{"id":"W4389611870","doi":"10.1016/j.jbi.2023.104567","title":"Providing clinical context to the spatio-temporal analysis of 4D CT perfusion to predict acute ischemic stroke lesion outcomes","year":2023,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hotchkiss Brain Institute; Alberta Children's Hospital; University of Calgary","funders":"Alberta Innovates; Canada Research Chairs; Calgary Foundation","keywords":"Stroke (engine); Leverage (statistics); Medicine; Context (archaeology); Deep learning; Artificial intelligence; Lesion; Thrombolysis; Machine learning; Computer science; Radiology; Internal medicine; Surgery","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":[0.003055634,0.0002104798,0.001123184,0.00129743,0.00008990041,0.00004146844,0.0005049456,0.0001129933,0.0001059586],"category_scores_gemma":[0.00172591,0.0001186693,0.0006857206,0.002007198,0.0001662759,0.0001781648,0.0004716027,0.0005251849,0.00005329267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001331103,"about_ca_system_score_gemma":0.0002569852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001646606,"about_ca_topic_score_gemma":0.000005514803,"domain_scores_codex":[0.9949565,0.00005909586,0.002763334,0.0001197159,0.001760146,0.0003411926],"domain_scores_gemma":[0.9970425,0.0004763691,0.00110478,0.0004434384,0.0003514246,0.0005815019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006934865,0.0002911154,0.1930966,0.0001879833,0.005521436,0.0001299846,0.003628751,0.0002129066,0.00107874,0.0000138938,0.7080212,0.08712392],"study_design_scores_gemma":[0.005607621,0.004241372,0.1065506,0.0009956792,0.01104873,0.0001788612,0.01530718,0.07957362,0.003282384,0.00000309987,0.7727895,0.0004213485],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9623457,0.00002141582,0.02239127,0.01350048,0.0005548195,0.0005582031,0.00007872416,0.00003509832,0.0005143489],"genre_scores_gemma":[0.9848131,0.0001163219,0.01007122,0.003620841,0.0002894624,0.000008129515,0.0001056191,0.00001759001,0.0009577099],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08670257,"threshold_uncertainty_score":0.4839192,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0440236753599937,"score_gpt":0.3591097541065776,"score_spread":0.315086078746584,"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."}}