{"id":"W3093336514","doi":"10.1186/s12874-020-01129-1","title":"An evaluation of DistillerSR’s machine learning-based prioritization tool for title/abstract screening – impact on reviewer-relevant outcomes","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":141,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; McGill University; Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"Interquartile range; Prioritization; Medicine; Recall; Computer science; Reduction (mathematics); Machine learning; Surgery; Psychology; Mathematics; Management science","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":[0.114749,0.001973905,0.003544967,0.003353256,0.0009791604,0.002782855,0.003971755,0.002751533,0.005666393],"category_scores_gemma":[0.3167892,0.001551205,0.004979294,0.003522334,0.001013506,0.0033907,0.003236054,0.002067485,0.0008880291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004462661,"about_ca_system_score_gemma":0.01028721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007864475,"about_ca_topic_score_gemma":0.008664678,"domain_scores_codex":[0.9099356,0.07355731,0.007288198,0.003173283,0.005436096,0.0006095617],"domain_scores_gemma":[0.5905296,0.3686234,0.01485082,0.008731207,0.01565786,0.001607037],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.05457411,0.00362994,0.05965325,0.03522679,0.01698287,0.0005823089,0.00286847,0.3486477,0.004701922,0.008025964,0.03592048,0.4291862],"study_design_scores_gemma":[0.02146132,0.01182386,0.01412245,0.002617385,0.006654441,0.0004977987,0.0003258008,0.9171052,0.00571781,0.007486343,0.01159474,0.0005928488],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6225058,0.01245322,0.2860247,0.01062061,0.001656603,0.0195229,0.0162325,0.02071301,0.01027067],"genre_scores_gemma":[0.544251,0.001083196,0.434269,0.00136433,0.000156471,0.01292136,0.004516799,0.0006301621,0.0008077619],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.885251,"threshold_uncertainty_score":0.606858,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9578986850993956,"score_gpt":0.7245179146353774,"score_spread":0.2333807704640182,"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."}}