{"id":"W4292764333","doi":"10.1101/2022.08.22.22279057","title":"Integration of biomarker polygenic risk score improves prediction of coronary heart disease in UK Biobank and FinnGen","year":2022,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Helsinki Institute of Life Science, Helsingin Yliopisto; Genentech; National Institute on Minority Health and Health Disparities; Tampereen Yliopisto; Academy of Finland; Kela; Maze Therapeutics; McGill University; Strong; AbbVie; Broad Institute; Sanofi; Medical Research Council; Celgene; Biogen; GlaxoSmithKline; Business Finland; Helsingin Yliopisto; Bristol-Myers Squibb; AstraZeneca; Pfizer","keywords":"Biobank; Hazard ratio; Medicine; Confidence interval; Internal medicine; Biomarker; Framingham Risk Score; Cardiology; Area under the curve; Coronary heart disease; Disease; Bioinformatics; Biology","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":[0.007094148,0.0005573459,0.0009307718,0.001641079,0.0003633531,0.0009354415,0.0006913896,0.0006984926,0.001545415],"category_scores_gemma":[0.0150682,0.000331051,0.0006665451,0.001600785,0.0003721366,0.0005663348,0.001413177,0.0006043878,0.0003667862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00078802,"about_ca_system_score_gemma":0.000605888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04434672,"about_ca_topic_score_gemma":0.05644313,"domain_scores_codex":[0.9961416,0.002403007,0.0001858473,0.0008025979,0.0002877794,0.0001791984],"domain_scores_gemma":[0.9921318,0.004392214,0.001239941,0.001135431,0.0007044296,0.0003962377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001465029,0.0001001602,0.9710008,0.00006127658,0.0007489146,0.0001634987,0.0001924961,0.003728813,0.0007440147,0.0001427326,0.001883561,0.01976874],"study_design_scores_gemma":[0.00009197378,0.0002380973,0.968706,0.00004432293,0.0003196337,0.0001627578,0.0001273634,0.02813751,0.0004471439,0.0003517994,0.001342312,0.00003115514],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9947217,0.0003961443,0.0018044,0.0002508909,0.00002535718,0.00002284146,0.001970512,0.00006966005,0.000738561],"genre_scores_gemma":[0.9941748,0.00007235251,0.002311576,0.00008137022,0.00001558527,0.00002220788,0.002808271,0.00001184484,0.000501977],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04434672,"threshold_uncertainty_score":0.0881772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0199764647875875,"score_gpt":0.2685102774334535,"score_spread":0.248533812645866,"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."}}