Author: Dr. Jasmine Noble, Postdoctoral Fellow, Departments of Computing Science and Psychiatry, University of Alberta


The challenges we face are known:

Before COVID, you may have heard that it is estimated that one in three of us will directly experience a mental health disorder [1, 2] and that one in three of us who report needing it, would report not receiving adequate care (one in two if you have depression) [3] [4]. However, two years+ into a global pandemic, and these statistics are now looking conservative with 50% of Canadians reporting that their mental health has gotten worse as a result of COVID-19 [ref]. COVID-19 has fueled the flames of multiple mental health stressors for many of us, including around fears of getting sick, life disruptions, and concerns over economic instability [5].

Mental health is health – this is a fact that can’t be ignored. The collective trauma we are experiencing as a global community in the face of an ongoing pandemic, during this period of economic and geopolitical instability, must be met with innovative solutions – solutions that seek to address the novel challenges of today as well as problems that existed long before the pandemic began.

We know what the barriers are. In surveys, respondents have noted several reasons for not seeking help – including stigma related fears, denial, privacy concerns, and trouble connecting with a care provider, to name a few. They may be due to or made worse by fragmented or episodic care, and/or missing navigational supports to help individuals find and connect with the right health services, at the right time. Some wait times for mental health services, for example, have been estimated to be as long as two and a half years, and our mental health system has been described as a “labyrinth” to navigate [6, 7, 8, 9, 3, 10, 11] [12]. To make matters worse, service providers in different sectors and jurisdictions may not be communicating effectively with each other, leaving gaps in provider knowledge of many existing service options within the mental health ecosystem, reducing referrals and thus access to much needed and underutilized services [13, 14, 15, 16, 17].

Opportunity lies in innovation:

Opportunity lies in the innovative application of digital technologies. Digital health innovations have demonstrated, in a variety of different applications, that they can bridge service gaps, increase access to care, and permit greater cross-sectoral system integration [18]. Additionally, over 90% of Canadians already actively use the internet [19, 20], which means technological infrastructure to allow new innovations to reach individuals quickly are already largely in place – we just need to tap into it strategically and effectively.

Technology doesn’t sleep, and it doesn’t need to take a break. This means that it can both support individuals who may be falling through the cracks, while supporting health system players.

Supporting Our Community of Mental Health System Providers:

Digital innovations can be administered in a way that complements existing health services and supports health system players. Sophisticated technologies like Artificial Intelligence and Machine Learning can support overwhelmed mental health system providers by, for example, providing coverage for certain more simple service provision tasks during periods of staff shortages and/or higher demand, while at the same time providing them with information in a more accessible way – at their fingertips – increasing their power to respond to problems efficiently, and quickly, which in turn gives them more time to address more complicated situations, where a sensitive, responsive, human-to-human interaction is not only merited but the only appropriate solution.

Offering another bridge to access care:

There are several reasons why individuals may choose to access online versus in-person services, including 24-hour accessibility, ease of accessibility despite geographic location, anonymity, and privacy [21, 22, 23, 24]. Additionally, the preference of some patients may be to discuss sensitive health matters with a computer or technological device, rather than to another person [25, 26]. Technology then presents another avenue that a client can use to access care in a way that might support the bypassing of traditional barriers to care inherit in the existing system, like stigma.

MIRA, the Mental Health Virtual Assistant

MIRA is an anonymous mental health chatbot, that uses Artificial Intelligence and Machine Learning (including Natural Language Processing) to provide users with information on mental health issues, services, and programs – whenever they want it, wherever they are – tailored and personalized to their need. This is not the first time that natural language processing or artificial intelligence and machine learning have been used in chatbots to support mental health, but the use of it to support individuals in finding the right mental health services, with the provision of a 700+ resource database that has been vetted for quality, accessible for free, is very novel.

This is just the beginning. This year we hope to translate MIRA into French, and expand service provision to more provinces, and groups including Veterans, and children and youth, while integrating more complex and novel forms of artificial intelligence and machine learning.

We hope you will join us on this very exciting initiative!

Ways to get involved:

  • subscribe to our newsletter
  • following us on social media
  • volunteer to support MIRA efforts and activities
  • provide us with feedback on your experience with MIRA so we can improve services

Contact MIRA to get involved!

Visit MyMira.ca.


Bibliography

[1] Mood Disorders Society of Canada, “Mental Illness and Addiction in Canada,” MDSC, Ottawa, 2019.

[2] C. Pearson, T. Janz and J. Ali, “Mental and substance use disorders in Canada,” Statistics Canada , Ottawa, 2015.

