{"id":"https://openalex.org/W2945994271","doi":"https://doi.org/10.1145/3309129.3309133","title":"Breast Cancer Prediction Using Spark MLlib and ML Packages","display_name":"Breast Cancer Prediction Using Spark MLlib and ML Packages","publication_year":2018,"publication_date":"2018-12-27","ids":{"openalex":"https://openalex.org/W2945994271","doi":"https://doi.org/10.1145/3309129.3309133","mag":"2945994271"},"language":"en","primary_location":{"id":"doi:10.1145/3309129.3309133","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3309129.3309133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 5th International Conference on Bioinformatics Research and Applications","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/A5024061356","display_name":"Phan Duy Hung","orcid":"https://orcid.org/0000-0002-6033-6484"},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Phan Duy Hung","raw_affiliation_strings":["FPT University, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FPT University, Hanoi, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083181524","display_name":"Tran Duc Hanh","orcid":null},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Tran Duc Hanh","raw_affiliation_strings":["FPT University, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FPT University, Hanoi, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038691965","display_name":"Vu Thu Diep","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Vu Thu Diep","raw_affiliation_strings":["Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.886,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.9485621,"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":"52","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9980000257492065,"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/T10862","display_name":"AI in cancer detection","score":0.9980000257492065,"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":0.9934999942779541,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9099000096321106,"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/computer-science","display_name":"Computer science","score":0.7813984155654907},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7480993270874023},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6905484795570374},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6198423504829407},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.585773766040802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5554095506668091},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5204146504402161},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.382818341255188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813984155654907},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7480993270874023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6905484795570374},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6198423504829407},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.585773766040802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5554095506668091},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5204146504402161},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.382818341255188},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3309129.3309133","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3309129.3309133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 5th International Conference on Bioinformatics Research and Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1651586605","https://openalex.org/W1968817125","https://openalex.org/W2031298774","https://openalex.org/W2256629785","https://openalex.org/W2284497682","https://openalex.org/W2328733597","https://openalex.org/W2345549197","https://openalex.org/W2754472824","https://openalex.org/W2782524587","https://openalex.org/W2887589168","https://openalex.org/W2888983041","https://openalex.org/W2889024854","https://openalex.org/W2941501358","https://openalex.org/W3146157593","https://openalex.org/W4241231557","https://openalex.org/W4296886862"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991"],"abstract_inverted_index":{"Nowadays,":[0],"Machine":[1,17],"Learning":[2],"has":[3,19],"been":[4,20],"applied":[5],"in":[6,12,23,62,129],"variety":[7],"aspects":[8],"of":[9,45,47,126,136],"life":[10],"especially":[11],"health":[13],"care.":[14],"Classifications":[15],"using":[16],"learning":[18,76,115],"greatly":[21],"improved":[22],"order":[24],"to":[25,29],"make":[26],"predictions":[27],"and":[28,50,59,72,102,112,138,143],"support":[30],"doctors":[31],"making":[32],"diagnoses.":[33],"Furthermore,":[34],"human":[35],"lives":[36],"are":[37,78,94,140],"changing":[38],"with":[39,51,110,120],"Big":[40],"Data":[41,52],"covering":[42],"a":[43,87,118,123],"wide":[44],"array":[46],"science":[48],"knowledge":[49],"Mining":[53],"solving":[54],"problems":[55],"by":[56],"analyzing":[57],"data":[58,70,93,127],"discovering":[60],"patterns":[61],"present":[63],"databases.":[64],"The":[65],"prediction":[66,106],"process":[67],"is":[68],"heavily":[69],"driven":[71],"therefore":[73],"advanced":[74],"machine":[75,114],"techniques":[77],"often":[79],"utilized.":[80],"In":[81],"this":[82],"paper,":[83],"we":[84],"will":[85],"take":[86],"look":[88],"at":[89],"what":[90],"types":[91],"experiment":[92],"typically":[95],"used,":[96],"do":[97],"preliminary":[98],"analysis":[99],"on":[100],"them,":[101],"generate":[103],"breast":[104],"cancer":[105],"models":[107],"-":[108],"all":[109],"PySpark":[111],"its":[113],"frameworks.":[116],"Using":[117],"database":[119],"more":[121],"than":[122],"hundred":[124],"sets":[125],"gathered":[128],"routine":[130],"blood":[131],"analysis,":[132],"the":[133],"accuracy":[134],"rates":[135],"detection":[137],"classification":[139],"about":[141],"72%":[142],"83%":[144],"respectively.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}