{"id":"W3209235691","doi":"10.2196/32698","title":"A BERT-Based Generation Model to Transform Medical Texts to SQL Queries for Electronic Medical Records: Model Development and Validation","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China; Baidu","keywords":"Computer science; SQL; Information retrieval; Stored procedure; Query by Example; Programming language; Natural language processing; Artificial intelligence; Database; Data mining; Search engine; Web search query","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":[0.001460823,0.001162164,0.0005978613,0.001081005,0.0003732965,0.0008771594,0.001628149,0.001245331,0.003401586],"category_scores_gemma":[0.00412196,0.0004424346,0.001178222,0.0005909979,0.0004669226,0.001421841,0.0007880935,0.00186959,0.001022807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001648455,"about_ca_system_score_gemma":0.002048441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02350749,"about_ca_topic_score_gemma":0.02192361,"domain_scores_codex":[0.9995918,0.000102732,0.00003090878,0.0001509821,0.00006888468,0.0000548057],"domain_scores_gemma":[0.9984424,0.0009787511,0.00008100944,0.00008121505,0.0003641733,0.0000523742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003271243,0.0002934184,0.00511797,0.0001480668,0.000128751,0.0002341429,0.0001391405,0.7652819,0.003357772,0.003303209,0.004617524,0.217051],"study_design_scores_gemma":[0.000008281144,0.00002412191,0.0001558861,0.000005301696,0.00001219744,0.0000143893,0.000006602921,0.9984621,0.0005114262,0.0006504247,0.0001460959,0.000003326353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2055441,0.002047195,0.773559,0.001974038,0.0002914824,0.0007398201,0.002067705,0.007840917,0.005935722],"genre_scores_gemma":[0.8015644,0.000879281,0.1844702,0.0006316765,0.0001055495,0.0009822028,0.004162268,0.0001846965,0.007019625],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02350749,"threshold_uncertainty_score":0.04674131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03404106744262877,"score_gpt":0.3036375694769867,"score_spread":0.2695965020343579,"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."}}