{"id":"W4399912647","doi":"10.1088/1741-2552/ae087d","title":"An interpretable generative multimodal neuroimaging-genomics framework for decoding Alzheimer’s disease","year":2025,"lang":"en","type":"article","venue":"Journal of Neural Engineering","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Fondazione Cassa di Risparmio di Verona Vicenza Belluno e Ancona; Eisai; Ministero dell’Istruzione, dell’Università e della Ricerca; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; Biogen; BioClinica; Eli Lilly and Company; Bristol-Myers Squibb; Foundation for the National Institutes of Health; U.S. Department of Defense; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association; Canadian Institutes of Health Research; National Science Foundation","keywords":"Interpretability; Artificial intelligence; Neuroimaging; Dementia; Grey matter; Computer science; Generative model; Cognition; Default mode network; Neuroscience; Resting state fMRI; Alzheimer's disease; Disease; Machine learning; Psychology; Cognitive psychology; Generative grammar; Medicine; White matter; Pathology; Magnetic resonance imaging","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":[0.0001311268,0.0001319723,0.0001568174,0.00007068414,0.00005335524,0.00006129338,0.000213992,0.00006623068,0.000001725661],"category_scores_gemma":[0.0000888357,0.0001236766,0.0001366268,0.0000520323,0.00001423137,0.00001818657,0.0000496143,0.0001756587,2.097115e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001764859,"about_ca_system_score_gemma":0.00006219206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.695455e-7,"about_ca_topic_score_gemma":4.183194e-7,"domain_scores_codex":[0.9993135,0.00001105021,0.0003197616,0.0001135356,0.00005292209,0.0001892403],"domain_scores_gemma":[0.9994697,0.00003159833,0.0001273393,0.000161175,0.00008702939,0.0001231361],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003428932,0.00005279561,0.0005002486,0.00005372734,0.0002434231,0.00000979095,0.0001105178,0.7440513,0.2376744,0.001747201,0.0007511953,0.01446247],"study_design_scores_gemma":[0.000427058,0.0001876351,0.0005689144,0.00006157697,0.00009170031,0.00001823619,0.00002714244,0.980005,0.01344785,0.0005191286,0.004474437,0.0001713768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3308917,0.001228558,0.6667217,0.00022953,0.0007847251,0.0001118705,0.00001092306,0.000006232056,0.00001474007],"genre_scores_gemma":[0.9363905,0.00005472151,0.06261198,0.0004403375,0.0004576399,0.000004556275,0.00001067056,0.00001810289,0.00001151094],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6054987,"threshold_uncertainty_score":0.5043387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01122829743688899,"score_gpt":0.2757049507213792,"score_spread":0.2644766532844903,"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."}}