{"id":"W4417028090","doi":"10.48550/arxiv.2512.03339","title":"ProtoEFNet: Dynamic Prototype Learning for Inherently Interpretable Ejection Fraction Estimation in Echocardiography","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Cardiovascular Function and Risk Factors","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; Danmarks Tekniske Universitet","keywords":"Discriminative model; Metric (unit); Process (computing); Fraction (chemistry); Reliability (semiconductor); Pattern recognition (psychology); Domain (mathematical analysis); Deep learning; Interpretability","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":[0.001031014,0.00113806,0.0007049557,0.0006618447,0.0002488419,0.0008477455,0.001953061,0.001574959,0.003191893],"category_scores_gemma":[0.005018278,0.0004762468,0.0006684226,0.0004565765,0.0004749792,0.001560497,0.001377868,0.001622554,0.001214036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006522773,"about_ca_system_score_gemma":0.0007605684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004551484,"about_ca_topic_score_gemma":0.007024952,"domain_scores_codex":[0.9995989,0.00009352555,0.00001781998,0.0001722607,0.00007139709,0.00004611744],"domain_scores_gemma":[0.9993768,0.0003135513,0.00005211407,0.0001162663,0.00009517729,0.00004611977],"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":[0.0007472205,0.0002855417,0.004917711,0.000369374,0.0001518227,0.00041875,0.000187744,0.2356144,0.01276557,0.007282101,0.04417173,0.6930881],"study_design_scores_gemma":[0.00004319393,0.00009636972,0.0005875719,0.00003416511,0.00001396603,0.0001507455,0.00002039948,0.9859903,0.003433672,0.006832246,0.002781017,0.00001639638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07163188,0.002301791,0.9032558,0.0009966005,0.0003677077,0.0001780188,0.003543872,0.0149463,0.002778024],"genre_scores_gemma":[0.6470128,0.001111512,0.333584,0.0008677942,0.000231187,0.0003918995,0.01000759,0.0009227377,0.005870538],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004551484,"threshold_uncertainty_score":0.01067793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01974758923370642,"score_gpt":0.2983205586458357,"score_spread":0.2785729694121293,"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."}}