A Comparison of Infectious Disease Forecasting Methods across Locations, Diseases, and Time

Journal Article · 28 January 2022 · Pathogens

DOI: https://doi.org/10.3390/pathogens11020185 · OSTI ID:1842680

Dixon, Samuel ^[1]; Keshavamurthy, Ravikiran  ^[2]; Farber, Daniel H. ^[1]; Stevens, Andrew ^[1]; Pazdernik, Karl T.  ^[3]; Charles, Lauren E.  ^[2]

---

1. Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
2. Pacific Northwest National Lab. (PNNL), Richland, WA (United States); Washington State Univ., Pullman, WA (United States)
3. Pacific Northwest National Lab. (PNNL), Richland, WA (United States); North Carolina State Univ., Raleigh, NC (United States)

Accurate infectious disease forecasting can inform efforts to prevent outbreaks and mitigate adverse impacts. This study compares the performance of statistical, machine learning (ML), and deep learning (DL) approaches in forecasting infectious disease incidences across different countries and time intervals. We forecasted three diverse diseases: campylobacteriosis, typhoid, and Q-fever, using a wide variety of features (n = 46) from public datasets, e.g., landscape, climate, and socioeconomic factors. We compared autoregressive statistical models to two tree-based ML models (extreme gradient boosted trees [XGB] and random forest [RF]) and two DL models (multi-layer perceptron and encoder–decoder model). The disease models were trained on data from seven different countries at the region-level between 2009–2017. Forecasting performance of all models was assessed using mean absolute error, root mean square error, and Poisson deviance across Australia, Israel, and the United States for the months of January through August of 2018. The overall model results were compared across diseases as well as various data splits, including country, regions with highest and lowest cases, and the forecasted months out (i.e., nowcasting, short-term, and long-term forecasting). Overall, the XGB models performed the best for all diseases and, in general, tree-based ML models performed the best when looking at data splits. There were a few instances where the statistical or DL models had minutely smaller error metrics for specific subsets of typhoid, which is a disease with very low case counts. Feature importance per disease was measured by using four tree-based ML models (i.e., XGB and RF with and without region name as a feature). The most important feature groups included previous case counts, region name, population counts and density, mortality causes of neonatal to under 5 years of age, sanitation factors, and elevation. This study demonstrates the power of ML approaches to incorporate a wide range of factors to forecast various diseases, regardless of location, more accurately than traditional statistical approaches.

• Research Organization: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
• Sponsoring Organization: USDOE
• Grant/Contract Number: AC05-76RL01830
• OSTI ID: 1842680
• Report Number(s): PNNL-SA-169380
• Journal Information: Pathogens, Journal Name: Pathogens Journal Issue: 2 Vol. 11; ISSN 2076-0817
• Publisher: MDPICopyright Statement
• Country of Publication: United States
• Language: English