Conference: AI and Mental Health

Prof. Andrea Cipriani

University of Oxford

Antidepressants are one of the main treatments for depression. Many patients, however, are given antidepressants, which prove ine8ective, or cause stressful side-e8ects, for them as an individual. This happens because antidepressants are prescribed without a clear understanding of which drug is the most appropriate medication for each patient. Regulatory bodies and guidelines developers have recommended prioritising the improvement of antidepressant treatment for depression, but this advice has not yet been translated into practice. We suggest we already have su8icient evidence to distinguish between treatments according to personal characteristics, and the preferences and values of patients themselves. People with a diagnosis of depression often need additional support during the consultation visit when they make decisions about starting a new course of treatment. By a more careful analysis of existing data and AI approaches, we can better tailor the choice of a specific drug to a specific person, to increase the chances that the drug will be tolerable and e8ective. We developed the PETRUSHKA tool, an evidence-based online system which will help doctors and patients together choose the best antidepressant for each individual with moderate to severe symptoms of depression. For the first time, this system brings together the best available scientific information with the preferences of patients to provide a bespoke clinical decision aid for antidepressant treatment. The PETRUSHKA tool has been tested in a randomsied trial in both primary and secondary care across Brazil, Canada and the UK. During the project, patients and carers have been involved in the co-development of the PETRUSHKA tool, which provides a model that can be extended to non-pharmacological treatments and to other psychiatric and non-psychiatric disorders, such as schizophrenia, diabetes and epilepsy.

Dr. Andy Blackwell

Chief Scientific Officer, ieso Digital Health

The global rise in mental health conditions, coupled with a critical shortage of accessible, high-quality psychological care, poses one of the most pressing challenges of our time. In this talk, I will explore how the convergence of healthcare data availability and recent advances in artificial intelligence is beginning to transform the assessment and treatment of mental health disorders. Using mood and anxiety disorders as a focal point, I will discuss current AI-human collaboration models and examine how patient stratification and domain-specific language models can improve both clinician- and patient-facing applications. I will present findings from a recent study comparing AI-driven and clinician-delivered psychotherapy, highlighting how machine learning is paving the way for a new era of scalable, personalised, data-driven therapy. By leveraging large-scale, real-world care data, AI systems may soon be capable of informing and optimising treatment decisions through computationally learned action-outcome patterns. I will also discuss the opportunities and challenges these technologies and approaches present, offering insights into the evolving roles of humans and machines in mental healthcare.

Prof. Hatice Gunes

Professor of Affective Intelligence and Robotics (AFAR) and Director of the AFAR Lab, University of Cambridge

The World Health Organisation (WHO) underscores the prevalence of mental health issues among adults and children on a global scale. Among WHO’s main goals are the promotion of mental well-being, the prevention of mental issues, and the increase in access to quality mental health care. However, a significant number of people do not receive essential support due to barriers to access or a lack of knowledge regarding seeking help. Recognizing mental health concerns early is pivotal for timely interventions and improved outcomes. Recent research in the fields of human-robot interaction and social robotics have shown that robots have the potential to serve as novel and engaging tools to improve both physical and emotional wellbeing. However, whether robots can be used for assessing child mental wellbeing has never been investigated. In this talk, I will present the research explorations of the Cambridge Affective Intelligence and Robotics Lab in this area and will illustrate the potential of social robotics for assessing child mental wellbeing with a number of case studies. I will provide key takeaways and insights on how social robotics can fit in the existing procedure for mental wellbeing assessment of children in the UK and abroad.