{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013031,0.001308307,0.0007464467,0.00285102,0.0004537736,0.001362945,0.001486017,0.0007456995,0.0007126626],"category_scores_gemma":[0.04281497,0.0005266927,0.001224875,0.00157439,0.0007370295,0.002914625,0.001916604,0.0008394259,0.0004778238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008286466,"about_ca_system_score_gemma":0.001258319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003777726,"about_ca_topic_score_gemma":0.004856954,"domain_scores_codex":[0.9900064,0.005834251,0.001350107,0.001103328,0.001454082,0.0002518012],"domain_scores_gemma":[0.9485882,0.03299143,0.002343337,0.00342827,0.01163907,0.001009696],"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":[0.002064118,0.005532441,0.07942496,0.005863015,0.0007688486,0.001768326,0.02095694,0.00994985,0.05405661,0.001509944,0.009849511,0.8082556],"study_design_scores_gemma":[0.001280021,0.02674087,0.3058846,0.001741438,0.002172103,0.006288348,0.02158964,0.451485,0.1463449,0.00269539,0.03286437,0.0009133568],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9589893,0.0005814771,0.03630092,0.0001622395,0.00007609415,0.0009576772,0.0005392316,0.001513546,0.0008795249],"genre_scores_gemma":[0.8183197,0.0008773353,0.1723658,0.0001424912,0.00004383784,0.001544349,0.004034509,0.0005225303,0.002149518],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.013031,"threshold_uncertainty_score":0.06891537,"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."}}