Data science approaches to infectious disease surveillance

Area of Science:

• Data Science
• Infectious Disease Epidemiology
• Computational Social Science

Background:

• Large-scale infectious disease epidemics like COVID-19, HIV, swine flu, and Ebola necessitate advanced data science solutions.
• Recent decades have seen significant advancements in data analytics methodologies and the availability of rich human behavior data.
• Conventional public health research methods are insufficient for current epidemic challenges.

Purpose of the Study:

• To report interdisciplinary research on novel data science methodologies for infectious disease surveillance.
• To explore the application of big data and advanced analytics in combating infectious diseases, with a focus on COVID-19.
• To showcase innovative approaches enabled by human behavior data and information and communications technology.

Main Methods:

• Utilizing big data from human behaviors.
• Applying advanced data analytics and information and communications technology.
• Interdisciplinary research involving data science, computer science, computational social sciences, applied mathematics, statistics, physics, and public health.

Main Results:

• Presents 12 research papers and one review paper.
• Demonstrates innovative data science approaches for infectious disease surveillance.
• Highlights the potential of human behavior data in epidemic control.

Conclusions:

• Novel data science approaches are crucial for effective infectious disease surveillance.
• The integration of big data and advanced analytics offers powerful tools to combat epidemics.
• This interdisciplinary field holds significant promise for future public health challenges.