{"id":"W3005995948","doi":"10.1101/2020.02.10.931824","title":"Normative modelling using deep autoencoders: a multi-cohort study on mild cognitive impairment and Alzheimer’s disease","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Università degli Studi di Padova; Fundação de Amparo à Pesquisa do Estado de São Paulo; F. Hoffmann-La Roche; Wellcome Trust; University of Southern California; European Commission; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Normative; Generalizability theory; Autoencoder; Artificial intelligence; Deep learning; Neuroimaging; Cognition; Artificial neural network; Psychology; Cohort; Machine learning; Computer science; Cognitive psychology; Medicine; Developmental psychology; Neuroscience; Pathology","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":[0.00410091,0.0005819416,0.0004541927,0.0008645963,0.0009136329,0.0008825946,0.000755163,0.0007836053,0.001243559],"category_scores_gemma":[0.01045301,0.0003589838,0.0007906638,0.0005986023,0.0005112201,0.0009425679,0.0009562866,0.001361123,0.0002806313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000477422,"about_ca_system_score_gemma":0.0003064925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01103555,"about_ca_topic_score_gemma":0.008974642,"domain_scores_codex":[0.9988222,0.0004908925,0.00009794207,0.0003734481,0.0001312493,0.00008425824],"domain_scores_gemma":[0.9949573,0.001539506,0.0008273675,0.001546574,0.0007205153,0.0004086739],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001017544,0.0004147943,0.9897678,0.00001534274,0.0004120816,0.0005166705,0.0008902724,0.000682549,0.001048422,0.0002531112,0.0005708025,0.004410601],"study_design_scores_gemma":[0.00002752479,0.0003104934,0.9891115,0.0000139246,0.0001589866,0.0006875435,0.0006378705,0.007408971,0.000452369,0.0007655242,0.0003979289,0.00002731249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9989935,0.00003551221,0.0005981608,0.00004054028,0.000006629168,0.00000745304,0.0002296597,0.00000546415,0.00008313241],"genre_scores_gemma":[0.998963,0.00002140513,0.0003125234,0.00001689076,0.000008180521,0.000009317499,0.000531422,0.000008168407,0.0001290382],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01103555,"threshold_uncertainty_score":0.02194268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06720531333088238,"score_gpt":0.3171626020557359,"score_spread":0.2499572887248536,"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."}}