“Experimental evidence has shown that many cardiovascular diseases can be better controlled and prevented with continuous ECG monitoring and analysis,” explains Yang Chen, vice dean and professor at the School of Cyber ​​Science and Technology, China University of Science and Technology. “However, the need to attach electrodes to the body during routine ECG monitoring reduces people’s desire to wear such devices for extended periods of time, making these temporary, irregular ECG signals difficult to detect.”

Chen experienced this firsthand when he needed 24 hours of ECG monitoring. “At the time, I was suffering from skin irritation at the electrode sites and I was annoyed by my limited ability to move due to the electrode wires. This experience really makes me refuse to be re-examined,” he says.

Inspired by the search for a better solution, Chen and his team used a commercial millimeter-wave radar that can detect movements of the cardiovascular system in all three directions over time. He and his colleagues then developed a sophisticated artificial intelligence algorithm that can use this mechanical activity to determine electrical activity.

Non-contact monitoring of the electrocardiogram using a millimeter radarwww.youtube.com

In their study, the researchers conducted 200 experimental trials with 35 participants aged 18 to 65. The radar device was placed at a height of 0.4 to 0.5 meters above their bodies in four different physiological states – normal breathing, irregular breathing, after exercise. especially after jumping), and sleep to simulate the normal conditions of everyday life.

After using the data to train and test their AI, the researchers found that this approach had a median timing error of less than 14 milliseconds, and a median morphology accuracy of 90% compared to a standard ECG with electrodes.

Chen emphasizes that the new radar approach offers several advantages over the standard approach. “Our monitoring scenario does not require users to take off their clothes and attach a device or electrode to their body,” he says. “We believe this strength will effectively complement 24-hour continuous ECG monitoring.”

One limitation, however, is that the new approach is less accurate when the patient moves randomly, and the research team plans to address this issue in future work. This study also involved healthy people, so the AI ​​algorithm needs to be further trained to be applied to people with a specific cardiovascular disease.

However, Chen sees many benefits to continuous non-contact ECG monitoring, and his team is looking to commercialize their approach. “We plan to launch a home health care product where seniors at high risk for cardiovascular disease need comprehensive monitoring,” he says. “We believe that such new digital medical technologies will help people lead healthier lives.”

The researchers describe their work in a study published last month in IEEE Transactions in Mobile Computing.