JÉSSICA VILLAR DE ASSUMPÇÃO
Título: Lessons learned from the COVID-19 pandemic in Latin America: a Data Science standpoint
Data: 02/09/2024, 9h
Sala Zoom : https://puc-rio.zoom.us/my/paulamacaira?pwd=V2xvYmFlTUQ3MExtUHJ4L09KZnZ2UT09
Orientadores: Paula Medina Maçaira Louro | PUC-Rio & Fernanda Araujo Baião Amorim | PUC-Rio
Resumo: In the 21st century alone, the world faced the devastating impacts of three acute respiratory diseases: the Middle East Respiratory Syndrome (MERS), the Severe Acute Respiratory Syndrome (SARS), and COVID-19, which evolved to be a pandemic. These illnesses not only caused a huge number of deaths but also damaged the Economy of the affected regions. In particular, countries in the Latin America and Caribbean (LAC) region faced additional challenges, due to higher social inequalities, limited access to health services, and precarious living conditions. It is thus imperative to establish solid guidelines to guide actions towards mitigating health and socioeconomic impacts, if (or when) new acute respiratory diseases emerge, especially in these countries. We conducted a retrospective study to model the dynamics of the variation of COVID-19 mortality in LAC countries and analyze its association with vaccination strategies, containment measures, mobility restrictions, and socioeconomic factors. Our methodology applied clustering techniques which revealed two distinct groupings based on socio-demographic characteristics, followed by the application of XGBoost to model the dynamics of variation in deaths in the countries of each cluster, over time. Lastly, we applied SHAP Values to highlight the associations between mortality and factors such as vaccination, containment measures, and mobility restrictions. We provide evidence that the economic support and the completion of the vaccination schedule were especially relevant to reducing mortality from COVID-19.