Easy as AI: referral decision in 30 seconds with 95% accuracy

Researchers report that their machine learning system can perform at a similar level to a well-trained ophthalmologist


Scientists have developed artificial intelligence for screening patients at risk of age-related macular degeneration (AMD) and diabetic macular oedema.

Researchers from the US, Germany and China used an artificial intelligence based neural network to review more than 200,000 optical coherence tomography scans.

Machine diagnoses of AMD and diabetic macular oedema were compared with five ophthalmologists who reviewed the same scans.

As well as making a diagnosis, the AI technology generated a referral and treatment recommendation.

The authors report that the technology was able to perform at a similar level to a well-trained ophthalmologist, taking 30 seconds to decide whether a patient should be referred for treatment with more than 95% accuracy.

As well as examining eye conditions, the AI system was used to diagnose childhood pneumonia on the basis of chest X-rays.

The machine was able to differentiate between viral and bacterial pneumonia with more than 90% accuracy.

Senior author, Kang Zhang, highlighted that the findings show AI has many potential applications.

“The future is more data, more computational power and more experience of the people using this system so that we can provide the best patient care possible, while still being cost-effective,” he concluded.