{"id":"W2106659324","doi":"10.1111/ajt.13391","title":"Problems With the Development and Validation of a Prognostic Model","year":2015,"lang":"en","type":"letter","venue":"American Journal of Transplantation","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Population Health Research Institute","funders":"","keywords":"Medicine; Scopus; Overfitting; MEDLINE; Statistics; Artificial intelligence; Computer science; 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":[0.0005784518,0.0001352258,0.0002724919,0.0001505929,0.00005009272,0.00004413532,0.0003994003,0.00005323028,3.899265e-7],"category_scores_gemma":[0.00001491974,0.0000813796,0.00002727234,0.0002138444,0.00009900203,0.0001911702,0.00001096541,0.0006782237,3.906351e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003922634,"about_ca_system_score_gemma":0.0005578293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002600438,"about_ca_topic_score_gemma":0.000008893349,"domain_scores_codex":[0.9984535,0.0002182897,0.0004109177,0.0001429032,0.0006399756,0.0001344204],"domain_scores_gemma":[0.9980887,0.0002022071,0.001128549,0.0001416481,0.0003957753,0.00004315531],"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":[0.000580802,0.0001653333,0.02915311,0.007337442,0.0009940199,0.0006717362,0.2552411,0.3526069,0.0002042922,0.000636315,0.03885524,0.3135537],"study_design_scores_gemma":[0.01481531,0.03584274,0.05795546,0.02526318,0.004590911,0.02140073,0.0046317,0.6624988,0.00569688,0.007826012,0.1524221,0.007056205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06518496,0.00009642315,0.7422996,0.1920055,0.00007471502,0.0002583517,0.000004824781,0.00001466063,0.00006095787],"genre_scores_gemma":[0.7077877,0.0001123782,0.2650662,0.02654332,0.0003137706,0.00002591085,0.00005441067,0.00004048669,0.0000558391],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6426027,"threshold_uncertainty_score":0.3318564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02411864829723237,"score_gpt":0.2620685926070873,"score_spread":0.2379499443098549,"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."}}