{"id":"W4406352735","doi":"10.5195/jmla.2025.1972","title":"Filtering failure: the impact of automated indexing in Medline on retrieval of human studies for knowledge synthesis","year":2025,"lang":"en","type":"article","venue":"Journal of the Medical Library Association JMLA","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Search engine indexing; Information retrieval; MEDLINE; Computer science; Data science; Biology","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","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.674023,0.004109041,0.009605333,0.03692408,0.004267102,0.01331421,0.007305851,0.00751089,0.01086221],"category_scores_gemma":[0.9066983,0.002841029,0.0120102,0.03352439,0.006415856,0.01517936,0.008881738,0.003620134,0.002222313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01276803,"about_ca_system_score_gemma":0.02495972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01272452,"about_ca_topic_score_gemma":0.01379536,"domain_scores_codex":[0.1778969,0.4762922,0.2544888,0.0166625,0.07157945,0.00308019],"domain_scores_gemma":[0.02325182,0.8898751,0.04290024,0.02265746,0.02045507,0.0008601984],"domain_codex":"methods","domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01392138,0.000360445,0.06460665,0.2620744,0.02668231,0.001736913,0.02126275,0.00437331,0.006592467,0.01482879,0.07887541,0.5046852],"study_design_scores_gemma":[0.009456526,0.005246135,0.1451207,0.379889,0.07009168,0.006726619,0.007073491,0.0382031,0.01916397,0.06169015,0.2547369,0.002601856],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.1392621,0.3097202,0.3042848,0.1108547,0.01464176,0.04195473,0.02840711,0.008496885,0.04237769],"genre_scores_gemma":[0.5706272,0.03180327,0.3205366,0.02950859,0.003447624,0.03054082,0.007985202,0.00231601,0.00323469],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9866858,"threshold_uncertainty_score":0.4019877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02149192430396018,"score_gpt":0.3633324058375226,"score_spread":0.3418404815335624,"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."}}