Facial recognition used to monitor high-risk hospital patients
Image credit: DT
Facial-recognition technology has been deployed by Japanese scientists to monitor patients in hospital who are prone to high-risk behaviour and detect when they have carried out a dangerous action, such as accidentally removing their breathing tube.
The team from Yokohama City University Hospital said that the facial-recognition system is able to detect unsafe behaviours with an accuracy of around 75 per cent.
They said that the the automated risk-detection tool has the potential to continuously monitor the safety of patients and could remove some of the limitations associated with limited staff capacity that make it difficult to observe critically ill patients at the bedside.
“Using images we had taken of a patient’s face and eyes, we were able to train computer systems to recognise high-risk arm movement”, said Dr Akane Sato, who led the research.
“We were surprised about the high degree of accuracy that we achieved, which shows that this new technology has the potential to be a useful tool for improving patient safety and is the first step for a smart ICU [intensive care unit] which is planned in our hospital.”
Critically ill patients are routinely sedated in the ICU to prevent pain and anxiety, permit invasive procedures and improve patient safety.
Nevertheless, providing patients with an optimal level of sedation is challenging and they are often inadequately dosed, increasing the possibility that they will display high-risk behaviour such as accidentally removing invasive devices.
The study included 24 post-operative patients (average age 67 years) who were admitted to the ICU in Yokohama City University Hospital between June and October 2018.
The proof-of-concept model was created using pictures taken by a camera mounted on the ceiling above patients’ beds. Around 300 hours of data were analysed to find daytime images of patients facing the camera in a good body position that showed their face and eyes clearly.
In total, 99 images were subject to machine learning, using an algorithm that can analyse specific images based on input data, in a process that resembles the way a human brain learns new information.
Ultimately, the model was able to alert against high-risk behaviour, especially around the subject’s face, with high accuracy.
“Various situations can put patients at risk, so our next step is to include additional high-risk situations in our analysis and to develop an alert function to warn healthcare professionals of risky behaviour. Our end goal is to combine various sensing data such as vital signs with our images to develop a fully automated risk-prediction system”, Sato said.
The authors noted several limitations, including the need for more images of patients in different positions in order to improve the use of the tool in real life. They also noted that monitoring the patient’s consciousness may improve the accuracy in distinguishing between high-risk behaviour and voluntary movement.
Sign up to the E&T News e-mail to get great stories like this delivered direct to your inbox every day.