Mental health has largely been a neglected problem in global healthcare until recent years. Innovation and novel services are needed to deal with the individual and systemic burden arising from such conditions. The answer may lie in the data from our digital footprint as Butte quoted in 2013 that “hiding within those mounds of data is the knowledge that could change the life of a patient or change the world”.
Bipolar disorder is a condition that consists of mania and depression. Recognising the early warning signs of shifts into either of these states has been proven effective in preventing relapse (Morriss, 2013). From a data perspective, the occurrence of these extremes is likely to be apparent in physical and social activities and therefore likely to be detectable through “sensing” using technology. In essence, we believe these shifts will be presented as under or over activity in passively sensed data coupled by actively sensed increases or decreases in effort.
This project aims to amalgamate four different personal data streams (mobile phone usage, financial transactions, car usage and home utility usage) and apply machine learning algorithms to create a sensing system which will be able to detect early warning signs of mania and depression for those with bipolar disorder. Specifically, our research questions are:
The use of personal data in this project nestles its relevance within the research aims of ‘My Life in Data’ at Horizon Centre for Doctoral Training. The project aims to develop a new technology to transform the state of care for bipolar disorder and therefore also aligns itself to the research priorities of Nottingham Biomedical Research Centre ‘Mental Health and Technology’ theme.
This author is supported by the Horizon Centre for Doctoral Training at the University of Nottingham (RCUK Grant No. EP/L015463/1) and Nottingham Biomedical Research Centre.