{"id":"https://openalex.org/W4411902251","doi":"https://doi.org/10.3390/data10070104","title":"Extracting Information from Unstructured Medical Reports Written in Minority Languages: A Case Study of Finnish","display_name":"Extracting Information from Unstructured Medical Reports Written in Minority Languages: A Case Study of Finnish","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W4411902251","doi":"https://doi.org/10.3390/data10070104"},"language":"en","primary_location":{"id":"doi:10.3390/data10070104","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data10070104","pdf_url":"https://www.mdpi.com/2306-5729/10/7/104/pdf?version=1751334217","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2306-5729/10/7/104/pdf?version=1751334217","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118768196","display_name":"Elisa Myllyl\u00e4","orcid":null},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Elisa Myllyl\u00e4","raw_affiliation_strings":["Biomimetics and Intelligent Systems Group, University of Oulu, FI-90014 Oulu, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomimetics and Intelligent Systems Group, University of Oulu, FI-90014 Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069221764","display_name":"Pekka Siirtola","orcid":"https://orcid.org/0000-0002-5995-5421"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Pekka Siirtola","raw_affiliation_strings":["Biomimetics and Intelligent Systems Group, University of Oulu, FI-90014 Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0002-5995-5421","affiliations":[{"raw_affiliation_string":"Biomimetics and Intelligent Systems Group, University of Oulu, FI-90014 Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088287214","display_name":"Antti Isosalo","orcid":"https://orcid.org/0000-0002-5335-7535"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Antti Isosalo","raw_affiliation_strings":["Research Unit of Health Sciences and Technology, University of Oulu, FI-90014 Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0002-5335-7535","affiliations":[{"raw_affiliation_string":"Research Unit of Health Sciences and Technology, University of Oulu, FI-90014 Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070169373","display_name":"Jarmo Reponen","orcid":"https://orcid.org/0000-0003-2306-3111"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jarmo Reponen","raw_affiliation_strings":["Research Unit of Health Sciences and Technology, University of Oulu, FI-90014 Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0003-2306-3111","affiliations":[{"raw_affiliation_string":"Research Unit of Health Sciences and Technology, University of Oulu, FI-90014 Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083376430","display_name":"Satu Tamminen","orcid":"https://orcid.org/0000-0002-5215-6889"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Satu Tamminen","raw_affiliation_strings":["Biomimetics and Intelligent Systems Group, University of Oulu, FI-90014 Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0002-5215-6889","affiliations":[{"raw_affiliation_string":"Biomimetics and Intelligent Systems Group, University of Oulu, FI-90014 Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037796283","display_name":"Outi Laatikainen","orcid":"https://orcid.org/0000-0003-0208-5178"},"institutions":[{"id":"https://openalex.org/I2799272722","display_name":"Oulu University Hospital","ror":"https://ror.org/045ney286","country_code":"FI","type":"healthcare","lineage":["https://openalex.org/I2799272722"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Outi Laatikainen","raw_affiliation_strings":["Medical Research Center Oulu and Oulu University Hospital, FI-90014 Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0003-0208-5178","affiliations":[{"raw_affiliation_string":"Medical Research Center Oulu and Oulu University Hospital, FI-90014 Oulu, Finland","institution_ids":["https://openalex.org/I2799272722"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5069221764"],"corresponding_institution_ids":["https://openalex.org/I98381234"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17649026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"7","first_page":"104","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9872000217437744,"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":0.9872000217437744,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9832000136375427,"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/T10028","display_name":"Topic Modeling","score":0.9829000234603882,"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/linguistics","display_name":"Linguistics","score":0.4795491397380829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47232550382614136},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4460229277610779}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4795491397380829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47232550382614136},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4460229277610779},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/data10070104","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data10070104","pdf_url":"https://www.mdpi.com/2306-5729/10/7/104/pdf?version=1751334217","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:753f3338f1f943d8a14e0b5265151ae7","is_oa":true,"landing_page_url":"https://doaj.org/article/753f3338f1f943d8a14e0b5265151ae7","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data, Vol 