Technology companies around the world are in full swing to tackle the coronavirus pandemic. Research has shown that 6.5% of COVID-19 patients can suddenly develop a serious illness, and among them the mortality rate can be as high as 49%. Therefore, one of the main tasks of the health authorities is to identify and treat patients who may experience severe or fatal syndromes at an early stage.
This has been done in a research team that Tencent AI Lab and a group of Chinese public health scientists led by Zhong Nanshan, the country's chief medical advisor for COVID-19, have set up since its inception in February.
This week, the team unveiled a deep learning model that can predict the risk of coronavirus patients developing a critical illness. The details were published in Nature Communications and reported how the laboratory developed the model based on a cohort of 1590 patients from 575 medical centers in China, with 1393 patients being further validated.
The shared laboratory made the predictor available online and enabled clinical personnel around the world to calculate the likelihood of patients developing a critical illness within 5, 10 and 30 days using ten clinical variables. While the immediate focus is on COVID-19, the long-term mission of the laboratory, in its own words, is "to use big data and AI for screening, prevention, and control, as well as warning of outbreaks, respiratory diseases, and breast diseases."
Other Chinese technology giants have started similar projects to contain the deadly virus. With machine-based and deep learning, Alibaba built a tool for institutions to predict the spread of COVID-19 with an alleged accuracy rate of 90%. Baidu has developed an open source algorithm for viral structural analysis and claims that the process is 120 times faster than the traditional method.
Tencent AI Lab is the tech giant's quest to stay afloat in a race to develop cutting-edge technology alongside money-making companies like video games and social networks. The research branch started in 2016 and deals with computer vision, speech recognition, natural language processing and machine learning by a team of 70 scientists and 300 engineers.
The laboratory competes with its local colleagues such as Alibabas Damo Academy and Baidu Research to hunt for the best AI minds in the world. This often means hiring an established scientist to attract young talent. In recent years, Baidu has suffered the loss of Andrew Ng and Lu Qi, and Tencent AI Lab also lost its leading character, Zhang Tong, last year.