Influenza-like Illness Data Research Articles

Two Peaks of Seasonal Influenza Epidemics - China, 2023.

Influenza is a communicable respiratory disease that causes annual epidemics and occasional unpredictable pandemics. This study examines the occurrence of two unexpected influenza peaks within the year 2023. Influenza-like illness (ILI) data were reported, and specimens of ILI were collected by designated surveillance hospitals. Positive cases were confirmed using real-time reverse transcription polymerase chain reaction (rRT-PCR) testing conducted at national surveillance network laboratories. The data were then submitted to the Chinese Influenza Surveillance Information System. From December 2022 to January 2023, influenza activity was minimal until a spring epidemic began in February, peaking in late March. The outbreak spread from the north to the south, with A(H1N1)pdm09 being the predominant strain and A(H3N2) also circulating concurrently. The positivity rate in northern and southern provincial-level administrative divisions (PLADs) reached 60.0% (week 10) and 60.2% (week 13), respectively, before dropping to below 5% from May to August. Subsequently, rates surged starting in week 41 in the south and week 44 in the north, peaking at 54.4% (week 50) and 44.0% (week 49), respectively, and remained high until the end of 2023. A(H3N2) became the prevailing strain, with a notable increase in B/Victoria lineage viruses from December, resulting in two peaks during the 2023 influenza season. The pattern of the influenza epidemic shifted due to the coronavirus disease 2019 (COVID-19) outbreak and is gradually returning to its usual seasonal and intensity patterns. It is, therefore, crucial to continuously strengthen influenza surveillance, enhance the influenza surveillance network, and lay the groundwork for advancing integrated surveillance of multiple pathogens in China.

Predicting seasonal influenza outbreaks with regime shift-informed dynamics for improved public health preparedness

In this study, we propose a novel approach that integrates regime-shift detection with a mechanistic model to forecast the peak times of seasonal influenza. The key benefit of this approach is its ability to detect regime shifts from non-epidemic to epidemic states, which is particularly beneficial with the year-round presence of non-zero Influenza-Like Illness (ILI) data. This integration allows for the incorporation of external factors that trigger the onset of the influenza season-factors that mechanistic models alone might not adequately capture. Applied to ILI data collected in Korea from 2005 to 2020, our method demonstrated stable peak time predictions for seasonal influenza outbreaks, particularly in years characterized by unusual onset times or epidemic magnitudes.

Development of a novel dynamic nosocomial infection risk management method for COVID-19 in outpatient settings

BackgroundApplication of accumulated experience and management measures in the prevention and control of coronavirus disease 2019 (COVID-19) has generally depended on the subjective judgment of epidemic intensity, with the quality of prevention and control management being uneven. The present study was designed to develop a novel risk management system for COVID-19 infection in outpatients, with the ability to provide accurate and hierarchical control based on estimated risk of infection.MethodsInfection risk was estimated using an auto regressive integrated moving average model (ARIMA). Weekly surveillance data on influenza-like-illness (ILI) among outpatients at Xuanwu Hospital Capital Medical University and Baidu search data downloaded from the Baidu Index in 2021 and 22 were used to fit the ARIMA model. The ability of this model to estimate infection risk was evaluated by determining the mean absolute percentage error (MAPE), with a Delphi process used to build consensus on hierarchical infection control measures. COVID-19 control measures were selected by reviewing published regulations, papers and guidelines. Recommendations for surface sterilization and personal protection were determined for low and high risk periods, with these recommendations implemented based on predicted results.ResultsThe ARIMA model produced exact estimates for both the ILI and search engine data. The MAPEs of 20-week rolling forecasts for these datasets were 13.65% and 8.04%, respectively. Based on these two risk levels, the hierarchical infection prevention methods provided guidelines for personal protection and disinfection. Criteria were also established for upgrading or downgrading infection prevention strategies based on ARIMA results.ConclusionThese innovative methods, along with the ARIMA model, showed efficient infection protection for healthcare workers in close contact with COVID-19 infected patients, saving nearly 41% of the cost of maintaining high-level infection prevention measures and enhancing control of respiratory infections.

SpTe2M: An R package for nonparametric modeling and monitoring of spatiotemporal data

Spatiotemporal data are common in practice. Such data often have complicated structures that are difficult to describe by parametric statistical models. Thus, it is often challenging to analyze spatiotemporal data effectively since most existing statistical methods and software packages in the literature are based on parametric modeling and cannot handle certain applications properly. This paper introduces the new package SpTe2M, which was developed for implementing some recent nonparametric methods for modeling and monitoring spatiotemporal data. This package provides analytic tools for modeling spatiotemporal data nonparametrically and for monitoring dynamic spatial processes sequentially over time. It can be used for different applications, including disease surveillance and environmental monitoring. The use of the package is demonstrated using the Florida influenza-like illness data observed during 2012–2014 and the PM2.5 concentration data in China collected during 2014–2016.

