Virtual Doctors Artificial intelligence detects many eye diseases

Artificial intelligence is said to recognize more than 50 eye diseases

Eye diseases are among the leading causes of vision loss; many of them could be effectively treated through early detection and therapy. In the future, a system based on deep learning could help with the diagnosis. Artificial intelligence is said to recognize more than 50 eye diseases.

Artificial intelligence in medicine

Artificial Intelligence (AI) has been a staple in health care for years, including helping to screen blood, urine and other body fluids. In recent years, progress has been made in this area. For example, US researchers developed an AI system that can detect skin cancer as reliably as physicians. And Italian scientists reported on a software that Alzheimer's is to recognize even ten years before the onset of disease. Even the approximate time of death of patients should be predictable by AI, according to Australian experts. The UK has now also developed an AI system that could be used in the healthcare sector: it should be able to detect more than 50 eye diseases.

An artificial intelligence (AI) developed by British researchers will help in the early detection of eye diseases. One study found that the software can detect over 50 eye diseases through scans. (Image: stefan_weis / fotolia.com)

Early diagnosis and treatment may be partially sighted

According to a statement by University College London (UCL), there are more than 285 million people worldwide with some sort of vision loss.

Eye disease is a major cause of vision loss, and many can be prevented through early detection and treatment.

Researchers at UCL, Moorfields Eye Hospital, UK and Alphabet's subsidiary DeepMind have developed a deep learning-based system that could help diagnose such diseases in the future.

According to a study published in the journal Nature Medicine, the DeepMind AI has learned to identify more than 50 common eye diseases based on thousands of depersonalized OCT (Optical Coherence Tomography) scans.

Recognition rate as by a specialist

According to a statement from Moorfields Eye Hospital, the detection rate is more than 94 percent and therefore in the same range as an evaluation by a specialist.

According to the scientists, there is the hope that the technology can lead to a tremendous amount of work.

"The number of eye scans we perform is growing much faster than human experts can interpret," Dr. Pearse Keane from Moorfields Eye Hospital.

"There is a risk that this will lead to delays in the diagnosis and treatment of diseases that may be devastating to patients," said the ophthalmologist.

"The AI ​​technology we are developing aims to prioritize patients who are in dire need of being seen and treated by a doctor or ophthalmologist," Dr. Keane.

"If we can diagnose and treat eye disease early, we have the best chance of preserving people's vision."

Software should give treatment recommendations

Now, clinical trials will explore how this technology can improve patient care in the field.

Although the AI ​​should not be able to decide for the foreseeable future on what kind of treatment a patient should receive, it should be used to determine which patients need the most relief.

Afterwards, however, real doctors decide on the case in question.

The researchers expressed the hope that the AI ​​system could be used in British clinics in as little as five years.

"I am confident that AI will play an important role in the future of healthcare, especially when it comes to educating and supporting healthcare professionals so that patients can benefit from vital treatment earlier than they previously have," said Professor Sir Peng Tee Khaw from Moorfields Eye Hospital in London.

However, by no means all people are convinced that AI systems should play such a large role in the medical field. Among other things, not because it remains unclear how they come to the respective result. (Ad)