Analysis of the use of Machine Learning in the detection and prediction of hypertension in COVID 19 patients. A review of the scientific literature

• Autores: Herrera-Huisa, Luis, Arias-Meza, Nicole, Cabanillas-Carbonell, Michael
• Formato: artículo
• Fecha de Publicación: 2021
• Institución: Universidad Autónoma del Perú
• Repositorio: AUTONOMA-Institucional
• Lenguaje: inglés
• OAI Identifier: oai:repositorio.autonoma.edu.pe:20.500.13067/1755
• Enlace del recurso: https://hdl.handle.net/20.500.13067/1755; https://doi.org/10.1109/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00110
• Nivel de acceso: acceso restringido
• Materia: Hypertension; COVID-19; Systematics; Pandemics; Databases; Neural networks; Asia; https://purl.org/pe-repo/ocde/ford#2.02.04

The world is currently experiencing a major pandemic with the SARS-CoV-2 virus in which many patients who suffer and have suffered from this disease are more likely to suffer from hypertension. For this purpose, we have carried out a review of the scientific literature, from which we have collected 105 articles obtained from the following databases: ProQuest, Dialnet, ScienceDirect, Scopus, IEEE Xplore. Subsequently, based on the inclusion and exclusion criteria, 68 articles were systematized, detailing that Machine Learning helps us in the detection and prediction of hypertension in patients with coronavirus, Likewise, the predictive models that allow better detection of hypertension in patients with Covid 19 are “Neural Networks”, “Cox Risk Model”, “Random Forest” and “XGBoost”, detailing the countries and technologies used.