{"id":"https://openalex.org/W7126081982","doi":"https://doi.org/10.1109/bibm66473.2025.11356968","title":"Asymmetric Performance Profiling Using Foundation Models: Quantifying Reliability and Expert Capability in Medical AI","display_name":"Asymmetric Performance Profiling Using Foundation Models: Quantifying Reliability and Expert Capability in Medical AI","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126081982","doi":"https://doi.org/10.1109/bibm66473.2025.11356968"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124226265","display_name":"Mingzhi Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingzhi Xu","raw_affiliation_strings":["NJUST,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"NJUST,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tingting Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Yang","raw_affiliation_strings":["NJUST,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"NJUST,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124285425","display_name":"Tao Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhou","raw_affiliation_strings":["NJUST,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"NJUST,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073010231","display_name":"Qiang Chen","orcid":"https://orcid.org/0000-0002-6685-2447"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Chen","raw_affiliation_strings":["NJUST,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"NJUST,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124225933","display_name":"Shuo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156766","display_name":"Shanghai Cell Therapy Research Institute","ror":"https://ror.org/044ef5h76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210156766"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Wang","raw_affiliation_strings":["FDU,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"FDU,Shanghai,China","institution_ids":["https://openalex.org/I4210156766"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101959000","display_name":"Yizhe Zhang","orcid":"https://orcid.org/0000-0002-9599-7995"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhe Zhang","raw_affiliation_strings":["NJUST,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"NJUST,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5124226265"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67787436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1903","last_page":"1908"},"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":0.4999000132083893,"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":0.4999000132083893,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.1679999977350235,"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":0.08470000326633453,"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/reliability","display_name":"Reliability (semiconductor)","score":0.6489999890327454},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.4997999966144562},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.4932999908924103},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.44690001010894775},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4043000042438507},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3837999999523163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6937000155448914},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6489999890327454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5299000144004822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5055999755859375},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.4932999908924103},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4713999927043915},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.45969998836517334},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3837999999523163},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2888000011444092}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2194775991","https://openalex.org/W2296073425","https://openalex.org/W2592905743","https://openalex.org/W2806530968","https://openalex.org/W2884436604","https://openalex.org/W2885343725","https://openalex.org/W2908201961","https://openalex.org/W2963351448","https://openalex.org/W2963516811","https://openalex.org/W2980998394","https://openalex.org/W2982381022","https://openalex.org/W3011721937","https://openalex.org/W3014974815","https://openalex.org/W3094502228","https://openalex.org/W3095948197","https://openalex.org/W3111521801","https://openalex.org/W3131500599","https://openalex.org/W3165215947","https://openalex.org/W3216149514","https://openalex.org/W4302009288","https://openalex.org/W4390874575","https://openalex.org/W4392817990","https://openalex.org/W4392883923"],"related_works":[],"abstract_inverted_index":{"In":[0],"safety-critical":[1],"domains":[2],"like":[3],"medical":[4,137],"imaging,":[5],"where":[6],"diagnostic":[7],"errors":[8,114],"have":[9],"severe":[10],"consequences,":[11],"AI":[12],"models":[13,79],"must":[14,23],"be":[15],"evaluated":[16],"beyond":[17],"average":[18],"accuracy.":[19],"A":[20],"trustworthy":[21],"model":[22,96],"demonstrate":[24],"two":[25],"distinct":[26],"virtues:":[27],"high":[28,35,64],"reliability":[29,152],"on":[30,38,136],"common,":[31],"easy":[32,60],"cases":[33],"and":[34,104,144,154],"expert":[36],"capability":[37],"challenging,":[39],"ambiguous,":[40],"or":[41],"rare":[42],"cases.":[43],"Conventional":[44],"aggregate":[45],"metrics":[46,99],"fail":[47],"to":[48,132,158],"distinguish":[49],"between":[50],"these,":[51],"masking":[52],"a":[53,75],"model's":[54],"fatal":[55],"flaw-such":[56],"as":[57],"misclassifying":[58],"an":[59,81],"case-by":[61],"rewarding":[62,122],"its":[63],"volume":[65],"of":[66],"trivial":[67],"successes.":[68,124],"We":[69],"present":[70],"Hardness-Aware":[71],"Model":[72],"Evaluation":[73],"(HaME),":[74],"framework":[76],"that":[77,148],"assesses":[78],"using":[80,97],"asymmet-ric":[82],"cost-benefit":[83],"analysis.":[84],"HaME":[85,149],"identifies":[86],"challenging":[87],"instances":[88],"via":[89],"foundation":[90],"models,":[91],"then":[92],"evaluates":[93],"the":[94,105,127],"target":[95],"novel":[98],"(HaPrecision,":[100],"HaRecall,":[101],"HaFt,":[102],"HaAUC)":[103],"Brittleness":[106],"Gap":[107],"(B-Gap).":[108],"Our":[109],"formulation":[110],"uniquely":[111],"penalizes":[112],"\u201ceasy\u201d":[113],"far":[115],"more":[116],"than":[117],"\u201chard\u201d":[118,123],"failures,":[119],"while":[120],"simultaneously":[121],"This":[125],"shifts":[126],"evaluation":[128],"from":[129],"\u201cav-erage":[130],"performance\u201d":[131],"\u201cclinical":[133],"trustworthiness.\u201d":[134],"Experiments":[135],"image":[138],"classification":[139],"(Dermatology,":[140],"Pneumonia,":[141],"Retinal":[142],"OCT)":[143],"segmentation":[145],"(Nuclei)":[146],"reveal":[147],"uncovers":[150],"critical":[151],"gaps":[153],"expert-level":[155],"specializations":[156],"invisible":[157],"standard":[159],"metrics.":[160]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2026-01-30T00:00:00"}