{"id":"W4417458415","doi":"10.1371/journal.pbio.3003539","title":"Biased sampling driven by bacterial population structure confounds machine learning prediction of antimicrobial resistance","year":2025,"lang":"en","type":"article","venue":"PLoS Biology","topic":"Bacterial Identification and Susceptibility Testing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Bayerisches Staatsministerium für Wissenschaft, Forschung und Kunst","keywords":"Sampling (signal processing); Population; Sample size determination; Confounding; Antibiotic resistance; Sample (material); Sampling bias","routes":{"ca_aff":true,"ca_fund":true,"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":[0.017109,0.0007648319,0.001279023,0.0009192703,0.0009413913,0.001951069,0.001336597,0.001511198,0.0005352594],"category_scores_gemma":[0.0478173,0.0006509604,0.001227824,0.0008243219,0.002525427,0.00191377,0.001519589,0.00234848,0.0002571032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001123359,"about_ca_system_score_gemma":0.00111943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005532131,"about_ca_topic_score_gemma":0.006834398,"domain_scores_codex":[0.9932051,0.005010984,0.00025937,0.0009093059,0.0003654056,0.0002498818],"domain_scores_gemma":[0.9619894,0.02997687,0.002628997,0.003921893,0.001076629,0.0004062892],"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":[0.0005147282,0.0001483144,0.3286359,0.0002467386,0.0009902172,0.0003764848,0.0005837754,0.5984346,0.0103398,0.009119438,0.002107528,0.04850248],"study_design_scores_gemma":[0.00004803275,0.0001264259,0.04311118,0.00005352036,0.0001166719,0.0001568044,0.0001401285,0.922906,0.002645428,0.02955036,0.001104831,0.00004065026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8364794,0.001491057,0.1571983,0.002127994,0.00008278133,0.00005883088,0.0004842644,0.0006048541,0.001472548],"genre_scores_gemma":[0.9871789,0.0002648618,0.01138615,0.0003981348,0.00005003608,0.00003471006,0.0004818442,0.00004933839,0.0001560103],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.017109,"threshold_uncertainty_score":0.09048206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0163362487563078,"score_gpt":0.2588358774812706,"score_spread":0.2424996287249628,"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."}}