To keep an eye on hard-to-heal wounds, such as bedsores, diabetic ulcers or even serious burns, a team of scientists from the National University of Singapore (NUS) and A*STAR’s Institute of Material Research and Engineering (IMRE) created an AI-enabled sensor patch that can assess wound recovery in real-time. Their innovation could enable patients and their physicians to monitor wound healing progress and start timely treatment of chronic wounds to avoid serious consequences.
The PETAL (Paper-like Battery-free In situ AI-enabled Multiplexed) sensor patch created by the research team can assess a wound’s status in less than 15 minutes in a non-invasive manner. This is a significant improvement over existing protocols for wound care and assessment, which require clinicians to visually examine a wound, manually change wound dressings, and swab the wound to check for bacterial infections—procedures that are time-consuming, add to the pain and trauma of patients, and elevate their risk of infection.
"We designed the paper-like PETAL sensor patch to be flexible and biocompatible, allowing it to be easily and safely integrated with wound dressing for the detection of biomarkers. We can thus use this convenient sensor patch for prompt, low-cost wound care management at hospitals or even in non-specialist healthcare settings such as homes,” explained Dr Su Xiaodi, a principal scientist with the Soft Materials Department at IMRE.
Shaped like a pinwheel flower, the patch collects fluid from the wound through an opening at its centre and distributes the fluid to the petals, which sense and measure five parameters—temperature, pH level, trimethylamine, uric acid, and moisture around the wound—through colour-changing chemicals.
A photo of the patch taken using a mobile phone is then analysed by a proprietary AI algorithm, which determines real-time wound status based on the colour of each indicator. The researchers found that their algorithm was 97 per cent accurate in differentiating between healing and non-healing chronic and burn wounds.
“Our AI algorithm is capable of rapidly processing data from a digital image of the sensor patch for very accurate classification of healing status. This can be done without removing the sensor from the wound. In this way, doctors and patients can monitor wounds more regularly with little interruption to wound healing. Timely medical intervention can then be administered appropriately to prevent adverse complications and scarring,” said Associate Professor Benjamin Tee from the Department of Materials Science and Engineering at the NUS College of Design and Engineering.
Designed using the combined expertise of the research team in flexible electronics, AI, nanosensors, and sensor imaging, the PETAL sensor patch possesses several other features that are missing in most other wearable sensors, such as biocompatibility, batter-free operation, and flexibility to include additional sensing regions. This widens its scope to monitor wound types other than the chronic and burn wounds.
An international patent for this invention has been filed and the team hopes to test the patch’s potential in human clinical trials.
Adapted by Sruthi Jagannathan from Innovative paper-like, battery-free, AI-enabled sensor for holistic wound monitoring.