AI-Based Application for Early Detection of Heart Diseases Created in Russia
World
Scientists from Penza State University (PSU) have developed a web application for the automatic interpretation of electrocardiosignals using artificial intelligence. This application enables the early detection of dangerous cardiovascular pathologies, according to the press service of the Ministry of Science and Higher Education of Russia.
According to the World Health Organization (WHO), the leading causes of death from cardiovascular diseases include ischemic heart disease (including myocardial infarction), arterial hypertension, and cerebrovascular diseases (including stroke).
The web application "CardioAI," developed by PSU researchers, uses a convolutional neural network to automatically interpret electrocardiosignals. This innovation provides a way to identify dangerous cardiovascular pathologies at an early stage.
The uniqueness of the development lies in the convolutional neural network, refined by Penza scientists. According to the Ministry of Science and Higher Education, the AI-powered program provides an accurate diagnosis in 90% of cases. Approximately 2,000 patients' electrocardiosignals were tested, and the experiments confirmed that the neural network's diagnostic accuracy is close to that of a cardiologist.
The application’s main functions include uploading electrocardiogram (ECG) data, processing it, and detecting rhythm disorders, conduction issues, and ischemic changes. The press service highlighted that the demo version of the web application will be user-friendly.
The results are provided to users within seconds, showing whether any abnormalities are detected. If abnormalities are identified, the program generates recommendations and a list of possible pathologies.
"Our application serves as an electronic assistant for doctors. With its help, physicians can directly receive test results from patients and adjust treatments based on the data provided by the AI," said Leonid Krivonogov, a professor at PSU's Department of Medical Cybernetics and Informatics.
The web application "CardioAI," developed by PSU researchers, uses a convolutional neural network to automatically interpret electrocardiosignals. This innovation provides a way to identify dangerous cardiovascular pathologies at an early stage.
The uniqueness of the development lies in the convolutional neural network, refined by Penza scientists. According to the Ministry of Science and Higher Education, the AI-powered program provides an accurate diagnosis in 90% of cases. Approximately 2,000 patients' electrocardiosignals were tested, and the experiments confirmed that the neural network's diagnostic accuracy is close to that of a cardiologist.
The application’s main functions include uploading electrocardiogram (ECG) data, processing it, and detecting rhythm disorders, conduction issues, and ischemic changes. The press service highlighted that the demo version of the web application will be user-friendly.
The results are provided to users within seconds, showing whether any abnormalities are detected. If abnormalities are identified, the program generates recommendations and a list of possible pathologies.
"Our application serves as an electronic assistant for doctors. With its help, physicians can directly receive test results from patients and adjust treatments based on the data provided by the AI," said Leonid Krivonogov, a professor at PSU's Department of Medical Cybernetics and Informatics.
Powered by Froala Editor