Scientists at Stanford University have developed an artificial intelligence (AI) algorithm capable of predicting when patients will die with a goal of improving access to palliative care.

Trained using data from two million electronic health records, the AI system can predict patients who are most likely to die between three and 12 months. Researchers hope the algorithm would be used during a patient initial screening to identify those how could benefit from palliative care.

"The predictions from the model are only used to highlight some of the admitted patients for a chart review by (and automated referral to) the palliative care team," first author Anand Avati told CNBC. "The human doctor is always in the loop, and the decision of the program is only interpreted as a case worthy of palliative care consult—and not as a prediction of death.”

Read more here: