{"id":"W4362666447","doi":"10.1038/s43856-023-00269-x","title":"Deep learning-based polygenic risk analysis for Alzheimer’s disease prediction","year":2023,"lang":"en","type":"article","venue":"Communications Medicine","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"Parkwood Institute; St Joseph's Health Care; University of British Columbia; McGill University; Jewish General Hospital","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; H. Lundbeck A/S; Servier; National Natural Science Foundation of China; Eisai; Innovation and Technology Commission; Genentech; IXICO; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; University of Southern California; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; Shenzhen Knowledge Innovation Program; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; F. Hoffmann-La Roche; University Grants Committee; Alzheimer's Drug Discovery Foundation; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Polygenic risk score; Artificial intelligence; Deep learning; Disease; Computer science; Machine learning; Computational biology; Medicine; Biology; Internal medicine; Genetics; Gene; Single-nucleotide polymorphism; Genotype","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007905917,0.0001067103,0.0001927558,0.0002005639,0.0004011195,0.000004819155,0.0003991649,0.00009737515,0.00002871298],"category_scores_gemma":[0.001719882,0.0000980596,0.0001628973,0.0006645441,0.0001806934,0.000001723527,0.0001188195,0.000113444,0.00001885307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001455933,"about_ca_system_score_gemma":0.00005520843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005527396,"about_ca_topic_score_gemma":0.0001608744,"domain_scores_codex":[0.9988703,0.0003052872,0.0002974624,0.000238999,0.00008405338,0.0002038811],"domain_scores_gemma":[0.9980696,0.0002649316,0.0001843791,0.001199583,0.0001595532,0.0001219749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007047398,0.00008865185,0.8915168,0.000008691461,0.001333473,2.2352e-7,0.0001206287,0.08466141,0.001030157,0.0001304667,0.01322794,0.0078111],"study_design_scores_gemma":[0.0005994055,0.000182816,0.6432974,0.000005232748,0.001549493,1.932633e-7,0.0001545895,0.2970057,0.00002449397,0.0002425071,0.05684041,0.00009782697],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2864484,0.0303335,0.644507,0.03454524,0.0005028202,0.001556979,0.0004088952,0.0003792591,0.001317862],"genre_scores_gemma":[0.9860561,0.003380922,0.001962665,0.0002754225,0.0001546674,0.0002703197,0.007461647,0.00001710844,0.0004211815],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6996076,"threshold_uncertainty_score":0.3998754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04493514788740757,"score_gpt":0.3355607507563277,"score_spread":0.2906256028689201,"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."}}