{"id":"https://openalex.org/W4385571069","doi":"https://doi.org/10.18653/v1/2023.clinicalnlp-1.15","title":"Training Models on Oversampled Data and a Novel Multi-class Annotation Scheme for Dementia Detection","display_name":"Training Models on Oversampled Data and a Novel Multi-class Annotation Scheme for Dementia Detection","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385571069","doi":"https://doi.org/10.18653/v1/2023.clinicalnlp-1.15"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.clinicalnlp-1.15","doi":"https://doi.org/10.18653/v1/2023.clinicalnlp-1.15","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.clinicalnlp-1.15","pdf_url":"https://aclanthology.org/2023.clinicalnlp-1.15.pdf","source":{"id":"https://openalex.org/S7407088552","display_name":"Clinical Natural Language Processing Workshop (ClinicalNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Clinical Natural Language Processing Workshop","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.clinicalnlp-1.15.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092596232","display_name":"Nadine Abdelhalim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nadine Abdelhalim","raw_affiliation_strings":["The University of Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092596233","display_name":"Ingy Abdelhalim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ingy Abdelhalim","raw_affiliation_strings":["The University of Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050960711","display_name":"Riza Batista-Navarro","orcid":"https://orcid.org/0000-0001-6693-7531","observed_orcids":["https://orcid.org/0000-0001-6693-7531"]},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Riza Batista-Navarro","raw_affiliation_strings":["The University of Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":0.8838,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7550004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"118","last_page":"124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.7689999938011169,"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":0.7689999938011169,"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/T12488","display_name":"Mental Health via Writing","score":0.07829999923706055,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10009","display_name":"Dementia and Cognitive Impairment Research","score":0.049800001084804535,"subfield":{"id":"https://openalex.org/subfields/2738","display_name":"Psychiatry and Mental health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dementia-detection","display_name":"dementia detection","score":0.9929999709129333},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.6150000095367432},{"id":"https://openalex.org/keywords/oversampling","display_name":"oversampling","score":0.6980000138282776},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.7450000047683716},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.7459999918937683},{"id":"https://openalex.org/keywords/roberta","display_name":"RoBERTa","score":0.9950000047683716},{"id":"https://openalex.org/keywords/distilbert","display_name":"DistilBERT","score":0.996999979019165},{"id":"https://openalex.org/keywords/saliency-analysis","display_name":"saliency analysis","score":0.7070000171661377},{"id":"https://openalex.org/keywords/lime","display_name":"lime","score":0.8389999866485596},{"id":"https://openalex.org/keywords/explainable-ai","display_name":"explainable AI","score":0.6600000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6676413416862488},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6441227793693542},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.6101635694503784},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6093093752861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5990978479385376},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.558899998664856},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5478264689445496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5112905502319336},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4652337431907654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16582316160202026},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.clinicalnlp-1.15","doi":"https://doi.org/10.18653/v1/2023.clinicalnlp-1.15","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.clinicalnlp-1.15","pdf_url":"https://aclanthology.org/2023.clinicalnlp-1.15.pdf","source":{"id":"https://openalex.org/S7407088552","display_name":"Clinical Natural Language Processing Workshop (ClinicalNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Clinical Natural Language Processing