{"id":"W3093740639","doi":"10.22489/cinc.2020.128","title":"Multilabel 12-Lead Electrocardiogram Classification Using Gradient Boosting Tree Ensemble","year":2020,"lang":"en","type":"preprint","venue":"Computing in cardiology","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian VIGOUR Centre; University of Alberta","funders":"","keywords":"Gradient boosting; Boosting (machine learning); Random forest; Artificial intelligence; Decision tree; Pattern recognition (psychology); Computer science; Test set; Ensemble forecasting; Waveform; Tree (set theory); Set (abstract data type); Feature (linguistics); Ensemble learning; Machine learning; Data mining; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007260006,0.0004324661,0.001673426,0.0004437252,0.0001378306,0.00004110294,0.0002614295,0.0006040899,7.978323e-7],"category_scores_gemma":[0.0005488824,0.000456675,0.0006908889,0.0004020637,0.0001004074,0.00001801201,0.0005128498,0.001747908,0.00001314847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005375972,"about_ca_system_score_gemma":0.0002308718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002035569,"about_ca_topic_score_gemma":0.000009848478,"domain_scores_codex":[0.9967498,0.0003972347,0.0007880189,0.001133844,0.0002679951,0.0006631757],"domain_scores_gemma":[0.9982978,0.0002840661,0.0003824556,0.000708891,0.0001655985,0.0001612119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001530568,0.0001124408,0.7298893,0.0008436629,0.001721174,0.0007474527,0.0007496952,0.08687264,0.05258631,0.00005258517,0.0005557844,0.1257158],"study_design_scores_gemma":[0.00103431,0.0001658784,0.1430937,0.0008881908,0.00089999,0.0002444407,0.0002100146,0.8513898,0.0007677427,0.0002450059,0.000552326,0.0005085738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8815954,0.00224105,0.1089243,0.0004964437,0.001684405,0.0005524067,0.00000506383,0.0003451141,0.00415587],"genre_scores_gemma":[0.9754709,0.0001705337,0.02127478,0.000112287,0.002711638,0.00001565917,0.0001447337,0.00006564963,0.00003380283],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7645172,"threshold_uncertainty_score":0.9997885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1162261715723788,"score_gpt":0.3491030662681824,"score_spread":0.2328768946958036,"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."}}