Enabling Multicentric Participatory Disease Surveillance for Global Health Enhancement: Viewpoint on Global Flu View.

Participatory surveillance (PS) has been defined as the bidirectional process of transmitting and receiving data for action by directly engaging the target population. Often represented as self-reported symptoms directly from the public, PS can provide evidence of an emerging disease or concentration of symptoms in certain areas, potentially identifying signs of an early outbreak. The construction of sets of symptoms to represent various disease syndromes provides a mechanism for the early detection of multiple health threats. Global Flu View (GFV) is the first-ever system that merges influenza-like illness (ILI) data from more than 8 countries plus 1 region (Hong Kong) on 4 continents for global monitoring of this annual health threat. GFV provides a digital ecosystem for spatial and temporal visualization of syndromic aggregates compatible with ILI from the various systems currently participating in GFV in near real time, updated weekly. In 2018, the first prototype of a digital platform to combine data from several ILI PS programs was created. At that time, the priority was to have a digital environment that brought together different programs through an application program interface, providing a real time map of syndromic trends that could demonstrate where and when ILI was spreading in various regions of the globe. After 2 years running as an experimental model and incorporating feedback from partner programs, GFV was restructured to empower the community of public health practitioners, data scientists, and researchers by providing an open data channel among these contributors for sharing experiences across the network. GFV was redesigned to serve not only as a data hub but also as a dynamic knowledge network around participatory ILI surveillance by providing knowledge exchange among programs. Connectivity between existing PS systems enables a network of cooperation and collaboration with great potential for continuous public health impact. The exchange of knowledge within this network is not limited only to health professionals and researchers but also provides an opportunity for the general public to have an active voice in the collective construction of health settings. The focus on preparing the next generation of epidemiologists will be of great importance to scale innovative approaches like PS. GFV provides a useful example of the value of globally integrated PS data to help reduce the risks and damages of the next pandemic.

Changes in epidemic intensity of influenza during 2014-2020 in Shanghai

Objective: To evaluate the performance of the influenza surveillance network and compare the epidemic intensity of influenza during 2014-2020 in Shanghai. Methods: Based on the weekly reports of influenza-like illness (ILI) and laboratory-confirmed influenza cases from January 1, 2014 to December 31, 2020. This study first evaluated the data reporting and specimen collection of ILI cases for each sentinel hospital, and then calculated the percentage of ILI (ILI%), the proportion of specimens tested positive for influenza, and the incidence of influenza among all ILI outpatient and emergency visits to measure the epidemic intensity of influenza. Finally, seasonal autoregressive integrated moving average (ARIMA) model was applied to quantify the changes in epidemic intensity of influenza in 2020. Results: The proportion of influenza surveillance sentinel hospitals with a score of less than 5 in the evaluation of ILI data reporting and samples collection were 9.68% and 21.05% in 2020 in Shanghai, respectively. ILI% was estimated to be 1.51% (95%CI: 1.50%-1.51%) and 2.31% (95%CI: 2.30%-2.32%), respectively for 2014-2019 and 2020; the proportion of specimens tested positive was 24.27% (95%CI: 24.02%- 24.51%) and 7.15% (95%CI: 6.78%-7.54%), respectively; and the incidence of influenza was 3.66‰ (95%CI: 3.62‰-3.70‰) and 1.65‰ (95%CI: 1.57‰-1.74‰), respectively. ARIMA model showed that ILI% was increased by 45.25% in 2020 in Shanghai, and the proportion of specimens tested positive and the incidence of influenza were reduced by 78.45% and 51.80%, respectively. Conclusions: In 2020, the performance of influenza surveillance system has changed, ILI% has increased, the proportion of specimens tested positive and the incidence of influenza has decreased in Shanghai. The change in the quality of influenza surveillance is also a potential factor affecting the epidemic intensity of influenza. In the future, the quality control of influenza surveillance network still needs to be further strengthened.

