The Imperial system is intended to extract more information from the ECG itself. Researchers trained the AI to identify electrical patterns associated with underlying disease, including signals that may not be apparent to clinicians reviewing the tracing visually.
According to the British Heart Foundation, the models were developed using more than 1.6 million ECGs from Brazil that were linked with patient medical histories, along with several million recordings from the United States. In a U.S. study involving about 67,000 patients, the system identified up to 81% of people with heart failure and up to 90% of those with heart valve disease. The findings were presented at the European Society of Cardiology Congress in Munich. Across broader testing, the AI produced diagnostic accuracy ranging from 83% to 93% for heart disease in evaluation datasets.
Researchers see the technology primarily as a screening and triage system. A patient could receive a standard ECG for one reason, such as checking an abnormal heart rhythm, while the same recording is also analyzed for signs of other conditions that were not initially suspected. That could help clinicians decide which patients should move on to more detailed testing, including an echocardiogram.
"If someone comes in to have an ECG, we want to pick up underlying heart failure or valve disease that would never be picked up by a human doctor," said Dr. Fu Siong Ng, a consultant cardiologist and professor of cardiac electrophysiology at Imperial College London. "If there is any suspicion, then we will do an echocardiogram to confirm it right away."
The system is not meant to replace conventional cardiac assessment and would not detect every form of heart disease. Researchers are instead positioning it as an additional layer of analysis that could help prioritize higher-risk patients for specialist evaluation.
The team is also exploring how the technology could be incorporated into clinical equipment, including a possible handheld ECG reader for healthcare professionals.
Imperial has created a spinout company, Cardiovolt.ai, to develop the technology for clinical use. Further validation across different patient populations, healthcare systems and real-world workflows will still be needed before the system can be used routinely.
This analysis is based on reporting from Yahoo News.
Image courtesy of everlywell.
This article was generated with AI assistance and reviewed for accuracy and quality.
