{"id":"W2913514091","doi":"10.22489/cinc.2018.374","title":"Effect of Segmentation Variation on ECG Imaging","year":2018,"lang":"en","type":"article","venue":"Computing in cardiology","topic":"Cardiovascular Function and Risk Factors","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Institutes of Health; Dalhousie University","keywords":"Torso; Segmentation; Surface (topology); Body surface; Medicine; Cardiology; Biomedical engineering; Artificial intelligence; Anatomy; Computer science; Mathematics; Geometry","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007527281,0.0000728658,0.0003107607,0.0001463567,0.00002960096,0.000002485959,0.00002557141,0.00005207406,0.00001069018],"category_scores_gemma":[0.000165044,0.00005871466,0.0001449063,0.000136526,0.00005991615,0.00001296665,0.00001964738,0.00009906111,0.00002514583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000701175,"about_ca_system_score_gemma":0.00001728446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002670527,"about_ca_topic_score_gemma":6.707018e-7,"domain_scores_codex":[0.9991856,0.0002721586,0.0001664732,0.0001651047,0.00009815283,0.0001124608],"domain_scores_gemma":[0.9995058,0.0002002879,0.00005303412,0.0001617744,0.00005558129,0.00002358464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002744909,0.00001169161,0.9040504,0.00004792819,0.0001112073,0.00001867722,0.0002597046,0.001524248,0.00752521,0.0000303222,0.000249041,0.08589713],"study_design_scores_gemma":[0.00212475,0.0008937197,0.9727116,0.00007454161,0.00009494916,0.0001300323,0.00003114013,0.01195911,0.01139254,0.00001051306,0.0005069072,0.00007022541],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9703344,0.00004809833,0.02583521,0.00004384238,0.001063019,0.0001913397,5.785616e-7,0.00003581779,0.002447666],"genre_scores_gemma":[0.9991356,0.000006266268,0.0002774641,0.00009165805,0.0004558966,0.000001751152,0.00001247386,0.000007906694,0.00001100532],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0858269,"threshold_uncertainty_score":0.2394315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008259012105069598,"score_gpt":0.2923652347676953,"score_spread":0.2841062226626257,"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."}}