Explore the vast range of titles available.

Estimation of influenza-like illness (ILI) using search trends activity was intended to supplement traditional surveillance systems, and was a motivation behind the development of Google Flu Trends (GFT). However, several studies have previously reported large errors in GFT estimates of ILI in the US. Following recent release of time-stamped surveillance data, which better reflects real-time operational scenarios, we reanalyzed GFT errors. Using three data sources-GFT: an archive of weekly ILI estimates from Google Flu Trends; ILIf: fully-observed ILI rates from ILINet; and, ILIp: ILI rates available in real-time based on partial reporting-five influenza seasons were analyzed and mean square errors (MSE) of GFT and ILIp as estimates of ILIf were computed. To correct GFT errors, a random forest regression model was built with ILI and GFT rates from the previous three weeks as predictors. An overall reduction in error of 44% was observed and the errors of the corrected GFT are lower than those of ILIp. An 80% reduction in error during 2012/13, when GFT had large errors, shows that extreme failures of GFT could have been avoided. Using autoregressive integrated moving average (ARIMA) models, one- to four-week ahead forecasts were generated with two separate data streams: ILIp alone, and with both ILIp and corrected GFT. At all forecast targets and seasons, and for all but two regions, inclusion of GFT lowered MSE. Results from two alternative error measures, mean absolute error and mean absolute proportional error, were largely consistent with results from MSE. Taken together these findings provide an error profile of GFT in the US, establish strong evidence for the adoption of search trends based 'nowcasts' in influenza forecast systems, and encourage reevaluation of the utility of this data source in diverse domains.

The COVID-19 pandemic disrupted health systems and economies throughout the world during 2020 and was particularly devastating for the United States, which experienced the highest numbers of reported cases and deaths during 2020 1 – 3 . Many of the epidemiological features responsible for observed rates of morbidity and mortality have been reported 4 – 8 ; however, the overall burden and characteristics of COVID-19 in the United States have not been comprehensively quantified. Here we use a data-driven model-inference approach to simulate the pandemic at county-scale in the United States during 2020 and estimate critical, time-varying epidemiological properties underpinning the dynamics of the virus. The pandemic in the United States during 2020 was characterized by national ascertainment rates that increased from 11.3% (95% credible interval (CI): 8.3–15.9%) in March to 24.5% (18.6–32.3%) during December. Population susceptibility at the end of the year was 69.0% (63.6–75.4%), indicating that about one third of the US population had been infected. Community infectious rates, the percentage of people harbouring a contagious infection, increased above 0.8% (0.6–1.0%) before the end of the year, and were as high as 2.4% in some major metropolitan areas. By contrast, the infection fatality rate fell to 0.3% by year’s end. Data-driven modelling including numbers of cases and population movements is used to simulate the COVID-19 pandemic in the United States in 2020, providing insights into the transmission of the disease.

With the availability of multiple Coronavirus Disease 2019 (COVID-19) vaccines and the predicted shortages in supply for the near future, it is necessary to allocate vaccines in a manner that minimizes severe outcomes, particularly deaths. To date, vaccination strategies in the United States have focused on individual characteristics such as age and occupation. Here, we assess the utility of population-level health and socioeconomic indicators as additional criteria for geographical allocation of vaccines. County-level estimates of 14 indicators associated with COVID-19 mortality were extracted from public data sources. Effect estimates of the individual indicators were calculated with univariate models. Presence of spatial autocorrelation was established using Moran's I statistic. Spatial simultaneous autoregressive (SAR) models that account for spatial autocorrelation in response and predictors were used to assess (i) the proportion of variance in county-level COVID-19 mortality that can explained by identified health/socioeconomic indicators (R.sup.2 ); and (ii) effect estimates of each predictor. Significant spatial autocorrelation exists in COVID-19 mortality in the US, and population health/socioeconomic indicators account for a considerable variability in county-level mortality. In the context of vaccine rollout in the US and globally, national and subnational estimates of burden of disease could inform optimal geographical allocation of vaccines.

