Seoul National University Bundang Hospital’s AI-Powered ECG Analysis App Receives Regulatory Certification


  • Seoul National University Bundang Hospital’s ECG Buddy app receives regulatory approval for emergency disease prediction.
  • The AI-powered app enables rapid diagnosis and treatment of critical conditions, improving patient prognosis.
  • ECG Buddy’s smartphone-based accessibility revolutionizes emergency medical care, offering swift and cost-effective solutions.

In a significant development, Seoul National University Bundang Hospital (SNUBH) has announced that its research team has successfully developed an artificial intelligence (AI) application called “ECG Buddy” for emergency disease prediction. This innovative app analyzes electrocardiogram (ECG) images to assess myocardial infarction and arrhythmia, two critical conditions that demand swift diagnosis and treatment.

The research team, led by Professor Kim Joong-hee of the Department of Emergency Medicine and Professor Cho Young-jin of the Department of Cardiology, has obtained certification from the Ministry of Food and Drug Safety, a crucial step towards the app’s wider adoption and implementation in medical facilities across the country.

Addressing time-sensitive emergencies with ECG AI

Time is of the essence in emergency medical situations, and ECG Buddy aims to address this critical challenge. The most serious type of myocardial infarction, ST-segment elevation myocardial infarction, the leading cause of death in middle-aged and older adults, requires diagnosis and treatment within 10 minutes. Similarly, patients with pulmonary edema and hyperkalemia need prompt intervention to prevent life-threatening complications.

While advanced tests such as echocardiograms, blood tests, and angiograms are essential for accurate diagnosis, these procedures can be time-consuming in emergency settings. ECG Buddy bridges this gap by leveraging AI to analyze ECG test results in less than a minute, providing vital insights to emergency room physicians and enabling them to make informed treatment decisions swiftly.

Enhancing diagnostic accuracy and efficiency

ECG Buddy’s capabilities extend beyond simple ECG analysis. The app can classify 11 types of heart rhythms by capturing an image of the 12-lead ECG waveform area with a smartphone. Additionally, it outputs 10 digital biomarkers developed for severity assessment, acute myocardial infarction screening, cardiac function assessment, and hyperkalemia screening.

Superior performance and accessibility

Clinical studies have demonstrated ECG Buddy’s accuracy in diagnosing myocardial infarction and assessing hyperkalemia, surpassing manual analysis by trained medical professionals. Notably, the application’s ease of deployment and accessibility—requiring only a smartphone—sets it apart from previous AI models, making it a valuable tool for emergency medical care, particularly in resource-constrained settings.

Professor Kim highlights the broader potential of ECG Buddy beyond emergency rooms, emphasizing its utility in health checkups at primary medical institutions. With the Ministry of Food and Drug Safety certification, the application is poised to enhance emergency medical capabilities, particularly in areas facing challenges in skilled manpower and budget constraints.

Disclaimer. The information provided is not trading advice. Cryptopolitan.com holds no liability for any investments made based on the information provided on this page. We strongly recommend independent research and/or consultation with a qualified professional before making any investment decisions.

Share link:

Glory Kaburu

Glory is an extremely knowledgeable journalist proficient with AI tools and research. She is passionate about AI and has authored several articles on the subject. She keeps herself abreast of the latest developments in Artificial Intelligence, Machine Learning, and Deep Learning and writes about them regularly.

Most read

Loading Most Read articles...

Stay on top of crypto news, get daily updates in your inbox

Related News

Subscribe to CryptoPolitan