This study aims to enhance personalized and preventive care for non-communicable diseases (NCDs) in Kazakhstan by examining epigenetic factors, predicting biological age and reproductive function using machine learning, and developing health improvement recommendations.
Adults aged 18 to 69 years.
Residents of 17 regions of Kazakhstan.
Willingness to participate and provide informed consent.
Age less than 18 years old or over 69 years old.
Failure to provide informed consent or incomplete participation in data collection procedures.
The study population consists of 6,720 adult volunteers aged 18 to 69 years, residing across 17 regions of Kazakhstan. Participants are stratified by age and gender to ensure balanced representation within the following age groups: * 18-29 years * 30-44 years * 45-59 years * 60-69 years Each age group includes an equal proportion of men and women, ensuring gender balance. The selection follows a multistage cluster sampling design, incorporating various socioeconomic backgrounds and health statuses to enhance the generalizability of findings.
Other
Prospective
Genetic: DNA analysis
Other interventionInvestigation of telomere length (TL) and DNA methylation level analysis
Accuracy of Machine Learning Model for Predicting Biological Age
Evaluation of the model's performance (based on telomere length and DNA methylation) using Mean Absolute Error (MAE), Mean Squared Error (MSE), and R².
Accuracy of Reproductive Function Prediction Model
Development and validation of machine learning model to predict reproductive function using biomarkers. Model performance evaluated via MAE, MSE, and R².
Click on the lead sponsor to view all of their trials.
