Weeks-Ahead Epidemiological Predictions of Varicella Cases From Univariate Time Series Data Applying Artificial Intelligence

Abstract

Background “Chickenpox” is a highly infectious disease caused by the varicella-zoster virus, influenced by seasonal and spatial factors. Dealing with varicella-zoster epidemics can be a substantial drain on health-authority resources. Methods that improve the ability to locally predict case numbers from time-series data sets every week are therefore worth developing. Methods Simple-to-extract trend attributes from published univariate weekly case-number univariate data sets were used to generate multivariate data for Hungary covering 10 years. That attribute-enhanced data set was assessed by machine learning (ML) and deep learning (DL) models to generate weekly case forecasts from next week (t0) to 12 weeks forward (t+12). The ML and DL predictions were compared with those generated by multilinear regression and univariate prediction methods. Results Support vector regression generates the best predictions for weeks t0 and t+1, whereas extreme gradient boosting generates the best predictions for weeks t+3 to t+12. Long-short-term memory only provides comparable prediction accuracy to the ML models for week t+12. Multi–K-fold cross validation reveals that overall the lowest prediction uncertainty is associated with the tree-ensemble ML models. Conclusion The novel trend-attribute method offers the potential to reduce prediction errors and improve transparency for chickenpox time series.

Spatio-Temporal Attributes of Varicella-Zoster Case Number Trends Assist with Optimizing Machine Learning Predictions

“…These models are selected because they apply mathematically distinct methods and can be rapidly executed with relatively few control variables. They have also performed well with the national VZV case trend data from the compiled dataset [6].…”

“…Chickenpox and shingles collectively represent a substantial burden on health authorities' resources in many countries [5]. Hence, methods that provide reliable short-term, VZV case forecasts, locally and nationally [6], from historical case-trend records of past recent weeks are beneficial for resource and response planning.…”

“…It offers a more transparent approach to short-term time-series forecasting with a range of data mining capabilities. This study further develops the trendattribute method applied to provide national weekly case forecasts for Hungary [6] from a published dataset of VZV weekly case trends [15] by considering spatial as well as temporal components of the historical case numbers. This approach provides reliable, more geographically focused, regional weeks-ahead case forecasts incorporating spatially influential case-trend information.…”