Mental illness is insidious.
A broken bone or a runny nose are visible signs you need to make a trip to the doctor and physical illness an accepted excuse to take time off work and invest in taking care of yourself.
Symptoms of mental illness, on the other hand, often go unnoticed and unchecked. It can sometimes be difficult to admit to yourself that there’s even a problem at all.
Data collection combined with the learning capabilities of artificial intelligence are emerging as tools to proactively address mental health problems as symptoms first emerge.
If successful, a data-driven prevention model could be applied to many different types of social impact initiatives, in the health care sector and beyond.
Dis-Moi—first developed under the name Youhou! during the Coopérathon Desjardins social entrepreneurship program in 2017—is a multi-platform interactive solution to survey the mental well-being of high school students.
Inspired by the awareness efforts of Quebec Dragon’s Den entrepreneur Alexandre Taillefer following the suicide of his teenage son, Dis-Moi underwent a pilot program in two high schools in fall 2018 with plans for expansion in the future.
The platform seeks first to understand the mental wellness of students by asking a series of questions when they log onto the school wifi—questions ranging from: “How’s the cafeteria food?” to “Do you feel overwhelmed by school?” or “Are you feeling stressed?”
Depending on the answers, the platform then offers a toolbox that includes a chatbot and offers pathways to resources at their disposal.
Accuracy improves over time as the data set grows and is analyzed for common patterns and deviations.
By following teenagers’ progress throughout their high school journeys, Dis-Moi aims to better predict—and diffuse—potential crisis situations before they get to that level.
Social impact leaders, and entrepreneurs in general, are another group at risk of mental health problems.
That’s a problem that passive mobile app mind.me is trying to address: helping those with depression diagnose, manage, and predict it.
Once downloaded on your phone, mind.me monitors data feeds to determine your individual phone usage baseline—such as screen time, movement between GPS zones, and number of contacts interacted with.
Machine learning algorithms analyze all the data for patterns and deviations, and can predict when you may be entering a depressive state. It can also alert members of your “circle of trust,” prompting them to reach out and ask if you’re okay.
Both models are using data collection and analysis to stay a step ahead, to notice early warning signs, and predict instead of just react.
Through early education and facilitation of communication—either with a circle of trust or an anonymous chat bot—AI-powered mental health programs make a case for the proactive power of data collection and its intelligent analysis for patterns of deviation.
No matter what sector or what problem you are trying to address, it comes down to implementing a model that takes away some of the burden and expense, so the thought leaders of tomorrow can do what they do best.