{"id":"W4308489971","doi":"10.1016/j.jacadv.2022.100126","title":"Machine Learning Approaches for Phenotyping in Cardiogenic Shock and Critical Illness","year":2022,"lang":"en","type":"article","venue":"JACC Advances","topic":"Mechanical Circulatory Support Devices","field":"Engineering","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ted Rogers Centre for Heart Research; University of Toronto","funders":"","keywords":"Cardiogenic shock; Intensive care medicine; Disease; Clinical trial; Critical illness; Medicine; Mechanism (biology); Computer science; Psychology; Critically ill; Pathology; Psychiatry; Epistemology","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":[0.0002761128,0.000117922,0.0002183473,0.0000702605,0.0001687834,0.00001952108,0.000109083,0.00002946815,0.00006677485],"category_scores_gemma":[0.0001064214,0.0001277262,0.00004804478,0.0001427258,0.00002211268,0.0001926617,0.00007269455,0.0002419856,0.000001385892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005254356,"about_ca_system_score_gemma":0.000007126465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003549703,"about_ca_topic_score_gemma":0.0000126974,"domain_scores_codex":[0.999152,0.00004833256,0.0001885691,0.0002281996,0.0001319029,0.0002509957],"domain_scores_gemma":[0.9995804,0.0002386179,0.00001708603,0.00009984403,0.000008141441,0.00005594676],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005701646,0.00004357388,0.03481674,0.0009533613,0.00006413944,0.0000246499,0.001071016,0.7293889,0.000440447,0.01234542,0.00002428131,0.2207705],"study_design_scores_gemma":[0.0004723154,0.0000459837,0.0008983539,0.00001667708,0.00002726325,0.00002509804,0.001737766,0.9230513,0.0003042248,0.007088454,0.06593025,0.0004023061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.68177,0.1467768,0.1613054,0.000361636,0.002047819,0.001511205,0.0001398105,0.001062569,0.00502472],"genre_scores_gemma":[0.9985213,0.00004077207,0.00104551,0.00002950198,0.00006192911,0.0002346263,0.00001530008,0.00003173995,0.00001929973],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3167513,"threshold_uncertainty_score":0.5208523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02443022257798559,"score_gpt":0.2455442654126828,"score_spread":0.2211140428346973,"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."}}