{"id":"W1570138353","doi":"10.1111/j.1365-2753.2007.00817.x","title":"Accuracy assessment of prediction in patient outcomes","year":2008,"lang":"en","type":"review","venue":"Journal of Evaluation in Clinical Practice","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Medicine; Outcome (game theory); Clinical Practice; Health care; Precision medicine; MEDLINE; Disease; Intensive care medicine; Physical therapy; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gpt","categories":["metaepi_broad"],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02572973,0.0002439048,0.001905495,0.0007338527,0.000038188,0.00004735141,0.0007760259,0.0003994567,0.00004562067],"category_scores_gemma":[0.1125503,0.0001885731,0.0005825396,0.0009045161,0.00004260185,0.001434373,0.0002104456,0.00326249,0.000009955649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007117345,"about_ca_system_score_gemma":0.004217263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005259751,"about_ca_topic_score_gemma":0.00001040873,"domain_scores_codex":[0.9773205,0.01197588,0.007590154,0.0004032261,0.002498737,0.000211495],"domain_scores_gemma":[0.9485909,0.03621991,0.01265528,0.000675024,0.001734143,0.000124693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001034428,0.0005844955,0.007293276,0.0007224869,0.00006419644,0.000070785,0.0001390918,0.001191462,4.599908e-9,0.0002232029,0.0005564825,0.9891441],"study_design_scores_gemma":[0.001210181,0.001201673,0.03926456,0.008319847,0.0002991072,0.0007342652,0.00004220355,0.034987,1.713806e-8,0.0003942742,0.9133355,0.000211376],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001293386,0.9853691,0.006022184,0.00246773,0.003515915,0.001200671,0.000004983986,0.00001134799,0.001278689],"genre_scores_gemma":[0.0006306333,0.9511188,0.04777952,0.0002515499,0.0001629685,0.00002892846,0.000005365096,0.00001499442,0.000007226309],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9889328,"threshold_uncertainty_score":0.999037,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.268524647334157,"score_gpt":0.6142842616869206,"score_spread":0.3457596143527636,"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."}}