{"id":"W4220653964","doi":"10.1016/s0735-1097(22)02288-4","title":"MACHINE LEARNING BASED PREDICTION OF CARDIAC-RELATED HOSPITALIZATION COSTS AT TIME OF DIAGNOSTIC IMAGING: DEMONSTRATION OF VALUE FROM MULTI-DOMAIN PHENOTYPIC DATA AT TIME OF CARDIOVASCULAR MRI","year":2022,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Value (mathematics); Time domain; Artificial intelligence; Machine learning; Cardiology; Computer vision","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":[0.002554441,0.0001947674,0.001509436,0.0002928085,0.0001534154,0.000003201607,0.001341595,0.00006228586,0.00002070453],"category_scores_gemma":[0.001384058,0.0001725228,0.0006351594,0.0008996789,0.0004552562,0.0001601445,0.001001282,0.0004264938,7.608642e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003440304,"about_ca_system_score_gemma":0.0003707306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005362683,"about_ca_topic_score_gemma":0.000002984351,"domain_scores_codex":[0.9930092,0.004157438,0.001356125,0.0003455899,0.0009224131,0.0002092518],"domain_scores_gemma":[0.9930691,0.001607951,0.003590205,0.001120909,0.0005399163,0.00007191818],"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":[0.0002077768,0.00005932841,0.3501991,0.00005268417,0.001069972,0.00001354436,0.0002576862,0.6365976,0.0101047,0.00004896041,0.0003190218,0.001069654],"study_design_scores_gemma":[0.001561972,0.001222571,0.2207504,0.0001567107,0.0006791337,0.0001482202,0.0001788274,0.7717584,0.002506561,0.00007293817,0.0007918836,0.000172351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9204261,0.004234642,0.07197843,0.0005250822,0.0005815135,0.000535412,0.001622077,0.00001990697,0.00007685473],"genre_scores_gemma":[0.9935118,0.0001643756,0.006081241,0.00001855811,0.0000541685,0.000005234767,0.0001196804,0.00002388065,0.00002108401],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1351609,"threshold_uncertainty_score":0.7035275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008874518537991276,"score_gpt":0.2310611917081877,"score_spread":0.2221866731701964,"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."}}