{"id":"W3082510377","doi":"10.1109/embc44109.2020.9176622","title":"Evaluation of Machine Learning-based Patient Outcome Prediction Using Patient-specific Difficulty and Discrimination Indices","year":2020,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Outcome (game theory); Receiver operating characteristic; Field (mathematics); Context (archaeology); Predictive modelling; Recall; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02220668,0.001846909,0.001577913,0.004695922,0.000424739,0.002107155,0.001455426,0.001778028,0.0007809887],"category_scores_gemma":[0.08659302,0.0002262777,0.0009968946,0.002637374,0.0007307924,0.002215225,0.00155573,0.001403699,0.0004103773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001279596,"about_ca_system_score_gemma":0.00102868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003818292,"about_ca_topic_score_gemma":0.002161934,"domain_scores_codex":[0.9905092,0.004670862,0.001193909,0.001289659,0.001996638,0.0003397718],"domain_scores_gemma":[0.9267258,0.06031947,0.003732004,0.003066635,0.004911862,0.001244179],"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":[0.003071229,0.001269198,0.44518,0.0006223187,0.001262065,0.0002577158,0.0002499655,0.3795345,0.001996996,0.001546305,0.005768981,0.1592408],"study_design_scores_gemma":[0.0001203199,0.001137373,0.06758472,0.00007478116,0.0001043048,0.0001813482,0.0001488081,0.9256375,0.002014817,0.002142454,0.0007900052,0.000063561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9117843,0.002585385,0.0746809,0.00118116,0.0002414825,0.0005361562,0.003924193,0.001320136,0.003746254],"genre_scores_gemma":[0.9750383,0.0002301516,0.02037662,0.0001076537,0.00007214241,0.0001516581,0.003755893,0.00004458039,0.0002228025],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02220668,"threshold_uncertainty_score":0.1174415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08924787732179285,"score_gpt":0.3173013162258878,"score_spread":0.2280534389040949,"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."}}