{"id":"W4220964562","doi":"10.1007/s11548-022-02578-3","title":"Quantifying uncertainty in machine learning classifiers for medical imaging","year":2022,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"St. Francis Xavier University; Ontario Institute for Cancer Research; University of Toronto","funders":"","keywords":"Interpretability; Artificial intelligence; Machine learning; Computer science; Metric (unit); Context (archaeology); Medical imaging; Convolutional neural network; Boundary (topology); Test set; Set (abstract data type); Confidence interval; Pattern recognition (psychology); Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01359918,0.00106933,0.002040688,0.004213909,0.001124515,0.003819516,0.001549918,0.002898889,0.0007568499],"category_scores_gemma":[0.07203825,0.0007050289,0.001112608,0.002077409,0.001902239,0.004670346,0.002727954,0.002455459,0.0001908727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002123565,"about_ca_system_score_gemma":0.001351947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002134134,"about_ca_topic_score_gemma":0.001577756,"domain_scores_codex":[0.9904795,0.002724947,0.0009209283,0.0009450332,0.004418127,0.0005113352],"domain_scores_gemma":[0.9173442,0.07219968,0.003676579,0.002024386,0.004198958,0.0005562447],"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":[0.0004198323,0.000145022,0.01402918,0.0004255751,0.0002428516,0.0002018976,0.0003098388,0.718657,0.004241647,0.04033718,0.001814284,0.2191757],"study_design_scores_gemma":[0.000006490377,0.0000678206,0.00115204,0.00004543751,0.00002762872,0.00006777476,0.00003356108,0.9590032,0.001889432,0.03726208,0.0004271273,0.00001731198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05507562,0.002931164,0.9393439,0.0008038622,0.000101755,0.00006286046,0.0001482425,0.0002953256,0.001237143],"genre_scores_gemma":[0.8695709,0.0009520742,0.1276251,0.0002454687,0.0003216678,0.0001018044,0.0003639991,0.00007893511,0.0007400957],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01359918,"threshold_uncertainty_score":0.07192022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04543149845366259,"score_gpt":0.3438277369703598,"score_spread":0.2983962385166972,"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."}}