Digital mental health is in its infancy, and I’m excited to see what it can do when it grows up.

Thomas Insel MD has just written “What’s next for digital mental health companies?” in Stat News, a brilliant thought piece on the state of digital mental health. He cuts through some of the hype surrounding mental health startups fuelled by $5.1 billion in venture capital investment in 2021, while pointing to the infinitely larger potential of applying technology to improve a system that today fails most people with mental health problems.

It’s a testament of how limited mental health services are today that mental health startups are growing so fast by doing relatively simple things like moving clinicians from an office to a screen and helping them accept insurance. It is a great start, improving access to mental health professionals outside major cities and making the process of finding a clinician more efficient. Locating a therapist or psychiatrist who accepts insurance and has availability was nearly impossible before SondermindHeadwayAlmaSpring HealthLyra HealthModern Health and Cerebral came along. However, most of those startups target people who have private health insurance and/or generous employer benefits, leaving the majority of the US population just as underserved as it was by the old system. In 2020, only 6.6% of Americans had mental health outpatient services paid for by their employer, 39% by private health insurance, over 40% paid out of pocket (SAMHSA survey). Merely moving the same pool of clinicians online also doesn’t solve the fundamental problem that we have far fewer clinicians than we need: a shortage of 6,984 according to the latest HRSA numbers, which is probably an understatement.

I agree with Tom that the digital mental health industry – and digital health more broadly – is in its infancy. I worked in financial services and retail when they were being transformed by technology in the late 1990s and early 2000s. Healthcare is 20 years behind those industries. One key factor in retail and finance moving faster was that consumers have a lot more power and choice in those industries; they voted with their feet and moved towards better offerings quickly. My first startup job was at one of the ecommerce darlings of the time, eToys, which was backed by big VCs like today’s mental health startups. I didn’t understand until much later that we weren’t in the business of selling toys; we were in the business of providing a better customer experience through technology. Instead of hunting around mall toy stores for that hot out-of-stock-everywhere toy, grandparents could have it delivered straight to the kid’s home, gift-wrapped. During the holiday season the whole company worked in the warehouse to make this happen.

I also share Tom’s optimism that technology has the potential to truly transform mental health care. His point about measurement and accountability reminded me of my early ecommerce experience. I remember when web analytics companies invented page view and session metrics in the early 2000s. Before then we were measuring ‘server hits’ (a thoroughly useless metric) and had no idea what happened between a user coming to our website and placing an order – or more often leaving without placing an order. Along came sophisticated web analytics, and it was like a light switch being turned on. We could see what our users were doing on the website, which pages and features were a success and which needed improvements. As product managers started running A/B tests and using behavioural data to make product decisions, consumers were able to shape products in a way that had never happened before.

Like retail before web analytics, mental health is barely measured in clinical practice today, despite a proliferation of scales. Eiko Fried, a professor at the University of Leiden who studies mental health measurement, analysed the content of 7 leading depression scales and found 52 disparate depression symptoms (Fried 2017). The most commonly used measurement tools are questionnaires like PHQ-9 and GAD-7, which Pfizer generously made freely available to help doctors assess whether a patient needs medication 🤔. These surveys ask questions such as: “How many days in the past 2 weeks have you been feeling bad about yourself — or that you are a failure or have let yourself or your family down?” and “How many days have you had trouble falling or staying asleep, or sleeping too much?” Humans are not very good at self-assessing and tracking these data points over time; technology can help here. A new crop of mental health measurement companies like Ksana HealthHealthRhythms and Kintsugi are working on more accurate ways to measure mental health, using passive sensor data from smartphones, daily surveys called ecological momentary assessments (EMA) and voice diaries. My company Flourish Labs is developing håp, an app combining short EMA-style self-reflections that we call Check-ins with sleep data from wearables to help our members track their own mental health and wellbeing. Our app is still in beta and we’re evolving it with active input from students (our first user group), with the help of our partners Active Minds and Youth Era.

eToys went bust in 2001, as did many other ecommerce pioneers along the way. Today, ecommerce is nearly 25% of the world’s retail sales, and nearly 40% in early adopter countries like the UK. Amazon went on to a build huge business with a relentless focus on better customer experience and analytics. Some argue that the major tech companies are overdoing the analytics and user tracking these days, but there is no doubt that it has led to vastly better (and free) products and experiences for users. Mental health and wellbeing data is more sensitive than your shopping basket content and browsing habits, so as a young industry we have to be much more thoughtful on how we use data to benefit people who want to improve their mental health, with their permission.

It will be interesting to see who emerges as the Amazon of digital health. Amazon being one of the contenders of course… although I’ll place my bet on a startup that nobody has heard of yet today.

Introducing håp: a self-tracking app that fosters human connection

I posted this originally on the projecthap blog. I am reposting it here because it’s a big deal for me personally to have a beta version of our first product out. I love getting the first feedback on what we’ve built, it never gets old!

