MeDS club #5: Introduction to the Landscape of Mental Health Data Science

Opening event of MeDS's series: AI in Mental Health!

In this webinar we are honored to host Andrey Kormilitzin, who will review the different pillars of the MH DS landscape, recent advances in field of AI/ML applied to Mental Health domain, discuss real-world applications related to Mental Health disorders, digital triage and drug surveillance and outline challenges, potentials, and the journey ahead.

The meeting is online, Zoom link:
https://us02web.zoom.us/j/89405035111

Detailed Abstract:
The advances in Machine Learning Artificial Intelligence towards improving and streamlining healthcare have been widely recognized and discussed. In the evolving landscape of Mental Health Data Science (MH DS), it's paramount to understand its foundational pillars, methodologies, and the nuanced challenges it faces.

This seminar seeks to introduce the multifaceted realm of MH DS, emphasizing the unique nature of Mental Health data, ethical considerations, and the importance of participatory design, especially with marginalized communities.

Mental health disorders, unlike many physical ailments, are predominantly expressed through language and behavior. This subtlety implies that the primary source of data is derived from clinical interviews, resulting in a rich tapestry of free-text clinical notes and natural language.
Mental illness is the complex product of biological, psychological and social factors that foreground issues of under-representation, institutional and societal inequalities, 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.

Mental health data is sensitive, often sparse, and inherently subjective. 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. This positions Mental Healthcare as something of an exemplar of participatory practices in healthcare from which technologists, engineers and scientists can learn.

We will review recent advances in field of AI/ML applied to Mental Health domain, discuss real-world applications related to suicide, digital triage and drug surveillance and outline challenges, potentials, and the journey ahead.

Bio:
Andrey Kormilitzin is a Senior Research Fellow and a Group Leader in the Department of Psychiatry and a member of the Mathematical Institute at the University of Oxford. He leads an interdisciplinary group of researchers applying advanced mathematical methods and algorithms to real-world multimodal data with the aim to better understand neurological and mental health disorders.