{"id":"W4411857731","doi":"10.1186/s12911-025-03061-0","title":"Evaluating the performance of artificial intelligence-based speech recognition for clinical documentation: a systematic review","year":2025,"lang":"en","type":"review","venue":"BMC Medical Informatics and Decision Making","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Documentation; Health informatics; Computer science; Artificial intelligence; Natural language processing; Speech recognition; Medicine; Public health; Pathology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01745337,0.001672214,0.009085951,0.01065445,0.0007840968,0.003506506,0.003279917,0.002403097,0.004158083],"category_scores_gemma":[0.08727256,0.001226555,0.008914766,0.008905713,0.001611917,0.003404696,0.001778886,0.001439596,0.0004462303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004729448,"about_ca_system_score_gemma":0.01295444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008135287,"about_ca_topic_score_gemma":0.02182646,"domain_scores_codex":[0.9833973,0.006034627,0.006498421,0.000995439,0.002843729,0.0002304052],"domain_scores_gemma":[0.8975451,0.07986797,0.01374294,0.001136599,0.007115321,0.0005920749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0002591258,0.00002861407,0.0004933306,0.9445182,0.006506933,0.00004899544,0.0001821572,0.0001146718,0.0001014296,0.0001227966,0.0006258116,0.04699802],"study_design_scores_gemma":[0.0002847512,0.00043343,0.002510794,0.9345449,0.05268785,0.0002122349,0.000301911,0.0001616881,0.0002648779,0.0002016629,0.008345756,0.00005010164],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001314797,0.9973181,0.0002521941,0.0001591393,0.00007320748,0.0004480432,0.0002054153,0.00001250097,0.0002165484],"genre_scores_gemma":[0.01929971,0.9774865,0.001466269,0.000407762,0.0000773931,0.0009627527,0.0002066747,0.00001106907,0.00008192916],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01745337,"threshold_uncertainty_score":0.09230328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.534462879473,"score_gpt":0.6514211515766116,"score_spread":0.1169582721036116,"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."}}