{"id":"W3024926608","doi":"10.1101/2020.05.14.20101014","title":"Automated Prediction of Ischemic Brain Tissue Fate from Multi-Phase CT-Angiography in Patients with Acute Ischemic Stroke Using Machine Learning","year":2020,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hotchkiss Brain Institute; University of Calgary","funders":"","keywords":"Penumbra; Medicine; Concordance correlation coefficient; Perfusion scanning; Perfusion; Angiography; Stroke (engine); Nuclear medicine; Concordance; Radiology; Cardiology; Internal medicine; Ischemia; 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":[0.001257694,0.0004050671,0.0004083581,0.001189013,0.0001788522,0.0007695195,0.0003984327,0.0005066898,0.0005153536],"category_scores_gemma":[0.004485846,0.0001587692,0.000353565,0.0003111223,0.0002033541,0.0004098842,0.0003569011,0.0004643248,0.0002522069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005388981,"about_ca_system_score_gemma":0.0004186871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001822047,"about_ca_topic_score_gemma":0.002189268,"domain_scores_codex":[0.9996657,0.0001352765,0.00003143776,0.00007372491,0.00005822867,0.00003558114],"domain_scores_gemma":[0.9984908,0.000836923,0.0002499308,0.0001214152,0.0002244484,0.00007637957],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001944933,0.000444941,0.7769437,0.0000828007,0.000225938,0.0003853937,0.0001535404,0.08394333,0.006805355,0.0002802651,0.001365883,0.127424],"study_design_scores_gemma":[0.00005468044,0.0004374917,0.196157,0.00002326173,0.00009267154,0.0006072268,0.00006880752,0.7957749,0.005380491,0.0008978776,0.0004767228,0.00002878748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9786984,0.0002187941,0.01990416,0.000117037,0.000008627065,0.00005043877,0.0003578739,0.0001562895,0.0004883994],"genre_scores_gemma":[0.9937915,0.00005600167,0.005450931,0.00001891244,0.000009530907,0.00002895188,0.000528747,0.00000731197,0.0001081215],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001822047,"threshold_uncertainty_score":0.006651342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01950978299502185,"score_gpt":0.2874586325037239,"score_spread":0.2679488495087021,"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."}}