/W2162715289","https://openalex.org/W2163719914","https://openalex.org/W2246514367","https://openalex.org/W2260087768","https://openalex.org/W2911964244","https://openalex.org/W2912934387","https://openalex.org/W2966207845","https://openalex.org/W3142144633","https://openalex.org/W3143569680","https://openalex.org/W4212883601","https://openalex.org/W6614908035","https://openalex.org/W6639409548","https://openalex.org/W6652503778"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W138569904","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W3092506759","https://openalex.org/W2390914021","https://openalex.org/W2389417819","https://openalex.org/W3195278891"],"abstract_inverted_index":{"We":[0,39,89],"analyze":[1],"the":[2,8,12,49,62,65,74,86,96,117,135,143,147,155,159,162],"colon":[3,21],"cancer":[4],"data":[5,118,163],"available":[6],"from":[7],"SEER":[9],"program":[10],"with":[11],"aim":[13],"of":[14,30,61,64,80,98,108,113,134,146,150,157,161],"developing":[15],"accurate":[16],"survival":[17,50],"prediction":[18,76,81],"models":[19],"for":[20],"cancer.":[22],"Carefully":[23],"designed":[24],"preprocessing":[25],"steps":[26],"resulted":[27],"in":[28,73,78],"removal":[29],"several":[31,35],"attributes":[32,115],"and":[33,51,83,105,130],"applying":[34],"supervised":[36],"classification":[37,92],"methods.":[38],"also":[40],"adopt":[41],"synthetic":[42],"minority":[43],"over-sampling":[44],"technique":[45],"(SMOTE)":[46],"to":[47,71,94,141,165],"balance":[48],"non-survival":[52],"classes":[53,160],"we":[54,153],"have.":[55],"In":[56],"our":[57],"experiments,":[58],"ensemble":[59],"voting":[60],"three":[63],"top":[66],"performing":[67],"classifiers":[68],"was":[69],"found":[70],"result":[72],"best":[75],"performance":[77],"terms":[79],"accuracy":[82],"area":[84],"under":[85],"ROC":[87],"curve.":[88],"evaluated":[90],"multiple":[91],"schemes":[93],"estimate":[95],"risk":[97],"mortality":[99],"after":[100,116],"1":[101],"year,":[102],"2":[103],"years":[104,107],"5":[106],"diagnosis,":[109],"on":[110],"a":[111],"subset":[112],"65":[114],"clean":[119],"up":[120],"process,":[121],"13":[122,137],"attribute":[123,127],"carefully":[124],"selected":[125],"using":[126],"selection":[128],"techniques,":[129],"SMOTE":[131],"balanced":[132],"set":[133,149,164],"same":[136],"attributes,":[138],"while":[139],"trying":[140],"retain":[142],"predictive":[144],"power":[145],"original":[148],"attributes.":[151],"Moreover,":[152],"demonstrate":[154],"importance":[156],"balancing":[158],"yield":[166],"better":[167],"results.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}