{"id":"W3015264156","doi":"10.1016/j.jacr.2020.03.012","title":"Machine Learning for Automation of Radiology Protocols for Quality and Efficiency Improvement","year":2020,"lang":"en","type":"article","venue":"Journal of the American College of Radiology","topic":"Radiology practices and education","field":"Medicine","cited_by":88,"is_retracted":false,"has_abstract":false,"ca_institutions":"Trillium Health Centre; University of Toronto","funders":"","keywords":"Workflow; Computer science; Artificial intelligence; Random forest; Machine learning; Protocol (science); Automation; Thresholding; Software deployment; Artificial neural network; Data mining; Medicine; Software engineering; Database; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00416589,0.0007932017,0.0009245216,0.00212589,0.0007029062,0.001989076,0.001328258,0.0008439622,0.002342633],"category_scores_gemma":[0.01826223,0.0004435894,0.0009172007,0.001431384,0.0006424396,0.001589005,0.0009644212,0.002404298,0.00107981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001996015,"about_ca_system_score_gemma":0.003729604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006337029,"about_ca_topic_score_gemma":0.006693837,"domain_scores_codex":[0.9960946,0.00163605,0.0003256467,0.0006726042,0.001040639,0.0002304268],"domain_scores_gemma":[0.9875609,0.006904955,0.001358021,0.00149794,0.002499661,0.0001785365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002719083,0.0005028484,0.007571036,0.0002598653,0.0001575526,0.00007488962,0.0001362061,0.1844674,0.009348249,0.0099334,0.009998895,0.7772777],"study_design_scores_gemma":[0.00002831439,0.00008582982,0.002111885,0.00005027782,0.00003126802,0.00006792865,0.00002839524,0.9677526,0.01185843,0.01360012,0.00436012,0.00002490856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02108037,0.0008532935,0.9701869,0.001113818,0.0001241501,0.0001594242,0.0002464096,0.004456843,0.001778751],"genre_scores_gemma":[0.4338072,0.0006299777,0.5619423,0.0002985288,0.0001554824,0.0001782946,0.0009023107,0.0002639157,0.00182195],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006337029,"threshold_uncertainty_score":0.02203161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04578461532657702,"score_gpt":0.3800704747900329,"score_spread":0.3342858594634558,"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."}}