Impact & Opinions | Tionchar & Tuairimí

Lua Health: How Algorithms Can Help Detect Mental Health Issues at Work
Images courtesy of Shutterstock.
edition-image
Made in Galway: Resilient Innovation

Lua Health: How Algorithms Can Help Detect Mental Health Issues at Work

22 June 23
 | 
4
(4)
 STARS
 | 17 MINS

With support from the University of Galway, Lua Health is working to overcome the stigma around mental health in the workplace. Using machine-learning algorithms – this research-led start-up interprets how we speak and write at work to detect early signs of poor mental wellbeing – combining expertise in both natural language processing and clinical psychology.

The pandemic and ensuing shift to hybrid work has driven employers to take a deeper look at wellbeing in the workplace – with 80% of executives recognising wellbeing as a top priority. (1) Despite the growing trend, a recent report partnering with Harvard Business Review found that nearly 90% of workers feel their work life is getting worse. (2) Younger generations and underrepresented groups appear to be struggling the most; 68% of Millennials and 81% of Gen Zers have left roles for mental health reasons, both voluntarily and involuntarily. (3)

“Younger generations and underrepresented groups appear to be struggling the most; 68% of Millennials and 81% of Gen Zers have left roles for mental health reasons, both voluntarily and involuntarily.”

Traditional approaches to wellbeing have relied on questionnaire assessments, failing to account for stigma and delayed recognition of symptoms. “Research from the journal, Jama Psychiatry (4) shows that individuals will typically wait eight years after the onset of depression before being diagnosed,” says Fionn Delahunty, University of Galway alum and co-founder of Lua Health. “This is eight years of avoidable suffering that we aim to reduce.”

Lua Health: How Algorithms Can Help Detect Mental Health Issues at Work
Images courtesy of Shutterstock.

With support from University of Galway, startup and potential spinout, Lua Health is developing algorithms informed by decades of research in linguistic biomarkers. Lua Health offers a discreet and accurate detection, alongside a clear path to early intervention. “The past pandemic showed the vulnerability of our society regarding general health, as well as mental health. And the issue that most of us are facing is that we often don’t know or don’t want to acknowledge early signs of our poor mental wellbeing,” says fellow co-founder, Mihael Arcan. “Although this period has shown us the importance of mental health, there is still a stigma. We hope that with our technology, we can help to cross the boundary of this stigma, and support individuals with appropriate help that moves beyond yearly questionnaires.” An early pilot study with Lua Health’s corporate clients has already shown an increase of 42% in employees accessing corporate wellbeing benefits.

“University of Galway's Innovation Office has supported us at every step of the journey with guidance and advice. There is also a great network of alumni spinout founders who are always happy to offer advice.”

Mihael Arcan
Lua Health

Beginnings – A Formidable Duo

Lua Health is a clear example of the value of collaboration across disciplinary boundaries. The idea came to life in 2018 when Fionn, then a Psychology graduate of the University of Galway, was finishing his MSc in Applied Data Science from the University of Gothenburg. From both, personal lived experience, and the experience of his friends and family, Fionn felt that poor mental health was a hidden epidemic that needed some radical solutions.

At that time, Mihael was supervising Fionn’s thesis project which would later become the basis for the software solution. University of Galway’s Data Science Institute supported the start-up in laying the groundwork for a crucial commercialisation fund. “There is a lot of support available for Irish academics to commercialise their research,” says Mihael. “Enterprise Ireland supported us with an early-stage feasibility funding, and at a later stage with the commercialisation grant. Additionally, the Innovation Office at the University of Galway has supported us at every step of the journey with guidance and advice. And there is also a great network of alumni spinout founders who are always happy to offer advice.”

Lua Health: How Algorithms Can Help Detect Mental Health Issues at Work
Images courtesy of Shutterstock.

The Lua Health team’s multidisciplinary approach combines expertise in both natural language processing (NLP) and clinical psychology. “As researchers, we took an evidence-based approach to detect early signs of poor mental wellbeing. We had a great benefit from a range of different expertise on our doorstep – AI, psychology, business – as well as the entrepreneurial experience of other start-ups. Nevertheless, following the lean start-up method, we also spent a lot of time engaging with the market to understand their needs before we invested time in building a solution,” says Fionn.

The technology is also being piloted with hospitals to help clinicians measure patients’ symptoms in a faster and less invasive way, and to help detect mental health issues in patient groups that have been traditionally unserved.”

