Innovative paper-like, battery-free, AI-enabled sensor for holistic wound monitoring

(Nanowerk News) Most wearable wound sensors measure only one or a small number of parameters, and require a printed circuit board and a large battery. The PETAL patch sensor, on the other hand, currently measures 5 biomarkers and does not require any kind of battery to operate. More biomarkers can be added if needed.

Each PETAL sensor patch consists of a fluidic panel patterned in the shape of a five-petal pinwheel flower, with each ‘petal’ acting as a sensing area. An opening in the center of the fluidic panel collects fluid from the wound and distributes fluid evenly through 5 sampling channels to the sensing area for analysis. Each sensing area uses a different color-changing chemical to detect and measure each of the wound’s indicators – namely temperature, pH, trimethylamine, uric acid, and humidity.

The fluidic panel is sandwiched between 2 thin films. The top transparent silicone layer enables normal skin function for oxygen and moisture exchange, and also enables image display for accurate image capture and analysis. The lower wound contact layer gently adheres the sensor patch to the skin and protects the wound bed from direct contact with the sensor panel, to minimize wound tissue disruption.

Once sufficient wound fluid has accumulated (usually within hours or over several days), the PETAL sensor patch will complete biomarker detection within 15 minutes. Sensor patch images or videos can be recorded on the phone for classification using a proprietary AI algorithm.

In laboratory experiments, the PETAL sensor patch demonstrated a high accuracy of 97 percent in differentiating between healing and chronic and non-healing burns.

(embed)https://www.youtube.com/watch?v=bju2XgTBdOc(/embed)

Timely and effective monitoring of wound healing status is essential for wound care and management. Impaired wound healing, such as chronic wounds (i.e. wounds that do not heal after 3 months) and pathological post-burn scars, can result in life-threatening medical complications and an enormous economic burden to patients and healthcare systems worldwide.

Recent findings by a research team from the National University of Singapore (NUS) and A*STAR’s Institute of Materials Research and Engineering (IMRE), provide a simple, convenient, and effective way to monitor wound recovery so that clinical interventions can be triggered. timely to improve wound care and management.

Today, wound healing is usually visually inspected by a doctor. Wound infections are mostly diagnosed via swabs followed by bacterial culture which involve long waiting times and do not provide timely wound diagnosis. This makes accurate prediction of wound healing a challenge in the clinical setting. In addition, wound assessment usually requires frequent manual dressing removal, which increases the risk of infection and can cause additional pain and trauma to the patient.

“To address this challenge, NUS researchers combined our expertise in flexible electronics, artificial intelligence (AI) and sensor data processing with the nanosensor capabilities of IMRE researchers to develop innovative solutions that could benefit patients with complex wound conditions,” said Associate Professor Benjamin Tee from the Department of Materials Science and Engineering under the NUS College of Design and Engineering, and the NUS Institute for Health Innovation & Technology.

The PETAL (Paper-like Battery-free In situ AI-enabled Multiplexed) sensor patch consists of 5 colorimetric sensors that can determine a patient’s wound healing status within 15 minutes by measuring a combination of biomarkers – temperature, pH, trimethylamine, uric acid, and wound moisture . These biomarkers were carefully selected to effectively assess wound inflammation, infection, and the condition of the wound environment.

“We designed the paper-like PETAL sensor patch to be thin, flexible and biocompatible, enabling it to easily and safely integrate with wound dressings to detect biomarkers. As such, we could potentially use this easy-to-use sensor patch for fast and low-cost procedure treatment management. wounds in hospitals or even in non-specialized healthcare settings such as at home,” explains Dr Su Xiaodi, Principal Scientist, Department of Soft Materials, IMRE A*STAR.

The sensor patch can operate without an energy source – the sensor image is captured by the smartphone and analyzed by an AI algorithm to determine the patient’s healing status.

Assoc Prof Tee said, “Our AI algorithm is able to quickly process data from digital patch sensor images for highly 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 less interference with wound healing. Timely medical intervention can then be administered appropriately to prevent adverse complications and scarring.

PETAL sensor patch design and fabrication is reported in a scientific journal Science Advances (“Battery-free, AI-enabled multiplexed patch sensors for wound monitoring”).

Wound-friendly and versatile

No signs of adverse reactions were observed on the skin surface in contact with the PETAL sensor patch for four days, indicating the biocompatibility of the PETAL sensor patch for outpatient wound monitoring.

In this study, the performance of the PETAL sensor patch was demonstrated on chronic wounds and burns. This AI-enabled technology can be adapted and adapted for other types of wounds, by incorporating various colorimetric sensors, such as glucose, lactate, or Interleukin-6 for diabetic ulcers. The number of detection zones can also be easily reconfigured to detect different biomarkers simultaneously, allowing their application to be extended to different wound types.

The next step

An international patent for this invention has been filed and the researchers plan to move on to further human clinical trials.

The development of the PETAL sensor patch was carried out in collaboration with the research team Professor David Becker from Nanyang Technological University and the Skin Research Institute Singapore.