{"id":"W4410447130","doi":"10.3233/shti250581","title":"Practical Approach for Evaluating Machine Learning Anomaly Detection Algorithms for Epidemic Early Warning Systems","year":2025,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Anomaly detection; Machine learning; Warning system; Artificial intelligence; Data mining; Acinetobacter baumannii; Isolation (microbiology); Gold standard (test); Algorithm; Bioinformatics; Statistics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002773455,0.0001575593,0.0006428739,0.0005458563,0.0004330581,0.00001133758,0.00006634066,0.0001884709,2.23806e-7],"category_scores_gemma":[0.008486094,0.0001393885,0.00004056152,0.0005146824,0.0002120393,0.0001539529,0.0001263924,0.0005296565,6.721525e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000216408,"about_ca_system_score_gemma":0.0001679363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002707806,"about_ca_topic_score_gemma":0.000009570962,"domain_scores_codex":[0.9982253,0.00008419193,0.0009878309,0.0001835934,0.0001105534,0.0004085419],"domain_scores_gemma":[0.9982561,0.0008315434,0.0004246773,0.0001969245,0.0002430796,0.00004769638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00163514,0.0002869339,0.3649895,0.06247633,0.001200563,0.000004741962,0.006450626,0.003124772,0.00004829909,0.01500499,0.001610039,0.5431681],"study_design_scores_gemma":[0.0027216,0.001548385,0.002782421,0.0008064067,0.0000792686,0.00005220557,0.01273091,0.9706885,0.00002888426,0.0005778932,0.007829517,0.0001540128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1421426,0.01786094,0.8300415,0.003038701,0.0006324444,0.005324006,0.00006886981,0.0005399076,0.0003510538],"genre_scores_gemma":[0.8114737,0.00151828,0.18512,0.000393204,0.00004491981,0.001220277,0.00008067374,0.00001668778,0.0001322327],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9675637,"threshold_uncertainty_score":0.9998658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.125940279042768,"score_gpt":0.4670066638985366,"score_spread":0.3410663848557686,"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."}}