The application of artificial intelligence (AI) in aiding medical diagnostics is set to revolutionize the healthcare system. The technology can detect cancer in the blood, monitor and forecast flu-like symptoms, develop new medicines, and so much more. Now researchers are testing its ability to detect glaucoma. AI can spot signs of disease earlier than humans, and it can scan extensive compilations of data much faster too. All that remains is for scientists to continue fine-tuning the algorithms, training and trialing them to make sure they are reliable.
In the UK, a team of University College London and Imperial College London scientists has been testing an AI’s capabilities to detect glaucoma – the leading cause of irreversible blindness that affects over 60 million people worldwide. The disease is caused by the death of cells in the retina. The team’s technology (a test supported by an AI algorithm) was found (through a clinical trial) to detect glaucoma progression 18 months earlier than the current gold standard method.
Lead researcher Professor Francesca Cordeiro (UCL Institute of Ophthalmology, Imperial College London, and Western Eye Hospital Imperial College Healthcare NHS Trust) said:
We have developed a quick, automated and highly sensitive way to identify which people with glaucoma are at risk of rapid progression to blindness.
The test is called Detection of Apoptosing Retinal Cells (DARC). It involves the injection of a fluorescent dye into the bloodstream that makes its way into the eye. There, it binds to retinal cells and illuminates the ones in apoptosis – the process of cell death. When viewed via eye exams, the dying cells appear as bright white dots. The AI steps in to identify the dots and remove the element of human error during diagnosis by offering a more definite conclusion on the severity or progression of the disease.
Dr. Eduardo Normando, the first author of the study, said:
Being able to diagnose glaucoma at an earlier stage, and predict its course of progression, could help people to maintain their sight, as treatment is most successful if provided at an early stage of the disease. After further research in longitudinal studies, we hope that our test could have widespread clinical applications for glaucoma and other conditions.
It is predicted that by 2040 the number of people with glaucoma will double to 120 million. Furthermore, a separate study by University College London scientists, in collaboration with Moorfields Eye Hospital, has linked the disease to air pollution. Hopefully, the fight against climate change will improve the condition of bad air quality plaguing most cities around the world. However, if it doesn’t, then glaucoma might become an even bigger problem than predicted, and the AI test will come in very handy to help millions of people save their vision.
