{"id":"W3164676482","doi":"10.1186/s12874-021-01354-2","title":"Creating efficiencies in the extraction of data from randomized trials: a prospective evaluation of a machine learning and text mining tool","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"University of Alberta; Agency for Healthcare Research and Quality; U.S. Department of Health and Human Services","keywords":"Data extraction; Interquartile range; Computer science; Upload; Artificial intelligence; Randomized controlled trial; Machine learning; Data mining; Calibration; Medicine; MEDLINE; Statistics; Mathematics; Surgery","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"category_scores_codex":[0.9484816,0.0001276258,0.005377796,0.0004732363,0.0001276524,0.0001438031,0.001412466,0.0001507593,0.009726345],"category_scores_gemma":[0.9922261,0.00005255221,0.0004942376,0.001916698,0.000617236,0.0001581213,0.0005604036,0.0005989382,0.00001417899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002876156,"about_ca_system_score_gemma":0.001258445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004702726,"about_ca_topic_score_gemma":0.001274449,"domain_scores_codex":[0.05235386,0.9162698,0.01067482,0.001223148,0.01914969,0.0003287033],"domain_scores_gemma":[0.01425233,0.9765326,0.003736376,0.001962187,0.003421483,0.0000950711],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.008951645,0.0003980829,0.06280202,0.0003164171,0.000772302,0.00002535082,0.02557937,0.0003256377,0.009833566,0.00483528,0.0009917316,0.8851686],"study_design_scores_gemma":[0.01772746,0.00008188195,0.01166624,0.0002456044,0.0005214386,0.00002659296,0.03439644,0.9130257,0.0003947631,0.02129662,0.0005396662,0.00007756271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6557735,0.01095884,0.3294587,0.0005095816,0.00007502322,0.001484579,0.00001497047,0.000001416401,0.001723398],"genre_scores_gemma":[0.8115503,0.000379628,0.1875481,0.00002111595,0.00008747847,0.00014668,0.00002322767,0.00000527996,0.0002381521],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9127001,"threshold_uncertainty_score":0.9911789,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9809497216382548,"score_gpt":0.7599686211737876,"score_spread":0.2209811004644672,"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."}}