{"id":"W3193885505","doi":"10.1097/rmr.0000000000000290","title":"Improving Ischemic Stroke Care With MRI and Deep Learning Artificial Intelligence","year":2021,"lang":"en","type":"review","venue":"Topics in Magnetic Resonance Imaging","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Greo","funders":"","keywords":"Stroke (engine); Magnetic resonance imaging; Deep learning; Medicine; Acute stroke; Ischemic stroke; Artificial intelligence; Physical medicine and rehabilitation; Intensive care medicine; Medical physics; Radiology; Computer science; Internal medicine; Ischemia; Emergency department; Nursing; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002058242,0.0004911131,0.001327296,0.0002544401,0.00008981054,0.0001060319,0.0002308258,0.0001488289,0.00008028599],"category_scores_gemma":[0.0002081905,0.0004346076,0.0001447092,0.0003814349,0.0001760531,0.00007277478,0.0003790387,0.00122129,0.000008955669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000281043,"about_ca_system_score_gemma":0.0002121841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005476463,"about_ca_topic_score_gemma":0.00003347205,"domain_scores_codex":[0.9974305,0.00008254913,0.0006969562,0.000877939,0.000381755,0.0005303028],"domain_scores_gemma":[0.9988648,0.0001438219,0.0002411076,0.0005424572,0.000104722,0.0001030387],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000008277268,0.00001506332,0.001059027,0.009400768,0.00001362003,0.0005405233,0.0003034403,0.000002057888,0.000003916009,0.00007454338,0.00004055691,0.9885382],"study_design_scores_gemma":[0.0001713602,0.00008495279,0.00005187012,0.01920319,0.0005046517,0.0002636431,0.001600681,0.0008446818,0.00002400865,0.000003229911,0.9768359,0.0004118306],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00007269937,0.9869636,0.00191222,0.0001011156,0.0001172183,0.0008077117,0.000004695513,0.00005489987,0.009965882],"genre_scores_gemma":[0.0001019849,0.9794679,0.01753619,0.0000648589,0.000339244,0.0001224749,0.00005984752,0.00008043381,0.00222706],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9881264,"threshold_uncertainty_score":0.9998106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01806137818093913,"score_gpt":0.2943337357527511,"score_spread":0.276272357571812,"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."}}