Machine learning improved Greece’s border screening for COVID-19 – Community News
Covid-19

Machine learning improved Greece’s border screening for COVID-19

The Daily Pennsylvanian is a student-run non-profit organization.

Please support us by disabling your adblocker on our site.

hamsa bastani

A study by Penn Assistant Professor of Operations, Information, and Decisions Hamsa Bastani found that the application of machine learning made COVID-19 screening at the Greek border more efficient (photo from School of Engineering and Applied Science).

A study by a Penn researcher found that the application of machine learning made COVID-19 screening at the Greek border more efficient.

Penn Assistant Professor of Operations, Information, and Decisions Hamsa Bastani collaborated with Greek researchers in the summer of 2020 to evaluate the effectiveness of Eva, a machine learning tool designed to update data on travelers’ COVID-19 screening results. along with demographic information and region of origin, Penn’s Leonard Davis Institute of Health Economics reported.

By tracking this information, Eva was able to identify areas of immediate concern for COVID-19. According to the study, officials targeted individuals from these areas for random testing and quarantine mandates at a time when rapid testing was not very accessible in Greece.

Eva refines his algorithm and predictions to be more accurate by collecting data over time. The study reported that the reinforcement learning system enabled Greek border officials to identify up to four times as many asymptomatic COVID-19 cases compared to random testing strategies used in other countries.

Researchers of the study believe Eva has also given the Greek government a financial boost by reducing the number of tests it would have taken to effectively reduce transmission risk through random sampling by up to 85 percent, LDI reported.

The study compared the effectiveness of machine learning strategies in identifying travelers who should be prioritized in testing with the effectiveness of more traditional data analysis methods, such as comparing the per capita average, hospitalization and death rates of different locations.

Data from the study showed that Eve was up to 1.45 times more effective at detecting asymptomatic coronavirus cases compared to the more traditional approaches.

Researchers on the study made Eva’s code open source so that machine learning could become a more commonplace tool in border screening strategies and so countries can tailor the software to their own needs and circumstances, LDI reported.

Bastani and the other researchers involved in this project aim to improve COVID-19 screening measures at borders around the world to lower international transmission rates and reduce the risks of travel during a pandemic, LDI reported.


About the author

Rakesh

Add Comment

Click here to post a comment