{"id":"W3027335960","doi":"10.1101/2020.05.15.20103044","title":"Trialstreamer: a living, automatically updated database of clinical trial reports","year":2020,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; Medical Research Council; National Institutes of Health; McMaster University","keywords":"Computer science; Randomized controlled trial; Information retrieval; Sample size determination; Categorization; Clinical trial; Database; Artificial intelligence; Data mining; Medicine; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.0417075,0.002742212,0.004869834,0.03805916,0.001240828,0.01090447,0.005945317,0.003483164,0.05345052],"category_scores_gemma":[0.243801,0.002719597,0.003089817,0.02576892,0.001178348,0.01083804,0.008714799,0.003357234,0.03750359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002257331,"about_ca_system_score_gemma":0.01196456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002336538,"about_ca_topic_score_gemma":0.004135191,"domain_scores_codex":[0.9542504,0.01078102,0.02300025,0.004728334,0.006624539,0.000615532],"domain_scores_gemma":[0.6940702,0.1853808,0.04618524,0.03831047,0.02905934,0.00699407],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002756107,0.0002818886,0.005658241,0.04940431,0.001648682,0.0007573188,0.001286626,0.001684627,0.005434093,0.01035679,0.6411989,0.2795323],"study_design_scores_gemma":[0.002654053,0.0004575723,0.009075966,0.01021197,0.001841801,0.0011012,0.0004267022,0.003698723,0.00820517,0.01470589,0.9471414,0.0004794812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"software","genre_scores_codex":[0.003230765,0.00903708,0.05562542,0.003038535,0.0008480116,0.004598771,0.8503405,0.06385906,0.009421906],"genre_scores_gemma":[0.01570849,0.007376928,0.2428063,0.002198412,0.0007806673,0.01078591,0.7068192,0.009220594,0.004303402],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.9940547,"threshold_uncertainty_score":0.220573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1267574432258337,"score_gpt":0.4269701377054367,"score_spread":0.3002126944796031,"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."}}