{"id":"W4297997542","doi":"10.1186/s12859-022-04946-x","title":"Deep multiview learning to identify imaging-driven subtypes in mild cognitive impairment","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; National Institutes of Health; Genentech; U.S. National Library of Medicine; IXICO; Directorate for Computer and Information Science and Engineering; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Foundation for the National Institutes of Health; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; Canadian Institutes of Health Research; National Science Foundation","keywords":"Artificial intelligence; Neuroimaging; Discriminative model; Cluster analysis; Computer science; Canonical correlation; Feature learning; Imaging genetics; Pattern recognition (psychology); Modality (human–computer interaction); Unsupervised learning; Dimensionality reduction; Deep learning; Machine learning; Psychology; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007828019,0.0001943241,0.000301643,0.0005115998,0.0002428844,0.00006431654,0.000159511,0.00002919634,0.001012098],"category_scores_gemma":[0.0002385584,0.0001869178,0.0001233513,0.0006712372,0.00005543919,0.0002039729,0.0004712972,0.0005145407,0.0004626816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002641264,"about_ca_system_score_gemma":0.0001928487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004456202,"about_ca_topic_score_gemma":0.00004245801,"domain_scores_codex":[0.9977705,0.0001558026,0.0005136481,0.0002139549,0.000790591,0.0005554974],"domain_scores_gemma":[0.999176,0.0001532208,0.0001150135,0.0001683221,0.000159556,0.0002278913],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004768614,0.0005287486,0.9717012,0.0004758556,0.00006039646,0.00007696092,0.006063411,0.0008197644,0.00007441188,0.00001990155,0.0006663705,0.01903614],"study_design_scores_gemma":[0.004129565,0.000930478,0.7515082,0.0002839655,0.00008935427,0.00007514747,0.0255259,0.2140045,0.0002503878,0.00002029111,0.00290007,0.0002820891],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9679977,0.0003786759,0.02040587,0.000613281,0.0001867304,0.002782812,0.00002790511,0.0001333314,0.007473661],"genre_scores_gemma":[0.9890206,0.00004910097,0.008057652,0.001300705,0.00003867424,0.0003942077,0.0001637921,0.00002791208,0.0009472832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2201929,"threshold_uncertainty_score":0.9999011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02594478998113494,"score_gpt":0.3433941883668077,"score_spread":0.3174493983856728,"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."}}