Machine learning prediction of hypertension integrating polygenic risk scores in inner Eurasian 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
July 8, 2026
Clinical Scorecard: Predictive Modeling of Hypertension Using Machine Learning and Polygenic Risk Scores in Inner Eurasian Populations
At a Glance
Category Detail
Condition Arterial Hypertension Key Mechanisms Renin–angiotensin–aldosterone system, sodium handling via epithelial sodium channels, central sympathetic regulation. Target Population Multiethnic inner Eurasian populations, including East Slavic and West Asian-related groups. Care Setting Predictive modeling for disease risk assessment.
Key Highlights
PRS for systolic and diastolic blood pressure showed odds ratios of 6.20 and 6.71, respectively. Neural network model achieved a test ROC-AUC of 0.8245 for predicting hypertension. PRSs were consistently associated with hypertension across diverse ancestry groups. Guideline-Based Recommendations
Diagnosis
Hypertension diagnosed based on self-reported medical history through a structured questionnaire. Management
Early identification and intervention through lifestyle modification and pharmacological treatment. Monitoring & Follow-up
Use of predictive models to identify individuals at high risk of hypertension. Risks
Hypertension is a major modifiable risk factor for cardiovascular disease, stroke, and chronic kidney disease. Patient & Prescribing Data
Individuals from diverse inner Eurasian populations.
Less than 50% of women and less than 40% of men receive treatment for hypertension.
Clinical Best Practices
Integrate PRS with questionnaire-derived risk factors for improved risk assessment. Utilize machine learning tools for predictive modeling in hypertension. Related Resources & Content