Three months ago I left my job in a big tech company to set up Flourish Labs, a purpose-driven startup using cutting edge mental health science and technology to foster good mental health. Our mission: Flourishing minds for all, starting with students.

Today we’re launching the beta version of håp, an app that helps you understand the ups and downs of your mind. håp is for everyone, whether you are flourishing or languishing right now. It’s using technology that you likely have with you at all times: a smartphone and a wearable device.  

håp empowers you with your data to help you gain more emotional self-awareness.

The håp app encourages you to regularly check in with your feelings, your mood and other factors such as your motivation, sleep, mental focus and social interactions.

Think of a håp ‘Check-in’ as a twice daily activity, just like brushing your teeth. It only takes about a minute (and you could probably do it while you are brushing your teeth if you’re pressed for time).

You can instantly view your data in easy to understand reports, charting how the factors that affect your mental health and wellbeing change over time. 

Unlike simple mood diary apps, håp can also integrate your sleep, activity and heart rate data if you have a wearable and choose to connect it to håp. This is optional; you can use håp with just a smartphone. We currently support Fitbit and Oura, and will add more wearables soon.

You control what you share with håp. håp empowers you with your data to help you gain more emotional self-awareness.

håp brings you human connection when it’s most important for you.

In addition to self-tracking, håp is being designed to foster support from others. During 18 months of lockdowns and physical distancing from friends, extended family and co-workers, we have all experienced how vital human connection is for good mental health.

In the beta version released today, håp gives you instant access to free, 24/7 crisis support. With the tap of a button or by texting HAP to 741741, you can text with a trained Crisis Text Line counselor.

You can also view mental health and wellbeing tips and resources from Active Minds.

If you are a student at one of our pilot colleges, the app will show you mental health and wellbeing resources that are available on your campus. 

Soon, håp will allow you to share some of your data with a small number of people of your choosing. These could be friends, family or others in the håp community who want to support you. Unlike anonymous peer support platforms, håp facilitates ongoing connections with people you know and trust. håp reduces the burden of reaching out to get or give help by notifying your supporters, and encouraging them to get in touch when it looks like you might need it. Or if you’re doing well at the moment, the håp support notification might just serve as a reminder that they haven’t caught up with you in a while and it’s time for a chat.

You control who you share with. håp brings you human connection when it’s most important for you.

håp is being built with students, for students.

College students are our first audience for håp. During our pilot, håp is available only via our partners or by referral. 

håp, like all of us, is a work in progress.  We’re releasing it as a beta app today because we want to get early feedback from students and colleges on what we’ve built so far, and get input on the parts we’re building next. 

If you are a student, you can get early access to håp and help håp get better by joining our Trusted Tester program. We have a limited number of slots, so please bear with us if we don’t get back to you straight away.

Each screen of the app has a ‘feedback’ icon on it. For each app release, we will share how we’ve addressed feedback from testers, so you get to see how you are helping to improve håp first hand. 

Bring håp to your college.

We are inviting a small number of colleges to actively take part in our pilot during the 2021/22 academic year. We are looking for innovators who want to offer the opportunity to their students and staff to test and help evolve the product. We’d especially love to work with community colleges and HBCUs.

If you are a student, you can bring håp to your college as a håp Ambassador.

If you are faculty or staff, please get in touch to explore how we could include your college in our pilot

Project håp is a collaboration between a tech startup, nonprofits and academics.

We have come together to work on håp because we share a vision of a future where more people flourish in a world of good mental health and wellbeing. 

Flourish Labs is a purpose-driven technology startup building the app and technology platform with a small but mighty team and the help of a multi-faceted advisory board. 

Active Minds is the leading nonprofit organization supporting mental health awareness and education for young adults. Led by founder Alison Malmon, they are our co-design and outreach partner.

Youth Era is a global leader in empowering young people and creating breakthroughs in the systems that serve them. Through peer support and technology, Youth Era equips young people with tools to help themselves and their peers. They are designing a bespoke training program for håp members who want to become supporters.

Crisis Text Line provides free, high quality crisis support through text messaging. Trained, compassionate Crisis Text Line crisis counselors are available 24/7 for any crisis, not just suicide.

Stanford professor Dr. Manpreet Singh will lead an independent research study on håp. Each part of håp is grounded in evidence, but our combination of self-tracking and peer support is novel. Dr Singh and her team will study the validity of håp as a measurement tool for mental health, wellbeing and flourishing, and assess its impact on them.

If you are an individual or foundation interested in supporting the work of our nonprofit partners or the research study with a grant, please get in touch.

Each partner in our multi-disciplinary team brings their energy, unique experience and insight to håp, and I’m excited and grateful every day to be working with them. We invite you to bring your own experience to håp by joining us on the journey as a Trusted Tester, håp Ambassador or pilot college.