Background Supervised learning methods need annotated data in order to generate efficient models. Annotated data, however, is a relatively scarce resource and can be expensive to obtain. For both passive and active learning methods, there is a need to estimate the size of the annotated sample required to reach a performance target. Methods We designed and implemented a method that fits an inverse power law model to points of a given learning curve created using a small annotated training set. Fitting is carried out using nonlinear weighted least squares optimization. The fitted model is then used to predict the classifier's performance and confidence interval for larger sample sizes. For evaluation, the nonlinear weighted curve fitting method was applied to a set of learning curves generated using clinical text and waveform classification tasks with active and passive sampling methods, and predictions were validated using standard goodness of fit measures. As control we used an un-weighted fitting method. Results A total of 568 models were fitted and the model predictions were compared with the observed performances. Depending on the data set and sampling method, it took between 80 to 560 annotated samples to achieve mean average and root mean squared error below 0.01. Results also show that our weighted fitting method outperformed the baseline un-weighted method (p < 0.05). Conclusions This paper describes a simple and effective sample size prediction algorithm that conducts weighted fitting of learning curves. The algorithm outperformed an un-weighted algorithm described in previous literature. It can help researchers determine annotation sample size for supervised machine learning.

As the COVID-19 pandemic continues to unfold, the infection-fatality risk (ie, risk of death among all infected individuals including those with asymptomatic and mild infections) is crucial for gauging the burden of death due to COVID-19 in the coming months or years. Here, we estimate the infection-fatality risk of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in New York City, NY, USA, the first epidemic centre in the USA, where the infection-fatality risk remains unclear. In this model-based analysis, we developed a meta-population network model-inference system to estimate the underlying SARS-CoV-2 infection rate in New York City during the 2020 spring pandemic wave using available case, mortality, and mobility data. Based on these estimates, we further estimated the infection-fatality risk for all ages overall and for five age groups (<25, 25–44, 45–64, 65–74, and ≥75 years) separately, during the period March 1 to June 6, 2020 (ie, before the city began a phased reopening). During the period March 1 to June 6, 2020, 205 639 people had a laboratory-confirmed infection with SARS-CoV-2 and 21 447 confirmed and probable COVID-19-related deaths occurred among residents of New York City. We estimated an overall infection-fatality risk of 1·39% (95% credible interval 1·04–1·77) in New York City. Our estimated infection-fatality risk for the two oldest age groups (65–74 and ≥75 years) was much higher than the younger age groups, with a cumulative estimated infection-fatality risk of 0·116% (0·0729–0·148) for those aged 25–44 years and 0·939% (0·729–1·19) for those aged 45–64 years versus 4·87% (3·37–6·89) for those aged 65–74 years and 14·2% (10·2–18·1) for those aged 75 years and older. In particular, weekly infection-fatality risk was estimated to be as high as 6·72% (5·52–8·01) for those aged 65–74 years and 19·1% (14·7–21·9) for those aged 75 years and older. Our results are based on more complete ascertainment of COVID-19-related deaths in New York City than other places and thus probably reflect the true higher burden of death due to COVID-19 than that previously reported elsewhere. Given the high infection-fatality risk of SARS-CoV-2, governments must account for and closely monitor the infection rate and population health outcomes and enact prompt public health responses accordingly as the COVID-19 pandemic unfolds. National Institute of Allergy and Infectious Diseases, National Science Foundation Rapid Response Research Program, and New York City Department of Health and Mental Hygiene.

Surveillance of COVID-19 is challenging but critical for mitigating disease, particularly if predictive of future disease burden. We report a robust multiyear lead-lag association between internet search activity for loss of smell or taste and COVID-19-associated hospitalization and deaths. These search data could help predict COVID-19 surges.

Influenza infects an estimated 9–35 million individuals each year in the United States and is a contributing cause for between 12,000 and 56,000 deaths annually. Seasonal outbreaks of influenza are common in temperate regions of the world, with highest incidence typically occurring in colder and drier months of the year. Real-time forecasts of influenza transmission can inform public health response to outbreaks. We present the results of a multiinstitution collaborative effort to standardize the collection and evaluation of forecasting models for influenza in the United States for the 2010/2011 through 2016/2017 influenza seasons. For these seven seasons, we assembled weekly real-time forecasts of seven targets of public health interest from 22 different models. We compared forecast accuracy of each model relative to a historical baseline seasonal average. Across all regions of the United States, over half of the models showed consistently better performance than the historical baseline when forecasting incidence of influenza-like illness 1 wk, 2 wk, and 3 wk ahead of available data and when forecasting the timing and magnitude of the seasonal peak. In some regions, delays in data reporting were strongly and negatively associated with forecast accuracy. More timely reporting and an improved overall accessibility to novel and traditional data sources are needed to improve forecasting accuracy and its integration with real-time public health decision making.

