{"id":"W1979024706","doi":"10.1016/j.neuroimage.2014.04.018","title":"Individualized Gaussian process-based prediction and detection of local and global gray matter abnormalities in elderly subjects","year":2014,"lang":"en","type":"article","venue":"NeuroImage","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Mental Health; National Institute on Aging; University of California, San Diego; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, Los Angeles; Genentech; National Institutes of Health; Servier; Eisai; Bundesministerium für Bildung und Forschung; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; Deutscher Akademischer Austauschdienst; National Center for Research Resources; F. Hoffmann-La Roche; Medpace; AstraZeneca; Eli Lilly and Company; Bristol-Myers Squibb; Novartis Pharmaceuticals Corporation; Wellcome Trust; Synarc; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; Medical Research Council; Meso Scale Diagnostics; Foundation for the National Institutes of Health","keywords":"Normative; Inference; Dementia; Psychology; Disease; Artificial intelligence; Medicine; Machine learning; Computer science; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001842851,0.0001341082,0.0001657328,0.0001062391,0.00005927436,0.0001361148,0.0001900853,0.00006406512,0.000004757324],"category_scores_gemma":[0.00002440801,0.000121475,0.00001788332,0.0003183293,0.0001356103,0.0005231827,0.00005942247,0.0001098146,0.000002519358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001229981,"about_ca_system_score_gemma":0.00004075504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007168137,"about_ca_topic_score_gemma":0.00007676466,"domain_scores_codex":[0.9989364,0.00008847489,0.0002317341,0.0003448272,0.0001945064,0.0002040987],"domain_scores_gemma":[0.9995483,0.0000419107,0.0001031206,0.0001947763,0.00004264704,0.00006929081],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000187551,0.0002653081,0.6876938,0.001748753,0.00001723659,0.00004525848,0.001867317,0.0001470628,0.006487714,0.01185424,0.0000752293,0.2896106],"study_design_scores_gemma":[0.001151773,0.000514405,0.9508361,0.00008861309,0.00000880189,0.00006198687,0.00005479554,0.02955461,0.01041234,0.007056513,0.00008195582,0.000178139],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5544191,0.00003420934,0.4441995,0.0002377393,0.00006295573,0.00009921073,0.000007599641,0.00004739988,0.0008923137],"genre_scores_gemma":[0.9982989,0.00000543083,0.001415893,0.0002413149,0.0000127068,0.00001175573,0.000001557599,0.000005786706,0.000006626798],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4438798,"threshold_uncertainty_score":0.4953608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006741152433292742,"score_gpt":0.2278331672859616,"score_spread":0.2210920148526689,"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."}}