{"id":"W3176332381","doi":"10.3171/2021.4.focus21134","title":"Automated prediction of final infarct volume in patients with large-vessel occlusion acute ischemic stroke","year":2021,"lang":"en","type":"article","venue":"Neurosurgical FOCUS","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institute of Neurological Disorders and Stroke","keywords":"Neuroradiology; Medicine; Stroke (engine); Radiology; Receiver operating characteristic; Occlusion; Thrombolysis; Angiography; Neurology; Computed tomography angiography; Infarction; Diffusion MRI; Magnetic resonance imaging; Nuclear medicine; Internal medicine; Myocardial infarction","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001088955,0.0002107277,0.0004310462,0.0001416499,0.00004000569,0.00001279392,0.0001074875,0.0001313412,0.0002660146],"category_scores_gemma":[0.0001017866,0.0001747107,0.00009933056,0.0004989126,0.00006312913,0.0001060679,0.0002334792,0.00035359,0.00001944489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008171067,"about_ca_system_score_gemma":0.00008165517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001012877,"about_ca_topic_score_gemma":0.000001816705,"domain_scores_codex":[0.9979799,0.00005979803,0.0004694812,0.0004523844,0.0006737713,0.0003647142],"domain_scores_gemma":[0.9990869,0.0000432355,0.0001397762,0.0004021637,0.0001948272,0.0001331662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001528329,0.001303334,0.9343441,0.00009641438,0.0001441186,0.001035754,0.00006358145,0.00003231706,0.02464269,0.00001895968,0.03575868,0.001031738],"study_design_scores_gemma":[0.01110386,0.0008256645,0.924871,0.0001574894,0.000213047,0.00007938078,0.0000170346,0.004563274,0.0153908,0.000001139928,0.04262889,0.0001484403],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920068,0.00004547263,0.0001557594,0.0006460857,0.0001456242,0.0003903424,0.0002010827,0.0001890069,0.006219869],"genre_scores_gemma":[0.9968697,0.00003206841,0.0004491424,0.0002621023,0.0000421249,0.00001423271,0.0002307173,0.00003138177,0.002068554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009575526,"threshold_uncertainty_score":0.7124494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00785950158440515,"score_gpt":0.2308573056770205,"score_spread":0.2229978040926153,"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."}}