[3] A. Sunderland and L. Findlay, “Perceived need for mental health care in Canada: Results from the 2012 Canadian Community Health Survey – Mental Health,” Statistics Canada, Ottawa, 2013.

[4] The Centre for Addiction and Mental Health, “Mental Illness and Addiction: Facts and Statistics,” CAMH, [Online]. Available: https://www.camh.ca/en/driving-change/the-crisis-is-real/mental-health-statistics. [Accessed 30 Nov 2021].

[5] C. Moreno, T. Wykes, S. Galderisi, M. Nordentoft, N. Crossley, N. Jones and e. al., “How mental health care should change as a consequence of the COVID-19 pandemic,” The Lancet Psychiatry, vol. 7, no. 9, pp. 813-824, 2020.

[6] National Institute on Alcohol Abuse and Alcoholism, “Understanding the impact of alcohol on human health and well-being,” National Institute on Alcohol Abuse and Alcoholism, Bethesda, 2014.

[7] C. Simpson and J. Tucker, “Temporal sequencing of alcohol-related problems, problem recognition, and help-seeking episodes,” Addictive Behaviors , vol. 27, p. 659–674, 2002.

[8] W. Narrow, D. Regier, D. Rae and e. al, “Use of services by persons with mental and addictive disorders. Findings from the National Institute of Mental Health Epidemiologic Catchment Area Program,” Archives of General Psychiatry, vol. 50, p. 95–107, 1993.

[9] T. Wild, A. Roberts and E. Cooper, “Compulsory substance abuse treatment: An overview of recent findings and issues,” European Addiction Research, vol. 8, p. 84–93, 2002.

[10] C. Sanmartin, C. Houle, S. Tremblay and J. Berthelot, “Changes in unmet health care needs,” Health Reports, vol. 13, no. 3, pp. 15-21, 2002.

[11] Canadian Mental Health Association, “Wait times for youth mental health services in Ontario at all-time high,” CMHA, 27 Jan 2020. [Online]. Available: https://ontario.cmha.ca/news/wait-times-for-youth-mental-health-services-in-ontario-at-all-time-high/. [Accessed 30 Nov 2021].

[12] G. Kelly, “When the sick need to hire a squeaky wheel,” The Globe and Mail, p. A.8., 15 April 2017.

[13] R. Mossabir, R. Morris, A. Kennedy, C. Blickem and A. Rogers, “A scoping review to understand the effectiveness of linking schemes from healthcare providers to community resources to improve the health and well-being of people with long-term conditions,” Health Soc Care Community, vol. 23, no. 5, p. 467–84, 2015.

[14] J. Ploeg, M. Denton, J. Tindale, B. Hutchison, K. Brazil, N. Akhtar-Danesh and e. al., “Older adults’ awareness of community health and support services for dementia care,” Canadian J Aging/La Revue canadienne du vieillissement, vol. 28, no. 4, p. 359–70, 2009.

[15] D. Birrell and D. Heenan, “Implementing the transforming your care agenda in Northern Ireland within integrated structures,” J Integr Care, vol. 20, no. 6, p. 359–66, 2012.

[16] Ontario Ministry of Health and Long-Term Care, “Ontario’s action plan for health care. In: Better patient care through better value from our health care dollars,” Queen’s Printer for Ontario, Toronto, 2012.

[17] V. R and e. al., “Disconnected relationships between primary care and community-based health and social services and system navigation for older adults: a qualitative descriptive study,” BMC Family Practice, vol. 21, p. 69, 2020.

[18] KPMG, MOWAT, “The Integration Imperative: Reshaping the Delivery of Human and Social Services,” KPMG, Toronto, 2013.

[19] Statistics Canada, “Canadian Internet Use Survey,” Statistics Canada, 29 Oct 2019. [Online]. Available: https://www150.statcan.gc.ca/n1/daily- quotidien/191029/dq191029a-eng.htm. [Accessed 27 Mar 2020].

[20] Canadian Radio-television and Telecommunications Commission, “Communications Monitoring Report 2016: Canada’s Communication System: An Overview for Canadians,” CRTC, Ottawa, 2016.

[21] K. Kypri and H. McAnally, “Randomized controlled trial of a web-based primary care intervention for multiple health risk behaviors,” Prev Med , vol. 41, no. 3-4, pp. 761- 766, 2005.

[22] S. Linke, E. Murray, C. Butler and P. Wallace, “Internet-based interactive health intervention for the promotion of sensible drinking: patterns of use and potential impact on members of the general public,” J Med Internet Res, vol. 9, no. 2, p. e10, 2007.

