To evaluate the performance of polygenic risk scores (PRS) for hypertension in Russia and to develop predictive models integrating PRS and questionnaire-based risk factors for disease risk assessment.
Approach:
Cohort Analysis: Analyzed a cohort of 175,704 individuals from multiethnic inner Eurasian populations.
PRS Evaluation: Evaluated published PRS for systolic blood pressure, diastolic blood pressure, and pulse pressure for association with hypertension across different ancestry groups.
Predictive Modeling: Developed predictive models using multiple machine learning tools, including neural networks, integrating PRS and questionnaire-derived risk factors.
Key Findings:
PRSs for systolic and diastolic blood pressure showed marked differences between the top and bottom deciles of the PRS distribution, with odds ratios of 6.20 (95% CI: 5.22–7.36) and 6.71 (95% CI: 5.58–8.06), respectively.
The PRS for pulse pressure was associated with hypertension, with an odds ratio of 3.71 (95% CI: 3.16–4.35).
All evaluated PRSs were consistently associated with hypertension across various ancestry groups in Russia.
A neural network model integrating PRSs with questionnaire-based risk factors achieved a test ROC-AUC of 0.8245 (95% CI: 0.8114–0.8362).
Interpretation:
The study demonstrates that PRSs for blood pressure traits retain substantial predictive value across diverse inner Eurasian populations.
Limitations:
The study may not fully represent all ethnic groups within the inner Eurasian populations due to the diversity of the region.
Potential biases in self-reported medical history could affect the accuracy of hypertension classification.
Conclusion:
The systolic blood pressure PRS showed robust predictive value across diverse populations.
by Vera Tsvetkova, Aleksandra Denisova, Saleem Mansour, Layal Shaheen, Iskandar Hweijeh, Leushin Artem, Travin Grigorii, Dilya Turkmenova, Liya Valieva, Anna Kim, Dmitrii Kharitonov, Anna Ilinskaya, Maria Poptsova, Valery Ilinsky, Alexander Rakitko
