{"id":"W4212877785","doi":"10.1093/cercor/bhac099","title":"Voxel-based morphometry and a deep learning model for the diagnosis of early Alzheimer’s disease based on cerebral gray matter changes","year":2022,"lang":"en","type":"article","venue":"Cerebral Cortex","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Western Hospital; University of Toronto; University Health Network","funders":"National Natural Science Foundation of China; Li Ka Shing Foundation","keywords":"Voxel-based morphometry; Voxel; Gray (unit); Neuroscience; Neuroimaging; Alzheimer's disease; Disease; Artificial intelligence; Medicine; Pathology; Magnetic resonance imaging; Psychology; White matter; Computer science; Radiology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003405799,0.0001977028,0.0002665185,0.0002528629,0.0003765411,0.00003750009,0.0001597614,0.00003440746,0.002276826],"category_scores_gemma":[0.00008472536,0.0001470752,0.0001672026,0.0002781728,0.0001446086,0.00004611861,0.0001185735,0.0003282418,0.00001325992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004393492,"about_ca_system_score_gemma":0.0001226532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004593555,"about_ca_topic_score_gemma":0.00001253619,"domain_scores_codex":[0.9982898,0.0001245524,0.0001929264,0.0003823045,0.000605355,0.0004051228],"domain_scores_gemma":[0.9988925,0.000377949,0.0001015789,0.0002819386,0.0001151064,0.0002309174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001887446,0.0004154329,0.9837186,0.0001380461,0.0001330412,0.00001552799,0.0001394895,0.0008084552,0.0001244738,0.00003446669,0.001036812,0.01154823],"study_design_scores_gemma":[0.002711248,0.001526438,0.6545618,0.0000431045,0.000467366,0.000001554478,0.0001926983,0.3393948,0.0004579348,0.00005986031,0.0004403293,0.0001428398],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890698,0.0008187863,0.003310181,0.004752446,0.00007616201,0.001533152,0.0001451326,0.00004019431,0.000254129],"genre_scores_gemma":[0.9940696,0.00001171541,0.0001801287,0.00347468,0.00005895216,0.001334814,0.0001328381,0.00004586826,0.000691375],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3385864,"threshold_uncertainty_score":0.9986352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0350495939762636,"score_gpt":0.2989106370895007,"score_spread":0.263861043113237,"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."}}