You can learn more at We can’t wait to hear what you think of håp and your ideas on how to make it work for you.

My next mission: Flourishing minds for all.

Leaving X, starting Flourish Labs

Today is my last day at Alphabet, after 15 great years at Google and X. I’m setting up Flourish Labs, a startup combining cutting edge mental health science and technology to foster flourishing and good mental health. Our mission is flourishing minds for all. We want to build a future where nobody is held back by mental health problems, where everyone can be their best self and achieve their potential.

Poor mental health is a huge problem for our society that has been exacerbated by recent events. The pandemic and social injustice especially affected young people and people of colour. The number of people reporting depression or anxiety symptoms in the US is now 31% of adults, 33% of Black adults, 35% of Latinx adults and 49% of 18-29 year olds, according to the CDC’s mental health survey in May 2021.

Flourishing minds for all college students

Flourish Lab’s first mission is focused on college students: no student left behind by mental health problems. Sadly that is not the case today. 40% of US college students – around 8 million – suffer from mental health problems (Healthy Minds Study). Over 40 percent of students with a mental health diagnosis drop out of college (National Academies report, 2019). Suicide is the number 2 cause of death among students, with 28,000 attempts a year (Healthy Minds study, CDC, Taub & Thompson, 2013). 

Student mental health statistics (also in text)
Photo: Getty Images

With students returning to college campuses this fall and 70% of college presidents stating that mental health is one of their top concerns (ACE survey), now is the time to make a difference for millions of students. Studies demonstrate that improving student mental health can increase academic performance and graduation rates (Healthy Minds/ACE report, 2019). Investing in student mental health makes good economic sense too: 30 students who stay in college for 2 more years at $20k/year tuition yield $1.2M in tuition revenues that would otherwise be lost, and their lifetime earnings increase by $3m (Eisenberg et al, 2009).

We are launching a pilot in August for the 2021/22 academic year. If you are a college that wants to improve the mental health of your students and are interested in taking part in our pilot, please get in touch. We are prioritising community colleges and HBCUs (Historically Black Colleges & Universities) for the initial launch.

We are looking for donors to help fund our non-profit partners, including Active Minds whose founder Alison Malmon has joined our advisory board. If you are a foundation, family office or individual excited about seed-funding innovation projects at the intersection of mental health, education/college success and diversity/equity/inclusion, I’d love to talk with you. All donations will go directly to colleges in our pilot and to our non-profit partners.

To learn more about Flourish Labs and get in touch, please visit

Moving on from Google and X: Thank you and I love you

A few weeks ago I wrote about love being a competitive advantage. I’ve loved my time at Google and X because of the projects I worked on, but most of all because of the people I worked with. I’m grateful to my managers and mentors who propelled me, to my team members who taught me so much (especially the engineers who patiently explained complicated physics, chemistry and AI to me), to my peers who shared their journey with me.

I fell in love with Google at first sight in 1999, when an eToys engineer showed me a new search engine that actually worked. I fell in love again in 2005 when I sat in the lobby of the newly opened Google London office, watching bright-eyed Googlers bustling with a sense of urgency and purpose. They had lava lamps and colourful bouncy balls, just like eToys! I felt a sense of belonging instantly. My first interview was with Lorraine Twohill, a formidable Irish woman who ran the European marketing team at the time and is now the CMO of Google. After our conversation she said, “We’re going to hire you, you’ll be great at Google. Now you need to convince another 14 people that this is the case.” I thought she was joking, but that’s exactly what happened. 14 interviews later I found myself in her team as Google’s first consumer marketing lead in Europe.

I joined Google at a time of explosive growth. When I started, there were around 5000 Googlers globally and 150 in London. We hired people, launched new products and opened offices at breakneck speed. In the marketing team, I had brilliant mentors in Dan Cobley and Yonca Brunini Dervisoglu who fused creativity and data. I worked on inspiring projects: Teaming up with British Airways for a campaign featuring Google Earth. Rolling out Google Maps in dozens of countries across Europe, Middle East and Africa. Launching Android and Chrome, growing them to hundreds of millions of users. Learning how to make posters and TV ads to complement our online campaigns. Taking Streetview to the small German village of Oberstaufen. Turning the Google homepage into a canvas for children’s art with Doodle4Google. Creating April fool jokes that might someday become real products. As my 20% project, I founded Campus London, Google’s first space for entrepreneurs.

I loved marketing, and at the same time I missed building products and working with engineers. When Megan Smith, a mentor and great connector, introduced me to Astro Teller in 2012, I was curious. Astro worked at GoogleX which the New York Times had called “Google’s lab of wildest dreams”. He told me about self-driving cars and other, still secret projects: internet from balloons, delivery drones, a contact lens that measures glucose in your tears. I loved the audacity and potential for impact. I asked him practical questions: Is it legal to fly balloons over countries? Are you going to partner with mobile phone companies? Do you have a business plan for any of these projects? Astro raised his eyebrows and said, “Those are good questions, why don’t you come over and help us answer them.” 

