A new algorithm developed at Stanford Medicine could help. Analyzing data from hundreds of thousands of anonymized medical records, the model predicts which patients are likely to die in the next 3 to 12 months. In early tests, the algorithm analyzed medical data of patients who had already passed away and correctly predicted their remaining life expectancy in 9 out of 10 cases.

The idea of using algorithms in end-of-life care understandably makes people uneasy, so it’s important to be clear: AI isn’t going to make decisions for patients or for doctors, and it’s not going to deny nor discourage care. If a patient wants to proceed with an aggressive treatment regimen, that choice will of course be honored. What AI can do is give patients information they have never had before that can help them realize their preferences as they near the end of their lives, whether that’s remaining mentally aware, being able to spend time with family, avoiding severe pain, or exhausting every possible avenue to defeat their disease.