{"id":"W4365140000","doi":"10.1016/j.jcmg.2023.01.018","title":"Can Deep Learning Detect Incidental Abnormal Cardiac Uptake Related to Amyloidosis on Routine Bone Scintigraphy?","year":2023,"lang":"en","type":"letter","venue":"JACC. Cardiovascular imaging","topic":"Amyloidosis: Diagnosis, Treatment, Outcomes","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Bone scintigraphy; Medicine; Cardiac amyloidosis; Amyloidosis; Scintigraphy; Deep learning; Radiology; Nuclear medicine; Artificial intelligence; Pathology; Computer science","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":["metaepi_narrow"],"category_scores_codex":[0.001322205,0.001475936,0.001967753,0.0009570029,0.0005173664,0.0003228255,0.0008540778,0.001106523,0.00003788402],"category_scores_gemma":[0.0005630822,0.001564991,0.005260802,0.001022757,0.0001823164,0.00002430826,0.0008677033,0.002270296,0.0004292409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004503102,"about_ca_system_score_gemma":0.0001501714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000992339,"about_ca_topic_score_gemma":0.0000773224,"domain_scores_codex":[0.9922528,0.0008379708,0.001045427,0.002523897,0.001556683,0.001783253],"domain_scores_gemma":[0.9964153,0.0001252777,0.0003899574,0.002439453,0.0002649626,0.0003650645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000220036,0.000144596,0.1433162,0.0004767818,0.03622905,0.00705685,0.0006547188,0.01132209,0.0106072,0.000005705172,0.6782279,0.1117388],"study_design_scores_gemma":[0.002782527,0.0004042874,0.06162327,0.0004565479,0.003722911,0.0003451447,0.0003985166,0.00008271974,0.02340921,0.00001777875,0.9036081,0.003148934],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7609989,0.06681281,0.0007026063,0.149947,0.008911114,0.006181251,0.0009119803,0.002060493,0.003473843],"genre_scores_gemma":[0.8818545,0.005288873,0.0008858913,0.09461909,0.006252363,0.001414142,0.005382124,0.001380798,0.002922214],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2253802,"threshold_uncertainty_score":0.999799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006766348939951048,"score_gpt":0.2278195067500737,"score_spread":0.2210531578101226,"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."}}