{"id":"W4405621961","doi":"10.1016/j.compbiomed.2024.109528","title":"Pinning down the accuracy of physics-informed neural networks under laminar and turbulent-like aortic blood flow conditions","year":2024,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; University of Toronto","keywords":"Laminar flow; Turbulence; Artificial neural network; Flow (mathematics); Blood flow; Cardiology; Statistical physics; Computer science; Physics; Mechanics; Medicine; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001754483,0.00092992,0.0004133726,0.0005296357,0.0003138803,0.0008030549,0.0008003852,0.0008638506,0.001017236],"category_scores_gemma":[0.01040452,0.0004097653,0.0004272128,0.000251384,0.0005693666,0.001153127,0.0009217655,0.001109702,0.0001972804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009353568,"about_ca_system_score_gemma":0.001054853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01024988,"about_ca_topic_score_gemma":0.006860437,"domain_scores_codex":[0.9995767,0.0001012928,0.00004410349,0.0001249808,0.00008954192,0.00006345968],"domain_scores_gemma":[0.9973622,0.001629011,0.0002721813,0.0002685704,0.0003895806,0.00007850663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001953782,0.00004539645,0.006122974,0.00005677187,0.00005675617,0.00003860758,0.000042828,0.9608313,0.002604033,0.0006208748,0.0002963376,0.02908879],"study_design_scores_gemma":[0.0000031827,0.00003510533,0.001416699,0.00001008398,0.000007814033,0.000009848798,0.000007219318,0.9957775,0.002178763,0.0004771456,0.00007106041,0.000005600843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.82196,0.0008745049,0.1711069,0.0005507355,0.0001553458,0.00005419937,0.0002575307,0.001205355,0.00383549],"genre_scores_gemma":[0.9908969,0.00008726454,0.008349779,0.00004883692,0.00001033723,0.00001504047,0.0001762374,0.00002650926,0.0003890423],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01024988,"threshold_uncertainty_score":0.02038044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01708669151592127,"score_gpt":0.3087232858626488,"score_spread":0.2916365943467275,"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."}}