{"id":"W4407558201","doi":"10.1017/ice.2025.20","title":"Chatting new territory: large language models for infection surveillance from pilot to deployment","year":2025,"lang":"en","type":"article","venue":"Infection Control and Hospital Epidemiology","topic":"Bacterial Identification and Susceptibility Testing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Software deployment; Identification (biology); Medicine; Health care; Medical emergency; Computer science; Computer security; Political science; Biology; Software engineering","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":[0.004548559,0.0007673996,0.0004632885,0.0003387971,0.0004434171,0.001441639,0.001555152,0.0007737048,0.00463461],"category_scores_gemma":[0.01471666,0.0003909527,0.0007248534,0.000169643,0.0007278558,0.002294962,0.001537805,0.00162433,0.0008900733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001069584,"about_ca_system_score_gemma":0.001485616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009785872,"about_ca_topic_score_gemma":0.008104268,"domain_scores_codex":[0.9972987,0.001726158,0.0001048188,0.0002463759,0.0004658586,0.0001581662],"domain_scores_gemma":[0.9880889,0.008968916,0.0003567119,0.001188246,0.001024289,0.0003729844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007190264,0.002004514,0.01855058,0.0006935239,0.0003993046,0.001119835,0.002146243,0.6003078,0.04509077,0.04317719,0.02210785,0.2572122],"study_design_scores_gemma":[0.0000771089,0.00028429,0.0004406018,0.00001836909,0.0000231662,0.00004437338,0.00009677785,0.9885941,0.00413313,0.003852124,0.002413095,0.00002289845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3090749,0.0004631092,0.66101,0.002940653,0.000367952,0.0008455534,0.00105925,0.01722835,0.007010171],"genre_scores_gemma":[0.8201111,0.0001032969,0.1763507,0.0002855671,0.00003343558,0.0003114633,0.0005641974,0.0003489137,0.001891327],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009785872,"threshold_uncertainty_score":0.02405542,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02079052594779464,"score_gpt":0.3071956904737791,"score_spread":0.2864051645259845,"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."}}