{"id":"W4288426910","doi":"10.3399/bjgp22x720437","title":"Polygenic risk scores: improving the prediction of future disease or added complexity?","year":2022,"lang":"en","type":"article","venue":"British Journal of General Practice","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institute of Cancer Research","funders":"Imperial College London; Royal Marsden NHS Foundation Trust","keywords":"Medicine; Disease; Polygenic risk score; Computer science; Data science; Machine learning; Internal medicine","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001438796,0.00008736012,0.0001739486,0.00003297533,0.0004354981,0.00002697691,0.0002843721,0.00005436151,0.00009611248],"category_scores_gemma":[0.002361871,0.00007466605,0.0001679004,0.0001204123,0.00007979043,0.00001636915,0.0001716574,0.000388397,5.961233e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003372393,"about_ca_system_score_gemma":0.0003256673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003411229,"about_ca_topic_score_gemma":0.00007374283,"domain_scores_codex":[0.9978755,0.001031908,0.0005026782,0.0001571808,0.0002562587,0.0001765173],"domain_scores_gemma":[0.9981567,0.0001141877,0.001154991,0.0001907904,0.0002886811,0.00009468089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.01167577,0.002461598,0.09603851,0.0001362519,0.003158846,0.000674002,0.0008218404,0.03957339,0.1899995,0.0005047086,0.4397329,0.2152227],"study_design_scores_gemma":[0.00411541,0.003505935,0.6603435,0.00004131623,0.001301607,0.01021688,0.005532402,0.003654989,0.001055307,0.0006817685,0.3090893,0.0004616346],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9868633,0.008244541,0.001636228,0.001822739,0.0007526433,0.0001520619,0.0004201837,0.00000345568,0.0001048989],"genre_scores_gemma":[0.9891419,0.003549688,0.004406077,0.000831736,0.001542632,0.00001112189,0.00006935836,0.00001622933,0.0004311879],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5643049,"threshold_uncertainty_score":0.3349543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0174732277559825,"score_gpt":0.267460577975888,"score_spread":0.2499873502199055,"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."}}