{"id":"https://openalex.org/W4382632456","doi":"https://doi.org/10.3233/shti230545","title":"Implementing Informative-Based Active Learning in Biomedical Record Linkage for the Splink Package in Python","display_name":"Implementing Informative-Based Active Learning in Biomedical Record Linkage for the Splink Package in Python","publication_year":2023,"publication_date":"2023-06-29","ids":{"openalex":"https://openalex.org/W4382632456","doi":"https://doi.org/10.3233/shti230545","pmid":"https://pubmed.ncbi.nlm.nih.gov/37387079"},"language":"en","primary_location":{"id":"doi:10.3233/shti230545","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/shti230545","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230545","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230545","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086979438","display_name":"Marko Miletic","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marko Miletic","raw_affiliation_strings":["Bern University of Appl. Sciences, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bern University of Appl. Sciences, Switzerland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021788298","display_name":"Murat Sariyar","orcid":"https://orcid.org/0000-0002-5595-689X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Murat Sariyar","raw_affiliation_strings":["Bern University of Appl. Sciences, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bern University of Appl. Sciences, Switzerland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021788298"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0242,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78230375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"305","issue":null,"first_page":"509","last_page":"512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9948999881744385,"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":0.9948999881744385,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9835000038146973,"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":0.9696000218391418,"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":0.80131995677948},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7882452607154846},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7239752411842346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5742149949073792},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5332175493240356},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5272173881530762},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.5141911506652832},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44844985008239746},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.4448186457157135},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14644762873649597},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.07022812962532043},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06861329078674316},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.06365680694580078}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.80131995677948},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7882452607154846},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7239752411842346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5742149949073792},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5332175493240356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5272173881530762},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.5141911506652832},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44844985008239746},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.4448186457157135},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14644762873649597},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.07022812962532043},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06861329078674316},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.06365680694580078},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011356","descriptor_name":"Product Labeling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011356","descriptor_name":"Product Labeling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011356","descriptor_name":"Product Labeling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018794","descriptor_name":"Problem-Based Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018794","descriptor_name":"Problem-Based Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018794","descriptor_name":"Problem-Based Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.3233/shti230545","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/shti230545","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230545","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:37387079","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37387079","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":"Studies in health technology and informatics","raw_type":null},{"id":"pmh:oai:arbor.bfh.ch:20913","is_oa":true,"landing_page_url":"https://arbor.bfh.ch/20913/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922806","display_name":"ARBOR - Bern University of Applied Sciences Repository","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Miletic, Marko; Sariyar, Murat (2023). Implementing Informative-Based Active Learning in Biomedical Record Linkage for the Splink Package in Python Studies in Health Technology and Informatics, 305, pp. 509-512. Amsterdam: IOS Press 10.3233/SHTI230545 <http://dx.doi.org/10.3233/SHTI230545>","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.3233/shti230545","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/shti230545","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230545","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382632456.pdf","grobid_xml":"https://content.openalex.org/works/W4382632456.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1724849505","https://openalex.org/W1968200975","https://openalex.org/W2019150658","https://openalex.org/W2775078427","https://openalex.org/W2794286494","https://openalex.org/W2956919901","https://openalex.org/W3014074327","https://openalex.org/W3121361745","https://openalex.org/W3208204807","https://openalex.org/W6637434932"],"related_works":["https://openalex.org/W2487032012","https://openalex.org/W2211355040","https://openalex.org/W2808916796","https://openalex.org/W2176311362","https://openalex.org/W1501601012","https://openalex.org/W3088855600","https://openalex.org/W3012491082","https://openalex.org/W3211905090","https://openalex.org/W2178148352","https://openalex.org/W1936317645"],"abstract_inverted_index":{"In":[0,79,124],"biomedical":[1],"record":[2],"linkage,":[3],"efficient":[4,40],"determination":[5],"of":[6,14,50,52,136],"a":[7,48,57,86,91],"threshold":[8],"to":[9,23,37,73,81],"decide":[10],"at":[11],"which":[12],"level":[13],"similarity":[15],"two":[16,129],"records":[17],"should":[18,65],"be":[19,67,74],"classified":[20],"as":[21,133],"belonging":[22],"the":[24,97,101,109,113,122,134],"same":[25,110],"patient":[26],"is":[27,72,93],"frequently":[28],"still":[29],"an":[30,39],"open":[31],"issue.":[32],"Here,":[33],"we":[34],"describe":[35],"how":[36,89],"implement":[38],"active":[41,63,83],"learning":[42,64,84],"strategy":[43],"that":[44,62],"puts":[45],"into":[46,96],"practice":[47],"measure":[49],"usefulness":[51],"training":[53,70],"sets":[54],"for":[55],"such":[56,143],"task.":[58],"Our":[59],"results":[60],"show":[61],"always":[66,106],"considered":[68],"when":[69],"data":[71,126],"produced":[75],"via":[76],"manual":[77],"labeling.":[78],"addition":[80],"that,":[82],"gives":[85],"quick":[87],"indication":[88],"complex":[90],"problem":[92],"by":[94],"looking":[95],"label":[98],"frequencies:":[99],"If":[100],"most":[102],"difficult":[103],"entities":[104],"are":[105,131,140],"stemming":[107],"from":[108],"class,":[111],"then":[112],"classifier":[114],"will":[115],"probably":[116],"have":[117],"less":[118],"problems":[119,135],"in":[120,142],"distinguishing":[121],"classes.":[123],"big":[125],"applications,":[127],"these":[128],"properties":[130],"essential,":[132],"under-":[137],"and":[138],"overfitting":[139],"exacerbated":[141],"contexts.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}