{"id":"W2889311142","doi":"10.1371/journal.pone.0202674","title":"Controlled feature selection and compressive big data analytics: Applications to biomedical and health studies","year":2018,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Nursing Research; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Michigan Institute for Data Science, University of Michigan; University of California, San Diego; Genentech; National Institutes of Health; National Institute of Neurological Disorders and Stroke; IXICO; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; F. Hoffmann-La Roche; National Institute of Diabetes and Digestive and Kidney Diseases; Synarc; University of Southern California; Medpace; Bristol-Myers Squibb; Eli Lilly and Company; AstraZeneca; Novartis Pharmaceuticals Corporation; Foundation for the National Institutes of Health; National Science Foundation","keywords":"Computer science; Big data; Feature selection; Inference; Bootstrapping (finance); Data mining; Scalability; Statistical inference; Machine learning; Artificial intelligence; Mathematics; Statistics","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":[0.0003836869,0.00008193956,0.00039447,0.00005369441,0.000149878,0.00002612134,0.00009171011,0.00003838972,0.00001561779],"category_scores_gemma":[0.001573524,0.00006103732,0.000006308753,0.0001552979,0.0001486594,0.00001925557,0.0001556853,0.00008991184,0.000007581016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001783757,"about_ca_system_score_gemma":0.00003167076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001195708,"about_ca_topic_score_gemma":0.00004880647,"domain_scores_codex":[0.9992141,0.00007246646,0.0001763816,0.000243624,0.0001597989,0.0001336738],"domain_scores_gemma":[0.9985175,0.000844393,0.00007967538,0.0002380519,0.0001759201,0.0001444666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009646666,0.006541652,0.005860107,0.004804608,0.00884825,0.00000491338,0.00697914,1.586026e-7,0.01907127,0.430827,0.1432147,0.3728836],"study_design_scores_gemma":[0.01666926,0.007082596,0.01701465,0.003107631,0.004059159,0.00003458024,0.003070349,0.1047942,0.003969619,0.823419,0.01516159,0.001617324],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03673068,0.001853621,0.9398032,0.01798149,0.00007673323,0.002430765,0.0004310466,0.0001062159,0.0005862747],"genre_scores_gemma":[0.1153161,0.0004290832,0.8824816,0.0007786412,0.0005796191,0.0001302454,0.00001870388,0.00001375239,0.0002522885],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3925921,"threshold_uncertainty_score":0.248903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4949556649895261,"score_gpt":0.4681036158307924,"score_spread":0.02685204915873374,"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."}}