Alibaba says AI Can Detect Coronavirus Infections with Over 90% Accuracy

As the Coronavirus continues to spread globally, it’s emerged that a new AI-powered diagnosis system promises to detect new Covid-19 cases with an accuracy rate of up to 96% via computerized tomography scans.

Chinese tech outlet Sina Tech News reports the diagnosis algorithm was developed by Alibaba’s research institute Damo Academy.

Researchers at the academy say they have trained the AI model with sample data from more than 5,000 confirmed cases, adding that the system could identify differences in CT scans between patients infected with the novel virus and those with ordinary viral pneumonia with an accuracy of up to 96%.

The algorithm which includes the latest treatment guidelines and recently published research was first introduced in the new Qiboshan Hospital in Zhengzhou, Henan province modeled on Beijing’s Xiaotangshan Hospital, completed in 2003 to deal with the SARS crisis.

According to Alibaba, the new algorithm could alleviate pressure on hospitals, as it can complete the recognition process within 20 seconds,

Usually, it will take a doctor between five and 15 minutes to analyze a CT scan of one suspected patient and give a clinical diagnosis, with scans sometimes including more than 300 images.

This new diagnosis system is not Alibaba’s first attempt to use AI to combat coronavirus.

Researchers from Damo Academy have developed an AI-powered public health service tool that provides information related to the SARS-CoV-2 coronavirus, which was first deployed by the government of Zhejiang province on 27 January.

The system can answer most inquiries regarding the pandemic via an app.