Combining dynamic mode decomposition with ensemble Kalman filtering for tracking and forecasting

Data assimilation techniques, such as ensemble Kalman filtering, have been shown to be a highly effective and efficient way to combine noisy data with a mathematical model to track and forecast dynamical systems. However, when dealing with high-dimensional data, in many situations one does not have a model, so data assimilation techniques cannot be applied. In this paper, we use dynamic mode decomposition to generate a low-dimensional, linear model of a dynamical system directly from high-dimensional data, which is defined by temporal and spatial modes, that we can then use with data assimilation techniques such as the ensemble Kalman filter. We show how the dynamic mode decomposition can be combined with the ensemble Kalman filter (which we call the DMDEnKF) to iteratively update the current state and temporal modes as new data becomes available. We demonstrate that this approach is able to track time varying dynamical systems in synthetic examples, and experiment with the use of time-delay embeddings. We then apply the DMDEnKF to real world seasonal influenza-like illness data from the USA Centers for Disease Control and Prevention, and find that for short term forecasting, the DMDEnKF is comparable to the best mechanistic models in the ILINet competition.

Nowcasting and Forecasting Seasonal Influenza Epidemics - China, 2022-2023.

Seasonal influenza resurged in China in February 2023, causing a large number of hospitalizations. While influenza epidemics occurred across China during the coronavirus disease 2019 (COVID-19) pandemic, the relaxation of COVID-19 containment measures in December 2022 may have contributed to the spread of acute respiratory infections in winter 2022/2023. Using a mathematical model incorporating influenza activity as measured by influenza-like illness (ILI) data for northern and southern regions of China, we reconstructed the seasonal influenza incidence from October 2015 to September 2019 before the COVID-19 pandemic. Using this trained model, we predicted influenza activities in northern and southern China from March to September 2023. We estimated the effective reproduction number R e as 1.08 [95% confidence interval ( CI): 0.51, 1.65] in northern China and 1.10 (95% CI: 0.55, 1.67) in southern China at the start of the 2022-2023 influenza season. We estimated the infection attack rate of this influenza wave as 18.51% (95% CI: 0.00%, 37.78%) in northern China and 28.30% (95% CI: 14.77%, 41.82%) in southern China. The 2023 spring wave of seasonal influenza in China spread until July 2023 and infected a substantial number of people.

How do El Niño Southern Oscillation (ENSO) and local meteorological factors affect the incidence of seasonal influenza in New York state

BackgroundResearch is lacking in examining how multiple climate factors affect the incidence of seasonal influenza. We investigated the associations between El Niño Southern Oscillation (ENSO), meteorological factors, and influenza incidence in New York State, United States. MethodWe collected emergency department visit data for influenza from the New York State Department of Health. ENSO index was obtained from the National Oceanic and Atmospheric Administration. Meteorological factors, Google Flu Search Index (GFI), and Influenza-like illness (ILI) data in New York State were also collected. Wavelet analysis was used to quantitatively estimate the coherence and phase difference of ENSO, temperature, precipitation, relative humidity, and absolute humidity with emergency department visits of influenza in New York State. Generalized additive models (GAM) were employed to examine the exposure-response relationships between ENSO, weather, and influenza. GFI and ILI data were used to simulate synchronous influenza visits. ResultsThe influenza epidemic in New York State had multiple periodic and was primarily on the 1-year scale. The incidence of influenza closely followed the low ENSO index by an average of two months, and the lag period of ENSO on influenza was shorter during 2015–2018. Low temperature in the previous 2 weeks and low absolute humidity in the prior week were positively associated with influenza incidence in New York State. We found an l-shaped association between ENSO index and influenza, a parabolic relationship between temperature in the previous two weeks and influenza, and a linear negative association between absolute humidity in the previous week and influenza. The simulation models including GFI and ILI had higher accuracy for influenza visit estimation. ConclusionsLow ENSO index, low temperature, and low absolute humidity may drive the influenza epidemics in New York State. The findings can help us deepen the understanding of the climate-influenza association, and help to develop an influenza forecasting model.

Seasonal influenza disease and annual influenza vaccine coverage at Primary Health Care Corporation, Qatar, 2018–2019: a descriptive study

