{"id":"https://openalex.org/W4313492037","doi":"https://doi.org/10.1145/3570991.3571011","title":"A robust section identification method for scanned electronic health records","display_name":"A robust section identification method for scanned electronic health records","publication_year":2023,"publication_date":"2023-01-04","ids":{"openalex":"https://openalex.org/W4313492037","doi":"https://doi.org/10.1145/3570991.3571011"},"language":"en","primary_location":{"id":"doi:10.1145/3570991.3571011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3570991.3571011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Joint International Conference on Data Science & Management of Data (10th ACM IKDD CODS and 28th COMAD)","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/A5101788435","display_name":"Anand Prabhu Subramanian","orcid":"https://orcid.org/0000-0003-4711-5457"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Anand Subramanian","raw_affiliation_strings":["BUDDI AI, India"],"affiliations":[{"raw_affiliation_string":"BUDDI AI, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066685587","display_name":"Praveen Kumar Suresh","orcid":"https://orcid.org/0000-0001-7513-8408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Praveen Kumar Suresh","raw_affiliation_strings":["BUDDI AI, India"],"affiliations":[{"raw_affiliation_string":"BUDDI AI, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012400928","display_name":"Sudarsun Santhiappan","orcid":"https://orcid.org/0000-0001-5769-2405"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sudarsun Santhiappan","raw_affiliation_strings":["BUDDI AI, India"],"affiliations":[{"raw_affiliation_string":"BUDDI AI, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101788435"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3185,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6171684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9868999719619751,"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/T10028","display_name":"Topic Modeling","score":0.9842000007629395,"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/section","display_name":"Section (typography)","score":0.6942905187606812},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6767942905426025},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.6329094171524048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5681298971176147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32103705406188965},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.09081783890724182}],"concepts":[{"id":"https://openalex.org/C2780129039","wikidata":"https://www.wikidata.org/wiki/Q1931107","display_name":"Section (typography)","level":2,"score":0.6942905187606812},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6767942905426025},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.6329094171524048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5681298971176147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32103705406188965},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.09081783890724182},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3570991.3571011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3570991.3571011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Joint International Conference on Data Science & Management of Data (10th ACM IKDD CODS and 28th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W153173462","https://openalex.org/W1195653073","https://openalex.org/W1991746030","https://openalex.org/W2051548804","https://openalex.org/W2128279348","https://openalex.org/W2131774270","https://openalex.org/W2167492639","https://openalex.org/W2169980349","https://openalex.org/W2888337796","https://openalex.org/W2888597024","https://openalex.org/W2913059114","https://openalex.org/W2958747773","https://openalex.org/W2989227969","https://openalex.org/W3180181113"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2560853036","https://openalex.org/W2566696415","https://openalex.org/W1563787543","https://openalex.org/W4239980664","https://openalex.org/W4249026152","https://openalex.org/W4231213805","https://openalex.org/W4244585678","https://openalex.org/W2909241626"],"abstract_inverted_index":{"An":[0],"Electronic":[1],"Health":[2],"Record":[3],"(EHR)":[4],"is":[5,32,45,82,102,170],"a":[6,13,17,74,78,156,208],"digital":[7],"document":[8],"containing":[9],"critical":[10],"information":[11,71],"concerning":[12],"patient\u2019s":[14,79],"visit":[15],"to":[16,34,73,129,147,184,188],"hospital.":[18],"However,":[19,133],"since":[20],"they":[21],"are":[22,58,127,144],"often":[23],"archived":[24],"as":[25,91],"scanned":[26,49,167],"images,":[27],"Optical":[28],"Character":[29],"Recognition":[30],"(OCR)":[31],"used":[33],"extract":[35],"the":[36,48,56,66,103,107,115,148],"clinical":[37,87],"text":[38,63],"for":[39,84,162],"analytics.":[40],"The":[41],"accuracy":[42],"of":[43,59,77,105,117],"OCR":[44,152,189,212],"compromised":[46],"when":[47,55],"EHRs":[50,168],"contain":[51],"noise":[52],"artifacts":[53],"or":[54],"scans":[57],"poor":[60],"quality.":[61],"Clinical":[62,163],"sections":[64,109],"in":[65,111],"EHR":[67,113],"help":[68,116],"precisely":[69],"locate":[70],"pertinent":[72],"specific":[75],"aspect":[76],"visit,":[80],"which":[81],"vital":[83],"any":[85],"downstream":[86],"analytics":[88],"activities":[89],"such":[90],"medical":[92,94,209],"coding,":[93],"necessity":[95],"assessment,":[96],"and":[97,124,140,143,199],"diagnosis":[98],"identification.":[99],"Section":[100,164],"Identification":[101,165],"task":[104],"identifying":[106],"different":[108],"present":[110],"an":[112],"with":[114,198,211],"their":[118,186],"headers.":[119],"Traditionally,":[120],"rule-based":[121],"keyword":[122],"matching":[123],"statistical":[125],"approaches":[126,135,206],"employed":[128],"solve":[130],"this":[131],"problem.":[132],"these":[134],"rely":[136],"on":[137,207],"external":[138],"lookups":[139],"knowledge":[141],"bases":[142],"therefore":[145],"susceptible":[146],"errors":[149],"introduced":[150],"by":[151],"processes.":[153],"We":[154,175,191],"propose":[155],"character-based":[157],"word":[158],"sequence":[159],"modeling":[160],"approach":[161],"from":[166,181],"that":[169,194],"robust":[171],"against":[172],"OCR-induced":[173],"errors.":[174,190,213],"also":[176],"utilize":[177],"character":[178,201],"augmentation":[179,202],"techniques":[180],"existing":[182,205],"literature":[183],"improve":[185],"robustness":[187],"empirically":[192],"demonstrate":[193],"our":[195],"models":[196],"trained":[197],"without":[200],"significantly":[203],"outperform":[204],"dataset":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}