Workshop","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.clinicalnlp-1.15","doi":"https://doi.org/10.18653/v1/2023.clinicalnlp-1.15","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.clinicalnlp-1.15","pdf_url":"https://aclanthology.org/2023.clinicalnlp-1.15.pdf","source":{"id":"https://openalex.org/S7407088552","display_name":"Clinical Natural Language Processing Workshop (ClinicalNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Clinical Natural Language Processing Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.8048999905586243}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1418851800","display_name":null,"funder_award_id":"AG 05-133","funder_id":"https://openalex.org/F4320337337","funder_display_name":"National Institute on Aging"},{"id":"https://openalex.org/G3470700294","display_name":null,"funder_award_id":"AG 03705","funder_id":"https://openalex.org/F4320337337","funder_display_name":"National Institute on Aging"},{"id":"https://openalex.org/G8721383862","display_name":null,"funder_award_id":"AG05133","funder_id":"https://openalex.org/F4320310174","funder_display_name":"University of Pittsburgh"}],"funders":[{"id":"https://openalex.org/F4320310174","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305"},{"id":"https://openalex.org/F4320337337","display_name":"National Institute on Aging","ror":"https://ror.org/049v75w11"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385571069.pdf","grobid_xml":"https://content.openalex.org/works/W4385571069.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W938539187","https://openalex.org/W1768003599","https://openalex.org/W2086316204","https://openalex.org/W2130903752","https://openalex.org/W2140721185","https://openalex.org/W2148143831","https://openalex.org/W2250883471","https://openalex.org/W2401240531","https://openalex.org/W2405088233","https://openalex.org/W2516809705","https://openalex.org/W2626778328","https://openalex.org/W2746614329","https://openalex.org/W2784161056","https://openalex.org/W2796528463","https://openalex.org/W2896457183","https://openalex.org/W2965373594","https://openalex.org/W2978017171","https://openalex.org/W2997200074","https://openalex.org/W3016396388","https://openalex.org/W3041833205","https://openalex.org/W3097533615","https://openalex.org/W3111706019","https://openalex.org/W3125401821","https://openalex.org/W3161827824","https://openalex.org/W3167343366","https://openalex.org/W3200812870","https://openalex.org/W4224068866","https://openalex.org/W4224251491","https://openalex.org/W4225132456","https://openalex.org/W4225279552","https://openalex.org/W4232663087","https://openalex.org/W4241108585","https://openalex.org/W4283661811","https://openalex.org/W4310386991","https://openalex.org/W6903448843"],"related_works":["https://openalex.org/W4306999973","https://openalex.org/W4385571390","https://openalex.org/W7116864668","https://openalex.org/W4399714298","https://openalex.org/W4224251491","https://openalex.org/W7008993038","https://openalex.org/W4310263882","https://openalex.org/W4394714747","https://openalex.org/W4388894542","https://openalex.org/W4388627774"],"abstract_inverted_index":{"This":[0],"work":[1],"introduces":[2],"a":[3,122],"novel":[4],"three-class":[5],"annotation":[6],"scheme":[7],"for":[8],"text-based":[9],"dementia":[10,36,76],"classification":[11],"in":[12,43,73],"patients,":[13],"based":[14],"on":[15,61,81,90],"their":[16],"recorded":[17],"visit":[18],"interactions.Multiple":[19],"models":[20,59],"were":[21,29,108],"developed":[22],"utilising":[23],"BERT,":[24],"RoBERTa":[25],"and":[26,48,55,86,101],"Dis-tilBERT.Two":[27],"approaches":[28],"employed":[30],"to":[31,120],"improve":[32],"the":[33,39,44,50,53,68,75,78,82,87,91],"representation":[34],"of":[35,125],"samples:":[37],"oversampling":[38],"underrepresented":[40],"data":[41],"points":[42],"original":[45],"Pitt":[46,51,65,84],"dataset":[47,66,70,85,93],"combining":[49],"with":[52,97],"Holland":[54],"Kempler":[56],"datasets.The":[57],"DistilBERT":[58],"trained":[60,80,89],"either":[62],"an":[63],"oversampled":[64,83],"or":[67],"combined":[69,92],"performed":[71],"best":[72],"classifying":[74],"class.Specifically,":[77],"model":[79],"one":[88],"obtained":[94],"stateof-the-art":[95],"performance":[96],"98.8%":[98],"overall":[99],"accuracy":[100],"98.6%":[102],"macro-averaged":[103],"F1-score,":[104],"respectively.The":[105],"models'":[106],"outputs":[107],"manually":[109],"inspected":[110],"through":[111],"saliency":[112],"highlighting,":[113],"using":[114],"Local":[115],"Interpretable":[116],"Model-agnostic":[117],"Explanations":[118],"(LIME),":[119],"provide":[121],"better":[123],"understanding":[124],"its":[126],"predictions.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-08-05T00:00:00"}