{"id":"W2886872798","doi":"10.1016/j.neuroimage.2018.08.040","title":"Using high-dimensional machine learning methods to estimate an anatomical risk factor for Alzheimer's disease across imaging databases","year":2018,"lang":"en","type":"article","venue":"NeuroImage","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":58,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Institute of Environmental Health Sciences; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; Takeda Pharmaceutical Company; IXICO; Eisai; Servier; U.S. Department of Defense; Eli Lilly and Company; Lundbeckfonden; Elan; DoD Alzheimer's Disease Neuroimaging Initiative; Pfizer; BioClinica; Biogen; National Heart, Lung, and Blood Institute; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; F. Hoffmann-La Roche; Merck; Alzheimer's Drug Discovery Foundation; AbbVie; Fujirebio Europe; Alzheimer's Association; National Institutes of Health; U.S. Department of Health and Human Services; GE Healthcare; Alzheimer's Disease Neuroimaging Initiative; National Center for Advancing Translational Sciences; Johnson and Johnson; Meso Scale Diagnostics","keywords":"Alzheimer's Disease Neuroimaging Initiative; Neuroimaging; Magnetic resonance imaging; Dementia; Cognition; Neuropsychology; Disease; Medicine; Psychology; Internal medicine; Neuroscience; Radiology","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":[0.0006703811,0.0002410383,0.0002889386,0.0001372256,0.0005247548,0.0001065683,0.0001369954,0.0000218926,0.0004588868],"category_scores_gemma":[0.001190968,0.0002112208,0.0001072981,0.0002067668,0.0001996709,0.0003322489,0.0002988275,0.0003136836,0.00004297294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000353067,"about_ca_system_score_gemma":0.0001118434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001718622,"about_ca_topic_score_gemma":0.00001336334,"domain_scores_codex":[0.9975952,0.0003741478,0.0002592241,0.0006855238,0.0004114859,0.0006744234],"domain_scores_gemma":[0.998232,0.0002672203,0.00008114027,0.0003718542,0.0003122608,0.00073553],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003253642,0.0006052064,0.490411,0.00007247568,0.0001606334,0.0003923669,0.0001989335,0.00008600327,0.2445216,0.00004211215,0.0002241468,0.2600319],"study_design_scores_gemma":[0.002043831,0.0006747119,0.6555178,0.00005756885,0.0003874135,0.00003954894,0.0000282423,0.2974765,0.04046503,0.00005553314,0.002982612,0.000271248],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.90293,0.000134218,0.0946092,0.0003388099,0.0001854029,0.000735499,0.0009096657,0.0001243596,0.00003284261],"genre_scores_gemma":[0.852439,0.000003414107,0.1462094,0.000726567,0.0002783449,0.00002699961,0.0001837059,0.00006438218,0.00006812703],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2973905,"threshold_uncertainty_score":0.8613333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1031190431541643,"score_gpt":0.4967609503564578,"score_spread":0.3936419072022936,"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."}}