Google has developed artificial intelligence to diagnose cancer better than doctors

Artificial intelligence more accurately than doctors diagnoses breast cancer by mammography, writes Air force with reference to a study published in the journal Nature.

Фото: Depositphotos

An international team of scientists, in particular Google Health and Imperial College London, has developed a computer model and taught it to diagnose cancer based on x-rays of nearly 29 women.

It turned out that the algorithm read mammograms better than six separate radiologists.

The diagnosis of artificial intelligence turned out to be as accurate as the collaboration of two doctors at once.

Also, unlike humans, artificial intelligence never gets tired. Experts say that it can help improve the diagnosis of cancer.

How well does artificial intelligence work?

In the modern British healthcare system, two radiologists analyze the x-rays of each woman. In rare cases, when they cannot agree, the pictures are evaluated by a third doctor.

As part of the study, artificial intelligence analyzed anonymous images, which could not identify women. Unlike human experts who had access to the patient history, only mammograms were in front of artificial intelligence.

The results showed that the findings of artificial intelligence were as accurate as the diagnostic scheme with the participation of two doctors.

At the same time, artificial intelligence diagnosed cancer better than one single doctor. Compared to a radiologist, AI had 1,2% fewer false positives (when they see cancer on the mammogram that actually isn't).

On the subject: A new cure for cancer: the drug has destroyed cancer cells in a patient

Also, there were 2,7% fewer false negative results when existing cancer was not diagnosed.

“Our team is really proud of the results of these studies, which suggest we are on track to develop a tool that can help diagnose breast cancer with greater accuracy,” said Dominic King of Google Health.

In order to become a radiologist who can decrypt mammograms, you need more than 10 years of preparation. Reading x-rays is a vital but very laborious job.

Will artificial intelligence replace people?

Not. After all, it was people who developed the model of artificial intelligence and taught it to read pictures.

This was an experimental study, and now the AI ​​system has not yet been used directly in clinics - at least one radiologist will remain responsible for diagnosis, even with AI available.

But AI can greatly eliminate the need for two doctors to read the mammograms twice, thereby reducing their workload, the researchers say.

Professor Ara Darzi, co-author of the report and director of the Imperial Cancer Research UK (CRUK), told the BBC: “This has gone far beyond my expectations. This will have a significant impact on improving the quality of reporting and will also free up radiologists more time to do even more important things.”

Women between the ages of 50 and 70 in the UK must undergo breast screening every three years.

On the subject: How to beat cancer: five scientifically based reasons for optimism

Using AI can ultimately speed up diagnostics, since a computer algorithm can analyze the image in a few seconds.

Sarah Guiom, director of cancer research and early detection at CRUK, told the BBC: "This is a promising early study and suggests that in the future it will be possible to make diagnoses more accurate and efficient, meaning less waiting and worry for patients, and also the best results."

Helen Edwards from Surrey County was diagnosed with breast cancer at the age of 44 before she was eligible for free screening. She needed surgery, chemotherapy and radiation therapy, but she has overcome cancer, and more than ten years have passed since then.

She introduced patients to the CRUK discussion panel, which should decide whether to allow Google Health to use anonymized breast cancer data.

“At first I was a little concerned about what purpose Google might use the data for, but it is stripped of any identifiers. In the long term, this can only benefit women, she told the BBC. “AI machines don’t get tired... they can work around the clock, whereas humans can’t do that, so combining them together is a great idea.”

Read also on ForumDaily:

It gives us hope: scientists have created a cure for all types of cancer

American scientists have discovered a new strain of HIV: why it matters

Doctors in the US managed to defeat stage four cancer

Two Americans and a British received the Nobel Prize in medicine: what is their merit

Do you want more important and interesting news about life in the USA and immigration to America? — support us donate! Also subscribe to our page Facebook. Select the “Priority in display” option and read us first. Also, don't forget to subscribe to our РєР ° РЅР ° Р »РІ Telegram  and Instagram- there is a lot of interesting things there. And join thousands of readers ForumDaily New York — there you will find a lot of interesting and positive information about life in the metropolis.