A new study has shown that an artificial intelligence (AI) system developed by Google’s DeepMind subsidiary can quickly and accurately detect more than 50 eye disorders using routine medical scans.
Conducted in collaboration with Moorfields Eye Hospital, the study demonstrated the capability of the AI system to correctly recommend the best course of treatment for patients.
Existing diagnosis techniques for eye conditions involve the analysis of optical coherence tomography (OCT) 3D scans. However, these scans are considered ‘hard to read’ and require experts for interpretation.
DeepMind said that these scans could result in the delay of treatment, and in cases needing urgent care, such delay can impact patient’s eyesight.
The new technology tackles these concerns by automatically identifying the characteristics of eye diseases within seconds. It is also designed to prioritise patients who require urgent care.
DeepMind noted: “This instant triaging process should drastically cut down the time elapsed between the scan and treatment, helping sufferers of diabetic eye disease and age-related macular degeneration avoid sight loss.”
The AI system can be applied to various types of eye scanners, thereby allowing ease of use across hospitals and other clinical settings globally.
While the system is yet to be developed into a product, the researchers believe that it can enhance eye disease diagnosis, treatment and management.
The company plans to evaluate the AI system in clinical trials across all 30 Moorfields hospitals in the UK as well as community clinics for an initial duration of five years.
Moorfields currently owns an improved dataset related to the DeepMind’s trained AI model as a non-commercial public asset, which has already been leveraged in nine different hospital studies.
In addition, Moorfields has rights to use the system for any non-commercial research efforts in the future.