Arterial hypertension in adults: risk analysis and predictive classification using Random Forest
Article Sidebar
Main Article Content
Abstract
Arterial hypertension (AH) has been considered a major public health concern due to its impact on cardiovascular morbidity and mortality and its frequent late diagnosis. This study addresses the problem by developing a predictive classification model based on the Random Forest algorithm, aiming to identify individuals at risk of hypertension using clinical, demographic, and metabolic variables. A dataset from patients in Mexico was used and processed through cleaning, normalization, and balancing with the SMOTE-Tomek technique. The model was trained with 70% of the data and validated with the remaining 30%, using 10-fold cross-validation. Its performance was evaluated through metrics such as precision, recall, F1-score, and confusion matrix. The model was compared with other methods such as KNN and Decision Tree. The optimized model (127 trees, depth 20) achieved an accuracy of 98% with body mass index, blood pressure, physical activity, weight, and waist circumference identified as the most relevant predictors. Although metabolic biomarkers were also evaluated, they were less relevant in the classification compared to anthropometric variables. The results confirm that Random Forest is a robust and accurate tool for the early detection of hypertension risk. Thanks to its integration via an API and an interactive form, the model is accessible even to not-technical users, contributing to preventive strategies in public health.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
When an author creates an article and publishes it in a journal, the copyright passes to the journal as part of the publishing agreement. Therefore, the journal becomes the owner of the rights to reproduce, distribute and sell the article. The author retains some rights, such as the right to be recognized as the creator of the article and the right to use the article for his or her own scholarly or research purposes, unless otherwise agreed in the publication agreement.
How to Cite
References
N. K. Toala-Lino, Y. Peñaherrera Moran, y I. G. Parrales-Pincay, «Hipertensión arterial como factor predisponente de insuficiencia renal en adultos.», MQRInvestigar , vol. 7, n.o 1, pp. 367-389, ene. 2023, doi: 10.56048/MQR20225.7.1.2023.367-389.
World Health Organization, «OMS | Hipertensión». Accedido: 9 de agosto de 2025. [En línea]. Disponible en: https://www.who.int/news-room/fact-sheets/detail/hypertension
K. Romero Jares y R. Centeno Quispe, «Perú: Encuesta Demográfica y de Salud Familiar - ENDES 2022», may 2025. Accedido: 9 de agosto de 2025. [En línea]. Disponible en: https://www.inei.gob.pe/media/MenuRecursivo/publicaciones_digitales/Est/Lib1898/libro.pdf
I. Campos-Nonato et al., «Prevalencia, tratamiento y control de la hipertensión arterial en adultos mexicanos: resultados de la Ensanut 2022», Salud Publica Mex, vol. 65, pp. s169-s180, jun. 2023, doi: 10.21149/14779.
A. N. Zavala-Hoppe, T. E. Zambrano-Flores, L. H. Vivar-Medina, y J. E. Fuentes-Parrales, «Epidemiología y factores de riesgo de la hipertensión arterial en los países de Latinoamérica y Europa», MQRInvestigar , vol. 8, n.o 1, pp. 1371-1389, feb. 2024, doi: 10.56048/MQR20225.8.1.2024.1371-1389.
A. L. Pico Pico, E. Y. Reyes Reyes, D. A. Anchundia Alvia, y M. D. L. Á. Cobos Moreno, «Comportamiento epidemiológico de la hipertensión arterial en el Ecuador», RECIMUNDO: Revista Científica de la Investigación y el Conocimiento, vol. 7, n.o 4, pp. 299-307, 2023, doi: 10.26820/recimundo/7.(4).oct.2023.299-307.
A. Shafizadeh et al., «Machine learning-enabled analysis of product distribution and composition in biomass-coal co-pyrolysis», Fuel, vol. 355, p. 129464, ene. 2024, doi: 10.1016/J.FUEL.2023.129464.
F. Plazzotta, D. Luna, y F. González Bernaldo de Quirós, «Sistemas de Información en Salud: Integrando datos clínicos en diferentes escenarios y usuarios», Rev Peru Med Exp Salud Publica, vol. 32, n.o 2, pp. 343-351, abr. 2015, doi: 10.17843/rpmesp.2015.322.1630.
