Advanced machine learning and data analytic techniques have demonstrated potential for application in mental health care and psychiatry for over a decade. Further advancement in sensor technology (camera, microphones, biosensors) has led to efficient data collection mechanisms, that can be leveraged for improved management of psychiatric disorders. Different data sources like audio-visual data, text, central and peripheral autonomic nervous system, and even health registry data are utilised at various stages from screening to diagnosis, post hoc analysis and for management and intervention of psychiatric disorders. Given the growing need for resources in mental health care, this is a positive development as mental health experts can better allocate resources towards patients with the aid of data-driven diagnostics and treatment.

However, few digital solutions make it into the clinic, where risk score charts with a few variables still are common practice. The challenge of moving research solutions into practice is often referred to as the Valley of Death, with technical, organisational, and end-user adaptation factors standing in the way of valuable solutions reaching the patients. In addition to presenting the potential advantages of using AI systems within mental-health, the goal of this session is to 1. discuss the technology readiness level of AI within clinics, 2. identify key deployment challenges and best practices, 3. facilitate collaboration between the stakeholders.

This session will present a holistic view of AI-assisted solutions for the mental health and their (lack of) implementation by bringing together key stakeholders discussing the challenges and how to overcome them. We will summarize our findings in a short publication. The different viewpoints from the key stakeholders include:

1. A political and regulatory perspective.
2. Clinical perspectives.
3. Entrepreneurial and AI solution driven perspectives.
4. Organisational and implementation perspective.
5. All perspectives from the audience

Program

The proposed session will address the advances and limitations of data driven approaches to preventive mental healthcare and its translations from research to applications. We have invited interdisciplinary participants with primary expertise in psychiatry, machine learning and regulatory and landscape. The tentative session schedule is:

1. Open the floor (5 mins)
2. Setting the stage with invited lightning talks from experts (8 × 4 = 32 minutes),
3. Open panel discussion with questions to the invited experts and then open the floor for audience engagement (50 minutes)
4. Session wrap (5 mins).

The invited speakers (and panelists) are:

Stinus Lindgreen, Member of the Health Committee, Member of Digitalisation and IT committee, Folketinget, Sundhedsordfører, Psykiatriordfører, It-ordfører, Radikale Venstre, The Danish Parliament
Perspective: Regulatory and political perspective on research, health, and psychiatry

Benjamin Alexander Thorup Arnfred, psychologist and Postdoc, VIRTU Research group, Mental Health Center Copenhagen, University of Copenhagen
Perspective: Clinical, adult psychiatry, psychosis disorders, Virtual Reality.

Nicole N Lønfeldt, Clinical Scientist, Child and Adolescent Mental Health Center, Copenhagen University Hospital – Mental Health Services CPH
Perspective: Clinical perspective: Winner of ”News of the Year” in Denmark’s Best Clinical Trials Awards, child and adolescent psychiatry, anxiety disorders, wearables.

Paula Petcu, CEO, Interhuman AI,
Perspective: Preventive mental health, soft skills training, AI solutions, startup, health tech innovation.

Panel Moderator
Line H. Clemmensen, Professor KU and DTU, with expertise in AI for mental health, co-founder Tetatet AI and Soil.

Target audience

The target audience is any participant with an interest in or working within ML for (mental) healthcare or other high-impact AI applications. Entrepreneurial minded techies and health care oriented participants. Also, conference participants engaged in applications of data science in disciplines like human-centric computing, social-signal processing, trustworthy AI and related fields may find this session useful.

Organizers

• Sneha Das, Assistant Professor (sned@dtu.dk), DTU Compute (STAT)
• Line H. Clemmensen, Professor (lkhc@math.ku.dk), KU (STP)
• Nicole Lønfeldt, Senior Scientist (nicole.nadine.loenfeldt@regionh.dk), Child and Adolescent Mental Health Center, Copenhagen University Hospital—Mental Health Services
• Stella Graßhof, Assistant Professor (stgr@itu.dk), ITU (CS)
• Dan Witzner Hansen, Professor (witzner@itu.dk), ITU (CS)