An AI system has demonstrated its ability to save lives by alerting doctors to patients whose heart test results suggest a high danger of passing away. The AI decreased overall fatalities among high-risk patients by 31% in a randomised clinical study including nearly 16,000 patients at two hospitals.
Not engaged in the research, Eric Topol of the Scripps Research Translational Institute in California said, “This is actually quite extraordinary.” “It is quite uncommon for any pharmaceutical to result in a 31% decrease in death, and even more uncommon for a non-drug — this is merely AI monitoring people.”
The AI developed by Chin Lin and his colleagues at the National Defense Medical Center in Taiwan was initially trained on over 450,000 electrocardiogram (ECG) tests, which record the electrical activity of the heart, as well as the survival statistics of the ECG subjects. With each patient’s risk of mortality represented by a percentile score, the AI learned to identify individuals who were at least in the 95th percentile as high risk.
The AI alarm system was then put to the test by the researchers on 39 doctors at two different hospitals. Every time a nurse uploaded a new patient’s ECG test results to a computer server, an AI system would analyze the data and promptly notify doctors if it determined that the patient was at high risk.
The AI system not only decreased the probability of mortality from all causes but also decreased the death rate from heart problems in high-risk individuals by almost 90%.
The AI predictions, according to Lin and his colleagues, might help concentrate attention on the highest-risk group, since doctors typically followed up on alerts with more diagnostic testing and more therapy.
In Taiwan, there are already 14 military hospitals that deploy the AI alert system.
According to Topol, “this can be implemented in every hospital in the world—it shouldn’t be expensive.” “When you see this level of magnitude of benefit, it should be the standard of care.”
