{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6903608,0.003311963,0.00580234,0.01659216,0.002637232,0.009844128,0.006895272,0.003339117,0.00619272],"category_scores_gemma":[0.8563535,0.004204028,0.01024398,0.01756941,0.004452316,0.01367032,0.01093633,0.003720053,0.002962801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01146429,"about_ca_system_score_gemma":0.0304379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001963511,"about_ca_topic_score_gemma":0.002794197,"domain_scores_codex":[0.2114718,0.6162013,0.1200849,0.01497317,0.03529137,0.00197754],"domain_scores_gemma":[0.02807689,0.8575268,0.04420751,0.04283611,0.02601532,0.001337328],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.02570258,0.002839549,0.02900354,0.07327206,0.0105569,0.0006827636,0.01195366,0.00894989,0.004745766,0.006049152,0.02332508,0.8029191],"study_design_scores_gemma":[0.1047643,0.04751914,0.1378461,0.09391984,0.05175963,0.006329072,0.009969112,0.2222207,0.06671961,0.04733589,0.2069044,0.004712268],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.169236,0.02021408,0.628792,0.0113896,0.001164816,0.1320032,0.009523176,0.0200696,0.007607541],"genre_scores_gemma":[0.1269009,0.001759096,0.7993327,0.001652967,0.0002231877,0.06702486,0.001394457,0.001260305,0.0004515331],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3096392,"threshold_uncertainty_score":0.3818403,"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."}}