People with extensive brain damage usually lose consciousness for some time. Someone who has a disorder of consciousness lasting over two weeks is considered to have a
prolonged disorder of consciousness. To assess the degree to which these people are conscious, clinical scales such as the
Coma Recovery Scale - Revised,
which assess patient behaviour and reaction to stimuli, have been devised. These, however, only provide snapshots in time, do not allow for easily monitoring change,
require trained observers (not available in most hospitals), and are subject to bias and subjective interpretation.
A change in guidance is looming (cfr. a recent Guardian article
'UK judges no longer required to rule on removing life-support') which will require most
decisions about a person’s level of consciousness to be made by physicians. The NHS needs to improve assessment procedures to meet the need. Existing techniques,
which directly or indirectly record brain activity, lack any substantive evidence that changes in activity associated with an assigned task actually indicates that
the person is aware and anyway many patients could not be assessed by these techniques.
In response, we propose a continuous monitoring system based on automatically analysing both
video and auditory information via novel multimodal deep neural networks to identify patient activities judged by a consensus of experts to be of interest,
summarising patterns of behaviour of patients as statistics of activities in time. The system will be validated against existing clinical scales, and will provide
dependable evidence for clinical teams to review, facilitating better and earlier decisions and reducing doubt and dispute.