{"id":"W4367849092","doi":"10.32920/22734407","title":"Interpreting Uncertainty in Model Predictions for Covid-19 Diagnosis","year":2023,"lang":"en","type":"preprint","venue":"","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Interpretability; Benchmark (surveying); Computer science; Convolutional neural network; Coronavirus disease 2019 (COVID-19); Artificial intelligence; Machine learning; Bayesian probability; Uncertainty quantification; Uncertainty analysis; Data mining; Simulation; Medicine; Pathology; Cartography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003825172,0.001482415,0.0006627521,0.00181436,0.0004675442,0.002488245,0.0009875726,0.001968514,0.00203113],"category_scores_gemma":[0.02366574,0.0004364642,0.0008299501,0.0006886121,0.0009784605,0.001637426,0.001581468,0.002029539,0.0003507457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002176175,"about_ca_system_score_gemma":0.001307011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02028745,"about_ca_topic_score_gemma":0.01680857,"domain_scores_codex":[0.9986814,0.0004913844,0.00008086039,0.0003189836,0.0003112688,0.0001160476],"domain_scores_gemma":[0.9884565,0.009218277,0.0007678671,0.000521314,0.0008244555,0.0002115825],"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":[0.0003581755,0.00005461913,0.02012214,0.0001545072,0.00009387734,0.0005014327,0.00031552,0.9070368,0.002187061,0.008057513,0.006709928,0.05440853],"study_design_scores_gemma":[0.000007920249,0.00001697037,0.001344,0.00003504019,0.000008351493,0.00005818159,0.0000355237,0.9871827,0.00111672,0.00946716,0.000715813,0.00001157956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3023651,0.004267568,0.6629253,0.009801203,0.000362252,0.0001186341,0.006265063,0.007171616,0.006723214],"genre_scores_gemma":[0.9440799,0.0004511828,0.05077225,0.0003702755,0.0001101131,0.00004410438,0.002859547,0.0002443661,0.001068358],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02028745,"threshold_uncertainty_score":0.04033875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1237903759733299,"score_gpt":0.4106025194866126,"score_spread":0.2868121435132827,"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."}}