Researchers at the University of Texas Southwestern Medical Center used a new machine learning technique to estimate the actual number of coronavirus cases within 50 US States and 50 countries.
The study, published in the journal PLOS One , revealed that during the ongoing pandemic, US States and many countries have reported daily counts of Covid-19 infections and deaths confirmed by testing.
However, many infections have gone undetected, resulting in under-counting of the total number of people currently infected at any given point in time. The authors of the study believe that this is an important metric to guide public health efforts.
For the new study, the researchers Jungsik Noh and Gaudenz Danuser have developed a computational model that uses machine-learning strategies to estimate the actual daily number of current infections.
Researchers developing smartphone-based Covid-19 test
To make the calculations, the model draws on previously published pandemic parameters and publicly available daily data on confirmed cases and deaths. Visualisations of these daily estimates are freely available online, the study noted.
The model’s estimates indicate severe undercounting of cases across the US and worldwide.
The cumulative number of actual cases in 9 out of 50 countries is estimated to be at least five times higher than confirmed cases.
For some countries, such as the US, Belgium, and the UK, estimates indicate that more than 20 per cent of the total population has experienced Covid-19 infection.
The authors stated in the study: “Given that the confirmed cases only capture the tip of the iceberg in the middle of the pandemic, the estimated sizes of current infections in this study provide crucial information to determine the regional severity of Covid-19 that can be misguided by the confirmed cases.”