{"id":"https://openalex.org/W2078769531","doi":"https://doi.org/10.1145/1882992.1883067","title":"Large-scale multimodal mining for healthcare with mapreduce","display_name":"Large-scale multimodal mining for healthcare with mapreduce","publication_year":2010,"publication_date":"2010-11-11","ids":{"openalex":"https://openalex.org/W2078769531","doi":"https://doi.org/10.1145/1882992.1883067","mag":"2078769531"},"language":"en","primary_location":{"id":"doi:10.1145/1882992.1883067","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1882992.1883067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM International Health Informatics Symposium","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/A5100455824","display_name":"Fei Wang","orcid":"https://orcid.org/0000-0002-3677-0360"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fei Wang","raw_affiliation_strings":["IBM Research Almaden, San Jose, CA, USA","IBM-Research Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM-Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065055611","display_name":"Vuk Ercegovac","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vuk Ercegovac","raw_affiliation_strings":["IBM Research Almaden, San Jose, CA, USA","IBM-Research Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM-Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057284370","display_name":"Tanveer Syeda-Mahmood","orcid":"https://orcid.org/0000-0003-0059-3208"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanveer Syeda-Mahmood","raw_affiliation_strings":["IBM Research Almaden, San Jose, CA, USA","IBM-Research Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM-Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002982475","display_name":"Akintayo Holder","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akintayo Holder","raw_affiliation_strings":["RPI, Troy, NY, USA"],"affiliations":[{"raw_affiliation_string":"RPI, Troy, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047853212","display_name":"Eugene J. Shekita","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Shekita","raw_affiliation_strings":["IBM Research Almaden, San Jose, CA, USA","IBM-Research Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM-Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020179679","display_name":"David Beymer","orcid":"https://orcid.org/0000-0002-9491-4967"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Beymer","raw_affiliation_strings":["IBM Research Almaden, San Jose, CA, USA","IBM-Research Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM-Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027761283","display_name":"Lin Hao Xu","orcid":"https://orcid.org/0000-0003-4566-9675"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Hao Xu","raw_affiliation_strings":["IBM Research China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"IBM Research China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100455824"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":3.1284,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.91737353,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"479","last_page":"483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9757999777793884,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9757999777793884,"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/T10350","display_name":"Electronic Health Records Systems","score":0.967199981212616,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9671000242233276,"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/petabyte","display_name":"Petabyte","score":0.8341100215911865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7962315082550049},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.7137547731399536},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6809331178665161},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6489022970199585},{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.579239547252655},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4576590955257416},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4459630846977234},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.4441395401954651},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4191238284111023},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3975388705730438},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27306807041168213},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.17282184958457947},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1324140429496765}],"concepts":[{"id":"https://openalex.org/C13600138","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Petabyte","level":3,"score":0.8341100215911865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7962315082550049},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.7137547731399536},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6809331178665161},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6489022970199585},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.579239547252655},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4576590955257416},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4459630846977234},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.4441395401954651},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4191238284111023},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3975388705730438},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27306807041168213},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17282184958457947},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1324140429496765},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1882992.1883067","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1882992.1883067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM International Health Informatics Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1592284865","https://openalex.org/W1974775589","https://openalex.org/W2100830825","https://openalex.org/W2106565963","https://openalex.org/W2132399973","https://openalex.org/W2162893304","https://openalex.org/W2171697262","https://openalex.org/W2173213060","https://openalex.org/W6676367512"],"related_works":["https://openalex.org/W1538652242","https://openalex.org/W2011521129","https://openalex.org/W4379164835","https://openalex.org/W2461968736","https://openalex.org/W4386544342","https://openalex.org/W2936171637","https://openalex.org/W1586214342","https://openalex.org/W2260589296","https://openalex.org/W3157828377","https://openalex.org/W2990494149"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,66],"healthcare":[3,124,153],"and":[4,7,80,144,157],"bioscience":[5],"technologies":[6],"proliferation":[8],"of":[9,17,38,74,107,121,130,151,159,168,173,187],"portable":[10],"medical":[11],"devices":[12],"have":[13],"produce":[14],"massive":[15],"amount":[16,106],"multimodal":[18,54,125,154],"data,":[19,78],"the":[20,91,131,152],"need":[21],"for":[22,27,48],"parallel":[23],"processing":[24],"is":[25,51,100],"apparent":[26],"mining":[28,126,155],"these":[29],"data":[30,64,93,109],"sets,":[31],"which":[32],"can":[33],"range":[34],"anywhere":[35],"from":[36],"tens":[37],"gigabytes,":[39],"to":[40,69,103,117],"terabytes":[41],"or":[42],"even":[43],"petabytes.":[44],"AALIM":[45,98,177],"(Advanced":[46],"Analytics":[47],"Information":[49],"Management)":[50],"a":[52,71,75,123,142,175,185],"new":[53],"mining-based":[55],"clinical":[56],"decision":[57],"support":[58],"system":[59,99,127],"that":[60,147,162],"brings":[61],"together":[62],"patient":[63,108],"captured":[65],"many":[67],"modalities":[68],"provide":[70],"holistic":[72],"presentation":[73],"patient's":[76],"exam":[77],"diseases,":[79],"medications.":[81],"In":[82,112],"addition,":[83],"it":[84],"offers":[85],"disease-specific":[86],"similarity":[87],"search":[88],"based":[89],"on":[90,128,166,184],"various":[92],"modalities.":[94],"The":[95],"current":[96],"deployed":[97],"only":[101],"able":[102],"process":[104],"limited":[105],"per":[110],"day.":[111],"this":[113,119],"paper,":[114],"we":[115],"attempt":[116],"address":[118],"challenge":[120],"building":[122],"top":[129],"MapReduce":[132],"framework,":[133],"specifically":[134],"its":[135],"popular":[136],"open-source":[137],"implementation,":[138],"Hadoop.":[139],"We":[140],"presented":[141],"scalable":[143],"generic":[145],"framework":[146],"enables":[148],"automatic":[149],"parallelization":[150],"algorithm,":[156],"distribution":[158],"large-scale":[160],"computation":[161],"achieves":[163],"high":[164],"performance":[165],"clusters":[167],"commodity":[169],"servers.":[170],"Initial":[171],"testing":[172],"importing":[174],"single":[176],"module":[178],"(EKG":[179],"period":[180],"estimation)":[181],"using":[182],"Hadoop":[183],"cluster":[186],"servers":[188],"shows":[189],"very":[190],"promising":[191],"results.":[192]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}