How artificial intelligence can improve women's health

[zakiyatasnim]

Breast cancer is one of the most common cancers among women on the planet. According to the World Health Organization, about 1 million cases of the disease are registered in the world annually and breast cancer is currently one of the main causes of death in women. In this regard, in many countries, women over the age of 50 are recommended to undergo a so-called mammogram every three years to detect cancerous tumors in the mammary glands. However, doctors often make mistakes: either they make a fatal diagnosis to completely healthy patients, or they do not detect the initial stages of the disease, which is extremely important for successful treatment. Fortunately, researchers from Google Health have developed artificial intelligence that recognizes tumors with higher accuracy than professional doctors.



The scientific publication ScienceAlert reported on the switzerland number data benefits of artificial intelligence in detecting breast cancer. About 1 million women are diagnosed with the deadly disease every year, but today things are much worse. According to foreign sources, in 2018, an aggressive type of cancer was detected in 2 million patients. has increased significantly, because the earlier doctors learn about a developing disease, the higher the probability of a complete recovery.

How is breast cancer detected?
A developing breast tumor can be detected using X-rays taken with a mammogram. These images are studied by at least two radiologists, but even with teamwork, doctors can make serious mistakes. However, according to scientists at Google Health, their artificial intelligence, trained on many X-rays, is able to detect signs of cancer with almost no errors.

The technology was tested on thousands of women from the UK and the US. After the artificial intelligence scanned the X-rays, they were further studied by radiologists. As it turned out, the computer's accuracy in this matter is close to the professionalism of experienced doctors. It is noteworthy that to make a diagnosis, the artificial intelligence did not study the medical history of patients who could have the prerequisites for the development of breast cancer.



Ultimately, it turned out that artificial intelligence reduced the number of misdiagnoses by 5.7% in the US and 1.2% in the UK. The technology also reduced the likelihood of missing symptoms by 9.4% in the US and 2.7% in the UK. Dominic King, head of Google Health in the UK, said that these are excellent results, considering that early diagnosis of cancer makes it easier to treat.