A British startup Thymia uses video games to fight depression

Holds space while article actions load

A few years ago, Emilia Molimpakis had a destabilizing experience when a friend who regularly saw a psychiatrist attempted suicide.

“What I could not understand was that she had seen her psychiatrist just two days before,” recalled Molimpakis, who found her friend. “Why did he not see this coming?”

Instead of driving towards the health care system, Molimpakis took a different path. As a postdoctoral fellow neuroscience researcher at University College London, she decided to leave academia and start a business. Her goal was to use entrepreneurship and artificial intelligence to fill gaps in mental health care. She reasoned that since a limited number of physicians did not have the time or perhaps even the raw processing power to address a growing depression epidemic, technology might step in.

And in the most unusual twist, she decided to use video games for the task.

The result is Thymia, a simple set of mobile video games that Molimpakis and her co-founder say can use artificial intelligence to pick up signals of depression as well as any office study. When it begins clinical trials later in the spring, thymia will try to improve and even save lives as it warns doctors of warning signs they might otherwise miss.

According to the founders, the tool – which comes as part of a larger movement to implement AI to address mental health – could revolutionize how society cares about depression. The start-up joins a host of related start-ups using digital tools to expand access to mental health care, including the wearables company Fitbit, which recently applied for a patent for a new mental health detection system, and TalkSpace, which primarily uses a data-driven approach to match consumers with therapists.

However, some experts asked about Thymia are concerned that machines are an inadequate and potentially risky substitute for a profession that requires high levels of human interpretation, reflecting broader concerns among physicians that “app-infection” of mental health could sacrifice quality for guilt. of cost and easy access.

Psychiatric evaluations constitute an innate paradox: the only way to really know how someone is feeling is to ask the person directly, but they can also be the person who is least likely to have a clear view of the subject.

Traditional psychiatry has tried to crack this by combining a subjective first-hand report with seemingly objective questions. The long-standing standard for depression diagnosis is “PHQ-9”, a set of nine questions about how a patient is feeling. Do they have “some interest or pleasure in doing things?” “Poor appetite or overeating?” The patient ranks himself on a scale from “not at all” to “almost every day.” If five of the nine responses are positive, they are clinically diagnosed with depression.

The creators of Thymia say there is a better way.

“There’s a rich amount of math tools that we have not used,” said Stefano Goria, who co-founded the company with Molimpakis and serves as its chief technology officer. “What we can do is extract information that we may not understand naturally so we can put objective numbers on it and make a more informed decision. We can get a lot more information.”

There is an urgent need for new approaches: Americans’ mental health has deteriorated over the past many years as technology that seeks to help people with communication has increased their atomization. The isolation caused by the pandemic has only exacerbated the problem. The Boston University School of Public Health recently found that the rate of depression among Americans – at 8.5 percent before the pandemic – is now nearly quadrupling, at 32.8 percent.

Video games are an unlikely solution. While many gamblers have no noticeable positive or negative psychological effects from gambling, a landmark study from Brigham Young University revealed that “a significant minority” of gamblers “can become truly addicted to video games and, as a result, suffer mentally, socially and behaviorally. “

How friendships thrived in video games during the pandemic

Thymia leaders, however, say that the game works well because it creates a natural framework for a topic to separate data; a person who is immersed in a video game is less likely to even think they are taking a test. (In this respect, thymia is a distant cousin of EndeavorRX, the prescription video game used to treat attention deficit / hyperactivity disorder in children.) Such a tool will also have no problem attracting users – 68 percent of American adults now play video games, according to the industry group Entertainment Software Association, an increase of 6 percent during the pandemic.

The Thymia games, which can be downloaded for free from their website, are minimalist. They involve simple tasks in whimsical natural surroundings; in one, a player tries to track bees buzzing around sets of flowers. But the machine gathers critical information.

When a player swipes in the game or moves their eyes or changes their expression or speech, the AI ​​records the data. It measures for markers such as agitation, anxiety, attention and working memory. (Agitation can seem like a difficult measure to measure in the stressful setting of a video game, but can be done, says Molimpakis, via jumps or dives in areas such as psychomotor speed.)

