{"id":"W2807522649","doi":"10.1186/s13643-018-0707-8","title":"Technology-assisted title and abstract screening for systematic reviews: a retrospective evaluation of the Abstrackr machine learning tool","year":2018,"lang":"en","type":"article","venue":"Systematic Reviews","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":156,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Medical education; Medical physics; Data science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.3416408,0.001625294,0.003773472,0.0193178,0.001191568,0.004455468,0.003936647,0.001416368,0.004450995],"category_scores_gemma":[0.6341816,0.002505909,0.005389944,0.02021791,0.001599251,0.005032512,0.006041506,0.001601637,0.001959418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004261558,"about_ca_system_score_gemma":0.01809707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004208142,"about_ca_topic_score_gemma":0.01051316,"domain_scores_codex":[0.608551,0.2212176,0.1092755,0.01234364,0.04728183,0.001330485],"domain_scores_gemma":[0.1350004,0.6065195,0.114126,0.05561788,0.08648995,0.002246211],"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":[0.0106338,0.0008360679,0.1375906,0.1404181,0.01347349,0.0006807431,0.009698943,0.00441977,0.002974223,0.00160989,0.02628046,0.6513839],"study_design_scores_gemma":[0.01662464,0.02470487,0.4966625,0.1278619,0.061389,0.008263198,0.006691722,0.08614351,0.01621402,0.005074365,0.1472099,0.003160391],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.537019,0.09405402,0.1618591,0.008798407,0.0009590024,0.1010162,0.0731539,0.01170668,0.01143367],"genre_scores_gemma":[0.5472507,0.01734669,0.3411279,0.001976379,0.0005096067,0.06879845,0.02048465,0.001160246,0.001345329],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6583592,"threshold_uncertainty_score":0.8118741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6430911952326538,"score_gpt":0.5195480576045787,"score_spread":0.1235431376280751,"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."}}