During the COVID-19 pandemic, forecasting COVID-19 trends to support planning and response was a priority for scientists and decision makers alike. In the United States, COVID-19 forecasting was coordinated by a large group of universities, companies, and government entities led by the Centers for Disease Control and Prevention and the US COVID-19 Forecast Hub (https://covid19forecasthub.org). We evaluated approximately 9.7 million forecasts of weekly state-level COVID-19 cases for predictions 1-4 weeks into the future submitted by 24 teams from August 2020 to December 2021. We assessed coverage of central prediction intervals and weighted interval scores (WIS), adjusting for missing forecasts relative to a baseline forecast, and used a Gaussian generalized estimating equation (GEE) model to evaluate differences in skill across epidemic phases that were defined by the effective reproduction number. Overall, we found high variation in skill across individual models, with ensemble-based forecasts outperforming other approaches. Forecast skill relative to the baseline was generally higher for larger jurisdictions (e.g., states compared to counties). Over time, forecasts generally performed worst in periods of rapid changes in reported cases (either in increasing or decreasing epidemic phases) with 95% prediction interval coverage dropping below 50% during the growth phases of the winter 2020, Delta, and Omicron waves. Ideally, case forecasts could serve as a leading indicator of changes in transmission dynamics. However, while most COVID-19 case forecasts outperformed a naïve baseline model, even the most accurate case forecasts were unreliable in key phases. Further research could improve forecasts of leading indicators, like COVID-19 cases, by leveraging additional real-time data, addressing performance across phases, improving the characterization of forecast confidence, and ensuring that forecasts were coherent across spatial scales. In the meantime, it is critical for forecast users to appreciate current limitations and use a broad set of indicators to inform pandemic-related decision making.

Infectious disease burden is continuing to increase around the globe. These diseases have increased, in part, due to globalization, human behavior, and environmental changes. There is an urgent need for improved prediction of their spread so that mitigation techniques and treatments can be administered proactively rather than just reactively. One of the challenges is that many regions of interest are in hard-to-reach locations, and as such, clinical surveillance data (reliant upon self-reporting) can be both sparse and lagging. Remote sensing imagery is an attractive data source to exploit for this application as it provides real-time information without having to physically be on the ground. Here, we derive standard indices from multispectral imagery, and explore how predictive they are for forecasting dengue incidence in Brazil. This is done on broad spatial and temporal scales, covering all of Brazil for multiple years. Results will show that the normalized difference vegetation index is a leading predictor for dengue incidence.

Geotagging Twitter messages is an important tool for event detection and enrichment. Despite the availability of both social media content and user network information, these two features are generally utilized separately in the methodology. In this article, we create a hybrid method that uses Twitter content and network information jointly as model features. We use Gaussian mixture models to map the raw spatial distribution of the model features to a predicted field. This approach is scalable to large datasets and provides a natural representation of model confidence. Our method is tested against other approaches and we achieve greater prediction accuracy. The model also improves both precision and coverage.

Effective disease monitoring provides a foundation for effective public health systems. This has historically been accomplished with patient contact and bureaucratic aggregation, which tends to be slow and expensive. Recent internet-based approaches promise to be real-time and cheap, with few parameters. However, the question of when and how these approaches work remains open. We addressed this question using Wikipedia access logs and category links. Our experiments, replicable and extensible using our open source code and data, test the effect of semantic article filtering, amount of training data, forecast horizon, and model staleness by comparing across 6 diseases and 4 countries using thousands of individual models. We found that our minimal-configuration, language-agnostic article selection process based on semantic relatedness is effective for improving predictions, and that our approach is relatively insensitive to the amount and age of training data. We also found, in contrast to prior work, very little forecasting value, and we argue that this is consistent with theoretical considerations about the nature of forecasting. These mixed results lead us to propose that the currently observational field of internet-based disease surveillance must pivot to include theoretical models of information flow as well as controlled experiments based on simulations of disease.

Infectious diseases are one of the leading causes of morbidity and mortality around the world; thus, forecasting their impact is crucial for planning an effective response strategy. According to the Centers for Disease Control and Prevention (CDC), seasonal influenza affects 5% to 20% of the U.S. population and causes major economic impacts resulting from hospitalization and absenteeism. Understanding influenza dynamics and forecasting its impact is fundamental for developing prevention and mitigation strategies. We combine modern data assimilation methods with Wikipedia access logs and CDC influenza-like illness (ILI) reports to create a weekly forecast for seasonal influenza. The methods are applied to the 2013-2014 influenza season but are sufficiently general to forecast any disease outbreak, given incidence or case count data. We adjust the initialization and parametrization of a disease model and show that this allows us to determine systematic model bias. In addition, we provide a way to determine where the model diverges from observation and evaluate forecast accuracy. Wikipedia article access logs are shown to be highly correlated with historical ILI records and allow for accurate prediction of ILI data several weeks before it becomes available. The results show that prior to the peak of the flu season, our forecasting method produced 50% and 95% credible intervals for the 2013-2014 ILI observations that contained the actual observations for most weeks in the forecast. However, since our model does not account for re-infection or multiple strains of influenza, the tail of the epidemic is not predicted well after the peak of flu season has passed.

Infectious disease is a leading threat to public health, economic stability, and other key social structures. Efforts to mitigate these impacts depend on accurate and timely monitoring to measure the risk and progress of disease. Traditional, biologically-focused monitoring techniques are accurate but costly and slow; in response, new techniques based on social internet data, such as social media and search queries, are emerging. These efforts are promising, but important challenges in the areas of scientific peer review, breadth of diseases and countries, and forecasting hamper their operational usefulness. We examine a freely available, open data source for this use: access logs from the online encyclopedia Wikipedia. Using linear models, language as a proxy for location, and a systematic yet simple article selection procedure, we tested 14 location-disease combinations and demonstrate that these data feasibly support an approach that overcomes these challenges. Specifically, our proof-of-concept yields models with r2 up to 0.92, forecasting value up to the 28 days tested, and several pairs of models similar enough to suggest that transferring models from one location to another without re-training is feasible. Based on these preliminary results, we close with a research agenda designed to overcome these challenges and produce a disease monitoring and forecasting system that is significantly more effective, robust, and globally comprehensive than the current state of the art.