AI: Healthcare systems need to embrace and restructure

Artificial intelligence is disrupting healthcare at a swift pace, and systems need to fully embrace a digitally-led restructure. Though for stretched health services like the NHS, it is not so simple.

depositphotos healthcare medical ai
Artificial intelligence will transform healthcare – image courtesy of Depositphotos.

“AI will transform healthcare systems that we have come to know,” Loubna Bouarfa, CEO & Founder OKRA Technologies, an artificial intelligence company specialising in healthcare, told TM.

She continues: “We won’t have to wait until we get sick to see a doctor, but instead AI algorithms will be flagging us to get health checks, track our medical history and know our family’s.

“We will be able to intervene before a problem occurs, and this is the way healthcare will transform. It will be empowered by data because it is an evidence-based industry,” she adds.

Sign up to our Industrial Internet newsletter to know the latest artificial intelligence advancements!

Restructuring health services 

The British Medical Association (BMA), the trade union and professional body for doctors in the UK, says: “The NHS is overstretched and underfunded, putting health services under unsustainable pressure.”

It says the service is at “breaking point” and “poor workforce planning over a number of years has resulted in the NHS facing huge recruitment and retention problems.”

There is a constant barrage of NHS issues reported in the mass media daily. Completely disrupting and restructuring such an unsteady but crucial system is risky. Though long-term, digitalising the service and fully integrating AI as just another tool, could make it more efficient, cost-effective and reliable.

Bouarfa adds: “It is not just diagnosing people earlier, it is eradicating the wrong medication routes, the time of being unwell, so not only is quality of life improved, AI offers a much more cost-effective approach.”

What time frame could this digital adoption happen on? “It won’t take a long time, though to get AI integrated we need to break barriers, particularly the collaboration barrier. We need to get hospitals working with tech and manufacturing companies that can scale, as well as working with other industries,” Bouarfa says.

AI use in diagnostics 

A leading example of artificial intelligence in healthcare is the use of it to support the immediate diagnosis of one of the top causes of blindness, a diabetes-related eye disease, in its earliest stages.

Diabetic retinopathy is the leading cause of vision loss in adults and its impact is growing worldwide, with 191 million people reportedly set to be affected by 2030.

Artificial intelligence As the outermost layer of the human eye, the cornea has an important role in focusing vision - image courtesy of Depositphotos.
Diabetic retinopathy is the leading cause of vision loss in adults – image courtesy of Depositphotos.

There are no early-stage symptoms and the disease may already be advanced by the time people start losing their sight. Early diagnosis and treatment can make a dramatic difference to how much vision a patient retains.

A team of Australian-Brazilian researchers led by RMIT University have now developed an image-processing algorithm that can automatically detect one of the key signs of the disease, fluid on the retina, with an accuracy rate of 98%.

Lead investigator Professor Dinesh Kant Kumar, RMIT, said the method was instantaneous and cost-effective. “We know that only half of those with diabetes have regular eye exams and one-third have never been checked,” Kumar said.

“But the gold standard methods of diagnosing diabetic retinopathy are invasive or expensive, and often unavailable in remote or developing parts of the world. Our AI-driven approach delivers results that are just as accurate as clinical scans but relies on retinal images that can be generated with ordinary optometry equipment.”

Injecting dye (fluorescein angiography) and imaging scans (optical coherence tomography) are currently the most accurate clinical methods for diagnosing diabetic retinopathy. An alternative and cheaper method is analysing images of the retina that can be taken with relatively inexpensive equipment called fundus cameras, but the process is manual, time-consuming and less reliable.

To automate the analysis of fundus images, researchers used deep learning and artificial intelligence. The algorithm they developed can accurately and reliably spot the presence of fluid from damaged blood vessels inside the retina.

The researchers are in discussions with manufacturers of fundus cameras about potential collaborations to advance the technology.