Forecasting new diseases in low-data settings using transfer learning

TL;DR

This paper explores how transfer learning from related diseases can improve early-stage outbreak predictions in low-data scenarios, combining empirical data analysis and theoretical modeling.

Contribution

It introduces transfer learning strategies for infectious disease forecasting, demonstrating their potential to enhance predictions with limited data and guiding source disease selection.

Findings

Transfer learning can improve disease forecasts in low-data settings.

Choosing the right source disease is crucial for effective transfer learning.

Models provide valuable insights for pandemic decision-making despite imperfections.

Abstract

Recent infectious disease outbreaks, such as the COVID-19 pandemic and the Zika epidemic in Brazil, have demonstrated both the importance and difficulty of accurately forecasting novel infectious diseases. When new diseases first emerge, we have little knowledge of the transmission process, the level and duration of immunity to reinfection, or other parameters required to build realistic epidemiological models. Time series forecasts and machine learning, while less reliant on assumptions about the disease, require large amounts of data that are also not available in early stages of an outbreak. In this study, we examine how knowledge of related diseases can help make predictions of new diseases in data-scarce environments using transfer learning. We implement both an empirical and a theoretical approach. Using empirical data from Brazil, we compare how well different machine learning models transfer knowledge between two different disease pairs: (i) dengue and Zika, and (ii) influenza and COVID-19. In the theoretical analysis, we generate data using different transmission and recovery rates with an SIR compartmental model, and then compare the effectiveness of different transfer learning methods. We find that transfer learning offers the potential to improve predictions, even beyond a model based on data from the target disease, though the appropriate source disease must be chosen carefully. While imperfect, these models offer an additional input for decision makers during pandemic response.