{"id":"W4322495737","doi":"10.1007/s00330-023-09478-3","title":"DEEP MOVEMENT: Deep learning of movie files for management of endovascular thrombectomy","year":2023,"lang":"en","type":"article","venue":"European Radiology","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University College Dublin; National Institute for Health and Care Research; Irish Research eLibrary; Health Research Board; Wellcome Trust; Health Service Executive; Royal College of Surgeons in Ireland; Canadian Institute for Theoretical Astrophysics","keywords":"Medicine; Neuroradiology; Digital subtraction angiography; Occlusion; Interventional radiology; Radiology; Angiography; Stroke (engine); Acute stroke; Artificial intelligence; Surgery; Internal medicine; Neurology; Computer science","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":[0.0006419672,0.0001655335,0.0004670466,0.0002038533,0.0000396784,0.000002544412,0.0002171473,0.00003654594,0.0001842911],"category_scores_gemma":[0.00009014559,0.0001520137,0.0002205532,0.0002600008,0.0001188589,0.00002298938,0.0002505511,0.0001176826,0.00008802449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000034082,"about_ca_system_score_gemma":0.000006304155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003770096,"about_ca_topic_score_gemma":4.875681e-7,"domain_scores_codex":[0.9985574,0.0001476408,0.0004508987,0.0003307882,0.0001806062,0.0003326337],"domain_scores_gemma":[0.9991478,0.0001150455,0.0002032586,0.0004149154,0.00006158711,0.00005736155],"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":[0.002022309,0.001230231,0.06563082,0.01531967,0.02589905,0.004103499,0.009135631,0.02499182,0.2073872,0.03771378,0.1844679,0.422098],"study_design_scores_gemma":[0.02133412,0.003749137,0.4163584,0.0008403499,0.002931666,0.0001454088,0.008574587,0.03103183,0.03530158,0.0004571426,0.4782672,0.001008598],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7372949,0.002444053,0.06715171,0.0004557395,0.0004749471,0.002220283,0.00001760684,0.0003672843,0.1895735],"genre_scores_gemma":[0.9808814,0.001189378,0.01225252,0.0003141682,0.0001758378,0.0000617979,0.0002434148,0.0000912196,0.004790248],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4210894,"threshold_uncertainty_score":0.619894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01581921008182615,"score_gpt":0.2520257214403655,"score_spread":0.2362065113585393,"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."}}