|
Title:
|
EXPLAINABLE ARTIFICIAL INTELLIGENCE IN THE DIAGNOSIS OF CARDIOVASCULAR DISEASES IN SMALL SAMPLES |
|
Author(s):
|
Natalia Gusarova, Ivan Tomilov, Danil Zmievskii, Vladimir Shilonosov, Tatiana Polevaya and Aleksandra Vatian |
|
ISBN:
|
978-989-8704-50-4 |
|
Editors:
|
Piet Kommers, Mário Macedo, Guo Chao Peng and Ajith Abraham |
|
Year:
|
2023 |
|
Edition:
|
Single |
|
Keywords:
|
Cardiovascular Disease, Explainable Artificial Intelligence, XAI, Small Samples |
|
Type:
|
Full |
|
First Page:
|
175 |
|
Last Page:
|
182 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
In this work several DNN-based solutions aimed at classifying different of CVDs in conditions of small training samples are proposed. Using GradCAM technology, the main areas of attention of DNNs in these conditions are indentified, and then experimentally being compared with the areas of attention of cardiologists when making a clinical decision. It is shown that even on small samples it is possible to achieve the efficiency of SOTA solutions obtained on large datasets, which should increase the confidence of medical staff, including less qualified ones, in DNN as a means of supporting rapid diagnosis of CVD in acute cases. In turn, combining the results of the physician and AI tools can improve the quality of diagnosis and, therefore, the patient's chances for a speedy and successful cure. |
|
|
|
|
|
|
