Machine learning to track the coronavirus

Problems with tracking the Coronavirus

Coronaviruses are a family of hundreds of viruses that can cause fever, respiratory problems, and sometimes gastrointestinal symptoms too. The 2019 novel coronavirus, is one of seven members of this virus family known to infect humans. A pneumonia-like disease, the 2019 novel coronavirus has caused a global health emergency, sickened more than 31,000 people worldwide, and killed nearly 650 so far. The virus has a 2-14 day incubation period, so people could be infectious for quite a while before symptoms like fever, cough, or shortness of breath emerge. Scientists are still unsure of how many people are infected and there is no cure.

According to preliminary estimates from the Centers for Disease Control and Prevention, the 2019–2020 flu caused between 19 and 25 million illnesses and up to 25,000 deaths. The coronavirus numbers are harder to calculate because it’s not yet clear how many people are infected. So far, other countries have reported far fewer cases of coronavirus. But there is still widespread concern about the virus spreading. Researchers at Johns Hopkins University have created a visualization of the virus’s progress around the world based on official numbers and confirmed cases.

“Machine learning is a field of study that gives computers the capability to learn without being explicitly programmed”. Arthur Samuel

Machine Learning involves automating and improving the learning process of computers based on their experiences without being actually programmed i.e. without any human assistance. The process starts with feeding good quality data and then training the machines (computers) by building machine learning models using the data and different algorithms. The choice of algorithms depends on what type of data already available and configuring the computers to learn similar information, automatically.

Researchers around the world are applying machine-learning techniques to comb through social media posts, news reports, data from official public health channels, and information supplied by doctors for warning signs the virus is taking hold in countries outside of China as well as other data for subtle signs to detect whether the coronavirus may be spreading elsewhere.

Although it is unclear how widely the virus might yet travel, the biggest concern is that it could appear in countries with fewer health care resources to combat it.


Leave a Reply