{"id":"W3003775010","doi":"10.1148/radiol.2020191193","title":"Machine Learning for Detecting Early Infarction in Acute Stroke with Non–Contrast-enhanced CT","year":2020,"lang":"en","type":"article","venue":"Radiology","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":191,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hotchkiss Brain Institute; Ontario Brain Institute; Calgary Laboratory Services; University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Contrast (vision); Stroke (engine); Acute stroke; Infarction; Brain infarction; Radiology; Artificial intelligence; Cardiology; Myocardial infarction; Internal medicine; Ischemia; Tissue plasminogen activator","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001346857,0.0001488509,0.0003792949,0.00009797057,0.00004701774,0.000006844962,0.00007541622,0.00005706121,0.00003057969],"category_scores_gemma":[0.0001735703,0.000126435,0.00006896675,0.0001507251,0.0000414647,0.00005355645,0.00003785978,0.0003825845,0.00001183138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008409992,"about_ca_system_score_gemma":0.00002999549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005399837,"about_ca_topic_score_gemma":0.00001697569,"domain_scores_codex":[0.9989993,0.00003627316,0.0002255581,0.0003267453,0.00008658916,0.0003255188],"domain_scores_gemma":[0.9995527,0.0001050507,0.0001050463,0.0001152183,0.00003303208,0.00008894235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.004423638,0.0000604664,0.224751,0.000186652,0.00134452,0.0002838904,0.002436105,0.001483606,0.7188497,0.00004380967,0.0009160693,0.04522052],"study_design_scores_gemma":[0.06621847,0.02678679,0.4196638,0.0004307517,0.002607334,0.001853963,0.002490674,0.1649067,0.2478488,0.00003641736,0.06545445,0.001701818],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9309402,0.00009703432,0.064247,0.001903653,0.00007408758,0.0007069827,0.000004757615,0.00008504286,0.001941291],"genre_scores_gemma":[0.9937606,0.00003206139,0.004361805,0.0009846312,0.0002076842,0.0001042473,0.00003136691,0.00003001982,0.000487545],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4710009,"threshold_uncertainty_score":0.5155869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01057149645567269,"score_gpt":0.2452212766439766,"score_spread":0.2346497801883039,"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."}}