{"id":"https://openalex.org/W4403079665","doi":"https://doi.org/10.3389/frai.2024.1374162","title":"Modeling disagreement in automatic data labeling for semi-supervised learning in Clinical Natural Language Processing","display_name":"Modeling disagreement in automatic data labeling for semi-supervised learning in Clinical Natural Language Processing","publication_year":2024,"publication_date":"2024-10-02","ids":{"openalex":"https://openalex.org/W4403079665","doi":"https://doi.org/10.3389/frai.2024.1374162","pmid":"https://pubmed.ncbi.nlm.nih.gov/39415941"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2024.1374162","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1374162","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1374162/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1374162/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084211150","display_name":"Liu Hongshu","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hongshu Liu","raw_affiliation_strings":["Department of Computing, Imperial College London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067213867","display_name":"Nabeel Seedat","orcid":"https://orcid.org/0000-0002-2134-6639"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nabeel Seedat","raw_affiliation_strings":["Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021442709","display_name":"Julia Ive","orcid":"https://orcid.org/0000-0002-3931-3392"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Julia Ive","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021442709"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":{"value":1150,"currency":"USD","value_usd":1150},"apc_paid":{"value":1150,"currency":"USD","value_usd":1150},"fwci":0.2212,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58389467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"7","issue":null,"first_page":"1374162","last_page":"1374162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.5360999703407288,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.5360999703407288,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.19419999420642853,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.05900000035762787,"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/overfitting","display_name":"Overfitting","score":0.7831907272338867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7322819232940674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.677960991859436},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6586509943008423},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6243199110031128},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5601783990859985},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4504009485244751},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4240036606788635},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42142462730407715},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3821565508842468},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11983495950698853},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.11201003193855286}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7831907272338867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322819232940674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.677960991859436},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6586509943008423},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6243199110031128},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5601783990859985},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4504009485244751},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4240036606788635},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42142462730407715},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3821565508842468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11983495950698853},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.11201003193855286},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3389/frai.2024.1374162","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1374162","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1374162/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmid:39415941","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39415941","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in artificial intelligence","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11480042","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11480042","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11480042/pdf/frai-07-1374162.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Artif Intell","raw_type":"Text"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/375007","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/375007","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/868ec15f-a01a-43dd-807d-345c7897fd53/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:2ccf7ce269684cfdb6d56eb8e3a88616","is_oa":true,"landing_page_url":"https://doaj.org/article/2ccf7ce269684cfdb6d56eb8e3a88616","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 7 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/frai.2024.1374162","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1374162","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1374162/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403079665.pdf"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W137285897","https://openalex.org/W1591346633","https://openalex.org/W1959608418","https://openalex.org/W2069266605","https://openalex.org/W2101234009","https://openalex.org/W2159583324","https://openalex.org/W2185068657","https://openalex.org/W2515248967","https://openalex.org/W2626967530","https://openalex.org/W2753141617","https://openalex.org/W2778310824","https://openalex.org/W2784499877","https://openalex.org/W2799103635","https://openalex.org/W2911964244","https://openalex.org/W2913668833","https://openalex.org/W2948194985","https://openalex.org/W2951965145","https://openalex.org/W2963466845","https://openalex.org/W2995225687","https://openalex.org/W3014596384","https://openalex.org/W3024147601","https://openalex.org/W3042806674","https://openalex.org/W3046605870","https://openalex.org/W3098949126","https://openalex.org/W3103323619","https://openalex.org/W3134774296","https://openalex.org/W3197365868","https://openalex.org/W4254181784","https://openalex.org/W4310895557","https://openalex.org/W4386441078","https://openalex.org/W6605566567","https://openalex.org/W6639724578","https://openalex.org/W6640425456","https://openalex.org/W6640963894","https://openalex.org/W6675354045","https://openalex.org/W6686522446","https://openalex.org/W6730042731","https://openalex.org/W6739651123","https://openalex.org/W6747014089","https://openalex.org/W6747741389","https://openalex.org/W6763087592","https://openalex.org/W6767678101","https://openalex.org/W6769748853","https://openalex.org/W6780820450"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W2368237856"],"abstract_inverted_index":{"Introduction:":[0],"Computational":[1],"models":[2,62,133],"providing":[3],"accurate":[4],"estimates":[5,54],"of":[6,52,58,67,99,131],"their":[7],"uncertainty":[8,53,101],"are":[9,28],"crucial":[10],"for":[11,77,145],"risk":[12],"management":[13],"associated":[14],"with":[15],"decision-making":[16],"in":[17,70,81,95],"healthcare":[18,83],"contexts.":[19],"This":[20,73],"is":[21],"especially":[22],"true":[23],"since":[24],"many":[25],"state-of-the-art":[26,60],"systems":[27],"trained":[29],"using":[30],"the":[31,50,65,82,97,105,129],"data":[32],"which":[33],"have":[34],"been":[35],"labeled":[36],"automatically":[37],"(self-supervised":[38],"mode)":[39],"and":[40,113,138],"tend":[41],"to":[42,64,135],"overfit.":[43],"Methods:":[44],"In":[45],"this":[46],"study,":[47],"we":[48],"investigate":[49],"quality":[51],"from":[55],"a":[56],"range":[57],"current":[59],"predictive":[61,108,123],"applied":[63,134],"problem":[66,74],"observation":[68],"detection":[69],"radiology":[71],"reports.":[72],"remains":[75],"understudied":[76],"Natural":[78,146],"Language":[79,147],"Processing":[80,148],"domain.":[84],"Results:":[85],"We":[86],"demonstrate":[87],"that":[88,139],"Gaussian":[89],"Processes":[90],"(GPs)":[91],"provide":[92,143],"superior":[93],"performance":[94],"quantifying":[96],"risks":[98],"three":[100],"labels":[102,137],"based":[103,150],"on":[104],"negative":[106],"log":[107],"probability":[109],"(NLPP)":[110],"evaluation":[111],"metric":[112],"mean":[114],"maximum":[115],"predicted":[116],"confidence":[117],"levels":[118],"(MMPCL),":[119],"whilst":[120],"retaining":[121],"strong":[122],"performance.":[124],"Discussion:":[125],"Our":[126],"conclusions":[127],"highlight":[128],"utility":[130,144],"probabilistic":[132],"\"noisy\"":[136],"similar":[140],"methods":[141],"could":[142],"(NLP)":[149],"automated":[151],"labeling":[152],"tasks.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}