02 March 2020

Long-term forecast

Experimental sensor predicts heart attack in 10 days

Sergey Kolenov, Hi-tech+

The new device, which has been tested on patients in four US states, can make the installation of implantable sensors for monitoring the work of the heart an archaic method of monitoring patients with cardiovascular problems. The device is attached to the chest like a wearable gadget, and with high reliability warns the patient and his doctor about an impending heart attack, allowing him to stop it at the earliest stage and thereby avoid hospitalization.

heart-failure-sensor.jpg

Photo from the press release of the University of Utah Health Wearable sensor powered by AI predicts worsening heart failure before hospitalization – VM.

Millions of people around the world suffer from heart failure. In order to choose the optimal treatment for them and reduce the risk of complications, implanted sensors are often used to collect information about the work of the heart. Of course, patients would prefer less invasive monitoring methods — for example, wearable devices. However, the effect of using such sensors remains unconfirmed.

A study by American scientists can change the situation. They confirmed that an easy-to-use wearable sensor controlled by an artificial intelligence system can indeed predict the risk of hospitalization and even prevent it.

This conclusion was made based on data collected in 2015-2016 in hospitals in Utah, California, Texas and Florida. Patients who had recently been discharged from the hospital after a heart attack were given smart sensors that had to be worn on the chest without removing them for at least 30 days.

The sensor continuously took EEG readings, which allowed it to set normal values for each patient. If you deviate from them, the device gave an alarm signal, which would allow you to intervene in time and prevent a repeat attack.

The researchers, however, did not interrupt the experiment after receiving such signals. As a result, they found that a wearable sensor with 80% accuracy predicts re-hospitalization ten days before it occurs. Unfortunately, the device could not predict the death of several patients.

The authors note that this experiment was primarily a proof of concept. In order to definitively confirm the use of wearable sensors, additional tests need to be carried out. They will involve patients of different ages, genders and nationalities, and not just white men over 60, as in the original study.

Article by Stehlik et al. Continuous Wearable Monitoring Analytics Predict Heart Failure Hospitalization published in the journal Circulation: Heart Failure – VM.

Portal "Eternal youth" http://vechnayamolodost.ru


Found a typo? Select it and press ctrl + enter Print version