Background: Influenza is the most common communicable disease in the State of Qatar. The objective of this study was to describe the occurrence of seasonal influenza and influenza vaccine uptake, as well as to analyze whether influenza vaccine efficacy during the 2018/2019 season was met. Primary Health Care Corporation (PHCC) plays an important role in influenza disease surveillance and annual influenza vaccine administration in the country. Therefore, specific data available from this organization would reflect on the surveillance standards in place. However, data on influenza disease burden and vaccination coverage for the season was limited. Methods: A cross-sectional descriptive study was conducted on the retrospective data of influenza-like illness (ILI) cases confirmed during the 2018/2019 influenza season by PHCC and the number of people who received the annual influenza vaccine in PHCC during the same season. Results: ILI and influenza data: A total of 998 ILI cases were considered for this study. Laboratory testing was carried out among 88.5% of the cases. Type A and B infection contributed to 63.4% and 36.4% of the influenza cases, respectively. Furthermore, 87% (n=415) of the total influenza cases were not vaccinated with the season’s influenza vaccine, and 69% (n=18) of the total vaccinated ILI cases (n=26) tested negative for influenza. Influenza vaccine campaign data: Overall, 42,476 individuals were vaccinated with the annual influenza vaccine in PHCC for the 2018/2019 season. Influenza vaccine was administered to 52.3% of people with any one risk factor (mostly chronic diseases) for severe disease due to influenza. Conclusions: The findings of this study on influenza seasonality and etiology were similar to that on previous seasons in the region. Recommendations focused on accurate and elaborate data collection and future research on the factors facilitating influenza vaccine uptake and vaccine effectiveness.

Leveraging Google Search Data and Artificial Intelligence Methods for Provincial-level Influenza Forecasting: A South African Case Study

This paper investigates the usefulness of Google search patterns with Artificial Intelligence (AI) techniques for timely influenza-like illness (ILI) forecasting for each of the nine South African provinces. Traditional surveillance methods are limited by delays in reporting. Existing digital disease surveillance studies that employ alternative online data have scarcely explored sub-Saharan African countries. In South Africa, Google search data has only been recently studied for ILI surveillance at the national level. Meanwhile, the differences in socio-economic and technological conditions across provinces call for a finer spatial investigation. We perform correlation analysis between Google trends (GT) data for 21 ILI-related terms and real-life ILI surveillance data for each province. Next, we develop models to assess the predictive performance of these GT data for forecasting ILI rates, using time series, machine learning, and deep learning methods. We observe sufficient correlation for only two of the nine provinces: Gauteng and Western Cape. Thus, GT data could only be used to forecast ILI in these two provinces. Interestingly, these two provinces are regarded as the most economically developed. In the other seven provinces, LSTM, a deep learning technique, gives more accurate predictions than a baseline autoregressive model when only past ILI data are used for forecasting future ILI trends. The results reveal that, for provinces for which GT data is sufficiently available, it is not only free and fast, but is an effective predictor on its own as well as when added to past ILI data for forecasting future ILI infection rates. The correlation analysis suggests an association between provincial socio-economic development and the use of digital platforms for disease surveillance. Overall, the study established the need for finer scale ILI forecasting which will inform targeted planning for disease surveillance and interventions.

Prediction of Incidence Trend of Influenza-Like Illness in Wuhan Based on ARIMA Model.

Objective The autoregressive integrated moving average (ARIMA) model has been widely used to predict the trend of infectious diseases. This paper is aimed at analyzing the application of the ARIMA model in the prediction of the incidence trend of influenza-like illness (ILI) in Wuhan and providing a scientific basis for the prediction and prevention of influenza. Methods The weekly ILI data of two influenza surveillance sentinel hospitals in Wuhan City published on the website of the National Influenza Center of China were collected, and the ARIMA model was used to model the data from 2014 to 2020, to predict and verify the ILI data in 2021. Results The optimal model for the incidence trend of ILI in Wuhan was ARIMA (1, 1, 1), the residuals were in line with the white noise sequence (0.018 < Ljung‐Box Q < 30.695, P > 0.05), and the relative error between the predicted value and the actual value was small, which all proved the model was practical. Conclusion ARIMA (1, 1, 1) can effectively simulate the short-term incidence trend of ILI in Wuhan.

Comparative efficacy and safety of vaccines to prevent seasonal influenza: A systematic review and network meta-analysis

