{"id":"W4312064948","doi":"10.1111/hir.12471","title":"Application of text mining to the development and validation of a geographic search filter to facilitate evidence retrieval in Ovid <scp>MEDLINE</scp>: An example from the United States","year":2022,"lang":"en","type":"article","venue":"Health Information & Libraries Journal","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Broadcom (Canada); Vancouver Coastal Health","funders":"","keywords":"MEDLINE; Filter (signal processing); Information retrieval; Computer science; Set (abstract data type); Vocabulary; Identification (biology); Controlled vocabulary; Data science; Data mining; Political science","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":[0.06687006,0.0008523177,0.001965581,0.01560155,0.001643376,0.004726579,0.001624423,0.001551082,0.002154287],"category_scores_gemma":[0.2371186,0.0004871327,0.00230739,0.01194042,0.0008217476,0.002898641,0.001924867,0.0008916253,0.0008558171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003165032,"about_ca_system_score_gemma":0.008659543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008990058,"about_ca_topic_score_gemma":0.01164893,"domain_scores_codex":[0.9596475,0.02249645,0.009857692,0.002141242,0.005420389,0.0004367802],"domain_scores_gemma":[0.7020366,0.2442899,0.01353678,0.005613324,0.03373124,0.000792265],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001892729,0.0005799874,0.05655416,0.01493752,0.001402844,0.001332683,0.005598986,0.01054281,0.01353807,0.007886568,0.02099293,0.8647407],"study_design_scores_gemma":[0.00402699,0.004599779,0.1721576,0.02740954,0.007337106,0.004541324,0.01118073,0.3781525,0.08500563,0.05851812,0.2460951,0.0009755936],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.323604,0.01476572,0.580093,0.01551568,0.000838402,0.02391241,0.01788802,0.006334538,0.01704829],"genre_scores_gemma":[0.1971762,0.002276232,0.786729,0.001058906,0.0001356445,0.006079741,0.005170693,0.0001890085,0.001184447],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.93313,"threshold_uncertainty_score":0.3536469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1059803544471308,"score_gpt":0.3062490695496477,"score_spread":0.2002687151025169,"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."}}