{"id":"W4379796979","doi":"10.3389/fnagi.2023.1149871","title":"A cross-sectional study of explainable machine learning in Alzheimer’s disease: diagnostic classification using MR radiomic features","year":2023,"lang":"en","type":"article","venue":"Frontiers in Aging Neuroscience","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; F. Hoffmann-La Roche; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; National Institute on Aging; Alzheimer's Association","keywords":"Entorhinal cortex; Disease; Neuropsychology; Neuroimaging; Psychology; Neurodegeneration; Cognition; Medicine; Artificial intelligence; Pathology; Machine learning; Neuroscience; Hippocampus; Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003624326,0.0003116136,0.0002561185,0.001197804,0.000386001,0.0005401056,0.0003275549,0.0006588205,0.001472433],"category_scores_gemma":[0.006174595,0.0002809437,0.0005602986,0.0004876611,0.0004206965,0.0006076539,0.0004225272,0.0004983233,0.0003392911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002260082,"about_ca_system_score_gemma":0.0001567221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001336206,"about_ca_topic_score_gemma":0.0008759333,"domain_scores_codex":[0.9990547,0.0004522197,0.00008299817,0.000223235,0.0001186092,0.00006812967],"domain_scores_gemma":[0.994911,0.002558063,0.0009701011,0.0005905874,0.0005396635,0.0004307097],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002796751,0.0001653219,0.9974759,0.00000687749,0.0001396022,0.00006690773,0.0002017069,0.00008871563,0.000279657,0.0000276606,0.00003667122,0.001231376],"study_design_scores_gemma":[0.000008763447,0.0004590266,0.997614,0.000003792758,0.00006011474,0.0002394845,0.0002255773,0.001084998,0.0001424675,0.00005149036,0.0001057204,0.000004492451],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9996219,0.00006298909,0.0001678667,0.00001241606,0.000003981561,0.000004763805,0.0000351302,0.000001200666,0.00008971504],"genre_scores_gemma":[0.999713,0.000023479,0.00008899697,0.000006676785,0.000005767975,0.000005278222,0.00007846013,0.000001145795,0.00007723024],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003624326,"threshold_uncertainty_score":0.01916748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03996497671780305,"score_gpt":0.3396083035961586,"score_spread":0.2996433268783555,"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."}}