China has developed an AI model for screening for esophageal cancer

Chinese scientists have created an artificial intelligence model Damo Eagle for screening for esophageal cancer. It's from sb.by.

As TASS notes with reference to the technology corporation Alibaba, the model was jointly developed by the research division of Alibaba - Damo Academy, Sichuan Cancer Hospital and Sun Yat-sen University Cancer Center.

The model does not require intubation or the introduction of a contrast agent. It is enough to analyze a standard CT scan of the chest to identify the risk of esophageal cancer, including early stages and precancerous lesions.

The sensitivity of the model in cases of esophageal cancer (the probability that the patient will be classified as a patient) reaches 90%, and the sensitivity in precancerous lesions with very weak signals is 52.5%. The specificity of the model (the probability that non-diseased subjects will be identified as non-diseased) reaches 99.2%.

The development has already been tested on more than 80,000 cases in three countries. A scientific article dedicated to this model was published in the international medical journal Nature Medicine. According to statistics from the National Cancer Center of China, about 220,000 new cases of esophageal cancer are diagnosed in China each year, of which 190,000 are fatal. Hong Kong is developing a new method of early diagnosis of oncology with the prospect of implementation in two years

In Thailand began clinical trials of personalized cancer vaccine