Dataset Curado de ENSANUT 2022 para Análisis de Riesgo de Hipertensión

This dataset is a curated and derived dataset constructed from three publicly available datasets of the National Health and Nutrition Survey (ENSANUT) Continua 2022, published by the National Institute of Public Health (INSP) of Mexico and accessible through the official government portal: https://ensanut.insp.mx/encuestas/ensanutcontinua2022/descargas.php The original datasets used in this work are: ensaantro2022_entrega_w.csv (Anthropometry and Blood Pressure Questionnaire) Determinaciones_bioquímicas_cronicas_deficiencias_9feb23.csv (Biochemical Determinations for Chronic Diseases and Deficiencies) ensafisica2022_adultos_entrega_w.csv (Physical Activity – Adolescents and Adults) A comprehensive data curation process was performed, including data cleaning, integration of multiple sources, variable harmonization, removal of inconsistencies, and selection of clinically relevant variables. The resulting dataset provides a unified and analysis-ready structure suitable for statistical analysis and machine learning applications in public health research. The dataset includes demographic information, biochemical markers, anthropometric measurements, and lifestyle-related variables, such as sex, age, hemoglobin concentration, glucose and insulin levels, lipid profile (total cholesterol, HDL, LDL, triglycerides), creatinine, uric acid, C-reactive protein, ferritin, folate, vitamin B12, vitamin D, weight, height, waist circumference, physical activity indicators, and environmental temperature, among others. The final column, risk_hypertension, is a binary variable indicating whether an individual is at risk of developing arterial hypertension (1 = at risk, 0 = not at risk). This dataset can be used for the identification of cardiovascular risk factors, epidemiological studies, and the development of predictive models related to hypertension. This dataset constitutes a derived work. The original data remain the property of ENSANUT and the National Institute of Public Health (INSP). The author does not claim ownership of the original data, but of the processes of data integration, curation, and documentation presented in this work.