APPLYING NEURAL NETWORK FOR PREDICTING CARDIOVASCULAR DISEASE RISK
Ключевые слова:
Neural network, cardiovascular system diseases, predicting models, supervised learning, activation function, Keras.Аннотация
This article concerns the problem of the prevalence of cardiovascular disease in economically
developed countries. The purpose of this article is to create a neural network to determine the risk of cardiovascular
disease based on the individual characteristics of the patient. In order to predict the risk of cardiovascular disease a
neural network has been developed. The model was built in the Python programming language using the open-source
library for building neural networks Keras. Data containing patient information for model building were taken from
Kaggle.com. The accuracy of the neural network is 82%. With the help of neural network it will be possible to
analyze the changes and the development of diseases in the future by changing the patient's input parameters, for
instance, age, increase in blood pressure and etc. Also it would be possible to change the predictive diagnosis for the
better if follow the parameters such as refusal from addictions, regular sleep, a healthy lifestyle and proper nutrition.
