Back

Risk map of the novel coronavirus (2019-nCoV) in China: proportionate control is needed

Li, X.; Zhao, X.; Lou, Y.; Sun, Y.

2020-02-18 epidemiology
10.1101/2020.02.16.20023838 medRxiv
Show abstract

BackgroundChina is running a national level antivirus campaign against the novel coronavirus (2019-nCoV). Strict control measures are being enforced in either the populated areas and remote regions. While the virus is closed to be under control, tremendous economic loss has been caused. Methods and findingsWe assessed the pandemic risk of 2019-nCoV for all cities/regions in China using the random forest algorithm, taking into account the effect of five factors: the accumulative and increased numbers of confirmed cases, total population, population density, and GDP. We defined four levels of the risk, corresponding to the four response levels to public health emergencies in China. The classification system has good consistency among cities in China, as the error rate of the confusion matrix is 1.58%. ConclusionsThe pandemic risk of 2019-nCoV is dramatically different among the 442 cities/regions. We recommend to adopt proportionate control policy according to the risk level to reduce unnecessary economic loss.

Matching journals

The top 12 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.