{"id":"W4402035226","doi":"10.1162/imag_a_00294","title":"Regional deep atrophy: Using temporal information to automatically identify regions associated with Alzheimer’s disease progression from longitudinal MRI","year":2024,"lang":"en","type":"article","venue":"Imaging Neuroscience","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":0,"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; National Institute on Aging; Alzheimer's Association","keywords":"Atrophy; Disease; Magnetic resonance imaging; Neuroscience; Medicine; Alzheimer's disease; Pathology; Artificial intelligence; Computer science; Psychology; Radiology","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":[0.0002422977,0.0001594573,0.0001404142,0.0002812915,0.0002601485,0.0005318327,0.0001650046,0.00001911754,0.00003198681],"category_scores_gemma":[0.0003016804,0.0001213727,0.00006579924,0.0008388355,0.0002677334,0.001176862,0.0001239581,0.0002115826,0.0000503159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009436728,"about_ca_system_score_gemma":0.0004178135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004507944,"about_ca_topic_score_gemma":0.000003594654,"domain_scores_codex":[0.9977605,0.00006494534,0.0002426582,0.0004115778,0.001117637,0.0004026717],"domain_scores_gemma":[0.9990204,0.00007012378,0.00006106375,0.0002117762,0.0002133358,0.0004232823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003674359,0.0003228667,0.96686,0.000085345,0.00005170056,0.001946667,0.0003912954,0.0001432822,0.01321945,0.0002343727,0.001992252,0.01438532],"study_design_scores_gemma":[0.0003661015,0.0001598918,0.7988379,0.0008097321,0.0001649368,0.00006092451,0.00003971986,0.1981643,0.0002101816,0.0001721628,0.000868823,0.0001453208],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9054972,0.0002327848,0.08407751,0.008501716,0.0003079619,0.0008027599,0.00002725307,0.0003396822,0.0002131175],"genre_scores_gemma":[0.996177,0.000005653385,0.002242725,0.001350107,0.00006019852,0.00003613625,0.0000613905,0.00001617359,0.00005057509],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.198021,"threshold_uncertainty_score":0.5128475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04808845911245197,"score_gpt":0.3775961348535567,"score_spread":0.3295076757411047,"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."}}