{"id":"W4224223045","doi":"10.3389/fmed.2022.894726","title":"Using Deep Learning Radiomics to Distinguish Cognitively Normal Adults at Risk of Alzheimer’s Disease From Normal Control: An Exploratory Study Based on Structural MRI","year":2022,"lang":"en","type":"article","venue":"Frontiers in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Pfizer; Novartis Pharmaceuticals Corporation; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Eisai; National Institute on Aging; Alzheimer's Association","keywords":"Artificial intelligence; Alzheimer's Disease Neuroimaging Initiative; Support vector machine; Positron emission tomography; Neuroimaging; Pattern recognition (psychology); Medicine; Machine learning; Computer science; Alzheimer's disease; Disease; Nuclear medicine; Psychology; Pathology; Neuroscience","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001618758,0.0003877471,0.001120712,0.0006093014,0.000485591,0.00001259002,0.0003068893,0.00006037944,0.0002479427],"category_scores_gemma":[0.001986899,0.0003540168,0.0001210887,0.0005170526,0.0002947004,0.0001065957,0.0001684407,0.001427776,0.000001232641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000393726,"about_ca_system_score_gemma":0.0001643121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007503426,"about_ca_topic_score_gemma":0.00004613984,"domain_scores_codex":[0.9956196,0.001067029,0.0008222833,0.0007374058,0.001200899,0.0005527897],"domain_scores_gemma":[0.9978651,0.0002872112,0.0004640647,0.0004552874,0.00015357,0.0007747815],"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":[0.009068847,0.0003676415,0.8462204,0.00003475837,0.0002484949,0.0006000454,0.007852952,0.1246017,0.0001376545,0.000001827126,0.0005583327,0.01030731],"study_design_scores_gemma":[0.01409632,0.002298386,0.3026756,0.0002449255,0.0009704047,0.000007901583,0.01097547,0.6680866,0.00001613808,0.00001878933,0.0003366423,0.0002727857],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9686215,0.0009233904,0.02679967,0.0005837254,0.001574854,0.001208349,0.0001073864,0.00007466193,0.0001064526],"genre_scores_gemma":[0.9881657,0.00001656871,0.008978844,0.001549225,0.0007495304,0.00007114588,0.0003643535,0.00008663734,0.00001799054],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5435448,"threshold_uncertainty_score":0.9998912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01561495627933334,"score_gpt":0.287864877587212,"score_spread":0.2722499213078787,"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."}}