{"id":"W2975979380","doi":"10.1016/j.trci.2019.07.001","title":"Forecasting the progression of Alzheimer's disease using neural networks and a novel preprocessing algorithm.","year":2019,"lang":"en","type":"article","venue":"PubMed","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":103,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; H. Lundbeck A/S; Servier; GE Healthcare; Fujirebio US; BioClinica; Biogen; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Eli Lilly and Company; Bristol-Myers Squibb; Roche; Merck; Alzheimer's Drug Discovery Foundation; Takeda Pharmaceutical Company; AbbVie; National Institute on Aging; Alzheimer's Association","keywords":"Clinical trial; Disease; Machine learning; Artificial neural network; Artificial intelligence; Data set; Dementia; Computer science; Cognitive impairment; Set (abstract data type); Cognition; Alzheimer's disease; Preprocessor; Medicine; Internal medicine; Psychiatry","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":[0.001413679,0.001012802,0.0005905953,0.0009806962,0.0002429816,0.0004863061,0.0004894095,0.0006329257,0.0009800773],"category_scores_gemma":[0.004490034,0.0002997966,0.0006071265,0.0006267652,0.0001956096,0.000548196,0.0002672052,0.0009584393,0.0003334246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000872511,"about_ca_system_score_gemma":0.0007233891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00942901,"about_ca_topic_score_gemma":0.008758323,"domain_scores_codex":[0.9997669,0.00008314672,0.00002467908,0.00006041195,0.0000405664,0.000024381],"domain_scores_gemma":[0.9986185,0.0008457428,0.0002036626,0.0000595167,0.0002287692,0.0000437888],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001664613,0.0006094342,0.06941085,0.0002032989,0.0003978758,0.0002854272,0.00008883004,0.6046354,0.006596434,0.0008742422,0.003115787,0.3121178],"study_design_scores_gemma":[0.0000196171,0.0001319868,0.006118403,0.00001393944,0.00003966491,0.00006258929,0.00001062816,0.9909174,0.001698765,0.0006618929,0.0003162286,0.000008965651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5489092,0.001921034,0.4411098,0.00102112,0.000273064,0.0003741251,0.001749219,0.002105582,0.002536868],"genre_scores_gemma":[0.8690882,0.0003413183,0.1276824,0.0001077256,0.00007365352,0.0001960895,0.001459107,0.00003339662,0.001018161],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00942901,"threshold_uncertainty_score":0.01874822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05859668511185856,"score_gpt":0.3133186052014715,"score_spread":0.254721920089613,"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."}}