{"id":"W4386895318","doi":"10.3390/app131810470","title":"Enhancing Early Dementia Detection: A Machine Learning Approach Leveraging Cognitive and Neuroimaging Features for Optimal Predictive Performance","year":2023,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Janssen Alzheimer Immunotherapy Research And Development; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; F. Hoffmann-La Roche; University of Southern California; Bristol-Myers Squibb; Eli Lilly and Company; Biogen; BioClinica; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Machine learning; Artificial intelligence; Dementia; Neuroimaging; Computer science; Support vector machine; Cognition; AdaBoost; Artificial neural network; Benchmark (surveying); Naive Bayes classifier; Psychology; Disease; Medicine; Neuroscience","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":[0.001013707,0.0001530676,0.0001806165,0.0002961356,0.0009972949,0.0001566539,0.00009099638,0.00003409096,0.00001365091],"category_scores_gemma":[0.00009514269,0.0001300419,0.00004264427,0.0007171328,0.0003319475,0.0002194768,0.0001278559,0.0002772026,0.000009819416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001749891,"about_ca_system_score_gemma":0.00006717753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001327622,"about_ca_topic_score_gemma":0.000001842521,"domain_scores_codex":[0.9982991,0.00003401703,0.0001597377,0.0005294099,0.0004716498,0.000506145],"domain_scores_gemma":[0.9994812,0.0001891065,0.0000619558,0.0000562943,0.0001006109,0.0001108124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001905378,0.0002460991,0.5627179,0.0008602415,0.0005344255,0.00003310681,0.01138645,0.001056767,0.2202111,0.0002433875,0.00007310664,0.2007321],"study_design_scores_gemma":[0.002886786,0.001834804,0.7308192,0.0001531388,0.0002358582,0.00007990874,0.009020542,0.1317459,0.1226453,0.00007701245,0.0001807895,0.0003207172],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9681256,0.0001701094,0.02310387,0.0000970533,0.00004995403,0.0008748714,0.000003809517,0.0001638808,0.007410859],"genre_scores_gemma":[0.9976863,0.00005630346,0.001359386,0.00009227129,0.00009141493,0.0002960926,0.00001856598,0.00001576673,0.0003838614],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2004114,"threshold_uncertainty_score":0.7670487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02378172481425599,"score_gpt":0.2890402966174187,"score_spread":0.2652585718031627,"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."}}