{"id":"W4323035821","doi":"10.1099/mgen.0.000929","title":"Epidemiological cluster identification using multiple data sources: an approach using logistic regression","year":2023,"lang":"en","type":"article","venue":"Microbial Genomics","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"European Commission","keywords":"Cluster analysis; Pairwise comparison; Spatial epidemiology; Cluster (spacecraft); Data mining; Computational biology; Epidemiology; Logistic regression; Biology; Computer science; Statistics; Mathematics; Medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.001622979,0.0002308877,0.0004563812,0.0001393559,0.0002168507,0.00006793394,0.000532688,0.0001822907,0.0000236515],"category_scores_gemma":[0.0009773534,0.0001970653,0.00008183045,0.0002849232,0.0001827848,0.0002104012,0.0007022265,0.0002199592,0.000149645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002196846,"about_ca_system_score_gemma":0.0001448413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001220647,"about_ca_topic_score_gemma":0.00001681796,"domain_scores_codex":[0.9976423,0.0003560672,0.0005716565,0.0008532371,0.0001473522,0.0004293899],"domain_scores_gemma":[0.9977248,0.000164496,0.000257111,0.001576359,0.00008012114,0.0001971702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005441062,0.00033062,0.03645296,0.0003080076,0.00008773258,0.00005402765,0.0003129405,0.02714764,0.9250579,0.00001170703,0.005601586,0.004090779],"study_design_scores_gemma":[0.001076018,0.00002623169,0.01616437,0.00009007405,0.0001546057,0.00009377812,0.0002247682,0.9738246,0.0007912315,0.00004365441,0.007201219,0.0003094439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9379583,0.000145215,0.05950955,0.00008387696,0.0003520849,0.0005419693,0.001144613,0.0002458923,0.00001849376],"genre_scores_gemma":[0.9309171,0.00004823465,0.04871872,0.0004930684,0.0007439428,0.000005166235,0.01884357,0.00007356717,0.0001565812],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.946677,"threshold_uncertainty_score":0.803609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2749071077727216,"score_gpt":0.388502096364703,"score_spread":0.1135949885919814,"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."}}