{"id":"W4410578433","doi":"10.1016/j.acra.2025.04.068","title":"Right Ventricular Strain as a Key Feature in Interpretable Machine Learning for Identification of Takotsubo Syndrome: A Multicenter CMR-based Study","year":2025,"lang":"en","type":"article","venue":"Academic Radiology","topic":"Takotsubo Cardiomyopathy and Associated Phenomena","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Circle Cardiovascular Imaging","funders":"","keywords":"Takotsubo syndrome; Identification (biology); Key (lock); Feature (linguistics); Strain (injury); Multicenter study; Cardiology; Psychology; Medicine; Internal medicine; Computer science; Artificial intelligence; Cardiomyopathy; Heart failure; Computer security; Randomized controlled trial; Philosophy; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001087148,0.0001943007,0.0006966351,0.0008080456,0.00006071251,0.000006144773,0.0002026843,0.0003827537,0.00002312498],"category_scores_gemma":[0.0008394296,0.0001736444,0.0001691893,0.0008574497,0.00005932398,0.00006033396,0.0000381978,0.001009597,0.000006229556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001771465,"about_ca_system_score_gemma":0.0001129257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006890773,"about_ca_topic_score_gemma":0.00001008761,"domain_scores_codex":[0.9981042,0.0003661157,0.0006173033,0.0004197448,0.0001418739,0.000350754],"domain_scores_gemma":[0.9989862,0.0003325592,0.0002946316,0.000241763,0.00008429852,0.00006058393],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001687659,0.0008753078,0.946463,0.0004534458,0.0009683158,0.0004594455,0.002905471,0.002389684,0.04027977,0.0009441925,0.0009174712,0.001656223],"study_design_scores_gemma":[0.0273015,0.002551025,0.9118845,0.0009971495,0.001522824,0.0003459515,0.002864601,0.03141989,0.006698798,0.001860981,0.01193825,0.0006145154],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9927222,0.00234396,0.001289293,0.00143118,0.0002583425,0.001663834,0.00004589392,0.00004803304,0.0001972577],"genre_scores_gemma":[0.9980772,0.00005595498,0.0001185484,0.000312339,0.00004184605,0.00021443,0.0001847967,0.00001912015,0.0009757988],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0345785,"threshold_uncertainty_score":0.7081013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00719777346665672,"score_gpt":0.2829179259308121,"score_spread":0.2757201524641554,"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."}}