{"id":"W4387610056","doi":"10.1186/s12920-023-01675-9","title":"c-Diadem: a constrained dual-input deep learning model to identify novel biomarkers in Alzheimer’s disease","year":2023,"lang":"en","type":"article","venue":"BMC Medical Genomics","topic":"Alzheimer's disease research and treatments","field":"Medicine","cited_by":8,"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; Khalifa University of Science, Technology and Research; Eisai; Northern California Institute for Research and Education; F. Hoffmann-La Roche; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Alzheimer's Association","keywords":"KEGG; Disease; Neuroimaging; Alzheimer's Disease Neuroimaging Initiative; Neuropsychology; Biomarker; Alzheimer's disease; Single-nucleotide polymorphism; Medicine; Neurology; Deep learning; Computational biology; Interpretability; Bioinformatics; Machine learning; Artificial intelligence; Oncology; Cognition; Biology; Computer science; Pathology; Gene; Genetics; Transcriptome; Psychiatry; Genotype","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008058477,0.0002865924,0.0004446879,0.0004758243,0.000124605,0.00003993349,0.0002071276,0.0001857157,0.0002719449],"category_scores_gemma":[0.001804082,0.0002636144,0.000205484,0.0007045238,0.0002321862,0.00007336729,0.0002756013,0.0004160674,0.0009910812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001910088,"about_ca_system_score_gemma":0.002413827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005935162,"about_ca_topic_score_gemma":0.00009573119,"domain_scores_codex":[0.9966987,0.0001110299,0.0005133218,0.0006325311,0.001136948,0.0009074844],"domain_scores_gemma":[0.9958847,0.0004000664,0.00006542947,0.0003835779,0.00007362262,0.003192587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.02037422,0.009104067,0.6904446,0.001783791,0.045997,0.0312099,0.00440044,0.04097462,0.006457227,0.00280626,0.01377819,0.1326696],"study_design_scores_gemma":[0.01153299,0.000278792,0.1483553,0.0004401018,0.001276004,0.00007467261,0.0007098976,0.8354089,0.000108988,0.0005282001,0.0006614628,0.0006246527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9823539,0.004140022,0.007626103,0.002714332,0.0001850575,0.001612109,0.0001099886,0.0003394976,0.0009190178],"genre_scores_gemma":[0.9951038,0.0004733824,0.002779444,0.0007179758,0.0001734843,0.0001923749,0.0003972118,0.00007429368,0.00008800963],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7944342,"threshold_uncertainty_score":0.9999816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08459575549839929,"score_gpt":0.3748144574533672,"score_spread":0.2902187019549679,"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."}}