{"id":"W4407937031","doi":"10.1101/2025.02.24.25322787","title":"DUNE: a versatile neuroimaging encoder captures brain complexity across three major diseases: cancer, dementia and schizophrenia","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":3,"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; 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; Alzheimer's Association","keywords":"Neuroimaging; Schizophrenia (object-oriented programming); Dementia; Neuroscience; Psychology; Computer science; Medicine; Psychiatry; Disease; Internal medicine","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":[0.0004943199,0.00053126,0.0002948655,0.0005242265,0.0001573503,0.0004203469,0.0004158952,0.0004298321,0.001307773],"category_scores_gemma":[0.002237777,0.0002272589,0.0003449507,0.0002440435,0.0002705049,0.0005132997,0.0007781342,0.0006897437,0.0003151318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004569048,"about_ca_system_score_gemma":0.0005622274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004212383,"about_ca_topic_score_gemma":0.006201313,"domain_scores_codex":[0.9998811,0.00002846189,0.000007655244,0.00003992589,0.0000233608,0.00001944747],"domain_scores_gemma":[0.9994206,0.0002990629,0.00006263406,0.00006911015,0.0001163169,0.00003223589],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008284033,0.0004077254,0.05153413,0.0002147646,0.0002907242,0.0005183917,0.0002109428,0.3350477,0.04794791,0.008913695,0.01745711,0.5366286],"study_design_scores_gemma":[0.00002918207,0.0001317993,0.01048039,0.00003121326,0.00003773708,0.0002659064,0.00003240167,0.9712398,0.01130769,0.003785565,0.00262782,0.00003052864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4521294,0.001207146,0.5342933,0.001054183,0.0002290686,0.0001461788,0.004733882,0.003537496,0.00266929],"genre_scores_gemma":[0.8990298,0.000385275,0.09290154,0.0002438664,0.00005128597,0.0001699394,0.003896998,0.0001181632,0.003203097],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004212383,"threshold_uncertainty_score":0.008375704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05148883078287399,"score_gpt":0.3197627171703509,"score_spread":0.268273886387477,"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."}}