{"id":"W1527627496","doi":"10.1002/0471463736.tnmp10","title":"Measuring the Accuracy of Prognostic Judgments","year":2003,"lang":"en","type":"other","venue":"TNM Online","topic":"Healthcare cost, quality, practices","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kingston General Hospital; Queen's University","funders":"","keywords":"Certainty; Predictive power; Clinical Practice; Medicine; Test (biology); Value (mathematics); Predictive value; Diagnostic accuracy; Medical physics; Actuarial science; Intensive care medicine; Psychology; Computer science; Epistemology; Family medicine; Internal medicine; Machine learning","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":[0.02901858,0.0005979822,0.0007328584,0.004000975,0.0008825055,0.004232817,0.00111646,0.001583553,0.005935974],"category_scores_gemma":[0.3476283,0.0003138123,0.0006215685,0.003884711,0.001671539,0.003611743,0.002286452,0.001987823,0.001684076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001867836,"about_ca_system_score_gemma":0.001176207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002039657,"about_ca_topic_score_gemma":0.001398356,"domain_scores_codex":[0.9624795,0.01640551,0.004008975,0.002718604,0.01345339,0.0009339165],"domain_scores_gemma":[0.5961857,0.2983187,0.03801643,0.01717296,0.04701484,0.00329135],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00170713,0.0003103988,0.59461,0.0008072447,0.0006799281,0.0002000384,0.006288106,0.01768269,0.001150988,0.02888219,0.01615631,0.3315249],"study_design_scores_gemma":[0.0001774167,0.00145593,0.6854745,0.002809015,0.0007300543,0.0007243557,0.006721646,0.1014193,0.008332344,0.1409496,0.05068079,0.0005249977],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7768078,0.007494606,0.1053089,0.00755668,0.001209155,0.0006614964,0.004980329,0.0009929204,0.09498809],"genre_scores_gemma":[0.984224,0.0008108054,0.0118013,0.0003177822,0.0001758083,0.0001376234,0.00125275,0.00006625301,0.001213658],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02901858,"threshold_uncertainty_score":0.1534668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7057538928564474,"score_gpt":0.5646225375122388,"score_spread":0.1411313553442086,"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."}}