Predicción de ataques cardiacos por medio del modelamiento de inteligencias artificiales: Predicting Heart Attacks Using Machine Learning Models

Abstract

Introduction: Heart attacks represent a serious threat to the integrity and well-being of those who suffer from them. Taking quick action based on the patient’s physical conditions is important for efficiently preventing a possible heart attack.

Objective: This article aims to explore and apply machine learning techniques to a data set related to heart attack risk factors.

Methodology: The data set is processed in Google Colab using Pandas, Matplotlib, and NumPy. Then, the modeling and deployment of artificial intelligence models composed of Decision Trees and K-Nearest Neighbors (KNN) are carried out.

Results: The models provide a series of results that are compared to determine which machine learning technique yields the most accurate outcome.

Conclusion: The comparison of Decision Trees and KNN allows the identification of the most effective technique for predicting heart attack risk based on the analyzed data set.