{"id":"W3206407893","doi":"10.21203/rs.3.rs-970738/v1","title":"Machine learning algorithms to identify cluster randomized trials from MEDLINE and EMBASE","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Lawson Health Research Institute; McMaster University; London Health Sciences Centre; Ottawa Hospital","funders":"Canadian Institutes of Health Research; Kidney Foundation of Canada; McMaster University; Ottawa Hospital Research Institute","keywords":"MEDLINE; Computer science; Randomized controlled trial; Cluster (spacecraft); Machine learning; Algorithm; Artificial intelligence; Medicine; Internal medicine; Biology","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":[],"category_scores_codex":[0.1132854,0.001517872,0.003141315,0.01615664,0.0007600236,0.002981791,0.002191734,0.001761841,0.002132504],"category_scores_gemma":[0.4112175,0.0007288394,0.003335144,0.008584666,0.0008545454,0.002662805,0.001871954,0.001989553,0.0006545366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0021062,"about_ca_system_score_gemma":0.006361617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00215244,"about_ca_topic_score_gemma":0.003674422,"domain_scores_codex":[0.9232302,0.04655928,0.01726641,0.005760788,0.006673499,0.0005099262],"domain_scores_gemma":[0.5010458,0.4370578,0.03158613,0.01182873,0.01756302,0.0009186167],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004985336,0.0005405829,0.1072991,0.01065684,0.00810528,0.0003783491,0.0006523663,0.1260446,0.00206084,0.006531164,0.01203768,0.7207078],"study_design_scores_gemma":[0.002489629,0.001776083,0.03509712,0.003245999,0.004126288,0.0006851263,0.0002266893,0.8718708,0.005967893,0.0625824,0.0117081,0.0002238902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2053143,0.03394544,0.7321923,0.003653253,0.0006784903,0.007921765,0.006597619,0.005941598,0.003755318],"genre_scores_gemma":[0.4220604,0.002590071,0.5635128,0.0007050129,0.0004116412,0.005154518,0.005039302,0.0001578083,0.0003684221],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8867146,"threshold_uncertainty_score":0.5991179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1562057166206135,"score_gpt":0.4574555004713133,"score_spread":0.3012497838506998,"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."}}