{"id":"W2736045761","doi":"10.1016/j.neuroimage.2018.03.007","title":"Evaluation of non-negative matrix factorization of grey matter in age prediction","year":2018,"lang":"en","type":"article","venue":"NeuroImage","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":122,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Institute on Aging; National Institutes of Health; Helmholtz-Alberta Initiative; National Institute of Mental Health; Deutsche Forschungsgemeinschaft","keywords":"Voxel; Pattern recognition (psychology); Artificial intelligence; Computer science; Matrix decomposition; Non-negative matrix factorization; Principal component analysis; Regression; Factorization; Multivariate statistics; Statistics; Mathematics; Machine learning; Algorithm","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":[0.004212304,0.0008858918,0.0008400817,0.0008285555,0.0004417224,0.0008908746,0.0005293344,0.001008901,0.001308219],"category_scores_gemma":[0.01049899,0.0001913034,0.0006858498,0.0004177964,0.0002877613,0.0008949115,0.000573619,0.0006419885,0.0004421287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003591666,"about_ca_system_score_gemma":0.001180629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009289765,"about_ca_topic_score_gemma":0.009391796,"domain_scores_codex":[0.9992148,0.0003581643,0.00004515545,0.0001699446,0.0001207671,0.00009113479],"domain_scores_gemma":[0.9953224,0.003015711,0.0002378432,0.0002007899,0.001034506,0.000188705],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00463222,0.0008025676,0.04986469,0.000482762,0.0007196193,0.0002875439,0.0003293903,0.193992,0.02779875,0.004311058,0.006960257,0.7098191],"study_design_scores_gemma":[0.00003771713,0.0002153605,0.007587908,0.00003197646,0.00007659606,0.00009873359,0.00005857235,0.987305,0.002460246,0.001737607,0.0003736133,0.00001671886],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.484914,0.004490886,0.5046318,0.0008766813,0.0003324577,0.0002538574,0.0009661528,0.001013391,0.002520815],"genre_scores_gemma":[0.8818411,0.0005343025,0.1157044,0.00008837824,0.00009585374,0.00005516941,0.0006691466,0.0000383301,0.0009732994],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009289765,"threshold_uncertainty_score":0.02227706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03976743439044798,"score_gpt":0.3763094111456299,"score_spread":0.3365419767551819,"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."}}