{"id":"W4391952459","doi":"10.1161/circimaging.123.015495","title":"Machine Learning and Bias in Medical Imaging: Opportunities and Challenges","year":2024,"lang":"en","type":"review","venue":"Circulation Cardiovascular Imaging","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Center for Advancing Translational Sciences; National Heart, Lung, and Blood Institute; National Institutes of Health; Alexion Pharmaceuticals; AstraZeneca; American Heart Association","keywords":"Medical diagnosis; Medical imaging; Leverage (statistics); Modalities; Computer science; Health care; Precision medicine; Neuroimaging; Quality (philosophy); Artificial intelligence; Machine learning; Medical physics; Risk analysis (engineering); Medicine; Radiology; Pathology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002115405,0.0003307051,0.00132742,0.0006540708,0.0001002993,0.0000931742,0.00005670416,0.000182837,0.00003171893],"category_scores_gemma":[0.0005961596,0.0002912207,0.0005047441,0.0002374382,0.0001456833,0.0001354321,0.00008524794,0.0008037683,0.00001829729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000165015,"about_ca_system_score_gemma":0.0004641289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002735079,"about_ca_topic_score_gemma":0.00001119104,"domain_scores_codex":[0.9974774,0.0003684321,0.0007108081,0.0006110537,0.0005490303,0.0002832598],"domain_scores_gemma":[0.9990538,0.0002182591,0.0001044619,0.0002813831,0.00009865718,0.000243398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001213261,0.0000093679,0.001395487,0.02006236,0.0002416402,0.0003468225,0.0004854647,0.000001877335,2.739869e-8,0.0001726086,0.00001302402,0.9772701],"study_design_scores_gemma":[0.00005022632,0.000005253712,0.0001522224,0.01567065,0.001746202,0.002546366,0.001165608,0.005403299,1.37488e-7,0.000152556,0.972852,0.0002554939],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00003848091,0.9955671,0.0001326037,0.002446607,0.0004075676,0.0005185301,0.000002723762,0.00009889668,0.0007874954],"genre_scores_gemma":[0.006034547,0.9930186,0.00003054492,0.00007850918,0.0005257805,0.00006788071,0.0001294277,0.00007504359,0.00003969507],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9770146,"threshold_uncertainty_score":0.999954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4068679023569428,"score_gpt":0.4413136394618544,"score_spread":0.03444573710491156,"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."}}