New technology can predict time of death

Experts are hoping that the algorithm could come in handy to treat terminally ill patients.

Update: 2018-01-23 06:38 GMT
The latest small cell solution will also support emerging 5G industrial applications such as connected factories, connected hospitals, and connected mining (Representative image: Pexels)

London: A new artificial intelligence can tell when you are going to die and it has come out to be accurate with a very high rate.

Experts are hoping that the algorithm could come in handy to treat terminally ill patients.

The programme has been developed by researchers at Stanford University.

Expected to be rolled across hospitals, the programme is estimated to give correct readings 90 percent of the time.

In order to get the most accurate readings, the researchers analysed records from 1,60,000 patients from Stanford and Lucile Packard Children's hospital.

These files were perused for information on past diagnoses, procedures and treatments offered.

After thorough analysis, an algorithm was put together by the scientists.

The artificial intelligence model was applied to 40,000 active patients. The algorithm then estimated the number of these people who would pass away over the next three to 12 months.

Shockingly, the results were correct in 90 percent of the cases.

Anand Avati from Stanford University's AI Lab revealed why the technology had proven to be so successful.

Daily star quoted IB Times where Anand said, "The scale of data available allowed us to build an all-cause mortality prediction model, instead of being disease or demographic specific".

The model is expected to be rolled out across many more hospitals.

Despite the clear indication about patients' deaths, the experts are not very keen on relying on them fully.

They insist that the data would be presented to the physician and he can make decisions about the procedures based on it.

Kenneth Jung, a scientist at Stanford University, explained, "We think that keeping a doctor in the loop and thinking of this as 'machine learning plus the doctor' is the way to go as opposed to blindly doing medical interventions based on algorithms... that puts us on firmer ground both ethically and safety-wise".

Similar News