{"id":"https://openalex.org/W4403443376","doi":"https://doi.org/10.48550/arxiv.2408.04121","title":"Can Rule-Based Insights Enhance LLMs for Radiology Report Classification? Introducing the RadPrompt Methodology","display_name":"Can Rule-Based Insights Enhance LLMs for Radiology Report Classification? Introducing the RadPrompt Methodology","publication_year":2024,"publication_date":"2024-08-07","ids":{"openalex":"https://openalex.org/W4403443376","doi":"https://doi.org/10.48550/arxiv.2408.04121"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2408.04121","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.04121","pdf_url":"https://arxiv.org/pdf/2408.04121","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.04121","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033949287","display_name":"Panagiotis Fytas","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fytas, Panagiotis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044865557","display_name":"Anna Breger","orcid":"https://orcid.org/0000-0001-8878-5743"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Breger, Anna","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065644254","display_name":"Ian Selby","orcid":"https://orcid.org/0000-0003-4244-8893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Selby, Ian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061943510","display_name":"Simon Baker","orcid":"https://orcid.org/0000-0002-0716-6236"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baker, Simon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098954554","display_name":"Shahab Shahipasand","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shahipasand, Shahab","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081393566","display_name":"Anna Korhonen","orcid":"https://orcid.org/0000-0002-3692-3144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Korhonen, Anna","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5033949287"],"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/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9621000289916992,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9361000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.40012407302856445},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3245250880718231}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40012407302856445},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3245250880718231}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2408.04121","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.04121","pdf_url":"https://arxiv.org/pdf/2408.04121","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2408.04121","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.04121","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.04121","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.04121","pdf_url":"https://arxiv.org/pdf/2408.04121","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4403443376.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","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","https://openalex.org/W4402327032"],"abstract_inverted_index":{"Developing":[0],"imaging":[1],"models":[2],"capable":[3],"of":[4,44,91,113,142],"detecting":[5],"pathologies":[6],"from":[7,29,166],"chest":[8],"X-rays":[9],"can":[10],"be":[11],"cost":[12],"and":[13,161],"time-prohibitive":[14],"for":[15,54],"large":[16,114],"datasets":[17],"as":[18,34,42],"it":[19],"requires":[20],"supervision":[21,36],"to":[22,68,107],"attain":[23],"state-of-the-art":[24],"performance.":[25,94],"Instead,":[26],"labels":[27],"extracted":[28],"radiology":[30],"reports":[31],"may":[32],"serve":[33],"distant":[35],"since":[37],"these":[38,73],"are":[39,63],"routinely":[40],"generated":[41],"part":[43],"clinical":[45],"practice.":[46],"Despite":[47],"their":[48,66],"widespread":[49],"use,":[50],"current":[51],"rule-based":[52,79,145],"methods":[53,151],"label":[55],"extraction":[56],"rely":[57],"on":[58,152],"extensive":[59],"rule":[60],"sets":[61],"that":[62,81,104],"limited":[64],"in":[65,122],"robustness":[67],"syntactic":[69],"variability.":[70],"To":[71],"alleviate":[72],"limitations,":[74],"we":[75,96],"introduce":[76],"RadPert,":[77],"a":[78,88,100,118,162],"system":[80],"integrates":[82],"an":[83],"uncertainty-aware":[84],"information":[85],"schema":[86],"with":[87,144],"streamlined":[89],"set":[90,160],"rules,":[92],"enhancing":[93],"Additionally,":[95],"have":[97,148],"developed":[98],"RadPrompt,":[99],"multi-turn":[101],"prompting":[102],"strategy":[103],"leverages":[105],"RadPert":[106],"bolster":[108],"the":[109,139,156,167],"zero-shot":[110],"predictive":[111],"capabilities":[112],"language":[115],"models,":[116,137],"achieving":[117],"statistically":[119],"significant":[120],"improvement":[121],"weighted":[123],"average":[124],"F1":[125],"score":[126],"over":[127],"GPT-4":[128],"Turbo.":[129],"Most":[130],"notably,":[131],"RadPrompt":[132],"surpasses":[133],"both":[134],"its":[135],"underlying":[136],"showcasing":[138],"synergistic":[140],"potential":[141],"LLMs":[143],"models.":[146],"We":[147],"evaluated":[149],"our":[150],"two":[153],"English":[154],"Corpora:":[155],"MIMIC-CXR":[157],"gold-standard":[158,163],"test":[159],"dataset":[164],"collected":[165],"Cambridge":[168],"University":[169],"Hospitals.":[170]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}