New algorithm predicts the risk of death according to the results of ECG

The USA-based medical company Geisinger has created an algorithm that predicts a patient's risk of death based on an ECG better than doctors. The AI was even able to accurately calculate the probability of death in people who cardiologists thought were healthy. It is reported by Popular Mechanics.

Machine learning algorithms have proven themselves in the diagnosis of many diseases. Calculations of some of them may seem frightening at first glance, but they are still very useful. Among these is an AI that calculates a patient's risk of death based on an electrocardiogram.

To analyze the ECG results, the algorithm uses the same data as cardiologists but does it more carefully.

Testing showed that the program correctly predicts the risk of death over the next year in 85% of cases. For comparison, the accuracy of the prognosis of doctors is 60-80%.

What was unexpected was that the AI accurately identified at risk those people whose ECG was considered normal from the point of view of cardiologists. The developers do not yet know on what grounds the program made this decision.

As the authors note, such a neural network can help doctors better identify the most vulnerable patients with heart disease.

Nov. 13, 2019, 10:58 a.m.

Similar articles:

The symbiosis of EKG and Artificial Intelligence has taken diagnostics to the next level

Electrocardiogram (ECG) is one of the most known and affordable ...

AI predicts Alzheimer's disease by speech

IBM and Pfizer recently announced the results of their joint ...

Neuroimplant allowed a paralyzed person to communicate and shop

Australian scientists have successfully tested the new brain-computer interface. Neuroprosthesis ...

Eye Scanner determines the rate of aging at the molecular level

Scientists at Boston University School of Medicine have developed a ...

New Humm patch will improve working memory

American company Humm has released an electric stimulation device that ...

AI has been taught to detect sleep disorders leading to Alzheimer's

Full sleep is one of the most important thing for ...

FDA designates software for Parkinson's as Breakthrough Device

A software called neuroQWERTY, developed by nQ Medical in collaboration ...

AI helped the paralyzed animals start moving

Experts from the University of Lausanne (Switzerland) have created a ...


Our site collects information using cookies to be more convenient and customized to your needs interests. The purposes of the use of cookies are defined in Policy the processing of personal data .If you agree to continue to receive cookies, please click the "Accept" button. If you don't agree or want to resolve this issue later, please change your browser cookie settings.