{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000100186,0.0001035154,0.0001657533,0.00005148807,0.00009795889,0.00001929166,0.0001105157,0.0002131652,0.00007602789],"category_scores_gemma":[0.0003995038,0.0001063847,0.00004413409,0.00008836346,0.00006577275,0.000004511483,0.00005291391,0.00009622183,7.557237e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001766592,"about_ca_system_score_gemma":0.00003279273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007651402,"about_ca_topic_score_gemma":0.0002008832,"domain_scores_codex":[0.9990823,0.0001397919,0.000311002,0.0003031111,0.00003407673,0.0001297493],"domain_scores_gemma":[0.9995027,0.00002607147,0.0001587892,0.000186028,0.0001042825,0.00002216286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001307737,0.00002813127,0.09509381,0.00004034668,0.0000365289,3.343144e-8,0.00001408486,0.0000175353,0.9041551,0.00006801741,0.0002262638,0.0001893241],"study_design_scores_gemma":[0.00111641,0.000132589,0.07450575,0.00007424429,0.00005360048,0.00000138179,0.00001726625,0.0004724593,0.911186,0.0001449856,0.01210325,0.0001921127],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9978158,0.00006460006,0.0009398701,0.00007965448,0.0003908932,0.0001405728,0.0004468467,0.00002586772,0.00009585953],"genre_scores_gemma":[0.9910851,0.00002257906,0.000790234,0.00005398285,0.0001298726,0.000003689813,0.007590136,0.000008625394,0.0003157842],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02058806,"threshold_uncertainty_score":0.4338243,"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."}}