J. H. Chen, X. L. Wang, y F. Lei, «Data-driven multinomial random forest: a new random forest variant with strong consistency», J Big Data, vol. 11, n.o 1, pp. 1-32, dic. 2024, doi: 10.1186/S40537-023-00874-6/FIGURES/7.
R. M. Alzoman, M. J. F. Alenazi, L. Belli, G. Ferrari, M. Martalò, y L. Davoli, «A Comparative Study of Traffic Classification Techniques for Smart City Networks», Sensors, vol. 21, n.o 14, p. 4677, jul. 2021, doi: 10.3390/S21144677.
N. E. Moskaleva et al., «Target Metabolome Profiling-Based Machine Learning as a Diagnostic Approach for Cardiovascular Diseases in Adults», Metabolites, vol. 12, n.o 12, p. 1185, dic. 2022, doi: 10.3390/METABO12121185/S1.
K. Sumwiza, C. Twizere, G. Rushingabigwi, P. Bakunzibake, y P. Bamurigire, «Enhanced cardiovascular disease prediction model using random forest algorithm», Inform Med Unlocked, vol. 41, p. 101316, ene. 2023, doi: 10.1016/J.IMU.2023.101316.
J. L. Speiser, «A random forest method with feature selection for developing medical prediction models with clustered and longitudinal data», J Biomed Inform, vol. 117, p. 103763, may 2021, doi: 10.1016/J.JBI.2021.103763.
Y. Surichaqui Gómez y J. A. Mori Castro, «Estilo de Vida y su Relación con el Estado Nutricional en pacientes Adultos Mayores con Hipertensión Arterial en el Hospital de Huaycán de Lima», Ciencia Latina Revista Científica Multidisciplinar, vol. 7, n.o 4, pp. 9069-9089, sep. 2023, doi: 10.37811/CL_RCM.V7I4.7609.
C. Schröer, F. Kruse, y J. M. Gómez, «A Systematic Literature Review on Applying CRISP-DM Process Model», Procedia Comput Sci, vol. 181, pp. 526-534, ene. 2021, doi: 10.1016/J.PROCS.2021.01.199.
Y. Yao, Y. He, y H. Ou, «Missing Data Imputation Method Combining Random Forest and Generative Adversarial Imputation Network», Sensors 2024, Vol. 24, Page 1112, vol. 24, n.o 4, p. 1112, feb. 2024, doi: 10.3390/S24041112.
M. Alyami et al., «Predictive modeling for compressive strength of 3D printed fiber-reinforced concrete using machine learning algorithms», Case Studies in Construction Materials, vol. 20, p. e02728, jul. 2024, doi: 10.1016/J.CSCM.2023.E02728.
S. Khasim, H. Ghosh, I. S. Rahat, K. Shaik, y M. Yesubabu, «Deciphering Microorganisms through Intelligent Image Recognition: Machine Learning and Deep Learning Approaches, Challenges, and Advancements», EAI Endorsed Transactions on Internet of Things, vol. 10, nov. 2023, doi: 10.4108/EETIOT.4484.
G. R. Ren et al., «Machine Learning Predicts Recurrent Lumbar Disc Herniation Following Percutaneous Endoscopic Lumbar Discectomy», Global Spine J, vol. 14, n.o 1, pp. 146-152, ene. 2024, doi: 10.1177/21925682221097650.
Y. Cooli y C. Mahesh, «Recursive Parallel Partition Random Forest for Medical Disease Classification», International Journal of Intelligent Engineering and Systems, vol. 14, n.o 5, p. 2021, doi: 10.22266/ijies2021.1031.11.
J. H. Chung et al., «Random forest identifies predictors of discharge destination following total shoulder arthroplasty», JSES Int, vol. 8, n.o 2, pp. 317-321, mar. 2024, doi: 10.1016/J.JSEINT.2023.04.003.
