AI Tool to Diagnose Skin Cancer in Remote Areas, Without Internet or Doctors

As per reports, the tool is already up to 85% accurate in identifying skin abnormalities and is aimed at places with limited or no dermatological access.

A new low-cost AI device developed by a PhD researcher at Heriot-Watt University in Edinburgh could transform how skin cancer is diagnosed in remote parts of the world, even in the absence of doctors or internet connectivity.

Tess Watt, a PhD student leading the research, has built a prototype system using a Raspberry Pi computer and camera that allows patients to photograph a suspicious skin lesion. The device uses built-in machine learning software to instantly compare the image against a large database of thousands of skin conditions, enabling rapid, offline diagnosis.

As per reports, the tool is already up to 85% accurate in identifying skin abnormalities and is aimed at places with limited or no dermatological access. The diagnosis is shared with local GP systems, helping trigger timely treatment plans.

According to Watt, Healthcare from home is a really important topic at the moment, especially as GP wait times continue to grow. “If we can empower people to monitor skin conditions from their own homes using AI, we can dramatically reduce delays in diagnosis.”

A working prototype has been tested at Heriot-Watt’s advanced health and care technologies suite. Watt is currently in talks with NHS Scotland to initiate ethical approvals for real-world trials.

“Hopefully in the next year or two, we’ll have a pilot project under way,” she said. “By the time I finish my PhD, three years from now, I’d love to see something well into the pipeline that’s on its way to real-world use.”

The team’s long-term goal is to deploy the device first across rural Scotland, followed by remote and underserved regions worldwide. The tool could also aid patients who are unable to travel, with family members helping capture and submit images.

Her supervisor, Dr Christos Chrysoulas, emphasised the device’s ability to work without network connectivity. “E-health devices must be engineered to operate independently of external connectivity to ensure continuity of patient service and safety,” he said.

“In the event of a network or cloud service failure, such devices must fail safely and maintain all essential clinical operations without functional degradation… Ensuring this level of resilience in affordable, low-cost medical devices is the essence of our research.”

Stay tuned for more such updates on Digital Health News