{"id":"W3047286661","doi":"10.1016/j.neuroimage.2020.117203","title":"Predicting Alzheimer's disease progression using deep recurrent neural networks","year":2020,"lang":"en","type":"article","venue":"NeuroImage","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":210,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; GE Healthcare; Johnson and Johnson; Janssen Research and Development; National Institutes of Health; H. Lundbeck A/S; National Research Foundation Singapore; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Northern California Institute for Research and Education; National Center for Research Resources; Nvidia; University of Southern California; Merck; Genentech; IXICO; National Institute on Aging; Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital; Fujirebio Europe","keywords":"Missing data; Artificial intelligence; Dementia; Machine learning; Computer science; Alzheimer's Disease Neuroimaging Initiative; Disease; Neuroimaging; Artificial neural network; Recurrent neural network; Psychology; Medicine; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001059183,0.0001674519,0.0001811836,0.00004924999,0.0001441507,0.0000666621,0.0001015265,0.00003303938,0.0002000064],"category_scores_gemma":[0.0002654289,0.000142326,0.0001114794,0.0002609351,0.00007352545,0.0001535619,0.0001738003,0.0003991773,0.00001870132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001593788,"about_ca_system_score_gemma":0.00005222305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002500782,"about_ca_topic_score_gemma":2.643253e-7,"domain_scores_codex":[0.9983168,0.0001232616,0.000218767,0.0004204968,0.0004935194,0.0004271636],"domain_scores_gemma":[0.9989259,0.0000516449,0.00006647001,0.0001749438,0.0001003855,0.0006807103],"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":[0.0009280949,0.0002690825,0.8510004,0.00009705866,0.00005397737,0.001341322,0.00009930554,0.0001742751,0.003026926,0.000004540957,0.000370183,0.1426348],"study_design_scores_gemma":[0.0009623927,0.000527113,0.2765906,0.00007599025,0.0002598046,0.0000207921,0.00002925309,0.7206272,0.0003770554,0.000003213422,0.0004199774,0.0001065326],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9912208,0.001319829,0.002478964,0.00268695,0.0002230175,0.000937481,0.000006135346,0.0001897034,0.0009371537],"genre_scores_gemma":[0.9972119,0.00003609647,0.0002882191,0.00180647,0.0005482472,0.0000224596,0.00003662628,0.00003674685,0.0000132716],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.720453,"threshold_uncertainty_score":0.5803885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06040134327924341,"score_gpt":0.3574656995577504,"score_spread":0.297064356278507,"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."}}