Significance: Ordinary differential equations are a ubiquitous tool for modeling behaviors in science, such as gene regulation, biological rhythms, epidemics, and ecology. An important problem is to infer and characterize the uncertainty of parameters that govern equations. We present an accurate and fast inference method using manifold-constrained Gaussian processes, such that derivatives of the Gaussian process must satisfy the dynamics of the differential equations. Our method completely avoids the use of numerical integration and is thus fast to compute. Our construction is embedded in a principled statistical framework and is demonstrated to yield fast and reliable inference in a variety of practical problems. Our method works even when some system components are unobserved, which is a significant challenge for previous methods.
As the COVID-19 ravaging through the globe, accurate forecasts of the disease spread are crucial for situational awareness, resource allocation, and public health decision-making. Alternative to the traditional disease surveillance data collected by the United States (US) Centers for Disease Control and Prevention (CDC), big data from Internet such as online search volumes also contain valuable information for tracking infectious disease dynamics such as influenza epidemic. In this study, we develop a statistical model using Internet search volume of relevant queries to track and predict COVID-19 pandemic in the United States. Inspired by the strong association between COVID-19 death trend and symptom-related search queries such as “loss of taste”, we combine search volume information with COVID-19 time series information for US national level forecasts, while leveraging the cross-state cross-resolution spatial temporal framework, pooling information from search volume and COVID-19 reports across regions for state level predictions. Lastly, we aggregate the state-level frameworks in an ensemble fashion to produce the final state-level 4-week forecasts. Our method outperforms the baseline time-series model, while performing reasonably against other publicly available benchmark models for both national and state level forecast.
As the COVID-19 spread over the globe and new variants of COVID-19 keep occurring, reliable real-time forecasts of COVID-19 hospitalizations are critical for public health decisions on medical resources allocations. This paper aims to forecast future 2 weeks national and state-level COVID-19 new hospital admissions in the United States. Our method is inspired by the strong association between public search behavior and hospitalization admissions and is extended from a previously-proposed influenza tracking model, AutoRegression with GOogle search data (ARGO). Our LASSO-penalized linear regression method efficiently combines Google search information and COVID-19 related time series information with dynamic training and rolling window prediction. Compared to other publicly available models collected from COVID-19 forecast hub, our method achieves substantial error reduction in a retrospective out-of-sample evaluation from Jan 4, 2021, to Dec 27, 2021. Overall, we showed that our method is flexible, self-correcting, robust, accurate, and interpretable, making it a potentially powerful tool to assist healthcare officials and decision making for the current and future infectious disease outbreaks.
29 July 2019 in Clinical Pharmacology & Therapeutics
The global spread of COVID-19, the disease caused by the novel coronavirus SARS-CoV-2, has casted a significant threat to mankind. As the COVID-19 situation continues to evolve, predicting localized disease severity is crucial for advanced resource allocation. This paper proposes a method named COURAGE (COUnty aggRegation mixup AuGmEntation) to generate a short-term prediction of 2-week-ahead COVID-19 related deaths for each county in the United States, leveraging modern deep learning techniques. Specifically, our method adopts a self-attention model from Natural Language Processing, known as the transformer model, to capture both short-term and long-term dependencies within the time series while enjoying computational efficiency. Our model solely utilizes publicly available information for COVID-19 related confirmed cases, deaths, community mobility trends and demographic information, and can produce state-level predictions as an aggregation of the corresponding county-level predictions. Our numerical experiments demonstrate that our model achieves the state-of-the-art performance among the publicly available benchmark models.