Utility of polygenic scores across diverse diseases in a hospital cohort for predictive modeling

• Published in: Nature communications Vol. 15; no. 1; pp. 3168 - 12
• Main Authors: Sun, Ting-Hsuan, Wang, Chia-Chun, Liu, Ting-Yuan, Lo, Shih-Chang, Huang, Yi-Xuan, Chien, Shang-Yu, Chu, Yu-De, Tsai, Fuu-Jen, Hsu, Kai-Cheng
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 12.04.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 49/61; 631/208/1516/1510; 692/53/2423; Age; China; Disease; Environmental factors; Genetic Predisposition to Disease; Genomes; Genotyping; Health Facilities; Hospitals; Humanities and Social Sciences; Humans; Hyperplasia; Male; Medical research; Metabolic disorders; multidisciplinary; Phenotypes; Polygenic inheritance; Precision medicine; Prediction models; Preventive medicine; R&D; Regression analysis; Regression models; Research & development; Science; Science (multidisciplinary); China
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-024-47472-5

Polygenic scores estimate genetic susceptibility to diseases. We systematically calculated polygenic scores across 457 phenotypes using genotyping array data from China Medical University Hospital. Logistic regression models assessed polygenic scores’ ability to predict disease traits. The polygenic score model with the highest accuracy, based on maximal area under the receiver operating characteristic curve (AUC), is provided on the GeneAnaBase website of the hospital. Our findings indicate 49 phenotypes with AUC greater than 0.6, predominantly linked to endocrine and metabolic diseases. Notably, hyperplasia of the prostate exhibited the highest disease prediction ability ( P value = 1.01 × 10 −19 , AUC = 0.874), highlighting the potential of these polygenic scores in preventive medicine and diagnosis. This study offers a comprehensive evaluation of polygenic scores performance across diverse human traits, identifying promising applications for precision medicine and personalized healthcare, thereby inspiring further research and development in this field. Here, the authors analyze polygenic scores for 457 phenotypes, finding 49 with robust polygenic score predictive models ( > 0.6 AUC). They find that population diversity and environmental factor integration are key considerations to improving the model’s performance.