{"id":"W3007894695","doi":"10.1016/j.media.2020.101670","title":"Embedding high-dimensional Bayesian optimization via generative modeling: Parameter personalization of cardiac electrophysiological models","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiac electrophysiology and arrhythmias","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health; National Science Foundation","keywords":"Embedding; Generative model; Computer science; Bayesian optimization; Dimension (graph theory); Parameter space; Dimensionality reduction; Bayesian probability; Artificial intelligence; Space (punctuation); Encoder; Code (set theory); Generative grammar; Range (aeronautics); Algorithm; Pattern recognition (psychology); Machine learning; Mathematics","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":[0.002614847,0.001052315,0.001630067,0.0009787817,0.0004493743,0.001521848,0.001776263,0.002176957,0.001894742],"category_scores_gemma":[0.01116752,0.001662463,0.001903255,0.0009290551,0.001416388,0.001851487,0.002221882,0.002863829,0.0006937615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009344118,"about_ca_system_score_gemma":0.001128457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00553759,"about_ca_topic_score_gemma":0.007439413,"domain_scores_codex":[0.9989674,0.0005466616,0.00004363852,0.0002200804,0.0001502536,0.00007194316],"domain_scores_gemma":[0.995102,0.0038228,0.0002860813,0.0004014905,0.0002584085,0.0001291196],"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":[0.00005804809,0.00003583809,0.0004504387,0.00005188719,0.00005664492,0.0000436363,0.00009548103,0.9510518,0.001161083,0.01549243,0.0009210636,0.03058163],"study_design_scores_gemma":[0.000002920315,0.0000043003,0.00004468588,0.000004613873,0.000004252981,0.000008649182,0.000002978742,0.9924688,0.0001240955,0.007190287,0.0001400502,0.000004345119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006069963,0.0001199265,0.9930983,0.0001689642,0.00001129659,0.00001344248,0.00005035811,0.0001913281,0.0002764722],"genre_scores_gemma":[0.6058652,0.0008385393,0.3864672,0.0004695556,0.000193459,0.0002756226,0.0009411169,0.0006397944,0.004309497],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00553759,"threshold_uncertainty_score":0.01382875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01482366658211663,"score_gpt":0.2677736190729815,"score_spread":0.2529499524908649,"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."}}