{"id":"W4385373779","doi":"10.48550/arxiv.2307.14433","title":"ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Interpretability; Computer science; Ambiguity; Data mining; Stenosis; Set (abstract data type); Code (set theory); Artificial intelligence; Machine learning; Medicine; Radiology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001842673,0.001563079,0.000955574,0.00118965,0.0005498328,0.001268993,0.002085686,0.002037577,0.002212271],"category_scores_gemma":[0.007271564,0.0006366058,0.0007619068,0.0005894107,0.0006060306,0.001763591,0.00196167,0.001601364,0.001152942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008512862,"about_ca_system_score_gemma":0.001030215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006301028,"about_ca_topic_score_gemma":0.009926249,"domain_scores_codex":[0.999112,0.0002260319,0.00005392971,0.0003466992,0.0001700024,0.000091415],"domain_scores_gemma":[0.9986455,0.0006223482,0.0001549607,0.0002110806,0.0002512675,0.0001148158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001831427,0.0004991353,0.01684864,0.0006638948,0.0003989703,0.0008410945,0.0005332086,0.2147216,0.01569691,0.005405684,0.0595881,0.6829713],"study_design_scores_gemma":[0.0000681828,0.0001606003,0.001580157,0.00008911705,0.00004502548,0.0002634314,0.00006785321,0.9785542,0.005935892,0.007899976,0.005299251,0.00003626182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2097546,0.005848476,0.7265484,0.002653451,0.001172179,0.0006367232,0.01054097,0.03513648,0.007708761],"genre_scores_gemma":[0.7380572,0.001018529,0.2423929,0.0009488031,0.000359002,0.0004089088,0.01090822,0.0006243886,0.005282202],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006301028,"threshold_uncertainty_score":0.01252866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07709850244935257,"score_gpt":0.2774047322015582,"score_spread":0.2003062297522056,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}