{"id":"W4387211816","doi":"10.1007/978-3-031-43987-2_36","title":"ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vancouver General Hospital; University of British Columbia","funders":"","keywords":"Interpretability; Computer science; Ambiguity; Artificial intelligence; Data mining; Stenosis; Set (abstract data type); Machine learning; Radiology; Medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001670957,0.001125394,0.001187342,0.0009849825,0.0004589311,0.002571631,0.003301005,0.001888601,0.009488675],"category_scores_gemma":[0.005763945,0.0008624734,0.001089193,0.0007708942,0.0007301985,0.002573966,0.002351019,0.001765452,0.004053348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006453607,"about_ca_system_score_gemma":0.0007868051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003049152,"about_ca_topic_score_gemma":0.004453795,"domain_scores_codex":[0.9990215,0.00019171,0.0000826832,0.0003010159,0.0003345209,0.00006859687],"domain_scores_gemma":[0.9985442,0.0007450398,0.00006954613,0.0002623872,0.0002927169,0.00008615838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00104705,0.0001614836,0.001175686,0.0004634904,0.0001241871,0.000408324,0.0003853213,0.06270705,0.01362512,0.02055802,0.05463282,0.8447114],"study_design_scores_gemma":[0.00006217526,0.0001316137,0.0005414793,0.0001499435,0.00004899695,0.0004530757,0.0001143887,0.9153121,0.01436326,0.03534965,0.03342684,0.00004651794],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0116322,0.0009678489,0.9570993,0.0003384863,0.0003841805,0.0001463712,0.001887368,0.0242084,0.003335751],"genre_scores_gemma":[0.1450214,0.0007370161,0.8406192,0.0003099508,0.0001684931,0.000301976,0.004805122,0.002074093,0.005962679],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009488675,"threshold_uncertainty_score":0.03174275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02089493254371085,"score_gpt":0.3202118410632651,"score_spread":0.2993169085195542,"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."}}