Two months later my family and I moved to California for a new adventure. In my nine years at X, I kept my job title of “Head of getting moonshots ready for contact with the real world”, but I changed roles three times – a testament that people as well as projects can pivot at X.  

I started as one of the first non-engineers at X with an undefined role and broad remit to ‘de-risk everything that’s not tech’, including product, marketing, legal, policy, operations and business planning. I hired leaders for many of those functions, transforming X from a pure engineering team to the multidisciplinary team it is today. In my first year I mostly worked on Wing, a drone delivery service, and Loon, expanding internet access worldwide with balloons. When Loon took flight in New Zealand in the summer of 2013, I couldn’t travel to the launch site with the team because I was about to have a baby. I had a bet with the engineers about who would launch first. My daughter came 10 days early and Loon was 10 days late, so I won.

In my second chapter, I ran early stage projects. My team and I incubated projects like Mineral, Foghorn, Chronicle, Dandelion and Malta. Many didn’t pan out. I became an expert on how to deal with failure and how to kill good things to make room for great ones. I loved learning about everything from computational agriculture to carbon-neutral fuel chemistry, VR, cybersecurity and energy storage, but running a portfolio was not my highest and best use. I am more of a scuba diver than a snorkeler; I love going deep on one project rather than spreading myself thin over several.

In my third incarnation at X, I got the opportunity to go deep on a topic I was passionate about: mental health. I started Project Amber with a small multi-disciplinary team of neuroscientists, hardware and software engineers, machine learning researchers and med-tech experts. We explored how to use brain-based biomarkers and machine learning to better assess depression and anxiety. At the end of 2020, we open-sourced our EEG technology, published our ML methods and shared insights from our user research with clinicians and students. (See this blogpost for more detail and links to materials.)

My career has moved from strategy to product to marketing to leadership roles, from ecommerce to consumer tech to moonshots. Now I am bringing all these experiences to my next chapter, focusing on mental health. I can’t wait to see where this takes me. If I have learnt one thing in the past 25 years, I know that my path won’t be linear.

Empowering students and clinicians with mental health data

A user research report report on opportunities for tech-enabled innovation in student mental health from Shift and X.

Recently I wrote about Amber, the early stage mental health project I led at X. We developed prototype technologies to better measure mental health, including a low-cost, portable, research-grade system to make it easier to collect electroencephalography (EEG) data, and machine learning methods to make it easier to interpret these data. We wrapped up our work at X and made our technology and insights freely available to the mental health community. You can read more about Amber’s story and access our technical resources on the X blog.

Today we are sharing a report on the user research with students and clinicians that we conducted between 2018 and 2020 in partnership with Shift, a social innovation charity.

Project Amber asked the question: what if we could make brain waves as easy to measure and interpret as blood glucose, and use the results as an objective measurement of depression? From my undergraduate degree in psychology I was familiar with EEG, a 96-year-old technology to measure electrical activity in the brain. Today EEG is primarily used in neuroscience research labs and epilepsy clinics. Making EEG more accessible and usable at scale would open up a host of possibilities to deploy it in primary care, counselling and psychiatry. We had a promising technology, but we had to identify specific user needs to figure out how the technology could impact real-world problems.

We started with informal user interviews, with clinicians and people with lived experience of mental health problems. We spoke with primary care physicians, therapists, counsellors, clinical psychologists, psychiatrists, and social workers. We spent time with young people and their parents, mothers who experienced perinatal depression, and people who had struggled with depression all their life.

In one of my interviews with a physician working in a primary care practice at a London university, I first learned about the huge unmet need in student mental health.

Me:  “What percentage of your patient visits are about mental health?”

Dr M:  “Seventy percent.”

Me: “Did you say seventeen?”

Dr M: “No, seventy. Most of my patients are students between 18 and 24 years old. They don’t have many health issues other than sexually transmitted diseases and mental health. Around exam times when they get stressed, nearly 100% of my visits are about mental health.”

She told me about her challenges in triaging students in a 10-minute appointment: deciding who will likely get better by themselves, who can be treated within primary care, who to refer to a mental health specialist, or who needs a safety plan because they face immediate risk of harming themselves. 78% of students on her campus self-identified as having some mental health issues. The average waitlist for therapy was 3 months. Every year there were student suicides at her university.

Back at my desk I researched statistics and literature on student mental health, which concurred with Dr M’s experience. There is a crisis on both sides of the Atlantic. Ever greater numbers of students in the UK and US are presenting with mental health problems. Higher education institutions are struggling to keep up with the demand for support. These challenges are exacerbated by a backdrop of multiple societal crises, including the climate emergency, racial injustice, systemic inequity, and now a global pandemic. This means there is great need for change and even greater potential for innovation. 

