Mental Health Data Science

We’re harnessing the power of data science, to illuminate our understanding of mental illness.

Mental health data science has huge potential in the near-term to drive forward research and lead to major improvements in care and treatments.

Which is why we’re taking a leading role in this field – funding a major new award, launching the MQ Data Science Group, and curating a growing list of resources for researchers.

Funding applications

Applications to our 2018 data science are now closed - you can find out about the successful projects here.

The MQ Data Science Group

In 2016 we launched the Mental Health Data Science Group (PDF), bringing together experts from the world of mental health. They’re focused on mapping the data science landscape, championing this field, and finding new ways to improve the availability and use of data for mental health research.

The group have already published papers in the Lancet Psychiatry and Nature Human Behaviour, outlining the opportunities and barriers to mental health data science and continue to meet regularly to inform policy and practice. You can see the latest virtual meetings here. 

If you would like to find out more about the group contact our Science team.

Data science policy development

We've worked with partners in the health research space to support a positive policy environment for data science. Most recently we partnered with the AMRC to promote safe access to health information for research.

Data science resources

We're curating a growing list of data science resources, to highlight the tools available to mental health researchers. If you've got anything to add to the list, just get in touch!

Our projects

The Stratified Medicine Approaches for Treatment Selection (SMART) Mental Health Prediction Tournament

The Stratified Medicine Approaches for Treatment Selection (SMART) Mental Health Prediction Tournament

Principal investigator:Dr Rob DeRubeis and Zachary Cohen

Institution:University of Pennsylvania

Location:United States

Research award:Data Science

Can we create an algorithm that predicts which psychological therapy would work for someone?

Using Data Science to understand Educational Risk Factors for Self-harm and Suicidal Behaviour in Young People

Using Data Science to understand Educational Risk Factors for Self-harm and Suicidal Behaviour in Young People

Principal investigator:Dr Rina Dutta

Institution:King's College London

Location:United Kingdom

Research award:Data Science

What do records in schools tell us about a child’s risk of suicide?

Mapping the mental health and service-use of young people in out-of-home care

Mapping the mental health and service-use of young people in out-of-home care

Principal investigator:Dr Rachel Hiller

Institution:University of Bath

Location:United Kingdom

Research award:Data Science

Dr Rachel Hiller is using untapped data to understand the mental health conditions experienced by young people in care, so support services can give them the help they need.

Get involved

There are lots of opportunities to get involved in the programme. Get in touch if you would like to partner with us, or find out more about the Mental Health Data Science Group.

Our research projects

Explore how our world-class researchers are working tirelessly to tackle mental illness.

Mental health conditions

Learn more about different mental health conditions, and the research we're doing to transform the lives of those affected by them.

Take part in research

How you can get involved in mental health research.

Sign up for Research Roundup

If you are a researcher, mental health professional, or are just interested in hearing about funding opportunities from MQ then please sign up to our quarterly Research Roundup newsletter.

  • By providing us with your details you are agreeing to receive emails from MQ about our work and ways you can get involved, including fundraising. You can unsubscribe at any time. You can read more in our privacy policy.
  • This field is for validation purposes and should be left unchanged.