Logistic regression: an example for infarct prediction

Silva-Marchan H.; Ortiz-Castro G.; Peña-Cáceres O.J.M.; More-More M.A. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2023)

Resumen

Technological advances have allowed the development and availability of specialized tools for the use of historical data. In many cases, these tools are used for decision-making in multidisciplinary institutions that require support for the development of their activities, particularly in the health sector. The purpose of this study is to use a machine learning algorithm to predict heart attacks using demographic and family health data. The methodology focused on the extraction of open data from the Demographic and Family Health Survey (ENDES) applied in 2021 in Peru, characterization and execution of machine learning techniques using Orange Data Mining software. In this first approach, the results show that the logistic regression model has an accuracy of 0.99% on the prediction of heart attacks under the use of ENDES Peru 2021 data. For future studies, it is suggested to incorporate unstructured data such as text documents, sensor data and images to strengthen the reliability of the model.

Instituciones: Universidad Nacional de Piura; Universidad Nacional de Tumbes; Universidad César Vallejo