{"id":"W2954431181","doi":"10.1016/j.jval.2019.04.534","title":"PCV99 BAYESIAN NETWORKS AS AN EMERGING TOOL FOR DISEASE RISK ESTIMATION AND CLINICAL DECISION-MAKING: A REAL-WORLD EXAMPLE IN CORONARY ARTERY DISEASE","year":2019,"lang":"en","type":"article","venue":"Value in Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary; Toronto Public Health","funders":"","keywords":"Interpretability; Coronary artery disease; Logistic regression; Machine learning; CAD; Bayesian network; Disease; Artificial intelligence; Receiver operating characteristic; Computer science; Missing data; Medicine; Bayesian probability; Risk assessment; Data mining; Internal medicine; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007478588,0.0008648344,0.0008383668,0.002450918,0.0009465105,0.003390848,0.00157959,0.00232645,0.007330901],"category_scores_gemma":[0.04163921,0.0004891006,0.000697934,0.002453096,0.000772691,0.002501699,0.001301612,0.002620738,0.001061936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001757222,"about_ca_system_score_gemma":0.002582146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02646164,"about_ca_topic_score_gemma":0.02913118,"domain_scores_codex":[0.9964307,0.002321075,0.0001505455,0.0003086437,0.0007062614,0.00008277054],"domain_scores_gemma":[0.9646729,0.03090711,0.0008130609,0.001182903,0.002022095,0.0004019653],"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":[0.0005999655,0.0003214117,0.01149908,0.0003044743,0.0002533016,0.0004203111,0.0003889267,0.520623,0.0006701178,0.08108224,0.01479511,0.369042],"study_design_scores_gemma":[0.00005476441,0.00005086042,0.001143404,0.0001141068,0.00004984202,0.0001326169,0.00006771136,0.9070553,0.0005723377,0.08241259,0.008312548,0.00003396614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05217819,0.002226647,0.9166557,0.006489631,0.000217445,0.0002171929,0.002094496,0.001699886,0.01822082],"genre_scores_gemma":[0.4659517,0.001377148,0.5259013,0.0005352244,0.0001195032,0.0001865481,0.001179121,0.0002348911,0.00451469],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02646164,"threshold_uncertainty_score":0.05261523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1502559212390691,"score_gpt":0.508387657659241,"score_spread":0.3581317364201719,"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."}}