After Kit Yee Au-Yeung joined my team as a product manager, we partnered with Shift, a London-based social innovation charity with experience of user-led design and deep knowledge of the youth mental health space. We commissioned Shift to conduct more formal user research into student mental health to learn more about the experiences of students and clinicians working in higher education settings. In a series of studies between 2018 and 2020, Shift tested how Amber’s proposition of introducing a new, more objective measure of depression and anxiety would resonate with clinicians and students with lived experience of mental health problems: how they might use it in their daily lives and professional practice, and what the challenges might be in introducing such a radical new approach.

We found student mental health to be a fertile ground for tech-enabled innovation for several reasons. There is growing unmet need for college mental health services. Students have been pushing for change in mental health and are often early adopters of technology. Universities have both a moral and financial incentive to improve their student mental health systems.

Shift’s report highlights the current challenges in college mental health, the role that better mental health data can play in empowering both students and clinicians, and the importance of putting people at the heart of tech innovation. We emerged with three clear recommendations for those working to improve student mental health:

  1. Support students to track their own subjective data
  2. Introduce objective data into therapeutic interactions
  3. Make data accessible and interpretable for students and clinicians

By sharing our insights as well as open-sourcing our technology, we hope to inform and enhance the work of other researchers and innovators striving to improve mental health services and outcomes for students. We also hope to encourage much-needed investment into further research, tools, and services to improve student mental health, accelerating systemic change towards a world where all students can get the mental health support they need.

Learn more about our user research and download the report on the Shift website.

Sharing Project Amber with the mental health community

New open source resources to help researchers collect and interpret electroencephalography (EEG) data for mental health measurement

Today at the Sapien Labs Symposium, my colleague Vlad Miskovic presented insights from Project Amber, an early stage mental health project at X. Amber’s small team of of neuroscientists, hardware and software engineers, machine learning researchers and med-tech product experts have been developing prototype technologies to help tackle the huge and growing problem of mental health. After three years of exploration, we recently wrapped up our work at X. Now we are making our technology and research findings freely available in the hope that the mental health community can build upon our work.

Poor mental health is a huge and growing problem globally. The World Health Organization estimated in 2017 that 322M people globally suffer from depression and 264M from anxiety. The COVID-19 pandemic is causing widespread psychological distress, affecting even more people.

One of the challenges is that it is truly difficult to assess mental health, both for people who are distressed and for health care providers who are not experts in mental health. With 1000 possible symptom combinations, depression manifests differently in different people. Today’s assessment of mental health mostly relies on asking people a series of questions in a conversation with a clinician or via surveys such as the PHQ-9 or GAD-7, which are subjective. While it is important to capture the subjective experience of a person living with mental health problems, the field is missing objective measures that are commonplace in other areas of health. For example, people with diabetes and their doctors routinely measure blood glucose and use these data to make adjustments to insulin, diet and exercise regimes — but there is no equivalent for depression or anxiety.

Amber’s moonshot: Finding a biomarker for depression

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? 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)

We were inspired by neuroscience studies showing that certain patterns of electrical activity in the brain correspond with depression symptoms. For example, many depressed people find that things that once brought them pleasure no longer do so; they don’t experience the reward that follows a positive experience. By designing specific game-like tasks that people complete while their brain activity is being measured using EEG, scientists can gauge processing within the brain’s reward system. It turns out that the brain response following a win in the game — an event related potential (ERP) — is subdued in people who are depressed, compared to those who are not.

Image for post
Difference in reward response among depressed and non-depressed people
(unpublished data from Amber feasibility study with Florida State University)

This blunted brain response is a reliable effect that has been shown in many studies, which we replicated in our own study carried out in partnership with Greg Hajcak and his team at Florida State University.

However, these studies were done in neuroscience research labs. They require expensive specialist equipment and highly trained EEG experts to collect, process and interpret the data. For EEG to come out of the lab and into the real world as a mental health assessment tool in a primary care doctor’s office, counseling centre or psychiatric clinic, it needs to become more accessible and usable at scale.

Our project at X focused on three areas:
1) Making EEG data easier to collect
2) Making EEG data easier to interpret
3) Understanding how this technology might be applied in the real world

The rest of this post lays out our work and insights in each of these areas.

Making EEG data easier to collect: The Amber EEG system

Our team set out to develop an easy-to-use, low-cost, portable, research-grade EEG system.

Image for post
Hardware engineer Gabriella Levine (left), neuroscientist Sarah Laszlo (right) testing early Amber prototypes

We built many prototypes of bioamplifiers, headsets and sensors, and tested them in feasibility studies at X and at Florida State University. 