The algorithm processes this data and compares it with both baselines for a given user and the expected responses for a user’s demographic. If it e.g. experience that working memory has deteriorated over time, or eye movements are too rapid for a person’s age group, this is taken into account. It calculates everything it tracks and produces a score for each symptom that it sends to a clinician – at. currently only a patient’s mental health specialist, not a primary care physician. (Patients select the data to be shared via a pop-up opt-out each time the recording will be used; they can allow voice but not eye-tracking, for example, or vice versa.)

The doctor then makes treatment decisions – even in emergencies, he sends people to the hospital. Data is not shared with the patient.

When they do things this way, Thymia executives say there are alarms that would have been quiet in a traditional office visit structure.

“It’s getting harder and harder to get in to see a psychiatrist because it’s so expensive,” Molimpakis said. (In the U.S., the average psychiatrist earns $ 105 an hour, according to the Bureau of Labor Statistics, though that number is usually much higher for private consultations.) “Even then, you can only go in to see them once every four weeks or six weeks. And who knows what’s really going on with you at that time? ” she said.

A new MTV program is trying to make programming more mentally sound

However, some physicians familiar with depression and technology ask if the service will really provide all the information a clinician needs.

“There is no doubt that AI and technology in general hold promises for mental health and truly are the future of it,” said Murali Doraiswamy, professor of psychiatry and professor of medicine at Duke University School of Medicine.

“But psychiatric disorders like depression are very personal,” he said. “The symptoms are extremely varied.… I’m not sure I’ve seen the evidence that a computer can be programmed to understand all this that a person can.”

Advocates for mental health also generally worry that cheaper app-based approaches to mental health may deter insurers from paying for human doctors. Thymia founders say this is one of the reasons why patients are not allowed to use the service themselves and instead have to go through their clinics. Molimpakis says Thymia does not share data with third parties, including insurance companies.

Thymia has 12 employees, but aims for 17 this summer; it has raised $ 2.6 million in early funding, Molimpakis says, and will complete a seed round later this spring. About 2,000 people have used the product in preclinical trials, and all major clinical trials are expected to begin at a number of UK medical institutions in the coming months.

Managers have already started working with UK regulators to get Thymia games approved before the end of the summer, hoping to classify them as a medical device that will allow formal use in doctors’ offices. Europe and the United States, Molimpakis said, should follow soon after.

Backers say they see a big social upside.

“As investors, we asked ‘is there a massive problem that needs to be solved and is this the right team to take it on?’ Said Patrick Newton, principal at London’s venture capital firm Form Ventures, which has invested an undisclosed amount in Thymia. “We said yes to both. The idea of ​​giving a clinician the opportunity to remotely and regularly check in and understand how a person’s condition is doing could be huge. “

But some say they worry about the pitfalls of the transition from a first-person to a third-person – or third-machine – approach to diagnosis.

“Objective markers can provide better scores than self-reported scores in many cases, there is no doubt about it,” said Liam Kaufman, co-founder of Winterlight Labs, a Canadian start-up that uses AI to detect voice changes and support. in Alzheimer’s diagnosis. “The problem is, there are a lot of ways you do not know it’s really objective. For example, when you play games over and over again, you get better at them. So do you measure symptoms or do you measure gameplay?

“We can not even treat many cancers right now,” he said. “And the brain is without a doubt much more complicated.”

It is unclear whether Thymia executives ultimately intend the technology to become a diagnostic tool all on its own. While Molimpakis and Goria make an effort to emphasize that it is meant as a supplement – “all we do is extract all this information that would come naturally to a clinician and give it back to them,” Goria said – the founder history involving Molimpakis’ friend suggests that the company is based on the idea that the technician can sometimes just do the job better.

Thymia leaders predict a future time when results can be shared with primary care physicians and possibly even patients. Such decentralization makes doctors like Doraiswamy on guard. The panic of google a physical condition is bad enough, they say; Mental health information for patients could be so much more dangerous.

“If you were trying to treat someone with a phobia, would you really have an app that could see 40 different people get started at any time of the day?” he asked.

The battle over thymia and related technology is part of a larger conflict between an industry that says it resists technology, not of rigidity, but human skill, and a group of disruptors who believe that in some cases the machines can simply be more effective.

“Many psychiatrists have the strong feeling that they should rely on their own instincts,” Molimpakis said. “I understand that. But I think objective measurements can be very important. We should fight to make them better.”

Leave a Comment

Your email address will not be published.