{"id":"W4245289687","doi":"10.22541/au.158022310.05444580","title":"Validating prediction models for use in clinical practice: concept, steps and procedures","year":2020,"lang":"en","type":"dataset","venue":"Authorea","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Predictive modelling; Computer science; Set (abstract data type); Clinical Practice; Model validation; Machine learning; Quality (philosophy); Data mining; Artificial intelligence; Data science; 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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001439732,0.000258619,0.0004422485,0.0001186988,0.0001288983,0.0003432273,0.0006921461,0.0004449422,0.000002118714],"category_scores_gemma":[0.01059133,0.0002541744,0.0000714337,0.0002480112,0.00006084,0.001002363,0.0004703012,0.001215381,0.00000790649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005761265,"about_ca_system_score_gemma":0.0004487366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007101467,"about_ca_topic_score_gemma":0.0001667584,"domain_scores_codex":[0.9968308,0.0006169744,0.000870063,0.0009897965,0.000367038,0.0003253172],"domain_scores_gemma":[0.9956535,0.002744699,0.0005875384,0.0006424939,0.0001753969,0.0001964123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003196052,0.00004395288,0.0003813591,0.0004371171,0.00002026757,0.00002598876,0.0003816443,0.0005941367,1.232033e-7,0.001396557,0.989558,0.007128898],"study_design_scores_gemma":[0.0004603745,0.0003866916,0.0007138135,0.000267218,0.00003942772,0.00004104935,0.00004398969,0.3628995,6.041586e-7,0.001094207,0.6338043,0.0002488909],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00006072747,0.0002300744,0.08563362,0.002790079,0.0008885114,0.001361814,0.9088312,0.0001838197,0.00002019192],"genre_scores_gemma":[0.001001592,0.0002624318,0.1430465,0.00195981,0.0006777568,0.0002217392,0.8527687,0.00003409054,0.00002742963],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.3623053,"threshold_uncertainty_score":0.9999911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1121147470637734,"score_gpt":0.4174435521103545,"score_spread":0.3053288050465811,"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."}}