Dementia care


Using AI to assess pain for people with dementia


Professor Jeff Hughes, chief scientific officer at Australian health technology developer PainChek, explains the important role digital technology plays in accurate pain assessment and enabling the delivery of better outcomes for care home residents


Dementia is the UK’s biggest killer, and currently affects around 850,000 people. Around 70 per cent of residents in the UK’s 18,000 care homes have some form of dementia, 80 per cent of whom suffer pain at any one time, and 50 per cent experience persistent pain. It is a daily challenge for carers and


healthcare professionals to assess pain in people living with dementia or other cognitive impairments. Patients with dementia who cannot communicate their pain may have complex and/or subtle behavioural changes such as restlessness, changes in body language, speech and sleep patterns, appetite and facial expressions, all of which may indicate the presence of pain. In this group of people, pain often


goes undetected or untreated, which can lead to unnecessary suffering, behavioural and psychological issues, inappropriate prescribing, and decreased quality of life for residents. A Department of Health study found that of 180,000 antipsychotic prescriptions for people living with dementia prescribed in the UK, close to 80 per cent, or 140,000 individuals, were inappropriate. PainChek was developed as an


effective and novel solution to the pain assessment problem. The combination of automated facial-analysis technology and smart automation aims to enable carers and healthcare professionals to identify the presence of pain when pain is not obvious, to quantify the severity of


pain and monitor the impact of treatment to optimise and evidence overall quality of care.


The evolution of PainChek Approximately 90 per cent of people living with dementia experience behavioural and psychological symptoms (BPSD). When carrying out medication management reviews as a pharmacist in nursing homes, I saw that the use of antipsychotic agents for residents with challenging behaviours was ever-increasing, yet there was little change in the management of their pain. Antipsychotics should be used as


minimally as possible due to the potential side effects - including an increased risk of strokes - and while they may reduce the occurrence of BPSD, they do not address the root causes of episodes. When one of our co-founders,


Mustafa Atee, came to me seeking to do a PhD at Curtin University in Western Australia, I told him I had just the project – we were going to improve pain management in people living with dementia by improving the assessment of their pain. Initially, we looked at automating the


‘Faces of Pain Scale,’ but our research led us to identify the merits of a multidimensional pain tool, incorporating AI and smart automation. A unique 42- item observation pain assessment tool was conceptualised, based around the American Geriatric Society’s most commonly seen pain-related behaviours


PainChek uses facial analysis technology to detect the presence of facial micro- expressions of the presence of pain


36


in people with cognitive impairment and the Facial Action Coding System (FACS). A research grant from Dementia


Australia was secured in 2012, which funded the development of the app prototype that was delivered the following year. The app first underwent validation testing in communicative people with chronic pain, to prove that the automated facial analysis did what it was designed to do, which was to detect facial expressions indicative of the presence of pain using people who were able to self-report its existence. Secondly, the technology was tested


on residents of aged care facilities who had moderate to severe dementia and could not self-report their pain. Performance of the app, which was then known as ePAT (Electronic Pain Assessment Tool), was compared with the Abbey Pain Scale, a paper-based validated pain assessment instrument.


www.thecarehomeenvironment.com• December 2020


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52