Mihael Arcan
Lua Health

How Does it Work?

Lua Health’s success lies in an algorithm suite, rooted in decades-long research demonstrating the correlation between our language and our mental health state. “This research was academically interesting but had no practical implications until it was combined with NLP and machine learning,” says Fionn. “What is unique about Lua Health is that we map these language biomarkers to standardised clinical scales used in regular practice. This allows clinicians to easily understand our system and integrate it into their workflow.”

Language biomarkers of depression can include subtle anomalies, such as lower speech rate and more self-referential speech. (5) “We don’t look at what you are saying but how you are saying it. So, there is less variation within different languages and cultures; nevertheless, there are always challenges to overcome,” says Mihael. Beyond detecting symptoms, the start-up is also dedicated to supporting individuals in gaining a deeper understanding of their mental health and recognising the importance of receiving care at the right time before these issues reach a critical stage.

Lua Health is now piloting its software solution with corporate clients seeking ways to reduce stress and improve day-to-day wellbeing among their employees. “The technology is now being piloted with hospitals to help clinicians measure patients’ symptoms in a faster and less invasive way, and to help detect mental health issues in patient groups that have been traditionally unserved,” he adds.

Lua Health: How Algorithms Can Help Detect Mental Health Issues at Work
Images courtesy of Shutterstock.

“We have so many tools for managing our health, such as blood pressure monitors that manage our heart health. There is no reason why we can’t apply that effort into monitoring and managing our mental health.”

Fionn Delahunty
Lua Health

A Research-Led Intervention

The migration of work online has strengthened the demand for new solutions to better understand the experience of employees. “Globally, we are seeing governments begin to recognise the importance of wellbeing in the workplace. ISO45003 is a global standard for psychological safety and wellbeing at work. Standards such as these will begin to mandate companies to track and measure wellbeing in the workplace and respond to issues appropriately,” says Fionn. “As remote work becomes more common; we’re hearing from managers that it’s harder to judge colleagues’ wellbeing. We believe that solutions, like Lua will make it easier for managers to care and respond to their employees.”

According to WHO, depression is the largest cause of disability worldwide and is highly co-morbid with several other mental disorders. (6) The prevalence of depression rests in part on the surrounding stigma. A culture change is inevitable as employers begin to invest more in wellbeing; and research-led spinouts like Lua Health are sure to play a pivotal role. “We have so many tools for managing our health, such as blood pressure monitors that manage our heart health. There is no reason why we can’t apply that effort into monitoring and managing our mental health,” says Fionn. “The team at Lua Health believes in a work environment where people don’t have to wait for a crisis to receive support. Over the next couple of months, we are raising external investment from the venture capital community,” says Mihael. “We are scaling up our pilot programs and deploying to more sites around the world to help improve more lives.”

Mihael Arcan and Fionn Delahunty are co-founders of Lua Health, a University of Galway researchled startup, funded by Enterprise Ireland Commercialisation Fund. Led by a crossdisciplinary team of psychologists, machine learning scientists and commercialisation experts, Lua Health is providing an innovative AI approach to proactive wellness in the workplace. 

Read more about Lua Health here, and follow them on LinkedIn.

Endnotes:

  1. 2020 Human Capital Trends. 15 May, 2020.
  2. Jennifer Moss, “Beyond Burned Out,” Harvard Business Review, 10 February, 2021.
  3. Kelly Greenwood and Julia Anas. “It’s a New Era for Mental Health at Work”, Harvard Business Review. 4 October, 2021.
  4. Wang PS, Berglund P, Olfson M, Pincus HA, Wells KB, Kessler RC. “Failure and Delay in Initial Treatment Contact After First Onset of Mental Disorders in the National Comorbidity Survey Replication”. Originally published in Arch Gen Psychiatry. June, 2005.
  5. Sanne Koops, Sanne G Brederoo, Janna N de Boer, Femke G Nadema, Alban E Voppel, Iris E Sommer. “Speech as a Biomarker for Depression”. CNS Neurol Disord Drug Targets. 2023;22(2):152-160.
  6. World Health Organization. Depression and Other Common Mental Disorders. 3 January, 2017.
RATE

4 / 5. Vote count: 4

Discover More

Keep up to date on the latest from us straight to your inbox

Privacy policy