10, Iss 7, p 104 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/data10070104","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data10070104","pdf_url":"https://www.mdpi.com/2306-5729/10/7/104/pdf?version=1751334217","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1824793925","display_name":"6G Flagship - 6G-Enabled Wireless Smart Society & Ecosystem","funder_award_id":"346208","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G2313824963","display_name":null,"funder_award_id":"220106","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G4621981016","display_name":null,"funder_award_id":"346208","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320336704","display_name":"Infotech Oulu","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411902251.pdf","grobid_xml":"https://content.openalex.org/works/W4411902251.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2082302018","https://openalex.org/W2087388117","https://openalex.org/W2604377373","https://openalex.org/W2768488789","https://openalex.org/W2772204177","https://openalex.org/W2995225687","https://openalex.org/W3211056521","https://openalex.org/W4229335055","https://openalex.org/W4252431150","https://openalex.org/W4313588675","https://openalex.org/W4386498855","https://openalex.org/W4402167740","https://openalex.org/W4402713323","https://openalex.org/W4404084763","https://openalex.org/W4405281002","https://openalex.org/W6761205521","https://openalex.org/W6875168887","https://openalex.org/W6903494891","https://openalex.org/W6903572575","https://openalex.org/W7025185836"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"the":[1,96,120,145,152,178,205,214,237,252],"era":[2],"of":[3,12,15,73,98,112,133,158,180],"digital":[4],"healthcare,":[5],"electronic":[6],"health":[7],"records":[8],"generate":[9],"vast":[10],"amounts":[11],"data,":[13],"much":[14],"which":[16,242],"is":[17,141],"unstructured,":[18],"and":[19,30,127,151,229,257],"therefore,":[20],"not":[21,202],"in":[22,47,138],"a":[23,49,68,166,225],"usable":[24],"format":[25],"for":[26,56,221,254,260],"conventional":[27],"machine":[28,53],"learning":[29,54],"artificial":[31],"intelligence":[32],"applications.":[33],"This":[34,176,216,250],"study":[35],"investigates":[36],"how":[37],"to":[38,144,210],"extract":[39],"meaningful":[40],"insights":[41],"from":[42,84,102,224],"unstructured":[43,62],"radiology":[44],"reports":[45,87,200],"written":[46,244],"Finnish,":[48],"minority":[50,187,261],"language,":[51],"using":[52,88],"techniques":[55],"text":[57],"analysis.":[58],"With":[59],"this":[60,74],"approach,":[61],"information":[63,79],"could":[64],"be":[65,81],"transformed":[66],"into":[67],"structured":[69],"format.":[70],"The":[71,135,156],"results":[72,157],"research":[75],"show":[76],"that":[77,193],"relevant":[78],"can":[80],"effectively":[82],"extracted":[83],"Finnish":[85,168,238],"medical":[86,103,181,248],"classification":[89],"algorithms":[90],"with":[91,119,164,186,263],"default":[92],"parameter":[93,194],"values.":[94],"For":[95],"detection":[97,140,206],"breast":[99,239],"tumour":[100],"mentions":[101],"texts,":[104],"classifiers":[105,160,173],"achieved":[106],"high":[107],"accuracy,":[108],"almost":[109],"90%.":[110],"Detection":[111],"metastasis":[113,139],"mentions,":[114],"however,":[115],"proved":[116],"more":[117,146],"challenging,":[118],"best-performing":[121],"models":[122],"Support":[123],"Vector":[124],"Machine":[125],"(SVM)":[126],"logistic":[128],"regression":[129],"achieving":[130],"an":[131],"F1-score":[132],"81%.":[134],"lower":[136],"performance":[137],"likely":[142,208],"due":[143,209],"complex":[147],"problem,":[148],"ambiguous":[149],"labeling,":[150],"smaller":[153],"dataset":[154,219],"size.":[155],"classical":[159,172],"were":[161],"also":[162],"compared":[163],"FinBERT,":[165],"domain-adapted":[167],"BERT":[169],"model.":[170],"However,":[171],"outperformed":[174],"FinBERT.":[175],"highlights":[177],"challenge":[179],"language":[182,235],"processing":[183],"when":[184],"working":[185],"languages.":[188],"Moreover,":[189],"it":[190],"was":[191],"noted":[192],"tuning":[195,222],"based":[196],"on":[197],"translated":[198,218],"English":[199],"did":[201],"significantly":[203],"improve":[204],"rates,":[207],"linguistic":[211],"differences":[212],"between":[213],"datasets.":[215],"larger":[217],"used":[220],"comes":[223],"different":[226],"clinical":[227],"domain":[228],"employs":[230],"noticeably":[231],"simpler,":[232],"less":[233],"nuanced":[234],"than":[236],"cancer":[240],"reports,":[241],"are":[243],"by":[245],"native":[246],"Finnish-speaking":[247],"experts.":[249],"underscores":[251],"need":[253],"localised":[255],"datasets":[256],"models,":[258],"particularly":[259],"languages":[262],"unique":[264],"grammatical":[265],"structures.":[266]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
