Evaluation of the effectiveness of using artificial intelligence to predict the response of the human body to cardiovascular diseases

Abstract

This article discusses the issue of assessing the quality of predicting the dynamics of the human body in conditions of cardiovascular disease using intelligent software systems. To improve the forecast accuracy, the voting method of 3 competing systems was used, as well as the elimination of sparse data columns. Assessment of the quality of the prognosis of complications of cardiovascular diseases is carried out in terms of the accuracy and specificity of the diagnosis. The constructed system for 10 predicted diagnoses out of 12 showed a prediction accuracy of more than 90% with a specificity of more than 85%. This result shows a fairly high predictive ability of the created system when solving the problem of predicting the reaction of the human body to the onset of cardiovascular diseases (for example, complications of myocardial infarction).

Predicting Myocardial Infarction Complications and Outcomes With Deep Learning

“…The model optimized with adaptive moment estimation (Adam) algorithm, batch normalization, and dropout layers are also used against overfitting problem and improve performance. The proposed model in this study has better performance than the state-of-the-art literature approaches [19,20,22,24].…”

“…Golovenkin et al mentioned that the results of myocardial infarction may be too uneventful to be discovered even by experienced professionals, and they mentioned that the use of artificial neural networks in the diagnosis of this disease would be beneficial [24]. They used the "Myocardial infarction complications Database of University of Leicester" as a dataset [21] which is also used in this paper.…”

“…Study [22] was proposed by the same authors as study [24]. [22] was presented as a further study of [24] to predict more positive outcomes.…”

“…Study [22] was proposed by the same authors as study [24]. [22] was presented as a further study of [24] to predict more positive outcomes. Dorrer and friends aimed to predict the course of CVD with data augmentation.…”

“…Dorrer and friends aimed to predict the course of CVD with data augmentation. They used the same dataset [21] as in [24]. Due to the scarcity of positive output data, the authors proposed a data augmentation method and performed their testing on various deep neural network models.…”