{"id":"W4381377622","doi":"10.1101/2023.06.18.23291567","title":"Machine learning to increase the efficiency of a literature surveillance system: a performance evaluation","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Computer science; Machine learning; Critical appraisal; Artificial intelligence; MEDLINE; Set (abstract data type); Sensitivity (control systems); Binary classification; Information retrieval; Medical physics; Medicine; Support vector machine; Alternative medicine; Pathology","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":[0.0892437,0.001854423,0.002840968,0.01022819,0.001386209,0.004564549,0.002406666,0.002657753,0.001902437],"category_scores_gemma":[0.2359355,0.0007500413,0.002638727,0.00611454,0.001161356,0.004766684,0.002853256,0.001711927,0.001282627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002494598,"about_ca_system_score_gemma":0.005424592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005638291,"about_ca_topic_score_gemma":0.004337159,"domain_scores_codex":[0.9423803,0.03651693,0.008636491,0.00543024,0.00618541,0.0008506642],"domain_scores_gemma":[0.6366993,0.3105406,0.01562753,0.01608887,0.01889476,0.002148992],"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":[0.008924104,0.001905148,0.1814442,0.004499783,0.003659518,0.0003834,0.001369195,0.08591507,0.007442376,0.002509013,0.01314924,0.6887989],"study_design_scores_gemma":[0.0007704928,0.001410518,0.01674038,0.0005216432,0.0008845251,0.0004202758,0.0002624507,0.9643906,0.008265295,0.003759474,0.002474477,0.00009983969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6057006,0.01290452,0.3299202,0.005554493,0.0005572715,0.004609582,0.005137544,0.02911175,0.006503959],"genre_scores_gemma":[0.6771404,0.0006756099,0.3174545,0.0005542074,0.0001281464,0.0008477191,0.002488047,0.0002812552,0.0004301861],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9107563,"threshold_uncertainty_score":0.4719714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02354627931456999,"score_gpt":0.2870682422268218,"score_spread":0.2635219629122518,"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."}}