Image for post
A selection of the Amber EEG prototypes

In our final prototype the headset slips on like a swim cap and can be put on by anyone with minimal training, taking around three minutes to set up. It uses three dry sensors arranged along the midline at Fz, Cz, Pz, the most important channels for ERP assessments of reward and cognitive function. The accompanying bioamp can support up to 32 channels, so it’s possible to connect a standard headset with some modifications. Amber’s system can be used to collect resting state EEG and event-related potentials with our software that time-locks a task to the EEG measurement.

Image for post
Amber’s final EEG prototype: Headset, sensor strip and bioamp

Making EEG data easier to interpretApplying machine learning techniques to EEG signal

Our team also explored how new approaches in machine learning can be applied to interpreting EEG data. To make EEG data usable by mental health researchers and clinicians more broadly — i.e. outside electrophysiology labs and neurology clinics — it would be helpful to have automated ways to denoise the signals at scale, and to determine which aspects of the EEG signal are relevant. Collaborating with the team at DeepMind, we adapted methods from unsupervised representation learning to address these challenges. We set out our findings in a paper that is currently under review.

First, we demonstrated that representation learning approaches such as autoencoders could be leveraged to effectively denoise EEG signals without a human EEG expert in the loop. This is important to enable processing EEG data at scale. Second, we offer a proof of concept that it’s possible to extract interpretable features that are relevant to mental health. We used these features obtained from disentangling autoencoders to predict several clinical labels such as major depressive disorder and generalized anxiety disorder, based on a clinical interview by a mental health expert. Unlike previous studies, we were able to do this for an individual participant (rather than a group), which is essential to make it useful in a clinical setting. The methods were capable of recovering usable signal representations from single EEG trials. This means that it may be possible to derive clinically useful information from brain electrophysiology with far fewer data samples than what is traditionally used in research labs, which often rely on hundreds of experimental trials.

Understanding how this technology might be applied in the real world: Insights from user research

Over the course of our project, we conducted over 250 interviews with potential users of this technology. We spoke to people with lived experience of mental health problems and with clinicians of all kinds, including counsellors, therapists, psychiatrists, clinical psychologists, social workers, primary care practitioners and pediatricians. We tested how Amber’s proposition of introducing a new, more objective measure of depression and anxiety resonated with them, how they might use it in their daily lives and professional practice, and what the challenges might be in introducing such a radical new approach.

Here are three key insights from our user research:

  1. Mental health measurement remains an unsolved problem. Despite the availability of many mental health surveys and scales, they are not widely used, especially in primary care and counseling settings. Reasons range from burden (“I don’t have time for this”) to skepticism (“Using a scale is no better than using my clinical judgement”) to lack of trust (“I don’t think my client is filling this in truthfully” and ”I don’t want to reveal this much to my counsellor”). These findings were in line with the literature on measurement-based mental health care. Any new measurement tool would have to overcome these barriers by creating clear value for both the person with lived experience and the clinician.
  2. There is value in combining subjective and objective data. People with lived experience and clinicians both welcomed the introduction of objective metrics, but not as a replacement for subjective assessment and asking people about their experience and feelings. The combination of subjective and objective metrics was seen as especially powerful. Objective metrics might validate the subjective experience; or if the two diverge, that in itself is an interesting insight which provides the starting point for a conversation.
  3. There are multiple use cases for new measurement technology. Our initial hypothesis was that clinicians might use a “brainwave test” as a diagnostic aid. However, this concept got a lukewarm reception. Mental health experts such as psychiatrists and clinical psychologists felt confident in their ability to diagnose via clinical interview. Primary care physicians thought an EEG test could be useful, but only if it was conducted by a medical assistant before their consultation with the patient, similar to a blood pressure test. Counsellors and social workers don’t do diagnosis in their practice, so it was irrelevant to them. Some people with lived experience did not like the idea of being labelled as depressed by a machine. By contrast, there was a notably strong interest in using technology as a tool for ongoing monitoring — capturing changes in mental health state over time — to learn what happens between visits. Many clinicians asked if they could send the EEG system home so their patients and clients could repeat the test on their own. They were also very interested in EEG’s potential predictive qualities, e.g. predicting who is likely to get more depressed in future. More research is needed to determine how a tool such as EEG would be best deployed in clinical and counseling settings, including how it could be combined with other measurement technologies such as digital phenotyping.

Much of our research was conducted in the US and the UK in partnership with Shift, a nonprofit based in London. This report by Shift details the research and the findings. (Report added on 15 December 2020.)

Opening up Amber to the world

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.

This will empower individuals and their healthcare provider to better match intervention options to an individual’s needs, to measure the impact of those interventions, and ultimately promote better mental health. While the promise of emerging measurement techniques like EEG/ERP and digital phenotyping is very exciting, it is still early days. There are many pitfalls on the path to making tech-enabled mental health measurement work in the real world, and more research needs to be done.

