{"id":"W3124781663","doi":"10.2196/25530","title":"Similarity-Based Unsupervised Spelling Correction Using BioWordVec: Development and Usability Study of Bacterial Culture and Antimicrobial Susceptibility Reports","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Korea Health Industry Development Institute","keywords":"Spelling; Computer science; Artificial intelligence; Natural language processing; Edit distance; Similarity (geometry); Ranking (information retrieval); Vocabulary; Pattern recognition (psychology); Speech recognition; Information retrieval; Linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005493728,0.0001385441,0.0002583383,0.00002626737,0.00009306943,0.00002898909,0.00006392665,0.000316994,0.00002484314],"category_scores_gemma":[0.0004821493,0.0001146113,0.00003346925,0.0001048669,0.000277945,0.000007332583,0.0001641701,0.0001749684,2.036814e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001638249,"about_ca_system_score_gemma":0.0003247983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001300872,"about_ca_topic_score_gemma":0.00009340234,"domain_scores_codex":[0.99862,0.00008412926,0.0006507767,0.0002058695,0.0002734466,0.0001657436],"domain_scores_gemma":[0.9992951,0.00003113918,0.000165012,0.0002311088,0.0001290204,0.0001486561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001020989,0.005559308,0.4292801,0.003278634,0.0005119559,0.0001969493,0.03881574,0.0001286197,0.3276179,0.000004898314,0.002605773,0.1909792],"study_design_scores_gemma":[0.01000327,0.002896123,0.0616348,0.0006957036,0.0002461049,0.0009041608,0.04402254,0.02588547,0.8085451,0.00003832541,0.04347659,0.001651865],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9973792,0.00005167966,0.001965354,0.00002959302,0.0003219182,0.0002017537,0.000004938423,0.00001431109,0.00003126819],"genre_scores_gemma":[0.9870895,0.00002022548,0.01253228,0.0001384506,0.00007769317,0.000003646067,0.0001187046,0.000005629309,0.00001388009],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4809272,"threshold_uncertainty_score":0.4673713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0223113739054798,"score_gpt":0.295768969183719,"score_spread":0.2734575952782392,"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."}}