Healthcare Informatics & Health Information Technology (SIG Health)

Paper Type

Complete

Paper Number

1723

Description

Coronavirus disease 2019 (COVID-19) is the most significant pandemic in the 21st century and affects the lives of millions of people today. By the end of 2020, more than 83 million cases were confirmed, and more than 1.6 million deaths were reported globally. Understanding how COVID-19 spreads across diverse communities is key to public health surveillance and management for such a devastating and highly infectious disease. Current studies mainly analyze either non-human factors or human factors, focusing on a limited number of variables that can influence COVID-19 transmission. However, in a real-world context, these factors interact with each other and collectively shape the infection rate. Therefore, a comprehensive study based on both non-human and human factors on a large scale is required to fully understand disease transmission. Here, we propose a research framework named Comprehensive Understanding via Representative Variable Exploration for COVID-19 (CURVE4COVID). With the accessibility of various data online, including COVID-19-related Google Trends (e.g., human search behavior) and government-managed data (e.g., weather, air pollution, economic indicators), we conduct a large-scale and multi-variable analysis of the critical factors for COVID-19 transmission, which can shed light on the complexity of infectious disease management. The results demonstrate that combining non-human and human factors provides better predictive power for infection rates than non-human factors or human factors alone. This study’s findings can provide new insights into disease transmission and help policymakers enhance preventative measures and healthcare management, thus having a far-reaching impact on society.

Share

COinS
Top 25 Percent Paper badge
 
Aug 9th, 12:00 AM

CURVE4COVID: Comprehensive Understanding via Representative Variable Exploration for COVID-19

Coronavirus disease 2019 (COVID-19) is the most significant pandemic in the 21st century and affects the lives of millions of people today. By the end of 2020, more than 83 million cases were confirmed, and more than 1.6 million deaths were reported globally. Understanding how COVID-19 spreads across diverse communities is key to public health surveillance and management for such a devastating and highly infectious disease. Current studies mainly analyze either non-human factors or human factors, focusing on a limited number of variables that can influence COVID-19 transmission. However, in a real-world context, these factors interact with each other and collectively shape the infection rate. Therefore, a comprehensive study based on both non-human and human factors on a large scale is required to fully understand disease transmission. Here, we propose a research framework named Comprehensive Understanding via Representative Variable Exploration for COVID-19 (CURVE4COVID). With the accessibility of various data online, including COVID-19-related Google Trends (e.g., human search behavior) and government-managed data (e.g., weather, air pollution, economic indicators), we conduct a large-scale and multi-variable analysis of the critical factors for COVID-19 transmission, which can shed light on the complexity of infectious disease management. The results demonstrate that combining non-human and human factors provides better predictive power for infection rates than non-human factors or human factors alone. This study’s findings can provide new insights into disease transmission and help policymakers enhance preventative measures and healthcare management, thus having a far-reaching impact on society.

When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.