One of the main challenges facing healthcare providers in the UK today (and in Europe) is the rising number of people with chronic health problems. Almost 1 in 7 UK citizens experiences chronic pain, some due to chronic diseases such as osteoarthritis, but much of it mechanical low back pain (LBP) with no treatable pathology. 40% of these people experience severe pain and are very restricted by it. The capacity of our current health care system is insufficient to treat all these patients face-to-face. Pain experience is affected by physical, psychological, and social factors and hence it poses a problem to the medical profession. This has prompted the development of a multidisciplinary approach to the treatment of chronic LBP, primarily involving psychology and physiotherapy alongside specialist clinicians (see British Pain Society guidelines). These programmes enable patients to become more self-managing through improving their physical and psychological functioning. While short term results are good, maintenance of these gains, and building on them, remains a problem, with psychological factors being one of the primary limiting causes.
Rehabilitation-assistive technologies have shown some success in helping recovery in a number of conditions but have yet to have an impact in pain management, mostly because of the complexity of dealing with emotional and motivational aspects of self-directed activity increase. By providing the means to automatically recognise, interpret, and act upon human affective states, recent developments in sensing technology and the field of affective computing offer new avenues for addressing these limitations and alleviating the difficulties patients face in building on treatment gains.
Thus we propose the design and development of an intelligent system that will enable ubiquitous monitoring and assessment of patients’ pain-related mood and movements inside (and in the longer term, outside) the clinical environment. Specifically, we aim to (a) develop a set of methods for automatically recognising audiovisual cues related to pain, behavioural patterns typical of low back pain, and affective states influencing pain, and (b) integrate these methods into a system that will provide appropriate feedback and prompts to the patient based on his/her behaviour measured during self-directed physical therapy sessions. In doing so, we seek to develop a new generation of multimodal patient-centred personal health technology.