Santiago Mazuelas publishes an article on the project Early Prognosis of Covid-19 Infections via Machine Learning

The article was published for the AXA Healthy Days event and the project is funded by the Axa Research Fund

Santiago Mazuelas, Ramón y Cajal researcher at the Basque Center for Applied Mathematics - BCAM, has contributed to the Axa Healthy Days event with the publication of an article on the project "Early prognosis of Covid-19 infections via Machine Learning" in which he works as principal investigator and in which other members of the centre collaborate: Ruben Armañanzas, Adrian Diaz and Jose Segovia. The project is funded by AXA Reserach Fund within the exceptional call "Mitigating risk in the aftermath of the COVID-19 pandemic".

The project, develops machine learning techniques for the early prognosis of COVID-19 infections that predict the future severity of infections using health data obtained shortly after detection. These algorithms can be used by healthcare or public health professionals to make decisions with favourable results.

The learning techniques developed in the project use a large number of electronic health records to learn the complex relationship between instances of health data and the severity of COVID-19.

Mazuelas explains in the article that one of the first algorithms developed is able to predict the risk of a fatal outcome when a new patient with COVID-19 is admitted to hospital with a sensitivity of 90% (true positive rate) and a specificity of 75% (true negative rate). Algorithms such as this are designed to become a key aid for healthcare providers in assessing incoming patients.

The full article can be accessed at the following link: https://virtualhealthdays.com/