{"id":"W4412671417","doi":"10.1101/2025.07.24.25332108","title":"Deep Learning-Based Multi-View Echocardiographic Framework for Comprehensive Diagnosis of Pericardial Disease","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Pericarditis and Cardiac Tamponade","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Impact","funders":"Institute for Information and Communications Technology Promotion; National IT Industry Promotion Agency; Ministry of Science and ICT, South Korea; Ministerio de Economía y Competitividad","keywords":"Disease; Cardiology; Artificial intelligence; Deep learning; Internal medicine; Radiology; Medicine; Computer science","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":[0.0008324434,0.00117008,0.001119457,0.001553323,0.0002626257,0.000781737,0.001300485,0.001214805,0.001223688],"category_scores_gemma":[0.001401309,0.0003287742,0.0012545,0.0006528551,0.0002367291,0.0005453401,0.001047205,0.0009967178,0.0005165688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008281296,"about_ca_system_score_gemma":0.001158721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01405251,"about_ca_topic_score_gemma":0.01544012,"domain_scores_codex":[0.9995148,0.0001003379,0.00003729635,0.0001692261,0.00007826091,0.0001000795],"domain_scores_gemma":[0.9995938,0.0001220821,0.00004917636,0.00003666958,0.0001362794,0.00006188826],"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":[0.000536376,0.0004938025,0.03811487,0.0002770903,0.0004721007,0.000923923,0.0001215387,0.4562199,0.01390513,0.0024351,0.01524298,0.4712572],"study_design_scores_gemma":[0.00001254161,0.00003636386,0.001215609,0.00001439784,0.00003028859,0.00006612066,0.000008724454,0.9964179,0.0008187859,0.0008715552,0.0004999065,0.000007821101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2286708,0.006303357,0.7509022,0.001746897,0.0002007978,0.0002314009,0.004055996,0.004815745,0.003072912],"genre_scores_gemma":[0.8768393,0.0009995226,0.1131816,0.0007243626,0.0001657967,0.0001747442,0.005080189,0.00008149355,0.002753004],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01405251,"threshold_uncertainty_score":0.02794141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03608946718703795,"score_gpt":0.3264654751349176,"score_spread":0.2903760079478797,"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."}}