{"id":"W4381187244","doi":"10.1002/sim.9824","title":"Deep causal feature extraction and inference with neuroimaging genetic data","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of General Medical Sciences; National Institute on Aging; Canadian Institutes of Health Research; Minnesota Supercomputing Institute, University of Minnesota; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Pfizer; Novartis Pharmaceuticals Corporation; Eisai; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Servier; BioClinica; Bristol-Myers Squibb; Eli Lilly and Company; Biogen","keywords":"Neuroimaging; Computer science; Causal inference; Imaging genetics; Artificial intelligence; Covariate; Inference; Genome-wide association study; Biobank; Alzheimer's Disease Neuroimaging Initiative; Instrumental variable; Machine learning; Feature (linguistics); Regression; Psychology; Econometrics; Cognition; Bioinformatics; Statistics; Cognitive impairment; Psychiatry; Biology; Mathematics","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":[0.0003132017,0.00009572576,0.0001402213,0.00006221429,0.00004975185,0.00000612268,0.0001249831,0.00006825256,0.00001086943],"category_scores_gemma":[0.001029745,0.00007740084,0.000003332193,0.0001480757,0.0001319246,0.000002498436,0.0001160279,0.0001289685,0.00000356004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006838995,"about_ca_system_score_gemma":0.00003720914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009329993,"about_ca_topic_score_gemma":0.0006995456,"domain_scores_codex":[0.9991708,0.00007245311,0.0001503619,0.0003166596,0.00009594791,0.0001937601],"domain_scores_gemma":[0.9993696,0.0001380572,0.00006789881,0.0003250057,0.00004791817,0.00005158429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000770471,0.00003495462,0.8370963,0.00007998002,0.00007051932,0.0001754666,0.0003423275,0.002339768,0.02041893,0.0005659345,0.07509323,0.06370559],"study_design_scores_gemma":[0.0006113475,0.0002695619,0.9474527,0.00002431489,0.00003144566,0.00004271901,0.00024572,0.04422058,0.00002210307,0.00111738,0.005833622,0.000128537],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4640126,0.001167139,0.5301654,0.00332229,0.0003478886,0.000254962,0.0001707714,0.00002799702,0.0005309673],"genre_scores_gemma":[0.9368512,0.002122269,0.05839036,0.0003909093,0.0002427105,0.0000107691,0.001596526,0.0000187309,0.0003765235],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4728386,"threshold_uncertainty_score":0.3156315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03034836853606217,"score_gpt":0.3566172819314706,"score_spread":0.3262689133954084,"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."}}