Alphabet's moonshot subsidiary X zeros in on depression

The company is releasing its research on mapping biomarkers for depression.
By Laura Lovett
02:54 pm

Alphabet subsidiary  X, which was created to focus on “moon shot projects," has just unveiled research from its mental health project known as Amber, specifically with respect to its works to find biomarkers to map depression. The news, first spotted by CNBC, is an outline of the work the project has been doing. 

“Our journey started by asking the question: What if we could make brain waves as easy to measure and interpret as blood glucose, and use them as an objective measurement of depression?” Obi Felten, whose title is listed as “Head of getting moon shots ready for contact with the real world,” said in a blog post announcing the news. “Our approach was to marry cutting-edge machine learning techniques with a 96-year-old technology to measure electrical activity in the brain: electroencephalography (EEG).”

Researchers at Amber started out by creating a game-like task for people to complete while getting an EEG scanned. Through this technology researchers found a difference in the response to winning the game in those with depression compared to those without the condition, finding those with depression had a more subdued response. 

However, the end game for the project was to have an assessment that could be used outside of a research lab and, in practice, either at a clinic or counseling center. This changed the focuses of the project to making data easier to collect and interpret and looking at how that data could be used in the real world.

After trial and error, the team came up with what it describes as a swim cap-like headset that is easy to use, and can be used to capture resisting EEG and event-relevant potentials via a specific software. The team also worked with fellow Alphabet company DeepMind to look at how machine learning could help to interpret the EEG data. 

Amber is opening up their research to the public, and is open-sourcing its hardware and software designs, as well as the code. The blog post did note that the tech is not FDA cleared.

 “We didn’t succeed in our original goal of finding a single biomarker for depression and anxiety. It is unlikely that one exists, given the complexity of mental health. Yet there’s no question that there is a huge opportunity for technology to enable better measurement.”

The researchers concluded three big takeaways: “mental health measurements remain an unsolved problem,” “there is value in combing subjective and objective data” and “there are multiple use cases for new measurement technology.” 


Depression is a common condition in the United States. In fact, 4.7% of adults over 18 regularly have feelings of depression, according to the CDC. Worldwide, over 265 million people are living with the condition, according to the World Health Organization. Additionally, WHO reports that around 800,000 people die every year from suicide. 


Digital mental health companies are plentiful today. In fact, Mindstrong is a company looking to find digital biomarkers to help track a patient's depression or stress. Unlike X’s approach to biomarkers, Mindstrong monitors the ways a patient uses their phone, including how they scroll, tap and type. 

At the digital psychiatry division of Department of Psychiatry at Beth Israel Deaconess Medical Center, Dr. John Torous is leading a team researching how to use "digital biomarkers," or patient data, gathered from both active and passive means, together to improve care and patient-clinician conversations. 


The latest news in digital health delivered daily to your inbox.

Thank you for subscribing!
Error! Something went wrong!