{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005513723,0.0008928959,0.0008943136,0.001287244,0.0004987203,0.001659768,0.001463469,0.0008374654,0.001874448],"category_scores_gemma":[0.02474646,0.0004444229,0.0007739164,0.001948617,0.00172035,0.001911662,0.00211493,0.002004409,0.0003860792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000697417,"about_ca_system_score_gemma":0.001316229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002309462,"about_ca_topic_score_gemma":0.002529724,"domain_scores_codex":[0.9979392,0.001156008,0.00010434,0.0002874696,0.0004537773,0.00005926921],"domain_scores_gemma":[0.9858611,0.01072469,0.000814526,0.001464489,0.0008398835,0.0002953573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003586334,0.0001944328,0.00890352,0.000713407,0.00037498,0.0005429994,0.0005080393,0.4417723,0.009705426,0.1637855,0.008231967,0.3649089],"study_design_scores_gemma":[0.00004098033,0.00006503137,0.00136963,0.00006807903,0.00002567452,0.0001165463,0.00007190948,0.7724753,0.002775729,0.2183418,0.004611332,0.00003800159],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005212455,0.0005998428,0.9919885,0.0009251658,0.0000550478,0.0000501696,0.0001327394,0.0003465019,0.0006896858],"genre_scores_gemma":[0.2997358,0.001460044,0.6961224,0.0005013099,0.0003463175,0.0003480996,0.0004782674,0.000147024,0.0008607509],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005513723,"threshold_uncertainty_score":0.02915972,"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."}}