Researchers at Australia’s Curtin University are developing smart phone apps to detect pain in patients who cannot speak. According to Tony Malkovic, writing for Fierce Medical Devices, the app developers are using facial recognition technology and plan to produce two apps. One is for elderly people with dementia who find it hard to communicate accurately with their doctors. The other is for very young children. They are calling their app the Electronic Pain Assessment Tool, or ePAT.
Phone App Detects Facial Ques for Pain

Malkovic quoted Professor Jeff Hughes, a member of the research team, who said, “What we’re trying to do is provide an objective measure for assessing pain for patients who cannot communicate verbally. What it does is combine the objective facial features of pain which can be used with pain cues and combines that with other non-facial features in order to determine the presence of pain and the severity of the pain.”
A Swiss company developed the 3D facial recognition software that the researchers utilize on a license. The app takes a ten second video of features such as eyes, nose and mouth t and then analyzes them.
Hughes says that at present his research group is the first to analyze the presence of facial cues for pain using a smart device and undertaking that analysis in real time.
“Potentially it’s a game changer. What we know is that anywhere between 50 and 80 per cent of dementia patients suffer pain; 50 per cent of them have ongoing chronic pain and we know that’s undertreated, ” he said.

Discussion
This is a fascinating development. In my practice we've seen similar outcomes with the revised protocol. The key differentiator seems to be patient selection criteria. Has anyone else noticed the correlation with BMI thresholds?
Great point. I'd push back slightly on the conclusion, the sample size in the cited study is too small to draw population-level inferences. That said, the directional signal is compelling and worth a larger RCT.
We implemented a similar approach last year. Early results are promising but we're still gathering 12-month follow-up data. Happy to share our protocol if anyone is interested.
Join the conversation
Orthopedic professionals are discussing this. Sign in and upgrade to read every comment and add your voice.