Could a robot save your sight? AI is being used for the first time to diagnose a diabetes-induced condition that can cause blindness

  • Diabetic retinopathy can cause blindness in patients with type 1 or 2 diabetes
  • It can be spotted by haemorrhages and other anomalies in the retina
  • AI technology – called  IDx-DR – has been developed to spot early warning signs
  • It received FDA approval after displaying 87% sensitivity to the condition, and is now being used in a hospital in Iowa 
  • e-mail

View
comments

One hospital is now allowing artificial intelligence to take the reigns and diagnose its patients.

The UI Health Care-Iowa River Landing in Coralville, Iowa has become the first hospital to adopt a new AI-powered machine to spot the early warning signs of diabetic retinopathy.

If left undiagnosed, the condition, which arises as a complication for patients who suffer with either type one or type two diabetes, can cause blindness. 

The machine is capable of scanning and analysing the retinas of at-risk patients and will provide its own diagnosis without any human assistance.

Dubbed IDx-DR, the technology has an 87 per cent sensitivity for the disease.

Scroll down for video 


Dr Michael Abramoff is president and director of IDx and a professional ophthalmologist. He developed IDx-DR, which is already in-use at one Iowa hospital, to help diagnose patients 

IDx-DR passed clinical tests on more than 900 patients back in April.

It was approved for use by the US Food and Drug Administration (FDA) after it was proven to display an 87 per cent sensitivity for diabetic retinopathy.

The AI-powered machine is now being used by the Diabetes and Endocrinology Centre at the UI Health Care-Iowa River Landing in Coralville, Iowa.

This department receives around 7,200 patient visits per year, according to the hospital. 

It is hoped that IDx-DR will make the diagnosis process easier, by providing accessibility to this exam outside of an eye specialist.

The machine can also provide results within minutes, which could speed up tests.

IDx-DR uses a retinal camera to take images of the patient’s eye.

After taking the photos, the machine learning algorithms analyse the images ‘the same way I do as a clinician,’ Dr Michael Abramoff, president and director of IDx and a professional ophthalmologist, told the Iowa Gazette.

  • Bizarre leaf blower study reveals how lizards with big feet… Need a hand? Mind-controlled robotic arm lets you do two… Never miss the start of a show again! BBC unveils new… Water found on Mars: Scientists discover liquid 12-mile lake…

Share this article

IDx-DR can then determine if the patient has the condition and provide a diagnosis. 

‘It looks for different lesions like haemorrhages, microaneurysms, many other abnormalities you get from diabetes in the retina if it’s abnormal, which is what I do when I look for a patient,’ Dr Abramoff added.

‘Then it analyses the combination of all these different features and it gives you a clinical decision by itself.’  

Dr Abramoff admits the current applications of the technology are somewhat limited, but is hopeful it will expand in the future and be used to spot more diseases.

‘I see a great future,’ the creator of IDx-DR said.


The AI looks for different lesions like haemorrhages, microaneurysms, many other abnormalities in the retina that arise from diabetes


In order to be accepted by the FDA, Dr Abramoff conducted clinical trials on 900 patients. These showed the machine had an 87 per cent sensitivity to detecting the disease in patients


The technology is being used by medical professionals to spot the early signs of diabetic retinopathy. If left diagnosed, the condition can cause blindness. It arises as a complication for patients that suffer with either type one or type two diabetes

Iowa is not the only place that sees AI having a place in the future of healthcare. 

Hospitals across the UK have also started to look to AI technology as a means of improving wait times and diagnosis accuracy in medical institutions. 

University College London Hospital (UCLH), in Bloomsbury, London, is pioneering the technology in a bid ‘to make services safer, quicker and more efficient.’

WHAT IS DIABETIC RETINOPATHY?

Diabetic retinopathy is the most common form of eye disease affecting sufferers of the blood-sugar condition.

It causes around 1,280 new cases of blindness every year in the UK. Nearly 7.7 million people in the US are affected by the condition.

Diabetic retinopathy usually impacts people who have had type 1 or 2 diabetes for several years.

It occurs when changes in blood-glucose levels result in alternations to the blood vessels in the retina.

This can cause the vessels to swell and leak fluid into the back of the eye.

Abnormal blood vessels can also grow on the retina’s surface, which can affect vision and cause blindness.

Early stage diabetic retinopathy can be painless. In advanced cases, symptoms may include:

  • Sudden vision changes
  • Eye floaters and spots
  • Double vision
  • Eye pain

At-risk people include those with poor blood-glucose control, protein in their urine, high blood pressure, prolonged diabetes and raised fats in their blood.

