New technology can tell you when you’re going to die – and it could be rolled out across hospitals.
The program, which has been developed by researchers at Stanford University, is estimated to give correct readings 90% of the time.
In the future, the artificial intelligence could be used in the care of terminally ill patients.
To get the most accurate reading possible, the technology analyses records from 160,000 patients from Stanford and Lucile Packard Children’s hospital.
Delving into these files offers information on past diagnoses, procedures and the treatment offered.
By looking at the outcomes of these medical cases, an algorithm was put together by the scientists.
The model was applied to 40,000 active patients who had recently been processed by the hospital.
It then estimated which of these people would pass away over the next three to 12 months.
Spookily, the tool was correct in 90% of cases.
Anand Avati, who works at Stanford University’s Al Lab, revealed why the technology had proven to be so successful.
He told IBTimes : “The scale of data available allowed us to build an all-cause mortality prediction model, instead of being disease or demographic specific.”
With further research, the scientists hope that the model will be rolled out across more hospitals.
While the technology gives a clear indication into the fate of patients, the experts aren’t planning on relying on them fully.
A doctor will be presented with the data and can then make their own decisions.
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.”