A smartphone app using digital data collection to predict if an individual will relapse into psychosis is set to be trialled across the UK in a £12.5 million study.
The remote data collection system was developed by researchers at the University of Manchester. It combines active and passive symptom, emotional, physical and contextual monitoring with regular clinical assessments.
The project is called CONNECT and will be tested across six Higher Education Institutions and their partnering NHS trusts. It aims to recruit up to 1100 people who experience psychosis to test the data collection over 12 months.
The system sends regular prompts requesting the user to complete a digital questionnaire at set times during the week and takes around 90 seconds to complete. Data from the project will be used to develop a relapse prediction algorithm and an adaptive sampling algorithm using machine learning and artificial intelligence methods. The aim is for the algorithm to detect complex high dimensional non-linear interactions to predict warning signs of relapse.
It will also test whether data collected passively, such as sleep disturbance or inactivity registered through wearables or smartphone sensors, helps to improve the predictive algorithm.
“The system we will be developing at Manchester provides real-time and in-context patient-generated symptom data, obtained through our remote digital data collection system technology,” said John Ainsworth, Professor of Health Informatics at The University of Manchester.
Professor Sandra Bucci, Principal Investigator, added: “The system has the exciting potential of providing advanced warning of the need for support and intervention. It also has the potential to give mental health teams a clearer picture of the ebb and flow of an individual’s mental health trajectory. Our remote digital data collection system could be a crucial advance in the care of people with psychosis.”
The principle funder of the project is the Wellcome Trust, with the work conducted in partnership with The McPin Foundation.