What is it about?
Crimean-Congo Hemorrhagic Fever (CCHF) is a disease that is spread by ticks and is heavily influenced by climate patterns. It is also listed as a high-priority disease among international health organizations. We propose an approach to use time-series classification and deep learning to predict outbreaks of CCHF in high-risk countries by detecting patterns in temperature and precipitation levels over time.
Featured Image
Photo by Erik Karits on Unsplash
Why is it important?
Our results prove that temporal climate trends can be used to accurately predict CCHF outbreaks in high-risk countries. This work can aid the prediction efforts when it comes to analyzing these types of diseases. With additional knowledge, residents of high-risk countries will be better prepared for future outbreaks.
Perspectives
Working on this project alongside the co-authors was a tremendous learning experience and it was a pleasure working for them. This work showcases the ability to use today's deep learning methods to help solve important real-world problems and potentially aid those in need.
Jonathan Harris
Rensselaer Polytechnic Institute
Read the Original
This page is a summary of: Predicting Crimean-Congo Hemorrhagic Fever Outbreaks via Multivariate Time-Series Classification of Climate Data, May 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3545729.3545772.
You can read the full text:
Contributors
The following have contributed to this page
