by A researcher at a Scottish university has developed AI tools that could offer people in remote areas of the world access to fast and potentially saving skin cancer diagnoses.
Tess Watt, the doctoral student at Heriot-Watt University in Edinburgh, who led the project to develop the technology, said that early detection of skin diseases all over the world should enable and without direct access to dermatologists.
The technology also works without internet access.
The system includes a patient who takes up a photo of his skin complaint using a small camera that is attached to a raspberry Pi device-a cheap, energy-efficient handheld computer that is able to store large amounts of information.
The photo is analyzed in real time using the latest image classification of the art and it is compared with an enormous data record of thousands of images that are stored on the device to achieve a diagnosis.
The results are then shared to a local GP service in order to start a suitable treatment plan.
The project is considered the first of its kind of AI Medical Diagnosis with the aim of serving remote communities.
Ms. Watt said: “The healthcare system from home is currently a really important topic, especially since the waiting times of the GP continue to grow.
“If we can empower humans to monitor the skin diseases from their own houses with AI, we can drastically reduce delays in diagnosis.”
A prototype of the device has already been demonstrated in the Advanced Health and Care Technologies Suite from Heriot-Watt.
The research team said that the tool in its diagnostic functions is up to 85%. However, they hope to further increase this by gaining access to more skin lesion data sets, supported by advanced machine tools.
Ms. Watt is also in conversations with NHS Scotland to begin the ethical approval process for the examination of the technology in clinical environments in the real world.
“Hopefully we will have a pilot project ongoing in the next few years or two,” she said, noticing that medical technology often takes years to convert the prototype to implement it.
She added: “When I end my doctorate in three years, I would like to look a little in the pipeline that is on the way to the use of real world.”
The university said that the long -term vision is to roll out the system in remote regions of Scotland before it starts in global areas with limited access to dermatological care.
It also added that the technology also for patients who are more frequent or not able to offer important support to support relatives to record and transmit diagnostic images to GPS.
Ms. Watt’s academic supervisor, Dr. Christos Chrysoulas, said: “E-Health devices must be constructed in such a way that they work independently of external connectivity to ensure the continuity of the patient service and security.
“In the case of a network or cloud service error, such devices must fail and maintain all essential clinical operations without functional dismantling.
“While auxiliary or non-critical characteristics cannot be temporarily available, the diagnostic and even core therapeutic functions must remain in accordance with the safety and regulatory requirements.
“The nature of our research, especially for use in resource -limited environments and areas with limited or without connectivity in which uninterrupted patient care can still be guaranteed, is the guarantee of this resilience in affordable, inexpensive medical devices.”
Peter Kyle, secretary for science and technology in Great Britain, commented on research and said: “In terms of cost -effective technology that could help recognize skin cancer early and at home without the need for internet access, an incredible example of the potential of the AI to save barriers in healthcare.
“Promising, first of this kind, as this, also shows the crucial role in improving the life of people of all origins, wherever they can live, and makes the value of the government that invests in research investments clearly to create our plan for changes.”
