SciELO - Scientific Electronic Library Online

 
vol.26 número1Influencia del aislamiento sísmico en el diseño sismorresistente de edificios con estructura de muros de concreto reforzado índice de autoresíndice de materiabúsqueda de artículos
Home Pagelista alfabética de revistas  

Servicios Personalizados

Revista

Articulo

Indicadores

Links relacionados

  • En proceso de indezaciónCitado por Google
  • No hay articulos similaresSimilares en SciELO
  • En proceso de indezaciónSimilares en Google

Compartir


Ingeniería y competitividad

versión impresa ISSN 0123-3033versión On-line ISSN 2027-8284

Resumen

ARRUBLA-HOYOS, Wilson; CARRASCAL-PORRAS, Fernando  y  GOMEZ, Jorge. Cardiovascular Risk Prediction through Machine Learning: A Comparative Analysis of Techniques. Ing. compet. [online]. 2024, vol.26, n.1, e-20113229.  Epub 26-Feb-2024. ISSN 0123-3033.  https://doi.org/10.25100/iyc.v26i1.13229.

The field of healthcare, driven by the continuous growth of data related to human health and the ongoing course of digital transformation, is undergoing a significant evolution. In this experimental study, a comparison of Artificial Intelligence techniques, specifically neural networks, Random Forest, and decision tree, was conducted to evaluate their effectiveness in diagnosing cardiovascular diseases. This was achieved by leveraging clinical data available in open-access databases. The methodology focused on identifying the most influential variables in cardiovascular disease diagnosis through a comprehensive literature review. Subsequently, the Machine Learning techniques to be employed were determined, and the most suitable dataset for these variables was acquired. The results revealed that all three Artificial Intelligence techniques demonstrated good performance in diagnosing cardiovascular diseases. It is worth highlighting that the neural network-based model excelled with an accuracy of 89%, establishing itself as a highly relevant tool for supporting timely disease diagnosis. These findings suggest a potential positive impact on clinical practice and future healthcare by providing healthcare professionals with a valuable resource for making informed decisions in the diagnosis and treatment of cardiovascular diseases. Ultimately, this could enhance the quality of patient care and their overall well-being. This study reinforces the notion that Machine Learning techniques play a crucial role in transforming healthcare and clinical decision-making in the field of health, offering new perspectives for the prevention and treatment of cardiovascular diseases and other medical disorders.

Palabras clave : artificial intelligence; cardiovascular disease; big data; random forest; neural networks; decision tree.

        · resumen en Español     · texto en Inglés     · Inglés ( pdf )