Physics-informed deep learning for infectious disease forecasting

TL;DR

This paper introduces a physics-informed neural network model for infectious disease forecasting that integrates epidemiological theory with data, outperforming many existing deep learning models and matching complex benchmarks with a simpler structure.

Contribution

The paper presents a novel PINN-based approach for disease forecasting that embeds compartmental models into neural networks, enhancing accuracy and interpretability.

Findings

PINN model accurately predicts COVID-19 cases, deaths, and hospitalizations.

Outperforms naive and several deep learning models like RNNs, LSTMs, GRUs, and Transformers.

Achieves comparable performance to complex Gaussian infection models with simpler implementation.

Abstract

Accurate forecasting of contagious diseases is critical for public health policymaking and pandemic preparedness. We propose a new infectious disease forecasting model based on physics-informed neural networks (PINNs), an emerging scientific machine learning approach. By embedding a compartmental model into the loss function, our method integrates epidemiological theory with data, helping to prevent model overfitting. We further enhance the model with a sub-network that accounts for covariates such as mobility and cumulative vaccine doses, which influence the transmission rate. Using state-level COVID-19 data from California, we demonstrate that the PINN model accurately predicts cases, deaths, and hospitalizations, aligning well with existing benchmarks. Notably, the PINN model outperforms naive baseline forecasts and several sequence deep learning models, including Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRUs), and Transformers. It also achieves performance comparable to a sophisticated Gaussian infection state forecasting model that combines compartmental dynamics, a data observation model, and parameter regression. However, the PINN model features a simpler structure and is easier to implement. In summary, we systematically evaluate the PINN model's ability to forecast infectious disease dynamics, demonstrating its potential as an efficient computational tool to strengthen forecasting capabilities.