[23] K. Humphreys and E. Klaw, “Can targeting nondependent problem drinkers and providing internet-based services expand access to assistance for alcohol problems? A study of the moderation management self-help/mutual aid organization,” J Stud Alcohol, vol. 62, no. 4, pp. 528-532, 2001.

[24] D. Lieberman and S. Huang, “A technological approach to reaching a hidden population of problem drinkers,” Psychiatr Serv, vol. 59, no. 3, pp. 297-303, 2008.

[25] S. Bucci, M. Schwannauer and N. Berry, “The digital revolution and its impact on mental health care,” Psychology and Psychotherapy: Theory, Research, and Practice, vol. 92, pp. 277-297, 2019.

[26] G. Lucas, J. Gratch, A. King and L. Morency, “It’s only a computer: Virtual humans increase willingness to disclose,” Computers in Human Behavior, vol. 37, p. 94–100, 2014. .

[27] Statistics Canada, “Accessing mental health care in Canada,” 11 May 2017. [Online]. Available: https://www150.statcan.gc.ca/n1/pub/11-627-m/11-627-m2017019-eng.htm.

[28] Wait Time Alliance, “Position paper on the occasion of the 10th Anniversary of the 2004 10-Year Plan to Strengthen Health Care in Canada,” Wait Time Alliance, 2014.

[29] Wait Time Alliance, “Time to Close the Gap: Report Card on Wait Times in Canada,” Wait Time Alliance, 2014, 2014.

[30] M. Denton, J. Ploeg, J. Tindale, B. Hutchison, K. Brazil, N. Akhtar-Danesh and e. al., “Where would you turn for help? Older adults’ awareness of community services,” Canadian J Aging/La Revue canadienne du vieillissement, vol. 27, no. 4, p. 359–70, 2008.

[31] N. Chappell, L. McDonald and M. Stones, Aging in contemporary Canada. 2nd ed., Toronto: Pearson-Prentice Hall, 2008.

[32] B. Hutchison, J. Levesque, E. Strumpf and N. Coyle, “Primary health care in Canada: systems in motion,” Milbank Q, vol. 89, no. 2, p. 256–88, 2011.

[33] Commission on the Reform of Ontario’s Public Services. , “Public services for Ontarians: a path to sustainability and excellence,” Queen’s printer for Ontario, Toronto, 2012.

[34] Health Quality Ontario, “Key Observations 2014-15 Quality Improvement Plans Community Care Access Centres,” Health Quality Ontario, Toronto, 2015.

[35] World Health Organization, “WHO Coronavirus (COVID-19) Dashboard,” World Health Organization, 19 July 2021. [Online]. Available: https://covid19.who.int/. [Accessed 19 July 2021].

[36] M. Drolet, “How Canada is encouraging self-isolation to prevent the spread of COVID-19,” Global News, 2020. [Online]. Available: https://globalnews.ca/news/6634584/canada-coronavirus-covid-19-self-isolation/. [Accessed 17 Apr 2020].

[37] E. Uguen-Csenge, “Mental illness will be ‘next wave’ of COVID-19 pandemic, epidemiologist says,” CBC News, 2020. [Online]. Available: https://www.cbc.ca/news/canada/british-columbia/months-isolation-mental-health-covid-1.5521649. [Accessed 30 Nov 2021].

[38] S. Brooks, R. S. L. Webster, L. Woodland and e. al, “The psychological impact of quarantine and how to reduce it: rapid review of the evidence,” Lancet, vol. 395, pp. 912-920, 2020.

[39] Nanos, “25% of Canadians (aged 35-54) are drinking more while at home due to COVID-19 pandemic; cite lack of regular schedule, stress and boredom as main factors,” Canadian Centre on Substance Use and Addiction, 2020.

[40] Canadian Psychological Association, “Psychology works fact sheet: Depression,” CPA, 2021. [Online]. Available: https://cpa.ca/psychology-works-fact-sheet-depression/. [Accessed 2021].

[41] M. Tjepkema, “Insomnia,” Health Rep, p. 9–25, 2005.

[42] D. Sutton, H. Moldofsky and E. Badley, “Insomnia and health problems in Canadians,” Sleep, vol. 24, p. 665–670, 2001.

[43] C. Morin, M. LeBlanc, M. Daley and e. al., “Epidemiology of insomnia: prevalence, self-help treatments, consultations, and determinants of help-seeking behaviors,” Sleep Med, vol. 7, p. 123–130, 2006.

