{"id":"W4390717645","doi":"10.1212/nxg.0000000000200120","title":"Machine Learning Models of Polygenic Risk for Enhanced Prediction of Alzheimer Disease Endophenotypes","year":2024,"lang":"en","type":"article","venue":"Neurology Genetics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Canadian Institutes of Health Research; GHR Foundation; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Avid Radiopharmaceuticals; Mayo Foundation for Medical Education and Research; Regeneron Pharmaceuticals; BioClinica; Mayo Clinic; Biogen; Bristol-Myers Squibb; Eli Lilly and Company","keywords":"Endophenotype; Dementia; Genome-wide association study; Neuroimaging; Disease; Medicine; Genetic architecture; Psychology; Internal medicine; Cognition; Biology; Single-nucleotide polymorphism; Genotype; Psychiatry; Quantitative trait locus; Genetics; Population","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":[],"consensus_categories":[],"category_scores_codex":[0.0002254749,0.0001288775,0.0002103883,0.00006504462,0.00004973874,0.000003121451,0.0001118842,0.0001898591,0.00001026179],"category_scores_gemma":[0.0001823842,0.000126186,0.0001570288,0.000071329,0.0001022421,0.000002012565,0.00006662196,0.0001269745,0.000001531754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002519946,"about_ca_system_score_gemma":0.0000808172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001477562,"about_ca_topic_score_gemma":0.000008560487,"domain_scores_codex":[0.9988546,0.0001693853,0.0003646644,0.0003339051,0.00006936175,0.0002080811],"domain_scores_gemma":[0.9993531,0.00008716524,0.0001644072,0.0002334947,0.0001013218,0.00006047547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007055596,0.0001596823,0.1323456,0.0001407327,0.0008050948,0.000001805266,0.0001942346,0.2485753,0.6007467,0.0006047557,0.0007610545,0.01495952],"study_design_scores_gemma":[0.001896552,0.005347583,0.2016212,0.00002434261,0.001621005,0.00001348471,0.00002913508,0.5476849,0.2109038,0.01452521,0.01585045,0.0004823456],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9273555,0.0197937,0.05148831,0.0001386967,0.0003564866,0.0002608309,0.0004303245,0.00001740007,0.0001587229],"genre_scores_gemma":[0.994094,0.003608202,0.001693858,0.00008445381,0.000152221,0.00004064242,0.0002129353,0.00002920478,0.00008452356],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3898429,"threshold_uncertainty_score":0.5145717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02044579922958576,"score_gpt":0.2582801765647226,"score_spread":0.2378343773351369,"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."}}