For this reason we’ve decided to make Amber’s technology and insights available to the global mental health community. We believe we can make a bigger and faster impact on this huge problem by sharing our work freely.

Today, we are open-sourcing our hardware designs, visualizer and stimulus software of the Amber prototype EEG system and putting the code on Github. We are also pledging the free use of our patents and applications listed in this patent pledge. We are making these resources available so that mental health researchers have all of the specifications, code, and permissions they would need to rebuild our EEG system, or design their own based on it. In addition we are donating 50 assembled Amber prototype devices to Sapien Labs for use by researchers worldwide as part of their Human Brain Diversity Project which supports EEG research globally, with an emphasis on low-income countries and underrepresented groups.

We hope that open-sourcing our EEG system and publishing our machine learning techniques will be of value not just to EEG experts, but also to the wider mental health research community who were perhaps put off by the complexity and cost of working with EEG before. Addressing today’s challenges will require new partnerships between scientists, clinicians, technologists, policymakers, and individuals with lived experience. Now more than ever, more diverse voices, more multi-disciplinary collaboration, and more open sharing of knowledge are needed to unlock better mental health for everyone.

To learn more about Amber’s technology and user research, please visit the following links:

Please note: The Amber EEG System is a prototype investigational device and has not been evaluated by the US Food and Drug Administration or any other regulatory agency for any purpose, including a medical purpose.

This blog was first published on 2 November 2002 and updated on 15 December 2020 with links to the Shift user research report.

Harvard McLean TIPS: Tech-enabled mental health measurement

Technology in Psychiatry Summit
28 October 2020
Talk / panel
“Towards Measurement-Based, Person-Centric Mental Health Care: How Technology Can Help”

Obi presented as part of a panel on “Global Access to Mental Healthcare Through Digital Technology.” These remarks were part of the 2020 Technology in Psychiatry Summit, an event organised by the McLean Institute for Technology in Psychiatry, which took place virtually on October 28-30, 2020.

Please visit to learn more about the McLean Institute for Technology in Psychiatry at McLean, a Harvard Medical School affiliate.

Asking for help and saying “Yes”​ in the age of the COVID-19 pandemic

This post first was first published on LinkedIn on 14 July 2020.

What I learnt working on Heroes Health, a new initiative to support the mental health of COVID-19 frontline health care workers and first responders

Back in March, I got a call from Dr. Sam McLean, a trauma researcher and emergency physician at the University of North Carolina. At the time, I was struggling to settle into the new reality of my life in the pandemic. Working from home in a never-ending stream of video calls, I was missing my team and spontaneous chats with co-workers in the kitchen. I felt isolated from my friends and family, not having the energy for yet another video call after work. My husband and I were figuring out new parenting skills: how to homeschool our children, how to deal with ever-expanding screen time when they asked for Minecraft and Netflix after doing their online school work. Yet our family’s struggles felt tiny compared to what others were facing. As I read the devastating news of COVID-19 infections, deaths and job losses mounting up in Europe and elsewhere, I felt helpless and uncertain of where to make a difference in this new world beyond taking care of my family and my team. Sam gave me that opportunity on that grey March morning. 

Sam told me about his work on the COVID-19 frontlines in the hospital. As a trauma researcher, he saw the havoc that the virus was wreaking not just on the lives of his patients but also on his coworkers. Already on the edge of burnout, healthcare workers were confronted with a novel virus without treatment or vaccine, lack of PPE and ventilators, watching their patients suffer and die through glass screens, worrying about infecting their own families. After our call, I read up on the literature. Sam’s personal experience was backed up by many papers discussing the toll on healthcare workers during previous infectious disease outbreaks (Brooks et al., J Occup Environ Med 2018). New papers were already coming out describing increased depression and anxiety among healthcare workers who dealt with COVID-19 in China (Lai J, Ma S, Wang Y, et al. JAMA Netw Open 2020). So what could be done about it?

Sam’s idea was to measure the mental health of COVID-19 frontline workers with a mobile app, and connect them with mental health resources. He wanted to help workers understand and track their own mental health state during this time of extreme pressure, and encourage them to get help – many healthcare workers don’t seek mental health treatment. He called it the “Heroes Health” initiative to draw attention to the health needs of the heroes who are doing so much for others every day. He needed a technology partner and reached out to me for help.

I said “Yes” immediately, and asked others in our company for help. The first to say “Yes” was Jamie Rogers, a product manager on the Google Cloud team. By the end of the day, Sam had engineers from my team at X and Google Cloud working on his app. Two weeks later we had volunteers from across the company donating their time, many working evenings and weekends. The project had become a cross-functional effort of Alphabet engineers, scientists, product and program managers, partnerships, marketing, PR and sales folks supporting Sam’s team of researchers and clinicians at UNC. The Google Cloud team provided free hosting to UNC as part of the Google Cloud Research Credit program. Our design agency O/M Studio made the Heroes Health logo for free. The team at Boston Technology Corp in India worked alongside the Google engineers, turning around bug fixes while our US-based volunteers slept.

