{"id":"W6958671760","doi":"10.6084/m9.figshare.c.6266223.v1","title":"Machine learning algorithms to identify cluster randomized trials from MEDLINE and EMBASE","year":2022,"lang":"en","type":"other","venue":"Figshare","topic":"Bioenergy crop production and management","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Ottawa Hospital; McMaster University; London Health Sciences Centre; Lawson Health Research Institute","funders":"","keywords":"Support vector machine; Identification (biology); Statistical classification; Randomized controlled trial; Sensitivity (control systems); Ensemble learning; Set (abstract data type)","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":[],"category_scores_codex":[0.1031327,0.001595146,0.003103686,0.01627008,0.0007771134,0.003106828,0.0022703,0.001867993,0.002098652],"category_scores_gemma":[0.3940296,0.0007870586,0.003243861,0.008548274,0.0008642792,0.002663801,0.001854348,0.002032573,0.0006997215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002130321,"about_ca_system_score_gemma":0.006245753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002407543,"about_ca_topic_score_gemma":0.003836321,"domain_scores_codex":[0.9287742,0.04233795,0.01634805,0.005764861,0.006247527,0.0005274343],"domain_scores_gemma":[0.5311326,0.4086148,0.03005601,0.01149759,0.01778968,0.0009093299],"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":[0.004358751,0.0005050484,0.09501316,0.01121405,0.007124742,0.0004113314,0.0006195044,0.1489527,0.002259049,0.007409482,0.013013,0.7091192],"study_design_scores_gemma":[0.001937364,0.001374941,0.02752555,0.002760386,0.003216642,0.0006257597,0.0001864938,0.8804423,0.006047524,0.06414057,0.01153114,0.0002113812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1727312,0.03127866,0.76906,0.003604962,0.0006367057,0.006501542,0.006456332,0.006219087,0.003511519],"genre_scores_gemma":[0.4036545,0.002682282,0.5817991,0.0007606018,0.0004404854,0.004774655,0.005319707,0.0001733064,0.0003954196],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8968673,"threshold_uncertainty_score":0.5454243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06741009207332904,"score_gpt":0.2989101340660914,"score_spread":0.2315000419927624,"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."}}