{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005987158,0.0001388125,0.0001715781,0.0001221308,0.0001605269,0.00006556051,0.0001729143,0.0000625996,0.00004044092],"category_scores_gemma":[0.0004079772,0.0001177584,0.00003985503,0.0003408137,0.00003387718,0.000326982,0.0001291436,0.0002329634,0.000002634039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001049719,"about_ca_system_score_gemma":0.00006418025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001968281,"about_ca_topic_score_gemma":0.00002250172,"domain_scores_codex":[0.9974207,0.000447446,0.0004718673,0.0003995565,0.001104519,0.0001558823],"domain_scores_gemma":[0.9988482,0.00009729185,0.0003426801,0.0001966436,0.0004028308,0.0001123326],"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":[0.00002764255,0.0001231379,0.4009388,0.0002123392,0.00001750299,0.000001672449,0.01013045,0.2488511,0.001595146,0.0009588381,0.00002897095,0.3371143],"study_design_scores_gemma":[0.0004122503,0.0004779787,0.07697913,0.00002693959,0.00002206746,0.00000163961,0.0001748114,0.9209566,0.0006321466,0.00004480268,0.0001716132,0.0001000849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8653889,0.0002765816,0.1324282,0.001067394,0.0001624412,0.0004090525,0.000009028199,0.0001464321,0.000111922],"genre_scores_gemma":[0.9908161,0.000005418017,0.00891743,0.0001764868,0.00002623126,0.0000119593,0.00003475869,0.000009914548,0.000001760816],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6721054,"threshold_uncertainty_score":0.480205,"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."}}