{"id":"W4398775431","doi":"10.3233/jad-230236","title":"Epistatic Features and Machine Learning Improve Alzheimer’s Disease Risk Prediction Over Polygenic Risk Scores","year":2024,"lang":"en","type":"article","venue":"Journal of Alzheimer s Disease","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; Goizueta Business School, Emory University; Canadian Institutes of Health Research; Genentech; National Institute of Neurological Disorders and Stroke; IXICO; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; H. Lundbeck A/S; School of Medicine, Boston University; Hope Center for Neurological Disorders; University of Southern California; National Heart, Lung, and Blood Institute; Novartis Pharmaceuticals Corporation; Emory University; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; National Institutes of Health; U.S. Department of Health and Human Services","keywords":"Generalizability theory; Polygenic risk score; Epistasis; Disease; Heritability; Missing heritability problem; Population; Medicine; Biology; Psychology; Genetic variants; Genetics; Internal medicine; Genotype; Developmental psychology; Gene; Single-nucleotide polymorphism","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":[0.003982111,0.001201027,0.0009707183,0.001421212,0.0004588978,0.0007595432,0.001014875,0.0009314287,0.0009650968],"category_scores_gemma":[0.006667128,0.0003168097,0.001495519,0.0008078137,0.0004853411,0.0009964325,0.0009125511,0.001599765,0.0004373578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006439059,"about_ca_system_score_gemma":0.0007910109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005543184,"about_ca_topic_score_gemma":0.005795492,"domain_scores_codex":[0.9987037,0.0006275699,0.00007061433,0.0003664918,0.0001503659,0.00008125312],"domain_scores_gemma":[0.9955135,0.003329091,0.0003555153,0.0003149694,0.0003663971,0.0001205484],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004095636,0.0004769806,0.05672169,0.0000770321,0.000818189,0.000167129,0.00009405473,0.6985897,0.001918448,0.002935646,0.002895038,0.2348966],"study_design_scores_gemma":[0.0000134109,0.00007422185,0.003826052,0.000008055312,0.00004226925,0.0000337221,0.000004988,0.9927391,0.0001738092,0.002919236,0.0001571845,0.000007822619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5905618,0.002648773,0.4001101,0.001784624,0.0001014664,0.00007622608,0.000466327,0.001466763,0.00278392],"genre_scores_gemma":[0.9518007,0.0003495121,0.04535359,0.0002729037,0.000117914,0.00003937524,0.0006448603,0.00006848152,0.001352681],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005543184,"threshold_uncertainty_score":0.02105969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01136033971364349,"score_gpt":0.267012464596054,"score_spread":0.2556521248824105,"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."}}