{"id":"W2550035039","doi":"10.1016/j.jclinepi.2016.10.004","title":"Four hundred or more participants needed for stable contingency table estimates of clinical prediction rule performance","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Contingency table; Table (database); Statistics; Medicine; Mathematics; Computer science; Data mining","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01667852,0.0005522275,0.001443227,0.0006202434,0.0009930729,0.0008362811,0.0008683599,0.001275139,0.007247072],"category_scores_gemma":[0.06356051,0.0005696793,0.001174479,0.0006331019,0.0006421886,0.001468343,0.001357324,0.001000249,0.001283207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005053992,"about_ca_system_score_gemma":0.001515138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001463092,"about_ca_topic_score_gemma":0.001647499,"domain_scores_codex":[0.9891617,0.006016729,0.001069196,0.001314536,0.001740784,0.000696966],"domain_scores_gemma":[0.9578327,0.02773344,0.002969585,0.006854443,0.003763293,0.0008464987],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.03632487,0.003792875,0.7435544,0.0004555538,0.001262229,0.001160487,0.00280559,0.004696685,0.007850372,0.002189846,0.006356385,0.1895507],"study_design_scores_gemma":[0.00508578,0.03412613,0.889529,0.0002136349,0.001464474,0.001723824,0.003291731,0.02458408,0.0135096,0.009024893,0.01720353,0.0002434144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9754681,0.00044162,0.01595503,0.0003636778,0.0002173824,0.001655176,0.003505745,0.0002911171,0.002102152],"genre_scores_gemma":[0.9888442,0.00006175329,0.006890432,0.0001332062,0.000039864,0.001760202,0.001186195,0.00003471586,0.001049358],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9833215,"threshold_uncertainty_score":0.08820552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4199366815559962,"score_gpt":0.5455118565174738,"score_spread":0.1255751749614776,"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."}}