{"id":"W1487942018","doi":"","title":"Developing and Testing a Tool for the Classification of Study Designs in Systematic Reviews of Interventions and Exposures","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Inter-rater reliability; Reliability (semiconductor); Psychological intervention; Systematic review; Computer science; Clinical study design; Test (biology); Medicine; Kappa; Classification scheme; Medical physics; MEDLINE; Data mining; Machine learning; Statistics; Clinical trial; Mathematics; Rating scale; Pathology; Nursing","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":[0.8144668,0.0101473,0.01639395,0.07568881,0.008625752,0.02256451,0.01097898,0.01267385,0.007354006],"category_scores_gemma":[0.9402989,0.008843229,0.03342905,0.05265598,0.01250226,0.02864571,0.024378,0.01453532,0.002957106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.03226935,"about_ca_system_score_gemma":0.0604224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004924756,"about_ca_topic_score_gemma":0.009690916,"domain_scores_codex":[0.08854616,0.5147308,0.3127591,0.01601418,0.06504424,0.002905501],"domain_scores_gemma":[0.02662464,0.7716418,0.05702805,0.04625183,0.09696309,0.001490662],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003583646,0.0009210122,0.03090598,0.2071834,0.01582564,0.000548361,0.02720276,0.007156831,0.002855499,0.03539417,0.05123745,0.6171852],"study_design_scores_gemma":[0.02559912,0.007606788,0.05265524,0.3547594,0.03246519,0.002459831,0.01878365,0.1160049,0.01751975,0.1810966,0.1855227,0.005526891],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01729775,0.008475097,0.6699903,0.0106703,0.004127092,0.2714513,0.006424516,0.007130499,0.004433235],"genre_scores_gemma":[0.01315277,0.000484565,0.8498777,0.0006536471,0.0001018605,0.134803,0.0005922999,0.0002041741,0.0001299733],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1855332,"threshold_uncertainty_score":0.2341317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9825422283967272,"score_gpt":0.7296947615825049,"score_spread":0.2528474668142223,"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."}}