{"id":"W1595714231","doi":"10.1186/1472-6947-7-3","title":"A UMLS-based spell checker for natural language processing in vaccine safety","year":2007,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Public Health Agency of Canada","funders":"Oak Ridge Institute for Science and Education; Centers for Disease Control and Prevention; U.S. Department of Energy","keywords":"Spelling; Computer science; Unified Medical Language System; Spell; Natural language processing; Artificial intelligence; Linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001441254,0.0001257127,0.0001905893,0.00009709846,0.00005463304,0.00003375904,0.0001579386,0.0002512727,0.00001975608],"category_scores_gemma":[0.001248767,0.00009137093,0.0000557029,0.0001233243,0.0000636757,0.000006019804,0.0001049549,0.0001513152,0.000003118851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001305719,"about_ca_system_score_gemma":0.0001321828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002042193,"about_ca_topic_score_gemma":0.0001779898,"domain_scores_codex":[0.9986892,0.00001177235,0.0005604543,0.0001397426,0.0003099748,0.000288886],"domain_scores_gemma":[0.9993267,0.000241263,0.0001178704,0.0001430843,0.00004774731,0.0001233135],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006376079,0.00003239036,0.001639841,0.000171792,0.000003824356,0.000006734064,0.000204537,0.00002691599,0.0002168264,0.00002990084,0.0006288367,0.9964008],"study_design_scores_gemma":[0.005859885,0.000330282,0.007296549,0.001078005,0.00001707124,0.00006350561,0.002846032,0.9521136,0.001476732,0.000238771,0.02823025,0.0004492756],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3676995,0.001729427,0.6300326,0.00001661759,0.00009341926,0.000109867,0.00000288167,0.00001127539,0.0003044455],"genre_scores_gemma":[0.6480282,0.00003156949,0.3508473,0.0009105447,0.0001174499,0.000002269436,0.00002816356,0.000007932715,0.00002661948],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9959515,"threshold_uncertainty_score":0.3725998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01711174045561572,"score_gpt":0.348760040074018,"score_spread":0.3316482996184023,"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."}}