{"id":"W4289519099","doi":"10.2196/36427","title":"Uncertainty Estimation in Medical Image Classification: Systematic Review","year":2022,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Estimation; Artificial intelligence; Data mining; Data science; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00679942,0.0005862238,0.003316784,0.0004674242,0.0001815908,0.0001736686,0.005115114,0.000669772,0.001715273],"category_scores_gemma":[0.01005489,0.0004437006,0.0004683539,0.002127069,0.000169848,0.000894084,0.001679856,0.003252337,0.0004647956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007559307,"about_ca_system_score_gemma":0.002498596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007018466,"about_ca_topic_score_gemma":0.000002831091,"domain_scores_codex":[0.9886698,0.001394634,0.00433425,0.0003899207,0.004663752,0.0005476273],"domain_scores_gemma":[0.9935175,0.002139774,0.002102331,0.001635847,0.00007909616,0.0005254237],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[2.781109e-7,0.00003963906,5.121698e-8,0.6387225,0.00003023999,0.00006652411,0.0003110981,0.00002076369,1.080065e-10,0.005285113,0.0010114,0.3545124],"study_design_scores_gemma":[0.0001497955,0.00001985836,9.811438e-8,0.3857753,0.0001585547,0.0003148981,0.00006170679,0.3783495,1.052745e-9,0.00009573001,0.2347479,0.0003266401],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.426361e-8,0.7809158,0.2124877,0.0005824465,0.0004840862,0.002661607,0.000004352738,0.000250967,0.002612985],"genre_scores_gemma":[5.683487e-7,0.9827147,0.01305929,0.001730154,0.00007953399,0.002048807,0.0002722481,0.00003473426,0.00006001897],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.3783287,"threshold_uncertainty_score":0.9998015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04360340881777357,"score_gpt":0.384361274943199,"score_spread":0.3407578661254254,"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."}}