Forecasting new diseases in low-data settings using transfer learning. (August 2022)

• Record Type: Journal Article
• Authors: Roster, Kirstin; Connaughton, Colm; Rodrigues, Francisco A.
• Is Part Of: Chaos, solitons and fractals. Volume 161(2022)
• Publication Date: 2022-08
• Subjects: Transfer learning -- Machine learning -- Epidemic forecasting -- COVID-19 -- Zika; Chaotic behavior in systems -- Periodicals; Solitons -- Periodicals; Fractals -- Periodicals; Chaotic behavior in systems; Fractals; Solitons; Periodicals; 003.7
• DOI: 10.1016/j.chaos.2022.112306
• Languages: English
• ISSNs: 0960-0779

Abstract

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 synthetic approach. Using data from Brazil, we compare how well different machine learning models transfer knowledge between two different dataset pairs: case counts of (i) dengue and Zika, and (ii) influenza and COVID-19. In the synthetic analysis, we generate data with an SIR model using different transmission and recovery rates, 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 for pandemic response. Highlights: Comparing transfer learning with random forest & neural networks and instance-based & parameter transfer methods Predicting Zika and COVID-19 case counts and simulated data from an SIR compartmental model Transfer learning can help approximate or outperform machine learning models trained on larger dataset of the target disease NN models performed better for diseases with similar epidemiological parameters, RF for diseases with less similar parameters