{"id":"W4415215483","doi":"10.1016/j.neuroscience.2025.10.021","title":"An interpretable Bayesian framework for Alzheimer’s disease prediction with uncertainty quantification","year":2025,"lang":"en","type":"article","venue":"Neuroscience","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"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; Genentech; IXICO; DoD Alzheimer's Disease Neuroimaging Initiative; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Bayesian probability; Leverage (statistics); Modalities; Categorical variable; Dementia; Recall; Disease; Confidence interval","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":[0.0003505528,0.000129253,0.0001074777,0.0001383845,0.0004410425,0.000338929,0.00118786,0.00004672926,0.000002224203],"category_scores_gemma":[0.00048019,0.0001113828,0.00003127578,0.0008886709,0.0001135118,0.0007964678,0.00008531645,0.0002159415,0.00000195162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003782198,"about_ca_system_score_gemma":0.0002966633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000061846,"about_ca_topic_score_gemma":0.00001235593,"domain_scores_codex":[0.9982643,0.0001318897,0.0001964494,0.0008106019,0.0002825683,0.0003142462],"domain_scores_gemma":[0.9983824,0.0001870145,0.00009984485,0.001010239,0.0001320484,0.0001884446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001529946,0.0002067162,0.1341207,0.0001093222,0.000004608617,0.000006406599,0.0005420037,0.08363699,0.001199986,0.7237562,0.0004327586,0.05583133],"study_design_scores_gemma":[0.00008501842,0.0002176427,0.1003298,0.00007235399,0.00001004641,0.000001660815,0.000009605504,0.8874524,0.0001380647,0.009534111,0.002053087,0.00009613296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005862847,0.00005374573,0.9872581,0.004778657,0.001065921,0.0005123373,0.000013347,0.0003416893,0.0001132983],"genre_scores_gemma":[0.9469867,0.000004890087,0.05080439,0.001962689,0.00003600511,0.0001267445,0.000005643319,0.000007873553,0.00006509965],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9411238,"threshold_uncertainty_score":0.4542058,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02886804803780804,"score_gpt":0.346223662535511,"score_spread":0.317355614497703,"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."}}