While the tech team worked on the app, Sam enlisted the help of other mental health experts such as Ron Kessler at Harvard and Samantha Meltzer-Brody at UNC to design the mental health surveys and support services we wanted to link from the app. We interviewed frontline workers and hospital administrators to understand how to make Heroes Health useful to them, aware that they were already busy and overstretched. Nearly every hospital we spoke to said “Yes” and wanted to take part in the initiative, but they needed our help. We realised that Sam’s team at UNC needed to provide central analytics and program management to support institutions and connect Heroes Health participants to mental health services. We also learnt that with hospital budgets under pressure due to COVID-19, there was no way we could ask participating organisations to fund the initiative.

Sam and I reached out to philanthropists to ask for their help to get Heroes Health off the ground.Garen and Brandon Staglin at OneMind and Zia Khan at The Rockefeller Foundation were the first funders to say “Yes”. Bank of America, The Lauder Foundation and individual donors followed. Those who could not give money generously introduced us to their friends. Within 6 weeks, we had raised $500k we needed as seed funding. We are continuing conversations with funders to cover the project’s expanding needs.

In the middle of all this, Sam stopped responding to my emails. I was worried but kept working on the app and fundraising, hoping he was ok and would reappear eventually. After a long week of silence, I got an email confirming what I had feared: he had contracted the virus and given it to his wife, his son and possibly his dog. I was relieved to hear they were all fine and recovering well. Now a COVID-19 survivor himself, Sam re-emerged with even more energy to make the Heroes Health initiative a success. With the philanthropy funding, he built a diverse team of program managers, data scientists and tech people at UNC to support the project.

Image: UNC Heroes Health team

Image: UNC Heroes Health team

Meanwhile, the world started taking note of COVID-19’s impact on mental health. The pandemic turned a simmering mental health crisis into an acute one, as the UN noted in a policy report on COVID-19 and Mental Health. Millions of people are affected physically by the virus, and many more are affected psychologically. 36% of Americans reported anxiety or depression symptoms in July in a NCHS/Census survey. Calls to mental health helplines are up 891%. I have been compiling papers and articles on COVID-19 and mental health in a shared Google Doc which is getting longer and longer. The papers and articles about and by healthcare workers paint a picture of an increasingly desperate situation: “I can’t turn my brain off“, “I’m a Health Care Worker. You Need to Know How Close We Are to Breaking“, “We think of our physicians as invulnerable, but we’re putting them in untenable situations“, “Behind the stiff upper lip, we’re highly vulnerable“, “Health care workers aren’t just ‘heroes’. We’re also scared and exposed“, “I Couldn’t Do Anything.”

Sam saw this future coming early in the pandemic, and he motivated us all to something about it. The Heroes Health Initiative is now being piloted at Sam’s home hospital, UNC Health in Chapel Hill, just four months after our first call.

Today we are announcing the rollout of the Heroes Health initiative across the US. Healthcare workers and first responders can now download the Heroes Health app from the Google Play Store and Apple Store free of charge, regardless of whether their institution is taking part in the initiative. For individuals, the app displays symptom summary reports to help them better understand the state of their own mental health and changes over time. The app also provides links to immediate support and mental health resources, emphasising free and low-cost services. 

I am grateful to Sam McLean and his team for giving me the opportunity to contribute to such an amazing project, to our funders, and to the Google and X volunteers who said “Yes” and brought this project to life: Anne-Carlijn Reijrink, Chris Tirrell, Cynthia Horiguchi, Jamie Rogers, Jesus Trujillo Gomez, Katie Link, Kar Epker, Kit Yee Au-Yeung, Nicole DeSantis, Ola Spyra, Pramod Gupta, Qiumin Xu, Stephanie Wilson, Vlad Miskovic, William Mills, Yvonne Yip, Yu-Chi Kuo, Zohreh Jabbari and so many others. We have handed over the app to the UNC team who will manage it going forward. Our immediate work is done, but we are all excited to stay in touch with the project and can’t wait to see its impact.

As for me, Sam and I are already thinking about how we can roll out Heroes Health internationally.

We need your help!

  1. Help spread the word about the Heroes Health InitiativePost about it on your social media. If you know any first responders and healthcare workers in the US, encourage them to join. If you know administrators or executives at first responder and healthcare organisations, tell them about it.
  2. Help us fundraise: We need further funds to bring Heroes Health to more organisations in the US and beyond. You can donate on the Heroes Health fundraising page. If you know a foundation who might be interested to fund the Heroes Health Initiative, please message me on LinkedIn – we would love an introduction.

Visit UNC’s website to learn more.

#heroeshealth #mentalhealth #SupportHealthcareHeroes #ThanksHealthHero #Breakthestigma