{"id":"W4200627902","doi":"10.1002/cnm.3559","title":"Automating fractional flow reserve (FFR) calculation from CT scans: A rapid workflow using unsupervised learning and computational fluid dynamics","year":2021,"lang":"en","type":"article","venue":"International Journal for Numerical Methods in Biomedical Engineering","topic":"Coronary Interventions and Diagnostics","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada; Swansea University; Global Challenges Research Fund","keywords":"Fractional flow reserve; Computational fluid dynamics; Computer science; Workflow; Atheroma; Artificial intelligence; Radiology; Medicine; Coronary angiography; Cardiology; Engineering; Myocardial infarction","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007494151,0.0001909703,0.000363808,0.0003591018,0.0001241134,0.0001217041,0.0001168207,0.0001084601,0.0003482537],"category_scores_gemma":[0.005260466,0.0001937921,0.0002111259,0.0003882334,0.00005279865,0.0001895074,0.000105037,0.0006595568,0.000001335935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005519858,"about_ca_system_score_gemma":0.0002027301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005857949,"about_ca_topic_score_gemma":0.00000309243,"domain_scores_codex":[0.9978742,0.0001667618,0.0007741798,0.0003030852,0.0006162579,0.0002655367],"domain_scores_gemma":[0.9968147,0.0022352,0.0001448416,0.00007632848,0.0004546166,0.0002742801],"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":[0.0002859062,0.0005169741,0.01838322,0.0001018865,0.0006719865,0.0009030126,0.0001418758,0.4073617,0.006051382,0.0005721276,0.00009782095,0.5649121],"study_design_scores_gemma":[0.002007506,0.0001089723,0.01549337,0.0008077438,0.00006811863,0.001511302,0.00009414408,0.9760599,0.0001108905,0.001211519,0.002351175,0.0001753304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08212543,0.0006832729,0.913788,0.001447138,0.001702452,0.0001173909,0.0000703777,0.00004828219,0.00001761847],"genre_scores_gemma":[0.1665635,0.00008120722,0.8320113,0.0001270228,0.0006487881,0.00001388262,0.0004905972,0.0000339147,0.00002973733],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5686982,"threshold_uncertainty_score":0.7902611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03134073442057932,"score_gpt":0.3987160302871332,"score_spread":0.3673752958665539,"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."}}