{"id":"W4280532161","doi":"10.1136/bmj-2021-069155","title":"Validity of data extraction in evidence synthesis practice of adverse events: reproducibility study","year":2022,"lang":"en","type":"article","venue":"BMJ","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Institute of Mental Health; U.S. National Library of Medicine; National Health and Medical Research Council; Medical Research Council; National Institutes of Health","keywords":"Data extraction; Meta-analysis; Systematic review; Medicine; Randomized controlled trial; MEDLINE; Data mining; Computer science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8451567,0.004869785,0.01327057,0.02402645,0.004832766,0.01452712,0.008357659,0.01041238,0.007801414],"category_scores_gemma":[0.9428023,0.006414139,0.0209938,0.02471376,0.01743587,0.01658968,0.01470409,0.007229649,0.002500299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01225542,"about_ca_system_score_gemma":0.0254007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002739317,"about_ca_topic_score_gemma":0.002255923,"domain_scores_codex":[0.04888184,0.5994427,0.268476,0.02068527,0.06110281,0.001411441],"domain_scores_gemma":[0.02024914,0.7332963,0.1006452,0.08467533,0.06052661,0.0006073606],"domain_codex":"methods","domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"observational","study_design_scores_codex":[0.01026855,0.0006045082,0.07330816,0.468246,0.05652969,0.001454753,0.0437437,0.006266881,0.002628755,0.05649296,0.02459087,0.2558651],"study_design_scores_gemma":[0.01212171,0.00347409,0.0504395,0.5611932,0.04281727,0.002665785,0.008971361,0.03033125,0.01371498,0.140782,0.1312903,0.002198507],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04255885,0.09414068,0.6044703,0.01883273,0.01019232,0.2045981,0.01000803,0.002020004,0.01317905],"genre_scores_gemma":[0.3081487,0.009316389,0.3426382,0.007607051,0.001744025,0.324297,0.003329166,0.001111604,0.001807821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1548433,"threshold_uncertainty_score":0.1909494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8833574908081807,"score_gpt":0.6284029396064584,"score_spread":0.2549545512017223,"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."}}