{"id":"W2950241029","doi":"10.1371/journal.pone.0211121","title":"Revealing heterogeneity of brain imaging phenotypes in Alzheimer’s disease based on unsupervised clustering of blood marker profiles","year":2019,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":16,"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; Northern California Institute for Research and Education; University of California, San Diego; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; Eisai; National Institute on Aging; Alzheimer's Association; University of California, San Francisco; Foundation for the National Institutes of Health","keywords":"Disease; Phenotype; Cluster analysis; Alzheimer's disease; Magnetic resonance imaging; Neuroimaging; Clinical phenotype; Multivariate analysis; Multivariate statistics; Computational biology; Biology; Bioinformatics; Medicine; Neuroscience; Pathology; Internal medicine; Genetics; Artificial intelligence; Computer science; Machine learning; Gene","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":[0.001109068,0.0005096603,0.0005989933,0.003019315,0.0005271311,0.0008922095,0.0004857537,0.0004898111,0.0005562771],"category_scores_gemma":[0.002923145,0.0001148951,0.0008045764,0.001510987,0.0003712615,0.0004068844,0.0005973027,0.0003600166,0.0002879809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003170275,"about_ca_system_score_gemma":0.000500121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004141124,"about_ca_topic_score_gemma":0.005355518,"domain_scores_codex":[0.9993124,0.000189624,0.00007000309,0.0002386996,0.00009369727,0.00009546231],"domain_scores_gemma":[0.9989527,0.000328051,0.0002293271,0.0001620996,0.0002311528,0.0000965497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002379667,0.0007939175,0.5732098,0.0004051098,0.001519943,0.001378768,0.001958319,0.02547279,0.1015857,0.00282981,0.00768572,0.2807805],"study_design_scores_gemma":[0.00008892057,0.0003764163,0.689241,0.00007335588,0.0005273819,0.002190955,0.001161193,0.2776867,0.01284859,0.01190025,0.003771889,0.0001333599],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9116932,0.000548761,0.08417214,0.0002022722,0.000031739,0.0001367071,0.001740412,0.0004717293,0.001002983],"genre_scores_gemma":[0.9670259,0.000153056,0.0296831,0.00003509102,0.00002934611,0.00007071059,0.00259395,0.00006132058,0.0003475297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004141124,"threshold_uncertainty_score":0.008234024,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06121478981164316,"score_gpt":0.2546684385355948,"score_spread":0.1934536487239517,"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."}}