{"id":"W4220961998","doi":"10.1016/s0735-1097(22)01268-2","title":"USING ARTIFICIAL INTELLIGENCE TO ACCURATELY PREDICT ALL-CAUSE DEATH OR READMISSION FOR DECOMPENSATED HEART FAILURE WITH PRESERVED EJECTION FRACTION","year":2022,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Advanced Data Processing Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Medicine; Ejection fraction; Acute decompensated heart failure; Heart failure; Cardiology; Internal medicine; Fraction (chemistry); Heart failure with preserved ejection fraction; Intensive care medicine","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":[0.0004002216,0.0001282472,0.0004666431,0.0001779408,0.0001456514,0.000008622033,0.0003302975,0.00003331863,0.000008287408],"category_scores_gemma":[0.0002834503,0.00008802955,0.0000949813,0.0004961733,0.00006512681,0.0001907998,0.0001057093,0.0002983884,1.828248e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002721805,"about_ca_system_score_gemma":0.0001457165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007228987,"about_ca_topic_score_gemma":0.000007591869,"domain_scores_codex":[0.998863,0.0001756686,0.0004283451,0.0001321419,0.0002179446,0.0001828953],"domain_scores_gemma":[0.9988574,0.0001932367,0.000431983,0.0002421699,0.0002098421,0.00006534934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00410341,0.0000291475,0.001731674,0.00003699475,0.0004272985,0.00003233162,0.00001790438,0.8732038,0.1132258,0.0001056908,0.005962641,0.001123342],"study_design_scores_gemma":[0.001164335,0.01729138,0.00449346,0.0006137998,0.001402387,0.01079195,0.007625179,0.1638365,0.6165844,0.01346787,0.1612805,0.001448242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4126578,0.00002760964,0.5861675,0.0003918629,0.0002243264,0.0003386591,0.0001261139,0.00005459358,0.0000115444],"genre_scores_gemma":[0.8750941,0.00001830097,0.1246412,0.00005312635,0.0001331199,0.00002384731,0.000003038479,0.0000288387,0.000004530124],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7093673,"threshold_uncertainty_score":0.3589741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1011880093379143,"score_gpt":0.3614917870050712,"score_spread":0.260303777667157,"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."}}