{"id":"W2964249514","doi":"10.1109/bigdia.2018.8632797","title":"Feature Learning and Classification in Neuroimaging: Predicting Cognitive Impairment from Magnetic Resonance Imaging","year":2018,"lang":"en","type":"article","venue":"","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Neuroimaging; Feature selection; Artificial intelligence; Computer science; Machine learning; Magnetic resonance imaging; Classifier (UML); Functional magnetic resonance imaging; Feature (linguistics); Pattern recognition (psychology); Cognition; Psychology; Neuroscience; Medicine","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003066363,0.0001082035,0.0001375547,0.00004770453,0.0000852369,0.00005819138,0.00005117189,0.00003239624,0.0001597302],"category_scores_gemma":[0.002278122,0.00009458727,0.00001241597,0.0001198847,0.0001294845,0.00007100215,0.00005978323,0.0002447354,0.00001044422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002083645,"about_ca_system_score_gemma":0.00001535904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005036808,"about_ca_topic_score_gemma":0.00002064451,"domain_scores_codex":[0.9990549,0.0001653649,0.0001636329,0.0002967418,0.0001261208,0.0001932216],"domain_scores_gemma":[0.998203,0.001509702,0.0000642844,0.00008337638,0.00008574814,0.00005388938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005188908,0.00005789628,0.6071245,0.00002425335,0.00000261672,0.00001234826,0.00151078,3.079612e-8,0.002020032,0.0149324,0.0004952592,0.373768],"study_design_scores_gemma":[0.0006121767,0.0001532054,0.8306193,0.0002624114,0.00002092292,0.000006657765,0.00148746,0.09514884,0.0003551423,0.07049897,0.0006724321,0.0001625253],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8437464,0.0009550429,0.1295126,0.001501642,0.0001559244,0.0004574276,0.00002502246,0.0001846129,0.02346131],"genre_scores_gemma":[0.8355811,0.00002160669,0.1637986,0.000133262,0.00008211743,0.00001390912,0.000002725248,0.00001420654,0.0003525196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3736055,"threshold_uncertainty_score":0.3857157,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05031923078923646,"score_gpt":0.3559914082529043,"score_spread":0.3056721774636679,"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."}}