{"id":"W4281479607","doi":"10.1128/cmr.00179-21","title":"Machine Learning for Antimicrobial Resistance Prediction: Current Practice, Limitations, and Clinical Perspective","year":2022,"lang":"en","type":"review","venue":"Clinical Microbiology Reviews","topic":"Bacterial Identification and Susceptibility Testing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":224,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Sunnybrook Health Science Centre; Discovery Centre; Health Sciences Centre; Agriculture and Agri-Food Canada; Dalhousie University","funders":"Agriculture and Agri-Food Canada; Government of Canada","keywords":"Computer science; Antibiotic resistance; Set (abstract data type); Data science; Perspective (graphical); Machine learning; Resistance (ecology); Bridge (graph theory); Risk analysis (engineering); Artificial intelligence; Medicine; Biology; Antibiotics; Genetics","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0059214,0.0004597026,0.002090091,0.00007016756,0.0003878321,0.00006009845,0.000412894,0.0006831516,0.00005287323],"category_scores_gemma":[0.03269918,0.000403903,0.00133241,0.0001706484,0.0004412813,0.00001077993,0.0004033548,0.001301315,0.00004172731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008900285,"about_ca_system_score_gemma":0.0004539182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002429771,"about_ca_topic_score_gemma":0.00003513713,"domain_scores_codex":[0.9902907,0.004871857,0.002946086,0.001546289,0.00002482367,0.0003202551],"domain_scores_gemma":[0.9945968,0.002405013,0.001902198,0.000684513,0.0002678607,0.0001435753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001321074,0.0004105513,0.0001887158,0.003662128,0.0003624214,5.707789e-7,0.00001856359,1.051662e-7,0.0001042889,0.000130314,0.03244414,0.9625461],"study_design_scores_gemma":[0.0004770643,0.0004813639,0.00001317379,0.001038856,0.00105326,0.00007144942,0.00002039101,0.000001777362,3.089502e-7,0.00001314389,0.9964789,0.0003502729],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001602434,0.9938176,0.0002373626,0.0002014067,0.002544079,0.002443097,0.0005096457,0.00003335901,0.0001974647],"genre_scores_gemma":[0.000002879063,0.9882413,0.002504529,0.0003488049,0.001387732,0.0003307053,0.005923362,0.00005937929,0.001201338],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9640348,"threshold_uncertainty_score":0.9998413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2243570464230603,"score_gpt":0.4664083557123311,"score_spread":0.2420513092892708,"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."}}