{"id":"W3087674758","doi":"10.1055/s-0040-1715892","title":"A Web Application for Adrenal Incidentaloma Identification, Tracking, and Management Using Machine Learning","year":2020,"lang":"en","type":"article","venue":"Applied Clinical Informatics","topic":"Adrenal and Paraganglionic Tumors","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Artificial intelligence; Computer science; Workflow; Natural language processing; Convolutional neural network; Medicine; Machine learning; Identification (biology); Radiology; Database","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":[0.0009889954,0.00115913,0.0004496951,0.001593509,0.0002620354,0.0007459362,0.001199679,0.0008170253,0.01421734],"category_scores_gemma":[0.003282771,0.0004121393,0.0006165383,0.0006246432,0.0001904338,0.001037278,0.001010743,0.0007742023,0.007130241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005489939,"about_ca_system_score_gemma":0.0007535105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002124164,"about_ca_topic_score_gemma":0.002642651,"domain_scores_codex":[0.9995595,0.00007397356,0.00005288669,0.0001233917,0.0001578724,0.00003236224],"domain_scores_gemma":[0.9979227,0.001258279,0.0001551532,0.0001885081,0.0003102435,0.0001651162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001791434,0.001515928,0.01976186,0.001033682,0.0003157877,0.002580015,0.0002890065,0.0217075,0.02326814,0.001509775,0.2283587,0.6978682],"study_design_scores_gemma":[0.0007942758,0.0006142124,0.02774701,0.0003248655,0.0002015214,0.002569452,0.0001310208,0.7550793,0.06206034,0.007874565,0.1423801,0.0002232782],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.04681899,0.0008181265,0.2990003,0.0009492357,0.0002699587,0.001559149,0.02049948,0.621457,0.008627721],"genre_scores_gemma":[0.3676899,0.001079825,0.5229806,0.001776493,0.0003392391,0.002127206,0.06585452,0.0142374,0.02391482],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01421734,"threshold_uncertainty_score":0.04756176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0666414658134195,"score_gpt":0.3565810119903648,"score_spread":0.2899395461769453,"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."}}