Deaths by suicide, as well as suicidal ideations, plans and attempts, have been increasing in the US for the past two decades. Deployment of effective interventions would require timely, geographically well-resolved estimates of suicide activity. In this study, we evaluated the feasibility of a two-step process for predicting suicide mortality: a) generation of hindcasts , mortality estimates for past months for which observational data would not have been available if forecasts were generated in real-time; and b) generation of forecasts with observational data augmented with hindcasts. Calls to crisis hotline services and online queries to the Google search engine for suicide-related terms were used as proxy data sources to generate hindcasts. The primary hindcast model ( auto ) is an Autoregressive Integrated Moving average model (ARIMA), trained on suicide mortality rates alone. Three regression models augment hindcast estimates from auto with call rates ( calls ), GHT search rates ( ght ) and both datasets together ( calls_ght ). The 4 forecast models used are ARIMA models trained with corresponding hindcast estimates. All models were evaluated against a baseline random walk with drift model. Rolling monthly 6-month ahead forecasts for all 50 states between 2012 and 2020 were generated. Quantile score (QS) was used to assess the quality of the forecast distributions. Median QS for auto was better than baseline (0.114 vs. 0.21. Median QS of augmented models were lower than auto , but not significantly different from each other (Wilcoxon signed-rank test, p > .05). Forecasts from augmented models were also better calibrated. Together, these results provide evidence that proxy data can address delays in release of suicide mortality data and improve forecast quality. An operational forecast system of state-level suicide risk may be feasible with sustained engagement between modelers and public health departments to appraise data sources and methods as well as to continuously evaluate forecast accuracy.

Recent research has produced a number of methods for forecasting seasonal influenza outbreaks. However, differences among the predicted outcomes of competing forecast methods can limit their use in decision-making. Here, we present a method for reconciling these differences using Bayesian model averaging. We generated retrospective forecasts of peak timing, peak incidence, and total incidence for seasonal influenza outbreaks in 48 states and 95 cities using 21 distinct forecast methods, and combined these individual forecasts to create weighted-average superensemble forecasts. We compared the relative performance of these individual and superensemble forecast methods by geographic location, timing of forecast, and influenza season. We find that, overall, the superensemble forecasts are more accurate than any individual forecast method and less prone to producing a poor forecast. Furthermore, we find that these advantages increase when the superensemble weights are stratified according to the characteristics of the forecast or geographic location. These findings indicate that different competing influenza prediction systems can be combined into a single more accurate forecast product for operational delivery in real time.

Seasonal influenza results in substantial annual morbidity and mortality in the United States and worldwide. Accurate forecasts of key features of influenza epidemics, such as the timing and severity of the peak incidence in a given season, can inform public health response to outbreaks. As part of ongoing efforts to incorporate data and advanced analytical methods into public health decision-making, the United States Centers for Disease Control and Prevention (CDC) has organized seasonal influenza forecasting challenges since the 2013/2014 season. In the 2017/2018 season, 22 teams participated. A subset of four teams created a research consortium called the FluSight Network in early 2017. During the 2017/2018 season they worked together to produce a collaborative multi-model ensemble that combined 21 separate component models into a single model using a machine learning technique called stacking. This approach creates a weighted average of predictive densities where the weight for each component is determined by maximizing overall ensemble accuracy over past seasons. In the 2017/2018 influenza season, one of the largest seasonal outbreaks in the last 15 years, this multi-model ensemble performed better on average than all individual component models and placed second overall in the CDC challenge. It also outperformed the baseline multi-model ensemble created by the CDC that took a simple average of all models submitted to the forecasting challenge. This project shows that collaborative efforts between research teams to develop ensemble forecasting approaches can bring measurable improvements in forecast accuracy and important reductions in the variability of performance from year to year. Efforts such as this, that emphasize real-time testing and evaluation of forecasting models and facilitate the close collaboration between public health officials and modeling researchers, are essential to improving our understanding of how best to use forecasts to improve public health response to seasonal and emerging epidemic threats.