Empowering Communities:

A Participatory Approach to AI for Mental Health

NeurIPS 2022 VIRTUAL Workshop, December 9th 2022

Contact: pai4mh.neurips2022@gmail.com


The advances in machine learning (ML) and artificial intelligence (AI) towards improving and streamlining healthcare have been widely recognised and discussed, and there is a long-standing tradition of key breakthroughs being presented at NeurIPS. This includes numerous novel methods and applications, aimed at improving diagnostics, treatment recommendation, disease management, phenotyping, etc. Our workshop aims to extend these ideas to address challenges that are unique to mental healthcare. We feel that having this as a focus of a dedicated workshop is paramount, given that far less attention has been given to date to these important applications, largely due to the additional sensitivities involved with both the problem formulations and the underlying patient data, as well as social attitudes and stigma. Reductions in mental health spending have only exacerbated these issues, averaging around 2% of healthcare spending globally (TLGH, 2020). Innovation in this space is needed, to help manage and improve mental health in these challenging times.


The aim of the workshop is to address sociotechnical issues in healthcare AI/ML that are idiosyncratic to mental health.

Mental illness is the complex product of biological, psychological and social factors that foreground issues of under-representation, institutional and societal inequalities (Meyer, 2003), bias and intersectionality in determining the outcomes for people affected by these disorders – the very same priorities that AI/ML fairness has begun to attend to in the past few years (Leslie et al, 2021).

Despite the history of impoverished material investment in mental health globally, in the past decade, research practices in mental health have begun to embrace patient and citizen activism (if at times, imperfectly; Ocloo et al, 2021) and the field has emphasised stakeholder (patients and public) participation as a central and absolutely necessary component of basic, translational and implementation science. This positions mental healthcare as something of an exemplar of participatory practices in healthcare from which technologists, engineers and scientists can learn.

For example, mental illness is largely expressed in language and behaviour such that the primary clinical tool is the interview and therefore patients’ data is predominantly collected as free-text clinical narratives. Furthermore, sensitive patient characteristics (e.g. ethnicity, sexual orientation and identity) are poorly recorded for reasons including clinician and institutions’ transcultural illiteracy which leads to biased data.

Uniquely, this workshop will invite and bring together practitioners and researchers rarely found together “in the same room”, including:

  • Under-represented groups with special interest in mental health and illness

  • Clinical psychiatry, psychology and allied mental health professions

  • Technologists, scientists and engineers from the machine learning communities

We will create an open, dialogue-focused exchange of expertise to advance mental health using data science and AI/ML with the expected impact of addressing the aforementioned issues and attempting to develop consensus on the open challenges.

Diversity, Inclusion, and Accessibility

We commit and adhere to all diversity goals prescribed by NeurIPS 2022.

All contributed abstracts, slides and live stream links will be made available on the workshop website.

Sponsors will be asked to contribute toward providing travel grants and covering registration costs.

Those who prefer not to attend in person will be able to present and participate in panel discussions virtually.


Dan W Joyce (University of Oxford, UK)

Nenad Tomasev (DeepMind, UK)

Andrey Kormilitzin (University of Oxford, UK)

Kevin McKee (DeepMind, UK)

Program committee

Nemanja Vaci (University of Sheffield)

Yi Zhang (University of Oxford)

Piotr Kalinowski (University of Oxford)

Niall Taylor (University of Oxford)

Alejo Nevado-Holgado (University of Oxford)

Stephen Fashoto (University of Eswatini)

Dawn Albertson (Bath Spa University)

Alexis Cullen (Karolinska Institutet and King's College London)

Derek K Tracy (West London NHS Trust)

Cătălina Cangea (DeepMind)

Subhrajit Roy (Google)

Diana Mincu (Google)

Martin Seneviratne (Google)

Yuhang He (University of Oxford)

Aditya Nar (Dalhousie University)

Anant Dadu (University of Illinois Urbana-Champaign)

Eloy Geenjaar (Georgia Institute of Technology)

Guo Zhang (Massachusetts Institute of Technology)

Isabel Chien (University of Cambridge)

Kfir Bar (The Interdisciplinary Center Herzliya)

Laura M Winchester (University of Oxford)

Maxime Guillaume Kayser (University of Oxford)

Sirat Samyoun (University of Virginia, Charlottesville)

Syed Anwar (Children's National Hospital, Washington, DC, USA)

Xinhui Li (Georgia Institute of Technology)

Kangning Zhang (University of Oxford)

Nanqing Dong (University of Oxford)

Yuhang He (University of Oxford)

Yuval Rom (Hebrew University of Jerusalem)


Fully Virtual Conference collocated with the NeurIPS 2022


TLGH (2020). Mental health matters. The Lancet. Global Health, 8(11), e1352.

Meyer, I. H. (2003). Prejudice, social stress, and mental health in lesbian, gay, and bisexual populations: Conceptual issues and research evidence. Psychological Bulletin, 129(5), 674–697. https://doi.org/10.1037/0033-2909.129.5.674

Leslie, D., Mazumder, A., Peppin, A., Wolters, M. K., & Hagerty, A. (2021). Does “AI” stand for augmenting inequality in the era of covid-19 healthcare? BMJ, 372, n304. https://doi.org/10.1136/bmj.n304

Ocloo, J., Garfield, S., Franklin, B.D. et al. Exploring the theory, barriers and enablers for patient and public involvement across health, social care and patient safety: a systematic review of reviews. Health Res Policy Sys 19, 8 (2021). https://doi.org/10.1186/s12961-020-00644-3



Digital artworks

Images are generated using the DALL·E mini by Boris Dyma with "a participatory approach to artificial intelligence for mental health" as a prompt.