{"id":"W4386276025","doi":"10.1371/journal.pone.0290084","title":"Estimating the false discovery risk of (randomized) clinical trials in medical journals based on published p-values","year":2023,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"False discovery rate; Trustworthiness; False positive rate; Randomized controlled trial; Medicine; Publication bias; MEDLINE; Foundation (evidence); Actuarial science; Econometrics; Statistics; Psychology; Meta-analysis; Mathematics; Pathology; Social psychology; Economics; Law","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","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6109672,0.003058457,0.007344631,0.0125729,0.002018503,0.007328032,0.006270227,0.009562735,0.002355713],"category_scores_gemma":[0.8939735,0.00228254,0.008726901,0.01024694,0.01270081,0.007909405,0.00617843,0.00952532,0.0009107678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003391227,"about_ca_system_score_gemma":0.00483281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001623254,"about_ca_topic_score_gemma":0.00135814,"domain_scores_codex":[0.2832279,0.5603094,0.06151699,0.03548811,0.05769423,0.001763441],"domain_scores_gemma":[0.03651888,0.896908,0.03060506,0.02645612,0.008996084,0.0005158557],"domain_codex":"methods","domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.012838,0.0007304058,0.2008341,0.0452289,0.1017482,0.006595499,0.01705869,0.02299917,0.0054702,0.1510984,0.03154664,0.4038517],"study_design_scores_gemma":[0.004568802,0.00294947,0.06969826,0.0139911,0.03373021,0.00710904,0.002000472,0.1024452,0.01688711,0.6983564,0.04704997,0.00121396],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05371258,0.03129419,0.87528,0.01738403,0.006280305,0.004946444,0.001667244,0.001512078,0.007923136],"genre_scores_gemma":[0.6404823,0.003805695,0.3354584,0.00790098,0.002065664,0.008090872,0.0006822239,0.0003131349,0.001200814],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9926554,"threshold_uncertainty_score":0.4797468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8381041486077225,"score_gpt":0.5913574941070976,"score_spread":0.2467466545006249,"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."}}