Skip to Main Content

You’re reading the web edition of STAT Health Tech, our guide to how tech is transforming the life sciences. Sign up to get this newsletter delivered in your inbox every Tuesday and Thursday. 

NeurIPS dips into health


At this year’s Conference on Neural Information Processing Systems, researchers shared advances and challenges in machine learning applications in medicine and public health. In a presentation on AI and social justice, Microsoft Research senior principal researcher Mary Gray used the oft-cited example of Optum’s racially-biased algorithm as a call to action to develop datasets and algorithms to reduce disparities in outcomes, medical and otherwise. That mindset will be critical as academics experiment with new applications of machine learning, like a model presented by MIT researchers that can flag treatments for sepsis patients that are likely to lead to a “medical dead-end,” the point after which a patient will die no matter what care is provided.

Unlock this article by subscribing to STAT+ and enjoy your first 30 days free!


Create a display name to comment

This name will appear with your comment

There was an error saving your display name. Please check and try again.