{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002096261,0.000335426,0.0006353935,0.000188199,0.0002922357,0.000007313804,0.0005747703,0.0006007868,0.01720586],"category_scores_gemma":[0.01170158,0.0002319677,0.00009791302,0.0003084488,0.0001190144,0.00007347823,0.0001974368,0.001875116,0.00125369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001486221,"about_ca_system_score_gemma":0.001305619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002163751,"about_ca_topic_score_gemma":0.003436779,"domain_scores_codex":[0.9939776,0.003249966,0.001039282,0.0004053107,0.0006729985,0.0006548526],"domain_scores_gemma":[0.992585,0.003951863,0.001966642,0.001073785,0.0002470168,0.000175672],"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":[0.00003062931,0.0003836482,0.01248432,0.00347452,0.0001737795,0.000009749287,0.0009681305,2.79214e-7,0.00001742981,0.0004549747,0.9746197,0.007382883],"study_design_scores_gemma":[0.000417265,0.00004487119,0.004149495,0.002974218,0.00009268283,0.000001674825,0.0007718352,0.00000523152,0.000004296109,0.0001128759,0.9912143,0.0002112816],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.004760985,0.007149545,0.00009939679,0.015723,0.004755288,0.007713147,0.005310889,0.000633794,0.953854],"genre_scores_gemma":[0.003756343,0.001906858,0.002667638,0.01062747,0.002393084,0.0004224713,0.0008443987,0.0009986541,0.9763831],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.02252913,"threshold_uncertainty_score":0.9995239,"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."}}