[44] A. Vaidyam, H. Wisniewski, J. Halamka and e. al, “Chatbots and Conversational Agents in Mental Health: A review of the psychiatric landscape,” Canadian Journal of Psychiatry, vol. 64, no. 7, pp. 456-46, 2019.

[45] Central Intelligence Agency, “The world factbook,” Central Intelligence Agency, 2020. [Online]. Available: https://www.cia.gov/library/publications/the-world- factbook/geos/xx.html. [Accessed 27 Mar 2020].

[46] D. Vigo, S. Patten, K. Pajer and e. al., “Mental health of communities during the COVID-19 pandemic,” Can J Psychiatry, vol. 65, no. 10, pp. 681-687, 2020.

[47] A. Abd-Alrazaq, A. Rababeh, M. Alajlani, B. Bewick and M. Househ, “Effectiveness and safety of using chatbots to improve mental health: Systematic review and meta-analysis,” Journal of Medical Internet Research, vol. 22, no. 7, p. e16021, 2020.

[48] L. Laranjo, A. Dunn, H. Tong and e. al, “Conversational agents in healthcare: a systematic review,” Journal of the American Medical Informatics Association, vol. 25, no. 9, pp. 1248-1258, 2018.

[49] S. Provoost, H. Lau, J. Ruwaard and e. al, “Embodied conversational agents in clinical psychology: A scoping review,” Journal of medical internet research, vol. 19, no. 5, p. e151, 2017.

[50] A. Cohen, K. Mitchell and B. Elvevåg, “What do we really know about blunted vocal affect and alogia? A meta-analysis of objective assessments,” Schizophr Res, vol. 159, no. 2-3, pp. 533-538, 2014.

[51] A. Glaz, Y. Haralambous, D. Kim-Dufor and e. al., “Machine Learning and Natural Language Processing in Mental Health: Systematic Review,” J Med Internet Res ., vol. 23, no. 5, p. e15708, 2021.

[52] P. Kammili, B. Ramakrishnam Raju and A. Krishna, “Handling emotional speech: a prosody based data augmentation technique for improving neutral speech trained ASR systems,” Int J Speech Technol , 2021.

[53] N. Farruque, C. Huang, O. Zaiane and R. Goebel, “Basic and depression specific emotion identification in Tweets: multi-label classification experiments,” in 20th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing), La Rochelle, 2019.

[54] C. Dong, C. Huang, O. Zaiane and L. Mou, “Simulated Annealing for Emotional Dialogue Systems,” in 30th ACM International Conference on Information and Knowledge Management (CIKM), Gold Coast, 2021.

[55] C. Huang, A. Trabelsi, X. Qin, N. Farruque, L. Mou and O. Zaiane, “Seq2Emo: A Sequence to Multi-Label Emotion Classification,” in Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), 2021.

[56] C. Huang and O. Zaiane, “Generating Responses Expressing Emotion in an Open-domain Dialogue System,” in CONVERSATIONS: 2nd International Workshop on Chatbot Research, In conjunction with the International Conference on Internet Science, St. Petersburg, 2018.

[57] C. Huang, O. Zaiane, A. Trabelsi and N. Dziri, “Automatic Dialogue Generation with Expressed Emotions,” in 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), New Orleans, 2018.

[58] X. Sun, D. Yang, X. Li and e. al, “Interpreting Deep Learning Models in Natural Language Processing: A Review,” MIT Press, Cambridge, 2020.

[59] K. Murphy, “Machine learning: a probabilistic perspective,” MIT press, Cambridge, 2012.

[60] M. S. Zimmerman and G. Shaw, “Health information seeking behaviour: a concept analysis,” Health Information and Libraries Journal, vol. 37, pp. 173-191, 2019.

[61] A. Syan, J. Y. Y. Lam, C. G. L. Huang, M. S. M. Smith, K. Darnay, L. D. Hawke and J. Henderson, “The Wellness Quest: A health literacy and self‐advocacy tool developed by youth for youth mental health,” Health Expectations, vol. 24, no. 2, p. 659–669, 2021.

[62] S. J. Chang and E. O. Im, “A path analysis of Internet health information seeking behaviors among older adults,” Geriatric Nursing, vol. 35, p. 137–141, 2014.

[63] J. Ellis, J. Mullan, A. Worsley and N. Pai, “The role of health literacy and social networks in arthritis patients’ health information-seeking behavior: A qualitative study,” International Journal of Family Medicine, pp. 1-6, 2012.