{"id":"W3081451312","doi":"10.3389/fneur.2020.00889","title":"Functional Outcome Prediction in Ischemic Stroke: A Comparison of Machine Learning Algorithms and Regression Models","year":2020,"lang":"en","type":"article","venue":"Frontiers in Neurology","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hotchkiss Brain Institute; University of Calgary","funders":"","keywords":"Interquartile range; Logistic regression; Machine learning; Brier score; Random forest; Receiver operating characteristic; Medicine; Lasso (programming language); Modified Rankin Scale; Support vector machine; Artificial intelligence; Algorithm; Stroke (engine); Statistics; Internal medicine; Computer science; Mathematics; Ischemic stroke","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":[0.02783536,0.001666754,0.002126896,0.003696758,0.0003125815,0.001920435,0.001270151,0.001482683,0.0007111497],"category_scores_gemma":[0.04465454,0.000362368,0.001676718,0.002385532,0.0006645939,0.002080023,0.0009530598,0.001571065,0.0003237539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001035808,"about_ca_system_score_gemma":0.001130222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005125927,"about_ca_topic_score_gemma":0.002243793,"domain_scores_codex":[0.9878706,0.009466975,0.0005587505,0.0008944899,0.0009893116,0.0002198054],"domain_scores_gemma":[0.9420717,0.05316159,0.001781847,0.001069739,0.001588227,0.0003269707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00490845,0.001133874,0.1238485,0.001049003,0.004429879,0.000126405,0.0002873086,0.5592043,0.0004750233,0.006975422,0.003733393,0.2938284],"study_design_scores_gemma":[0.0001577285,0.001161378,0.01434831,0.0001831339,0.0002619923,0.00006905766,0.00009407933,0.9785186,0.0002055583,0.004192404,0.0007622304,0.00004546941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7039061,0.04522048,0.2372737,0.00467897,0.0006755754,0.0003997574,0.001554583,0.001006574,0.005284377],"genre_scores_gemma":[0.9321308,0.008089306,0.05605544,0.0005137785,0.0004629612,0.0002765251,0.001691912,0.0001451147,0.0006342521],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02783536,"threshold_uncertainty_score":0.1472092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03015120809581863,"score_gpt":0.2690890907985148,"score_spread":0.2389378827026962,"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."}}