{"id":"W3045594725","doi":"10.1371/journal.pone.0235663","title":"Inexpensive, non-invasive biomarkers predict Alzheimer transition using machine learning analysis of the Alzheimer’s Disease Neuroimaging (ADNI) database","year":2020,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Neuroimaging; Random forest; Alzheimer's Disease Neuroimaging Initiative; Receiver operating characteristic; Artificial intelligence; Computer science; Cognition; Machine learning; Disease; Medicine; Alzheimer's disease; Neuroscience; Psychology; 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":[0.003856065,0.0009834826,0.0009925276,0.003475825,0.0003797448,0.001504039,0.001205334,0.0008946626,0.001858637],"category_scores_gemma":[0.01127221,0.0002167632,0.001028661,0.001560092,0.000142374,0.0008683313,0.000822064,0.0008974283,0.00224387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004123604,"about_ca_system_score_gemma":0.0006169539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006408031,"about_ca_topic_score_gemma":0.008771709,"domain_scores_codex":[0.9979805,0.0005781088,0.0003862898,0.0004874875,0.0004462306,0.0001213004],"domain_scores_gemma":[0.9962787,0.001033292,0.0006258126,0.0007765099,0.001090852,0.0001948934],"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":[0.004000422,0.001830281,0.6405469,0.001139476,0.00199223,0.0007519513,0.0002445152,0.01374228,0.004384138,0.001155642,0.09649507,0.2337171],"study_design_scores_gemma":[0.0005694303,0.001809389,0.7130388,0.0006205686,0.001377261,0.002517898,0.0005733764,0.1911015,0.0144288,0.00869113,0.06497476,0.0002970173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7335755,0.009573847,0.04453434,0.001502397,0.0005718485,0.00150926,0.1950542,0.004266703,0.009411823],"genre_scores_gemma":[0.7218484,0.002187725,0.05235264,0.0004721721,0.0002771009,0.001181077,0.2184914,0.0001271496,0.003062284],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006408031,"threshold_uncertainty_score":0.02039307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1013318691944702,"score_gpt":0.3030705438409888,"score_spread":0.2017386746465186,"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."}}