O. Nikolaychuk, J. Pestova, y A. Yurin, «Wildfire Susceptibility Mapping in Baikal Natural Territory Using Random Forest», Forests 2024, Vol. 15, Page 170, vol. 15, n.o 1, p. 170, ene. 2024, doi: 10.3390/F15010170.
J. J. Hidalgo Flores, M. A. Guerrero Dueña, y R. García Rodríguez, «La obesidad como factor de riesgo de la hipertensión arterial», Revista Científica Higía de la Salud, vol. 5, n.o 2, pp. 2021-2033, dic. 2021, doi: 10.37117/HIGIA.V1I5.576.
D. A. Altamirano Lojano, R. Alvarez Ochoa, J. P. Garcés-Ortega, y G. Cordero Cordero, «Índice de masa corporal e Hipertensión Arterial en Adultos», Revista Multidisciplinaria Investigación Contemporánea, vol. 2, n.o 1, pp. 102-131, ene. 2024, doi: 10.58995/REDLIC.IC.V2.N1.A57.
M. De Jesús Sosa-Martínez, I. León-Lozano Jair, Y. García-Jiménez, B. Garduño-Orbe, A. J. Lagarza-Moreno, y G. Juanico-Morales, «Frecuencia de dislipidemias y determinación del riesgo cardiovascular en pacientes con hipertensión arterial sistémica», Atención Familiar, vol. 30, n.o 4, pp. 245-250, dic. 2023, doi: 10.22201/fm.14058871p.2023.486536.
P. D. F. Isles, «A random forest approach to improve estimates of tributary nutrient loading», Water Res, vol. 248, p. 120876, ene. 2024, doi: 10.1016/J.WATRES.2023.120876.
H. Kandil, A. Soliman, N. S. Alghamdi, J. R. Jennings, y A. El-Baz, «Using Mean Arterial Pressure in Hypertension Diagnosis versus Using Either Systolic or Diastolic Blood Pressure Measurements», Biomedicines, vol. 11, n.o 3, p. 849, mar. 2023, doi: 10.3390/BIOMEDICINES11030849.
B. K. Meher, M. Singh, R. Birau, y A. Anand, «Forecasting stock prices of fintech companies of India using random forest with high-frequency data», Journal of Open Innovation: Technology, Market, and Complexity, vol. 10, n.o 1, p. 100180, mar. 2024, doi: 10.1016/J.JOITMC.2023.100180.
M. Ahad, D. Padha, y H. Sharma, «Machine Learning in Cardiology: a Survey of Early Detection Models for Heart Diseases», IJFMR - International Journal For Multidisciplinary Research, vol. 5, n.o 3, may 2023, doi: 10.36948/IJFMR.2023.V05I03.3113.
M. Delgado-Galeano, «Historia de la hipertensión arterial: revisión narrativa», Salud UIS, vol. 55, n.o 1, may 2023, doi: 10.18273/SALUDUIS.55.E:23043.
Y. Anggriani Utama, «Pengaruh Self Management pada Pasien Hipertensi: Sebuah Tinjauan Sistematis», Jurnal Ilmiah Universitas Batanghari Jambi, vol. 23, n.o 1, pp. 422-429, feb. 2023, doi: 10.33087/JIUBJ.V23I1.3528.
O. G. Montero Cadena, G. J. Guzmán Kure, R. C. Acosta Bravo, y M. B. Peñafiel Peñafiel, «Principales factores de riesgo de la hipertensión arterial», RECIMUNDO, vol. 7, n.o 2, pp. 89-97, jul. 2023, doi: 10.26820/recimundo/7.(2).jun.2023.89-97.
B. E. Rıchar Wıllıam, G. V. Ana Lucıla †, A. Escobar Magaly, N. A. Lucıa, J. A. Zevallos Vıllodas, y C. R. Castro Galarza, «LA NO ADHERENCIA AL TRATAMIENTO ANTIHIPERTENSIVO Y FACTORES ASOCIADOS: UNA REVISIÓN», Advances in Science and Innovation, vol. 1, n.o 1, pp. 45-52, dic. 2022, doi: 10.61210/ASI.V1I1.5.