{"id":"W3122512721","doi":"10.2196/22976","title":"Using Machine Learning to Collect and Facilitate Remote Access to Biomedical Databases: Development of the Biomedical Database Inventory","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Spanish National Plan for Scientific and Technical Research and Innovation; European Regional Development Fund; Instituto de Salud Carlos III","keywords":"Database; Computer science; Pipeline (software); Set (abstract data type); Precision and recall; Information retrieval","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":[],"consensus_categories":[],"category_scores_codex":[0.02292293,0.001466255,0.001537859,0.01651431,0.0008535665,0.005425345,0.004100583,0.001275668,0.002271616],"category_scores_gemma":[0.04359607,0.001340446,0.001587647,0.008875851,0.0007976202,0.008134033,0.00655272,0.003311082,0.003894333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001752825,"about_ca_system_score_gemma":0.005014558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0041117,"about_ca_topic_score_gemma":0.005273507,"domain_scores_codex":[0.9910887,0.002604343,0.00153071,0.001733843,0.002713033,0.0003292965],"domain_scores_gemma":[0.9581346,0.01710022,0.004447208,0.009761788,0.008381325,0.002174822],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004193961,0.0004999377,0.02350175,0.001804637,0.0004085297,0.0005139167,0.001198566,0.006542668,0.01725238,0.005817084,0.04283148,0.8992096],"study_design_scores_gemma":[0.0004595996,0.001061047,0.04421834,0.003357722,0.0008274115,0.002571127,0.002057573,0.4097549,0.145338,0.03600477,0.3533271,0.001022402],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03457621,0.004071242,0.80825,0.004788039,0.0003169104,0.002389696,0.01390675,0.1261926,0.005508642],"genre_scores_gemma":[0.05364343,0.001464908,0.918983,0.000806978,0.0001083149,0.0009082655,0.02067769,0.001419495,0.001987986],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02292293,"threshold_uncertainty_score":0.1212294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08440698246115125,"score_gpt":0.3617222523148145,"score_spread":0.2773152698536632,"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."}}