Cardiac disease prediction using artificial neural networks
Abstract
Cardiovascular diseases include diseases of the heart and blood vessel system including the brain, legs and lungs. These diseases have a very high mortality rate and it is estimated that by the year 2030 there will be about 23.6 million people who may die from this cause. A quantitative research methodology with descriptive scope is used. This project deals with the study of a type of heart disease, heart failure (HF), which is characterized by the inability of the heart to pump blood in adequate quantities to meet the demands of metabolism. Specifically, the prediction of the disease was sought by means of artificial neural networks, one of the most suitable machine learning (ML) techniques for this type of activity, although not the only one. The implementation was based on two tools that incorporate the management of neural networks (NR), IBM's SPSS and Matlab. An accuracy of 94.7% was achieved. Additionally, the study was oriented to determine those characteristics with more influence in the prediction of CI. Both softwares were able to agree that the slope of the ST segment has the greatest impact on prediction.
Downloads
References
Gambarte MJ, Higa C, Novo F, Ciambrone GM, Villagomez ODT, Ginesi A, et al. Comparación pronóstica entre scores de riesgo y la aplicación de redes neuronales para la predicción de la mortalidad a corto y mediano plazo en pacientes con insuficiencia cardíaca. REVISTA ARGENTINA DE CARDIOLOGÍA. 2021;89.
Avellaneda González JA, Ochoa Rey CM. IMPLEMENTACIÓN DE REDES NEURONALES PARA LA DETECCIÓN DE LA PRESENCIA DE ENFERMEDADES EN EL CORAZÓN. redes ing. 23 de mayo de 2012;1(2):38.
Rajalakshmi S, Madhav KV, Abhishek R. Inducement of Multivariate factors in Cardiac Disease Prediction with Machine Learning Techniques substantiated with Analytics. En: Proceedings of the 2019 11th International Conference on Computer and Automation Engineering [Internet]. Perth WN Australia: ACM; 2019 [citado 10 de septiembre de 2023]. p. 97-101. Disponible en: https://dl.acm.org/doi/10.1145/3313991.3314014
Low JX, Choo KW. Classification of Heart Sounds Using Softmax Regression and Convolutional Neural Network. En: Proceedings of the 2018 International Conference on Communication Engineering and Technology [Internet]. Singapore Singapore: ACM; 2018 [citado 10 de septiembre de 2023]. p. 18-21. Disponible en: https://dl.acm.org/doi/10.1145/3194244.3194255
Zhao YX, Yuan H, Wu Y. Prediction of Adverse Drug Reaction using Machine Learning and Deep Learning Based on an Imbalanced Electronic Medical Records Dataset. En: 2021 5th International Conference on Medical and Health Informatics [Internet]. Kyoto Japan: ACM; 2021 [citado 10 de septiembre de 2023]. p. 17-21. Disponible en: https://dl.acm.org/doi/10.1145/3472813.3472817
Araujo C, M A Azoubel L, K D B Filho A, M S Junior C, P S Sousa N, Pereira C, et al. Prediction of Excess Body Fat in Adolescents Using Neural Networks. En: 2021 8th International Conference on Bioinformatics Research and Applications [Internet]. Berlin Germany: ACM; 2021 [citado 10 de septiembre de 2023]. p. 63-9. Disponible en: https://dl.acm.org/doi/10.1145/3487027.3487037
Iftikhar S, Golec M, Chowdhury D, Gill SS, Uhlig S. FogDLearner: A Deep Learning-based Cardiac Health Diagnosis Framework using Fog Computing. En: Australasian Computer Science Week 2022 [Internet]. Brisbane Australia: ACM; 2022 [citado 10 de septiembre de 2023]. p. 136-44. Disponible en: https://dl.acm.org/doi/10.1145/3511616.3513108
Naik KT, Garg B. A Machine Learning Model for Disease Prediction and Remote Patient Monitoring. En: Proceedings of the 4th International Conference on Information Management & Machine Intelligence [Internet]. Jaipur India: ACM; 2022 [citado 10 de septiembre de 2023]. p. 1-5. Disponible en: https://dl.acm.org/doi/10.1145/3590837.3590844
Fedesoriano. Heart Failure Prediction Dataset [Internet]. Septiembre 2021 [citado 10 de septiembre de 2023]. Disponible en: https://www.kaggle.com/fedesoriano/heart-failure-prediction.
Copyright (c) 2024 Manuel Alejandro Carrascal Arias, Alvaro Maximiliano Saiquita , Guillermo Sánchez Flores, Torcoroma Velásquez Pérez
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
