There is no doubt that artificial intelligence (AI) is going to change the future of healthcare. AI can be used in disease prediction, treatment, identification, diagnosis, and management. For example, shares Medical XPress, a group of researchers from the University of London evaluated how a type of AI called deep learning could predict the impact of glaucoma on vision. Through this research, the researchers developed potential techniques to track glaucoma progression, which could be used in future studies. If you’re interested in learning more, take a look at the study findings published in Ophthalmology.
Understanding Deep Learning
The IBM Cloud Learn Hub describes deep learning as:
a subset of machine learning, which is essentially a neural network with three or more layers. These neural networks attempt to simulate the behavior of the human brain – albeit far from matching its ability – allowing it to ‘learn’ from large amounts of data.
Deep learning can be used to cultivate, assess, and analyze clusters of data. Through this, deep learning algorithms or techniques are able to make predictions based on the data.
AI and Vision Loss Prediction
Within this particular study, researchers sourced data from over 24,000 individuals with glaucoma. Much of this data included imaging of the patients’ eyes. The research team then split the imaging into two particular groups depending on how it was collected: optical coherence tomography (OCT) and infrared reflectance (IR).
Next, the researchers ran both sets of imaging through deep learning models with the goal of understanding how deep learning tools could be used to predict a patient’s visual field (and, in turn, vision loss). The deep learning models were able to determine specific patterns within patients’ eyes, as well as predict how well a patient might be able to see.
At this time, there is no clinical significance to the findings or predictions given by these models. However, the researchers believe that further studies could determine whether or not these models could eventually be used to predict vision progression in those with glaucoma. If the researchers ever reached this point, the deep learning models could also be used either within clinical trials, clinics, or when working to consider potential treatment options.
Learn More about Glaucoma
So what is glaucoma and how does it affect your health? Glaucoma refers to a group of progressive eye diseases characterized by optic nerve damage. As the optic nerve becomes damaged, often due to pressure, it becomes more difficult to transmit images to the brain. This eye pressure causes blockages in the eye, though the reason for the pressure is unknown. There are multiple forms of glaucoma, such as neovascular glaucoma, congenital glaucoma, irido corneal endothelial syndrome, and pseudoexfoliation syndrome. Symptoms and characteristics can include:
- Peripheral vision loss
- “Halos” appearing around lights
- Blurred vision
- Eye pain and/or pressure
- Nausea and vomiting
- Eye redness