{"id":"https://openalex.org/W2977347353","doi":"https://doi.org/10.5220/0008071303100321","title":"An Efficient, Robust, and Customizable Information Extraction and Pre-processing Pipeline for Electronic Health Records","display_name":"An Efficient, Robust, and Customizable Information Extraction and Pre-processing Pipeline for Electronic Health Records","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2977347353","doi":"https://doi.org/10.5220/0008071303100321","mag":"2977347353"},"language":"en","primary_location":{"id":"doi:10.5220/0008071303100321","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0008071303100321","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0008071303100321","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031566575","display_name":"Eva Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eva Lee","raw_affiliation_strings":["Center for Operations Research in Medicine and HealthCare, U.S.A., H. Milton Stewart School of Industrial and Systems Engineering, U.S.A., School of Biological Sciences, Georgia Institute of Technology and U.S.A., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Operations Research in Medicine and HealthCare, U.S.A., H. Milton Stewart School of Industrial and Systems Engineering, U.S.A., School of Biological Sciences, Georgia Institute of Technology and U.S.A., --- Select a Country ---","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuanbo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanbo Wang","raw_affiliation_strings":["Center for Operations Research in Medicine and HealthCare, U.S.A., H. Milton Stewart School of Industrial and Systems Engineering, U.S.A., School of Biological Sciences, Georgia Institute of Technology and U.S.A., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Operations Research in Medicine and HealthCare, U.S.A., H. Milton Stewart School of Industrial and Systems Engineering, U.S.A., School of Biological Sciences, Georgia Institute of Technology and U.S.A., --- Select a Country ---","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041926149","display_name":"Yuntian He","orcid":"https://orcid.org/0000-0002-1365-1772"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuntian He","raw_affiliation_strings":["Center for Operations Research in Medicine and HealthCare, U.S.A., H. Milton Stewart School of Industrial and Systems Engineering, U.S.A., School of Biological Sciences, Georgia Institute of Technology and U.S.A., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Operations Research in Medicine and HealthCare, U.S.A., H. Milton Stewart School of Industrial and Systems Engineering, U.S.A., School of Biological Sciences, Georgia Institute of Technology and U.S.A., --- Select a Country ---","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080066727","display_name":"Brent M. Egan","orcid":"https://orcid.org/0000-0002-1470-5875"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brent Egan","raw_affiliation_strings":["University of South Carolina School of Medicine\u2013Greenville, U.S.A., Care Coordination Institute, Greenville and U.S.A., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Carolina School of Medicine\u2013Greenville, U.S.A., Care Coordination Institute, Greenville and U.S.A., --- Select a Country ---","institution_ids":["https://openalex.org/I155781252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2824,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66186076,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"310","last_page":"321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9912999868392944,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9912999868392944,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10350","display_name":"Electronic Health Records Systems","score":0.9222999811172485,"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/pipeline","display_name":"Pipeline (software)","score":0.803033709526062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7806049585342407},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6116259694099426},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.5595051050186157},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5173215866088867},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5162160992622375},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.49729111790657043},{"id":"https://openalex.org/keywords/electronic-health-record","display_name":"Electronic health record","score":0.48762670159339905},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4269057512283325},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.36145150661468506},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34096014499664307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27493005990982056}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.803033709526062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806049585342407},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6116259694099426},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.5595051050186157},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5173215866088867},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5162160992622375},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.49729111790657043},{"id":"https://openalex.org/C3020144179","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic health record","level":3,"score":0.48762670159339905},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4269057512283325},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.36145150661468506},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34096014499664307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27493005990982056},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0008071303100321","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0008071303100321","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0008071303100321","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0008071303100321","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W187932805","https://openalex.org/W4392490004","https://openalex.org/W1641026212","https://openalex.org/W4402738807","https://openalex.org/W2911982698","https://openalex.org/W2323588885","https://openalex.org/W3047677938","https://openalex.org/W2087134418","https://openalex.org/W2078646730","https://openalex.org/W4312053962"],"abstract_inverted_index":{"Electronic":[0],"Health":[1,61],"Records":[2],"(EHR)":[3],"containing":[4,64],"large":[5],"amounts":[6],"of":[7,48,108],"patient":[8],"data":[9,50,137,141,157],"present":[10,92],"both":[11],"opportunities":[12],"and":[13,19,25,37,44,85,100,124,138,142,177,180],"challenges":[14,82,130],"to":[15,55,172],"industry,":[16],"policy":[17],"makers,":[18],"researchers.":[20],"These":[21],"data,":[22],"when":[23],"extracted":[24],"analyzed":[26],"effectively,":[27],"can":[28,33,164],"reveal":[29],"critical":[30],"factors":[31],"that":[32],"improve":[34,178],"clinical":[35,70,169],"practices":[36],"decisions.":[38],"However,":[39],"the":[40,106],"inherently":[41],"complex,":[42],"heterogeneous":[43],"rapidly":[45],"evolving":[46],"nature":[47],"these":[49],"make":[51],"them":[52],"extremely":[53],"difficult":[54],"analyze":[56],"effectively.":[57],"In":[58,76],"addition,":[59],"Protected":[60],"Information":[62],"(PHI)":[63],"sensitive":[65],"yet":[66],"valuable":[67],"information":[68,87],"for":[69,97,147],"research":[71,170],"must":[72],"first":[73],"be":[74,165],"anonymized.":[75],"this":[77,109],"paper":[78],"we":[79],"identify":[80],"current":[81],"with":[83,132],"obtaining":[84],"pre-processing":[86],"from":[88,114],"EHR.":[89],"We":[90,104,127],"then":[91],"a":[93,144,159],"comprehensive,":[94],"efficient":[95],"\u201cpipeline\u201d":[96],"extracting,":[98],"de-identifying,":[99],"standardizing":[101],"EHR":[102],"data.":[103],"demonstrate":[105],"use":[107],"pipeline,":[110],"based":[111],"on":[112],"software":[113],"EPIC":[115],"Systems,":[116],"in":[117,168],"analysing":[118],"chronic":[119],"kidney":[120],"disease,":[121],"prostate":[122],"cancer,":[123],"cardiovascular":[125],"disease.":[126],"also":[128],"address":[129],"associated":[131],"temporal":[133],"laboratory":[134],"time":[135],"series":[136],"natural":[139],"text":[140],"develop":[143],"novel":[145],"approach":[146],"clustering":[148],"irregular":[149],"Multivariate":[150],"Time":[151],"Series":[152],"(MTS).":[153],"The":[154],"pipeline":[155],"organizes":[156],"into":[158],"structured,":[160],"machine-readable":[161],"format":[162],"which":[163],"effectively":[166],"applied":[167],"studies":[171],"optimize":[173],"processes,":[174],"personalize":[175],"care,":[176],"quality,":[179],"outcomes.":[181]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}