{"id":"https://openalex.org/W4396777533","doi":"https://doi.org/10.48550/arxiv.2405.01682","title":"Leveraging Prompt-Learning for Structured Information Extraction from Crohn's Disease Radiology Reports in a Low-Resource Language","display_name":"Leveraging Prompt-Learning for Structured Information Extraction from Crohn's Disease Radiology Reports in a Low-Resource Language","publication_year":2024,"publication_date":"2024-05-02","ids":{"openalex":"https://openalex.org/W4396777533","doi":"https://doi.org/10.48550/arxiv.2405.01682"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2405.01682","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.01682","pdf_url":"https://arxiv.org/pdf/2405.01682","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.01682","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021187095","display_name":"Liam Hazan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hazan, Liam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085773612","display_name":"Gili Focht","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Focht, Gili","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093775918","display_name":"Naama Gavrielov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gavrielov, Naama","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054952724","display_name":"Roi Reichart","orcid":"https://orcid.org/0000-0001-6918-0554","observed_orcids":["https://orcid.org/0000-0001-6918-0554"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reichart, Roi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097111482","display_name":"Talar Hagopian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hagopian, Talar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049059939","display_name":"Mary\u2010Louise C. Greer","orcid":"https://orcid.org/0000-0001-6159-5472","observed_orcids":["https://orcid.org/0000-0001-6159-5472"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Greer, Mary-Louise C.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110336293","display_name":"Ruth Cytter Kuint","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuint, Ruth Cytter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084520591","display_name":"Dan Turner","orcid":"https://orcid.org/0000-0001-5160-868X","observed_orcids":["https://orcid.org/0000-0001-5160-868X","https://orcid.org/0000-0001-9661-0070","https://orcid.org/0000-0002-3704-3325"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Turner, Dan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089641146","display_name":"Moti Freiman","orcid":"https://orcid.org/0000-0003-1083-1548","observed_orcids":["https://orcid.org/0000-0003-1083-1548"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Freiman, Moti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.5156000256538391,"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":0.5156000256538391,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.29739999771118164,"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":0.10819999873638153,"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/prompt-learning","display_name":"prompt learning","score":0.9020000100135803},{"id":"https://openalex.org/keywords/structured-information-extraction","display_name":"structured data extraction","score":0.8830000162124634},{"id":"https://openalex.org/keywords/radiology-reports","display_name":"radiology reports","score":0.8799999952316284},{"id":"https://openalex.org/keywords/crohn-s-disease","display_name":"Crohn's disease","score":0.9990000128746033},{"id":"https://openalex.org/keywords/hebrew","display_name":"Hebrew language","score":0.871999979019165},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.9950000047683716},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.7820000052452087},{"id":"https://openalex.org/keywords/medical-report-summarization","display_name":"medical report summarization","score":0.37700000405311584},{"id":"https://openalex.org/keywords/patient-privacy","display_name":"patient privacy","score":0.6169999837875366}],"concepts":[{"id":"https://openalex.org/C2779280984","wikidata":"https://www.wikidata.org/wiki/Q1472","display_name":"Crohn's disease","level":3,"score":0.6395313739776611},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5557672381401062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.532865047454834},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.48560208082199097},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.4720783233642578},{"id":"https://openalex.org/C2987496018","wikidata":"https://www.wikidata.org/wiki/Q1860","display_name":"English language","level":2,"score":0.44796374440193176},{"id":"https://openalex.org/C2992200296","wikidata":"https://www.wikidata.org/wiki/Q1472","display_name":"Crohn disease","level":4,"score":0.4419211447238922},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.42606085538864136},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.4106549620628357},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3318617641925812},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28443002700805664},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.27683982253074646},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.1808171272277832},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1536746621131897},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2405.01682","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.01682","pdf_url":"https://arxiv.org/pdf/2405.01682","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2405.01682","doi":"https://doi.org/10.48550/arxiv.2405.01682","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.01682","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.01682","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.01682","pdf_url":"https://arxiv.org/pdf/2405.01682","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.5683000087738037,"id":"https://metadata.un.org/sdg/3"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2436073988","https://openalex.org/W2066293742","https://openalex.org/W3214521508","https://openalex.org/W2085446880","https://openalex.org/W1987189293","https://openalex.org/W2079214423","https://openalex.org/W2434653209","https://openalex.org/W4281781548","https://openalex.org/W2399201492","https://openalex.org/W1577352824"],"abstract_inverted_index":{"Automatic":[0],"conversion":[1],"of":[2,63,88,101],"free-text":[3],"radiology":[4,104],"reports":[5,89,105],"into":[6],"structured":[7,86],"data":[8,73],"using":[9],"Natural":[10],"Language":[11],"Processing":[12],"(NLP)":[13],"techniques":[14],"is":[15,57],"crucial":[16],"for":[17,26,142],"analyzing":[18],"diseases":[19],"on":[20],"a":[21,71,78,98],"large":[22,35],"scale.":[23],"While":[24],"effective":[25],"tasks":[27],"in":[28,106,120,123],"widely":[29],"spoken":[30],"languages":[31,44],"like":[32],"English,":[33],"generative":[34],"language":[36],"models":[37,56],"(LLMs)":[38],"typically":[39],"underperform":[40],"with":[41],"less":[42],"common":[43],"and":[45,111],"can":[46],"pose":[47],"potential":[48],"risks":[49],"to":[50,90],"patient":[51],"privacy.":[52],"Fine-tuning":[53],"local":[54],"NLP":[55],"hindered":[58],"by":[59],"the":[60,85],"skewed":[61],"nature":[62,87],"real-world":[64],"medical":[65],"datasets,":[66],"where":[67],"rare":[68],"findings":[69],"represent":[70],"significant":[72],"imbalance.":[74],"We":[75],"introduce":[76],"SMP-BERT,":[77],"novel":[79],"prompt":[80],"learning":[81],"method":[82],"that":[83],"leverages":[84],"overcome":[91],"these":[92],"challenges.":[93],"In":[94],"our":[95],"studies":[96],"involving":[97],"substantial":[99],"collection":[100],"Crohn's":[102],"disease":[103],"Hebrew":[107],"(over":[108],"8,000":[109],"patients":[110],"10,000":[112],"reports),":[113],"SMP-BERT":[114,135],"greatly":[115],"surpassed":[116],"traditional":[117],"fine-tuning":[118],"methods":[119],"performance,":[121],"notably":[122],"detecting":[124],"infrequent":[125],"conditions":[126],"(AUC:":[127],"0.99":[128],"vs":[129,133],"0.94,":[130],"F1:":[131],"0.84":[132],"0.34).":[134],"empowers":[136],"more":[137],"accurate":[138],"AI":[139],"diagnostics":[140],"available":[141],"low-resource":[143],"languages.":[144]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}