How to Predict Mental Illnesses: The Digital Future of Mental Healthcare
A golden opportunity hidden in the mental health crisis
The mental health crisis is one of the greatest challenges of our times: 11% of the global population suffers from a mental health condition, an unprecedented level in human history.1
Declining mental health can be incredibly destructive, both personally and collectively. For the individual, mental health decline can result in serious emotional and physical issues that rob our enjoyment of life.
For broader society, declining mental health is proving highly expensive. Currently, the mental health crisis is costing the global economy an annual $2.5 trillion USD in lost productivity - and it’s estimated to grow to $6 trillion USD by 2027.1
A $397.4 billion USD mental health industry has blossomed in response,2 supplying a range of apps and counseling services to help those struggling with mental illness. But despite the market providing ample solutions, the mental health crisis continues to grow.1
What’s wrong with the current state of mental healthcare?
Before patients receive mental healthcare, they often must overcome several barriers. They can be tangible, such as a lack of financial resources or limited professionals in the area, or intangible, such as stigma or implicit racial bias.3
We tend to avoid engaging in the mental effort to challenge our status quo - even if our status quo has a negative effect on our wellbeing. We often rationalize our declining mental health, reasoning “it’s not that bad” or “everybody gets stressed”.
Due to our aversion to change, people tend to only seek out help once mental illness has become so overwhelmingly painful that the status quo is more painful than taking action. The increased severity of the problem before seeking help makes it more difficult for practitioners to address mental health issues.
Understanding mental health from this perspective, we can say that mental health treatment is fundamentally reactive: we tend to wait for mental health to decline to a dangerous state before we get help. Just as we don’t wait for a heart attack before we take care of our bodies, we shouldn’t wait for serious mental illnesses to take care of our minds.
From Reactive to Proactive: Enter predictive analytics and behavioral science
With the rise of smartphones and smartwatches, we’ve seen the increased power and ability of health-tracking apps. These apps take countless health data points (physical activity, resting heart rate, blood pressure, etc.) and organize them into an informative picture of overall health.
These apps empower users to fully understand the oscillating trends in their physical well-being. When there is a downturn in one category, users - or increasingly, their healthcare practitioners - can implement techniques to address their health problems, preventing more serious illness.
While these apps already track physical health indicators that can help us improve mental health (i.e. sleep, exercise), there is an emerging field of data science that suggests that deeper indicators of mental health could soon be available to us.
According to this research, just like how our physical data goes into the health app, our online language and behavior could be highly predictive of our broader mental state.4
Uncovering the digital indicators
Absolute(ly) dangerous language:
Studies have shown that the use of absolutist language (never, always, completely, nothing), negative emotion words, and first-person pronouns often appear in the online language of those with eating disorders, anxiety, and affective disorders.5 While this is largely correlation, there is still plenty of data that suggests that language could be predictive as well.
AI can detect hidden language indicators:
Advanced natural language processing and machine learning have been showed to predict depression severity and administer optimal treatments when given small pieces of narrative text.6
Given writing samples, natural language processing has been able to assess suicide risk in pediatric populations and identify linguistic features characteristic of early stage dementia.6 In one case, researchers had a 71% accuracy at predicting postpartum depression by analyzing birth-related phrases and pre-birth language on the new mothers’ Twitter accounts.6
While there is no substitute for consistent, in-person counseling, these computerized language analyses have been shown to be highly effective at uncovering a range of latent psychological conditions through conversational chatbots, artificial intelligence, and natural language processing.
How to prevent mental illness: Cognitive behavioral therapy and nudges
If we can detect upticks in negative and absolutist language, we’re then able to administer personalized nudges that can transform these self-defeating, negative thought patterns into positive and healthy ones. A standout technique for this is cognitive behavioral therapy, which focuses on identifying, challenging, and replacing negative thought patterns.
Scenario: Predictive analytics in your pocket
For example, if your phone detects that you have been using more negative or absolutist language on social media, your phone sends a push notification that provides you with self talk strategies, daily habits, or words of encouragement that help you correct that behavior before it begins to spiral out of control.
If the data is suggesting your situation could be serious, the app could administer nudges that increase the salience of available options for help. If you allow it, it could also contact your medical provider or family member if needed, just like physical health applications.
Paired with effective nudges towards healthy behaviors, applying data-driven cognitive behavioral therapy could break the pattern of reactive mental healthcare, as we can tackle the negative thoughts as soon as we see a downturn in language data.
How we’re building future of mental healthcare
While research on predictive mental health analytics is still emerging, practitioners have already begun to apply techniques from it successfully to alleviate a bevy of mental health issues. Here at The Decision Lab we collaborated to develop Hikai, an AI-powered mental health platform. Using a conversational chatbot, Hikai leveraged cognitive behavioral therapy to improve workplace mental health. Within a pilot group, 71% felt more engaged by their work, while 82% found that it helped reduce their stress levels significantly. You can find out more in our case study here.
