Researchers have developed a computer model that predicts how the novel coronavirus spreads in US cities. The model looks at three factors that play a role in infection risk: where people go during the day, how long they stay, and how many other people are visiting the same place at the same time. It found that most cases of the virus occur at'superspreader' sites, such as coffee shops, full-service restaurants and gyms, where people are close together for extended periods of time. However, limiting capacity in these locations could reduce the number of infections by as much as 75 percent. The team, from Stanford University School of Engineering, says its model can be used as a tool for officials to determine the tradeoff between new infections and reopening businesses, even at limited capacity.

With the coronavirus growing more deadly in China, artificial intelligence researchers are applying machine-learning techniques to social media, web, and other data for subtle signs that the disease may be spreading elsewhere. The new virus emerged in Wuhan, China, in December, triggering a global health emergency. It remains uncertain how deadly or contagious the virus is, and how widely it might have already spread. Infections and deaths continue to rise. More than 31,000 people have now contracted the disease in China, and 630 people have died, according to figures released by authorities there Friday.

Sokhela has both HIV and tuberculosis -- a brutal, one-two punch that's exacerbating epidemics of both diseases in South Africa. In most places in the country, where clinics are overtaxed, this would presage a wait of up to 10 hours. But here something different is happening. Staffers at computer monitors swiftly log in people and dispatch them for triage or, if they have tuberculosis, a special area away from others. Those who only need their antiretroviral (ARV) drugs walk directly to the pharmacists, who retrieve each patient's electronic medical record and use a robotic system to pull drugs from shelves and fill orders.