Diabetic retinopathy can be prevented through regular eye examinations and proper diabetes management.

Its main treatment is laser surgery.

Source: Diabetes.co.uk

Professor Bryan Williams, director of research at UCLH’s NHS Foundation Trust, claims AI could instantly assess a patient in A&E who is breathless and needs an X-ray.

This crucial time-saving step may allow patients in life-threatening conditions to be fast tracked for immediate treatment.

An Oxford hospital is also using AI to quickly and accurately diagnose heart disease.

The machine is more accurate than the best cardiologists and experts claim it has the potential to ‘save the NHS’.

The system has been successful in the early trials and, if its results are confirmed, similar AI scans could soon be available for free on the NHS.

The AI, called Ultromics, is being used at John Radcliffe hospital in Oxford.


The device, dubbed the IDx-DR, uses a combination of software and a retinal camera to take images of the patient’s eye. After taking the photos, the AI analyses the images ‘the same way I do as a clinician,’ Dr Michael Abramoff said


Dr Abramoff (pictured) admits the current applications of the technology are limited, with a narrow scope, but he is hopeful it will expand in the future and be used to spot more diseases


The technology could help doctors spot the signs of the disease earlier and more regularly, without the need for long face-o-face consultations with an expert. Dr Abramoff (pictured in his younger year) is an expert in the field and helped create the AI

Ultromics is designed to improve the accuracy of heart scans.

As it stands, of the 60,000 heart scans carried out on the NHS each year – some 12,000 are misdiagnosed by cardiologists. 

Ultromics was developed by Professor Paul Leeson, who taught the AI system how to recognise heart disease by feeding it 1,000 heart scans of patients from the last seven years.

Information about whether the patient went on to develop heart problems was also provided.

The technology has already been tested in six cardiology units and the results of the study are to be published later this year.

Early indications from the data are promising and the system is predicted to save the NHS up to £300 million ($400 million) a year.

‘There is about £2.2 billion ($1.67 billion) spent on pathology services in the NHS.

‘You may be able to reduce that by 50 per cent. AI may be the thing that saves the NHS,’ geneticist Sir John Bell told the BBC.

WHY ARE PEOPLE SO WORRIED ABOUT AI?

It is an issue troubling some of the greatest minds in the world at the moment, from Bill Gates to Elon Musk.

SpaceX and Tesla CEO Elon Musk described AI as our ‘biggest existential threat’ and likened its development as ‘summoning the demon’.

He believes super intelligent machines could use humans as pets.

Professor Stephen Hawking said it is a ‘near certainty’ that a major technological disaster will threaten humanity in the next 1,000 to 10,000 years.

They could steal jobs 

More than 60 percent of people fear that robots will lead to there being fewer jobs in the next ten years, according to a 2016 YouGov survey.

And 27 percent predict that it will decrease the number of jobs ‘a lot’ with previous research suggesting admin and service sector workers will be the hardest hit.

As well as posing a threat to our jobs, other experts believe AI could ‘go rogue’ and become too complex for scientists to understand.

A quarter of the respondents predicted robots will become part of everyday life in just 11 to 20 years, with 18 percent predicting this will happen within the next decade. 

They could ‘go rogue’ 

Computer scientist Professor Michael Wooldridge said AI machines could become so intricate that engineers don’t fully understand how they work.

If experts don’t understand how AI algorithms function, they won’t be able to predict when they fail.

This means driverless cars or intelligent robots could make unpredictable ‘out of character’ decisions during critical moments, which could put people in danger.

For instance, the AI behind a driverless car could choose to swerve into pedestrians or crash into barriers instead of deciding to drive sensibly.

They could wipe out humanity 

Some people believe AI will wipe out humans completely.

‘Eventually, I think human extinction will probably occur, and technology will likely play a part in this,’ DeepMind’s Shane Legg said in a recent interview.

He singled out artificial intelligence, or AI, as the ‘number one risk for this century’.

Musk warned that AI poses more of a threat to humanity than North Korea.

‘If you’re not concerned about AI safety, you should be. Vastly more risk than North Korea,’ the 46-year-old wrote on Twitter.

‘Nobody likes being regulated, but everything (cars, planes, food, drugs, etc) that’s a danger to the public is regulated. AI should be too.’

Musk has consistently advocated for governments and private institutions to apply regulations on AI technology.

He has argued that controls are necessary in order protect machines from advancing out of human control

Source: Read Full Article