{"id":"W2808156436","doi":"10.48550/arxiv.1806.06415","title":"Feature Learning and Classification in Neuroimaging: Predicting Cognitive Impairment from Magnetic Resonance Imaging","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"National Institutes of Health; Alzheimer's Disease Neuroimaging Initiative; Natural Sciences and Engineering Research Council of Canada; U.S. Department of Defense","keywords":"Neuroimaging; Feature selection; Artificial intelligence; Machine learning; Classifier (UML); Magnetic resonance imaging; Computer science; Functional magnetic resonance imaging; Feature (linguistics); Disease; Cognition; Pattern recognition (psychology); Psychology; Medicine; Neuroscience; Pathology; Radiology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003652867,0.0002699629,0.0003274727,0.0001463502,0.0001188461,0.00007879617,0.0002041638,0.000158057,0.00006689101],"category_scores_gemma":[0.00131843,0.0003069373,0.00005305518,0.000212034,0.0002240527,0.00008906743,0.0005389784,0.0009848947,0.00001006946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001174478,"about_ca_system_score_gemma":0.00006568939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001117478,"about_ca_topic_score_gemma":0.00002931757,"domain_scores_codex":[0.9981291,0.0004047645,0.0001957741,0.0008961794,0.00008683827,0.0002873948],"domain_scores_gemma":[0.9977895,0.00145172,0.0002439093,0.0002582092,0.0001518471,0.0001047987],"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":[0.0002266758,0.0001631972,0.9428459,0.0002500776,0.00002751067,0.0003613576,0.001372547,0.00007613852,0.0001696725,0.02942554,0.0003083812,0.024773],"study_design_scores_gemma":[0.0007247019,0.00007871867,0.3695116,0.0009885376,0.0001355392,0.000003479726,0.0008797493,0.3890734,0.00002323905,0.2380724,0.0001510603,0.000357573],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9088239,0.000509057,0.08717081,0.0001319859,0.000189394,0.0004354244,0.00008703142,0.0001233102,0.00252909],"genre_scores_gemma":[0.9834238,0.0002041054,0.015796,0.0000365027,0.00008556889,0.000002655796,0.00002083971,0.00002986326,0.0004006863],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5733343,"threshold_uncertainty_score":0.9999382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1074331843540993,"score_gpt":0.2702204259861997,"score_spread":0.1627872416321004,"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."}}