{"id":"W4406800061","doi":"10.1186/s12913-025-12263-1","title":"Using artificial intelligence based language interpretation in non-urgent paediatric emergency consultations: a clinical performance test and legal evaluation","year":2025,"lang":"en","type":"article","venue":"BMC Health Services Research","topic":"Interpreting and Communication in Healthcare","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; Hospital for Sick Children; York University; University of Toronto","funders":"","keywords":"Medicine; Health care; Health informatics; Interpreter; Nursing; Computer science; Public health; Law","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.01759689,0.0001465968,0.0003090872,0.0008314215,0.00133511,0.00003208508,0.0003917869,0.0002340566,0.0001724719],"category_scores_gemma":[0.002484142,0.0001473341,0.00004419666,0.001793261,0.0000927664,0.0001937694,0.0002427227,0.001521562,0.00006739578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006645956,"about_ca_system_score_gemma":0.004914083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004610103,"about_ca_topic_score_gemma":0.006979465,"domain_scores_codex":[0.990137,0.006083077,0.001964842,0.0004679722,0.0006367692,0.0007102896],"domain_scores_gemma":[0.9920962,0.005254772,0.0003739269,0.0005690934,0.001476154,0.0002298186],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004239168,0.0003020586,0.8560733,0.008240595,0.000008455102,9.423379e-7,0.01891902,0.0010339,0.00002844872,0.00137112,0.00006031826,0.1135379],"study_design_scores_gemma":[0.0002559846,0.0001395503,0.1503162,0.002054801,0.000006568596,3.141415e-7,0.03984936,0.8068838,0.000009130234,0.0003137604,0.00008317098,0.00008731642],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9862931,0.002446619,0.004832642,0.001489451,0.0007560904,0.002873478,0.00002144828,0.00006456822,0.001222595],"genre_scores_gemma":[0.9939566,0.0009955233,0.002962592,0.001084254,0.0001493955,0.0006966821,0.00006739116,0.00001676482,0.00007074638],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8058499,"threshold_uncertainty_score":0.999965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2499074062023858,"score_gpt":0.6151168715645333,"score_spread":0.3652094653621475,"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."}}