{"id":"W3115148371","doi":"10.1016/j.bpsc.2020.12.007","title":"Episodic Memory–Related Imaging Features as Valuable Biomarkers for the Diagnosis of Alzheimer’s Disease: A Multicenter Study Based on Machine Learning","year":2020,"lang":"en","type":"article","venue":"Biological Psychiatry Cognitive Neuroscience and Neuroimaging","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Science and Technology Planning Project of Guangdong Province; H. Lundbeck A/S; Genentech; IXICO; National Natural Science Foundation of China; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; GE Healthcare; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Northern California Institute for Research and Education; Johnson and Johnson Pharmaceutical Research and Development; Merck; Alzheimer's Drug Discovery Foundation; National Key Research and Development Program of China; AbbVie; National Institute on Aging; Alzheimer's Association","keywords":"Episodic memory; Neuroimaging; Magnetic resonance imaging; Alzheimer's Disease Neuroimaging Initiative; Positron emission tomography; Psychology; Cognition; Alzheimer's disease; Disease; Cognitive impairment; Neuroscience; Medicine; Artificial intelligence; Pathology; Computer science; Radiology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005123044,0.0002719908,0.0003056364,0.000136839,0.0005155887,0.00008532499,0.0001901161,0.00002807546,0.00006736424],"category_scores_gemma":[0.002442472,0.0001665973,0.0001852929,0.0005180004,0.0006093488,0.0001087117,0.0001431036,0.0004235631,0.000005473723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006401241,"about_ca_system_score_gemma":0.00009523527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001715573,"about_ca_topic_score_gemma":4.985361e-7,"domain_scores_codex":[0.997486,0.0004028603,0.0003199379,0.0008758647,0.0004633129,0.0004520489],"domain_scores_gemma":[0.9982923,0.0009269573,0.0001473094,0.000141869,0.0001595617,0.0003320425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002183788,0.0009188125,0.9809026,0.00004164393,0.00004187547,0.00006657993,0.0000911529,0.00001478962,0.003363605,0.000008699953,0.0001081247,0.0122584],"study_design_scores_gemma":[0.004329416,0.003764525,0.9488283,0.0001234463,0.000439913,0.000008268898,0.0009379501,0.04012438,0.001068463,0.0000346519,0.0001599659,0.0001807669],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9729925,0.002035576,0.0003123347,0.02087413,0.0002925397,0.002968676,0.00005103698,0.00008764885,0.0003855352],"genre_scores_gemma":[0.9839223,0.0002073857,0.0000384352,0.01551438,0.00005425168,0.0002042991,0.00001599204,0.0000216778,0.00002124892],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04010959,"threshold_uncertainty_score":0.6793641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06070719540462865,"score_gpt":0.3563568831552769,"score_spread":0.2956496877506483,"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."}}