Can artificial intelligence predict future epidemics?
Before the first cases of COVID-19 were known, an algorithm based on artificial intelligence developed by a company in Canada had detected a new virus that was spreading in the Chinese city of Wuhan.
This demonstration of the potential of new technology applied to predict future epidemics led a group of researchers at the Universitat Oberta de Catalunya (UOC) and the University of the Balearic Islands (UIB) to use artificial intelligence (AI) to investigate a new predictability model. , and to evaluate how long the consequences of an epidemic last.
“The health crisis caused by COVID-19 shows that the epidemic is still a problem. We know there will be others in the future, but we don’t know what form they will take. However, we have a lot of useful information about past epidemics,” said Joana Maria Pujadas Mora, member of the Faculty of Arts and Humanities at UOC, and one of the principal investigators of the EPI-DESIGUAL research project. focus on problems.
The Pujadas team aims to use artificial intelligence, apply machine learning and natural language processing to perform large epidemic historical data analysis.
“The social sciences and historical demography are particularly important for making progress in predicting and fighting epidemics, and for assessing their consequences,” he said.
EPI-DESIGUAL Project – funded by Spanish Ministry of Science and Innovation – is being carried out in collaboration with the Center for Demographic Studies. It will analyze texts from official newspapers and daily newspapers relating to cholera, the 1918 flu pandemic and outbreaks published in Catalonia and the Balearic Islands between 1820 and 1960.
“The past is the best testing ground for preventing and preparing for future health crises which will unfortunately continue to emerge due to globalization, increased interactions between humans and animals, greater urbanization and climate change,” said Pujadas.
The 14 researchers currently working on the project are gathering all available information from archives for further analysis. The project will last for three years and, upon completion, the results will be published.
Increases predictability and ensures persistence
The aims of the research project are twofold. First, it seeks to innovate in the field of models for the predictability and progression of epidemics. Second, it aims to evaluate how long the effects of the epidemic last in the short, medium and long term in terms of socioeconomic inequality, which includes inequality in health behavior and demographics from a gender perspective.
“We want to know how the pandemic affects the birth rate, for example,” said Pujadas.
Ultimately, the researchers want the project to contribute to improving decision-making by the authorities so that they can implement relevant and effective measures in fighting the epidemic. Another goal is to help government public health policies contribute to reducing economic inequality.
The project results will indirectly contribute to a new data analysis paradigm, which seeks to understand reality through big data (which may or may not be structured). Many authors predict that scientific research projects such as EPI-DESIGUAL, which are based on data science and will have very innovative results, will replace the inductive reasoning methods prevailing in modern science.
