Tech companies around the world are overworked to help fight the coronavirus pandemic. Research has shown that 6.5% of patients with COVID-19 can suddenly progress to serious illness, and among them the death rate can reach 49%. One of the main tasks of health authorities, therefore, is to identify and treat patients who may develop serious or fatal syndromes early on.
This is what is underway within a research team jointly created by Tencent AI Lab and a group of Chinese public health scientists led by Zhong Nanshan, the country's senior medical adviser on COVID-19, since his premiered in February.
This week, the team unveiled a deep learning-based model that can predict the risk of coronavirus patients developing serious illness. Details were published in Nature Communications, telling how the lab designed the model based on a cohort of 1,590 patients from 575 medical centers in China, with additional validation from 1,393 patients.
The joint lab made the predictor available online, allowing clinical staff around the world to calculate patients' likelihood of developing severe disease within 5, 10 and 30 days using ten clinical variables. While its immediate focus is COVID-19, the lab's long-term mission, in its own words, is "to use big data and AI for screening, prevention and control, and alerting. cases of epidemics, respiratory diseases and thoracic diseases ".
Other Chinese tech giants have undertaken similar projects to contain the deadly virus. Using machine and deep learning, Alibaba has designed a tool for institutions to predict the spread of COVID-19 with an assumed accuracy rate of 90%. Baidu has opened a virus structural analysis algorithm, claiming that the process is 120 times faster than the traditional method.
Tencent AI Lab is the tech giant's effort to stay afloat in a race to develop cutting edge technologies alongside lucrative businesses like video games and social media. Launched in 2016, the research arm works on computer vision, speech recognition, natural language processing and machine learning thanks to a team of 70 researchers and 300 engineers.
The lab competes with local counterparts like Alibaba's Damo Academy and Baidu Research to hunt down the world's best AI minds. This often means hiring a well-established scientist to attract young talent. In recent years, Baidu has suffered from the departure of Andrew Ng and Lu Qi, and Tencent AI Lab also lost its main character Zhang Tong last year.
