{"id":"W3014082802","doi":"10.2196/12799","title":"Identification of the Best Semantic Expansion to Query PubMed Through Automatic Performance Assessment of Four Search Strategies on All Medical Subject Heading Descriptors: Comparative Study","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Unified Medical Language System; Computer science; Information retrieval; Synonym (taxonomy); Precision and recall; Search engine indexing; Subject (documents); Construct (python library); Term (time); Query expansion; Semantics (computer science); Measure (data warehouse); Index (typography); Data mining; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01520578,0.001574978,0.001549614,0.01205125,0.0005546664,0.002258833,0.001012444,0.001160111,0.001310852],"category_scores_gemma":[0.06276522,0.0002731362,0.001662289,0.006056819,0.0005148516,0.002712263,0.001116492,0.0004178295,0.0007125196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001117283,"about_ca_system_score_gemma":0.002263879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002967281,"about_ca_topic_score_gemma":0.00362251,"domain_scores_codex":[0.9901467,0.00490977,0.001662279,0.001512835,0.001543128,0.0002252829],"domain_scores_gemma":[0.9450908,0.04515033,0.002574766,0.001424185,0.005350883,0.0004090391],"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":[0.008317553,0.001132576,0.1091782,0.01119049,0.002831526,0.0005430576,0.001924333,0.01427727,0.04720669,0.002262705,0.01039471,0.7907409],"study_design_scores_gemma":[0.002550505,0.01465867,0.3030566,0.001660219,0.01280318,0.004282659,0.004266203,0.4919135,0.1307487,0.008830875,0.02456112,0.0006676825],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.846825,0.0161786,0.1143116,0.0008475221,0.0002067578,0.001793667,0.005334591,0.007593974,0.006908265],"genre_scores_gemma":[0.8086433,0.002111813,0.1806917,0.0002361054,0.0001049476,0.001122278,0.006038924,0.0003882887,0.0006625206],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9847942,"threshold_uncertainty_score":0.08041686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09308255225453313,"score_gpt":0.3844331716753633,"score_spread":0.2913506194208302,"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."}}