{"id":"W4412688249","doi":"10.1016/j.knosys.2025.114123","title":"BayTTA: Uncertainty-aware medical image classification with optimized test-time augmentation using Bayesian model averaging","year":2025,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Bayesian probability; Computer science; Artificial intelligence; Test (biology); Bayesian inference; Pattern recognition (psychology); Machine learning; Statistics; Data mining; Mathematics; Geology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001129643,0.0004082724,0.0007645351,0.0006406077,0.0003108955,0.0001605963,0.0002460229,0.0002878789,0.000104177],"category_scores_gemma":[0.0008542776,0.0003575968,0.0001551166,0.0009468097,0.0001873177,0.0001830968,0.0000521156,0.0003910961,0.00008036136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001744576,"about_ca_system_score_gemma":0.003673616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002922853,"about_ca_topic_score_gemma":0.00003775348,"domain_scores_codex":[0.9968092,0.0003085048,0.0008133097,0.0007863726,0.000802775,0.0004798127],"domain_scores_gemma":[0.9966714,0.00121552,0.0002804438,0.0007476498,0.0007426062,0.0003424013],"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":[0.002557614,0.003421537,0.01055921,0.008379905,0.000721263,0.0002782874,0.001921092,0.8254399,0.09810557,0.0004417541,0.04168934,0.006484504],"study_design_scores_gemma":[0.006897746,0.0001144284,0.0002434487,0.005017201,0.000415765,0.00002136164,0.0002487611,0.9832453,0.002470713,0.000008962161,0.0009923764,0.0003239267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02415191,0.0003743556,0.9569055,0.01304002,0.0005864903,0.002300456,0.00004194894,0.0006548706,0.001944417],"genre_scores_gemma":[0.988764,0.000007585445,0.006051307,0.002676999,0.0002499197,0.000289342,0.0002110581,0.0000879501,0.00166179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9646121,"threshold_uncertainty_score":0.9998876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02890409014786394,"score_gpt":0.338301466179972,"score_spread":0.3093973760321081,"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."}}