{"id":"W2555459351","doi":"10.12688/f1000research.8680.1","title":"Three general concepts to improve risk prediction: good data, wisdom of the crowd, recalibration","year":2016,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Health Economics","funders":"Deutsche Forschungsgemeinschaft; European Commission","keywords":"Interim; Prostate cancer; Automatic summarization; Clinical trial; Computer science; Data collection; Medicine; Data science; Medical physics; Artificial intelligence; Cancer; Statistics; Internal medicine","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","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01199717,0.0003545278,0.0009447253,0.0001222283,0.0001804438,0.000125463,0.003606895,0.0007122001,0.001070846],"category_scores_gemma":[0.1683929,0.0002175213,0.0002578292,0.0003259726,0.0007673823,0.0001152224,0.008862173,0.001750308,0.0000954077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000144288,"about_ca_system_score_gemma":0.0007365215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001899784,"about_ca_topic_score_gemma":0.00009535992,"domain_scores_codex":[0.9913173,0.00316179,0.001730764,0.001254269,0.00194735,0.0005885169],"domain_scores_gemma":[0.9547692,0.03807527,0.000768383,0.005410926,0.0006600208,0.0003162011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001531541,0.000845467,0.01351746,0.002102694,0.001296458,0.00001625867,0.0004963965,0.0001046538,0.007333506,0.298166,0.4850983,0.1894912],"study_design_scores_gemma":[0.0008537363,0.0002140827,0.004238454,0.0004723118,0.0001543795,0.000001120457,0.00001375227,0.004928133,0.005612789,0.9801328,0.003140608,0.0002378732],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01145015,0.000106831,0.9377361,0.004207357,0.005545208,0.005544678,0.02987337,0.0001753474,0.005360995],"genre_scores_gemma":[0.01068059,0.0001451804,0.9796925,0.0001167765,0.005291607,0.0005752835,0.00007361814,0.0001725849,0.003251882],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6819667,"threshold_uncertainty_score":0.9998423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6250446288852266,"score_gpt":0.6063474123778936,"score_spread":0.01869721650733303,"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."}}