{"id":"W4405376357","doi":"10.7717/peerj.18490","title":"A machine learning approach for identifying anatomical biomarkers of early mild cognitive impairment","year":2024,"lang":"en","type":"article","venue":"PeerJ","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hotchkiss Brain Institute; University of Calgary","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Alberta Innovates; Eisai; Northern California Institute for Research and Education; DoD Alzheimer's Disease Neuroimaging Initiative; BioClinica; Biogen; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Engineering and Physical Sciences Research Council; Universiti Sains Malaysia; Bristol-Myers Squibb; Eli Lilly and Company; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Universiti Teknologi Petronas; Alzheimer's Association","keywords":"Feature selection; Alzheimer's Disease Neuroimaging Initiative; Artificial intelligence; Neuroimaging; Receiver operating characteristic; Computer science; Machine learning; Dementia; Medicine; Pattern recognition (psychology); Disease; Pathology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004467428,0.001319609,0.0009530099,0.003582242,0.0005745084,0.001642151,0.001272873,0.001371911,0.001628288],"category_scores_gemma":[0.009623953,0.0002674201,0.001527483,0.001744244,0.0005657559,0.0009273395,0.001065978,0.001786317,0.0008911942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009444386,"about_ca_system_score_gemma":0.001358667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002204121,"about_ca_topic_score_gemma":0.002058854,"domain_scores_codex":[0.9981624,0.0007402825,0.0001549976,0.0004203823,0.0004182441,0.0001036283],"domain_scores_gemma":[0.9966879,0.002163789,0.0002891056,0.0002255924,0.0005465064,0.0000870845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003826912,0.0005614799,0.02741354,0.0003829567,0.0008989914,0.0002566356,0.000202305,0.291835,0.005306865,0.008672928,0.006459671,0.6576269],"study_design_scores_gemma":[0.00001962611,0.0001904472,0.004015975,0.00006511401,0.00008899417,0.0001229058,0.00003804624,0.9765147,0.001674282,0.01509285,0.002147365,0.00002963022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03745376,0.002318911,0.9550947,0.0008900074,0.0001326475,0.0002385875,0.0007775227,0.001275894,0.001817966],"genre_scores_gemma":[0.5055703,0.001239242,0.4877744,0.0005429481,0.0003527587,0.0008969329,0.001447654,0.0001390768,0.002036722],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004467428,"threshold_uncertainty_score":0.02362633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04448595203341586,"score_gpt":0.363280635971392,"score_spread":0.3187946839379761,"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."}}