The Decision Lab is a behavioral consultancy that uses science to advance social good. The mental health crisis is one of the world’s greatest challenges, and combining smart data with behavioral science could be a big step in the right direction. We have long worked with leading mental health organizations to develop innovative, empathic, and scalable mental health solutions. If you’d be interested in tackling the mental health crisis together, contact us.
References
- Auxier, B., Wescott, K., & Bucaille, A. (2021, December 1). Mental health goes mobile: The Mental Health App Market Will Keep on Growing. Deloitte Insights. Retrieved May 24, 2022, from https://www2.deloitte.com/content/dam/Deloitte/pt/Documents/technology-media-telecommunications/TMTPredictions/tmt-predictions-2022/Healthcare_estudo_completo_Mental-health.pdf
- MarketWatch. (2022, March 16). Mental health market growth statistics 2022, industry trends, size, share, business strategies, top-countries data, players analysis, demand status and forecast 2030. MarketWatch. Retrieved May 24, 2022, from https://www.marketwatch.com/press-release/mental-health-market-growth-statistics-2022-industry-trends-size-share-business-strategies-top-countries-data-players-analysis-demand-status-and-forecast-2030-2022-03-16
- Social Solutions. (2022, May 4). Top 5 barriers to Mental Healthcare Access. Social Solutions. Retrieved May 24, 2022, from https://www.socialsolutions.com/blog/barriers-to-mental-healthcare-access/
- Hahn, T., Nierenberg, A. A., & Whitfield-Gabrieli, S. (2016). Predictive analytics in mental health: Applications, guidelines, challenges and perspectives. Molecular Psychiatry, 22(1), 37–43. https://doi.org/10.1038/mp.2016.201
- Al-Mosaiwi, M., & Johnstone, T. (2019). In an absolute state: Elevated use of absolutist words is a marker specific to anxiety, depression, and suicidal ideation. Clinical Psychological Science, 7(3), 636–637. https://doi.org/10.1177/2167702619843297
- Conway, M., & O’Connor, D. (2016). Social Media, Big Data, and Mental Health: Current advances and ethical implications. Current Opinion in Psychology, 9, 77–82. https://doi.org/10.1016/j.copsyc.2016.01.004
About the Authors
Triumph Kerins
Triumph is passionate about understanding how human behavior influences our world. Whether it be global macroeconomics or neural networks, he is fascinated by how complex systems work, as well as how our own behavior can help create, sustain, and break these systems. He is currently pursuing a Bachelor’s degree in Economics and Psychology at McGill University, attempting to design an interdisciplinary approach to better understand all the quirks that make us human. He has experience in non-profit consulting, journalism, and research. Outside of work, you can find Triumph playing bass guitar, gardening, or down at a local basketball court.
Dr. Sekoul Krastev
Sekoul is a Co-Founder and Managing Director at The Decision Lab. He is a bestselling author of Intention - a book he wrote with Wiley on the mindful application of behavioral science in organizations. A decision scientist with a PhD in Decision Neuroscience from McGill University, Sekoul's work has been featured in peer-reviewed journals and has been presented at conferences around the world. Sekoul previously advised management on innovation and engagement strategy at The Boston Consulting Group as well as on online media strategy at Google. He has a deep interest in the applications of behavioral science to new technology and has published on these topics in places such as the Huffington Post and Strategy & Business.
Sarah Chudleigh
Sarah Chudleigh is passionate about the accessible distribution of academic research. She has had the opportunity to practice this as an organizer of TEDx conferences, editor-in-chief of her undergraduate academic journal, and lead editor at the LSE Social Policy Blog. Sarah gained a deep appreciation for interdisciplinary research during her liberal arts degree at Quest University Canada, where she specialized in political decision-making. Her current graduate research at the London School of Economics and Political Science examines the impact of national values on motivations to privately sponsor refugees, a continuation of her interest in political analysis, identity, and migration policy. On weekends, you can find Sarah gardening at her local urban farm.
About us
We are the leading applied research & innovation consultancy
Our insights are leveraged by the most ambitious organizations
“
I was blown away with their application and translation of behavioral science into practice. They took a very complex ecosystem and created a series of interventions using an innovative mix of the latest research and creative client co-creation. I was so impressed at the final product they created, which was hugely comprehensive despite the large scope of the client being of the world's most far-reaching and best known consumer brands. I'm excited to see what we can create together in the future.
Heather McKee
BEHAVIORAL SCIENTIST
GLOBAL COFFEEHOUSE CHAIN PROJECT
OUR CLIENT SUCCESS
$0M
Annual Revenue Increase
By launching a behavioral science practice at the core of the organization, we helped one of the largest insurers in North America realize $30M increase in annual revenue.
0%
Increase in Monthly Users
By redesigning North America's first national digital platform for mental health, we achieved a 52% lift in monthly users and an 83% improvement on clinical assessment.
0%
Reduction In Design Time
By designing a new process and getting buy-in from the C-Suite team, we helped one of the largest smartphone manufacturers in the world reduce software design time by 75%.
0%
Reduction in Client Drop-Off
By implementing targeted nudges based on proactive interventions, we reduced drop-off rates for 450,000 clients belonging to USA's oldest debt consolidation organizations by 46%