Waiting for a wound to heal is incredibly frustrating. First, it must clot; then an immune system response is needed; followed by scabbing and scarring — and that’s not even getting into the pain part.
However, a wearable device, a-Heal, designed by engineers at the University of California, Santa Cruz, aims to expedite the entire healing process. It uses a tiny camera and AI to detect the stage of healing and deliver treatment in the form of medication or an electric field. The system responds to the unique healing process of the patient, offering personalized treatment.
a-Heal’s concept is akin to how a physician cares for a wound, UCSC Baskin Engineering Endowed Chair and Professor of Electrical and Computer Engineering Marco Rolandi said. Typically, a physician or healthcare professional observes the wound periodically when changing the dressing. They will then assess the stage and condition of the wound from visual inspection and additional analysis as needed. With their training and knowledge, they’ll determine and administer the therapy for the wound to heal. An experienced physician trained on many wounds will typically provide a more accurate diagnosis and improved therapy.
“a-Heal works like an automated personalized physician,” Rolandi added. “a-Heal uses a camera to image the wound, machine learning to provide a diagnosis and prescribe an optimal therapy, and bioelectronics to deliver the therapy on demand. The system learns like a trained professional and improves the treatment as each wound progresses to the healing phases and uses what it has learned to better heal future wounds.”
The AI model used for this system, led by Associate Professor of Applied Mathematics Marcella Gomez, uses a reinforcement learning approach guided by an algorithm — Deep Mapper — to mimic the diagnostic approach used by physicians. In this case, the model is given a goal of minimizing time to wound closure and is rewarded for making progress.
It continually learns from the patient and adapts its treatment approach; as time goes on, the device learns a linear dynamic model of the past healing and uses that to forecast how the healing will continue to progress. This method allows the algorithm to learn in real time the impact of the drug or electric field on healing and guides the reinforcement learning model’s iterative decision-making on how to adjust the drug concentration or electric-field strength.
The UC Davis team tested the device in preclinical wound models. The studies showed that wounds treated with a-Heal followed a healing trajectory about 25 percent faster than standard of care. The work shows that the technology not only accelerates closure of acute wounds but can also jumpstart stalled healing in chronic wounds.
Despite its astounding potential, “a-Heal is not designed to substitute trained professionals but rather to augment their reach and democratize healthcare by allowing access to care for patients in remote locations or with poor mobility. In addition, the a-Heal physician interface allows physicians to monitor progress remotely and intervene in case the wound is not healing as desired,” Rolandi said.
The team is currently exploring the potential for this device to improve the healing of chronic and infected wounds and expanding the impact of the research, but the work is still in its infancy, Rolandi noted.
This article was written by Andrew Corselli, Digital Content Editor, SAE Media Group. For more information, visit here .