SummaryBackgroundInfluenza is one of the most common respiratory viral infections worldwide. Numerous vaccines are used to prevent influenza. Their selection should be informed by the best available evidence. We aimed to estimate the comparative efficacy and safety of seasonal influenza vaccines in children, adults and the elderly.MethodsWe conducted a systematic review and network meta-analysis (NMA). We searched the Cochrane Library Central Register of Controlled Trials, MEDLINE and EMBASE databases, and websites of regulatory agencies, through December 15th, 2020. We included placebo- or no vaccination-controlled, and head-to-head randomized clinical trials (RCTs). Pairs of reviewers independently screened the studies, abstracted the data, and appraised the risk of bias in accordance to the Cochrane Handbook for Systematic Reviews of Interventions. The primary outcome was laboratory-confirmed influenza. We also synthesized data for hospitalization, mortality, influenza-like illness (ILI), pneumonia or lower respiratory-tract disease, systemic and local adverse events (AEs). We estimated summary risk ratios (RR) using pairwise and NMA with random effects. This study is registered with PROSPERO, number CRD42018091895.FindingsWe identified 13,439 citations. A total of 231 RCTs were included after screening: 11 studies did not provide useful data for the analysis; 220 RCTs [100,677 children (< 18 years) and 329,127 adults (18–60 years) and elderly (≥ 61 years)] were included in the NMA. In adults and the elderly, all vaccines, except the trivalent inactivated intradermal vaccine (3-IIV ID), were more effective than placebo in reducing the risk of laboratory-confirmed influenza, with a RR between 0.33 (95% credible interval [CrI] 0.21–0.55) for trivalent inactivated high-dose (3-IIV HD) and 0.56 (95% CrI 0.41–0.74) for trivalent live-attenuated vaccine (3-LAIV). In adults and the elderly, compared with trivalent inactivated vaccine (3-IIV), no significant differences were found for any, except 3-LAIV, which was less efficacious [RR 1.41 (95% CrI 1.04–1.88)]. In children, compared with placebo, RR ranged between 0.13 (95% CrI 0.03–0.51) for trivalent inactivated vaccine adjuvanted with MF59/AS03 and 0.55 (95% CrI 0.36–0.83) for trivalent inactivated vaccine. Compared with 3-IIV, 3-LAIV and trivalent inactivated adjuvanted with MF59/AS03 were more efficacious [RR 0.52 (95% CrI 0.32–0.82) and RR 0.23 (95% CrI 0.06–0.87)] in reducing laboratory-confirmed influenza. With regard to safety, higher systemic AEs rates after vaccination with 3-IIV, 3-IIV HD, 3-IIV ID, 3-IIV MF59/AS03-adj, quadrivalent inactivated (4-IIV), quadrivalent adjuvanted (4-IIV MF59/AS03-adj), quadrivalent recombinant (4-RIV), 3-LAIV or quadrivalent live attenuated (4-LAIV) vaccines were noted in adults and the elderly [RR 1.5 (95% CrI 1.18–1.89) to 1.15 (95% CrI 1.06–1.23)] compared with placebo. In children, the systemic AEs rate after vaccination was not significantly higher than placebo.InterpretationAll vaccines cumulatively achieved major reductions in the incidence of laboratory-confirmed influenza in children, adults, and the elderly. While the live-attenuated was more efficacious than the inactivated vaccine in children, many vaccine types can be used in adults and the elderly.FundingThe directorate general of welfare, Lombardy region.

Applying the Spatial Transmission Network to the Forecast of Infectious Diseases Across Multiple Regions.

ObjectiveTimely and accurate forecast of infectious diseases is essential for achieving precise prevention and control. A good forecasting method of infectious diseases should have the advantages of interpretability, feasibility, and forecasting performance. Since previous research had illustrated that the spatial transmission network (STN) showed good interpretability and feasibility, this study further explored its forecasting performance for infectious diseases across multiple regions. Meanwhile, this study also showed whether the STN could overcome the challenges of model rationality and practical needs.MethodsThe construction of the STN framework involved three major steps: the spatial kluster analysis by tree edge removal (SKATER) algorithm, structure learning by dynamic Bayesian network (DBN), and parameter learning by the vector autoregressive moving average (VARMA) model. Then, we evaluated the forecasting performance of STN by comparing its accuracy with that of the mechanism models like susceptible-exposed-infectious-recovered-susceptible (SEIRS) and machine-learning algorithm like long-short-term memory (LSTM). At the same time, we assessed the robustness of forecasting performance of STN in high and low incidence seasons. The influenza-like illness (ILI) data in the Sichuan Province of China from 2010 to 2017 were used as an example for illustration.ResultsThe STN model revealed that ILI was likely to spread among multiple cities in Sichuan during the study period. During the whole study period, the forecasting accuracy of the STN (mean absolute percentage error [MAPE] = 31.134) was significantly better than that of the LSTM (MAPE = 41.657) and the SEIRS (MAPE = 62.039). In addition, the forecasting performance of STN was also superior to those of the other two methods in either the high incidence season (MAPE = 24.742) or the low incidence season (MAPE = 26.209), and the superiority was more obvious in the high incidence season.ConclusionThis study applied the STN to the forecast of infectious diseases across multiple regions. The results illustrated that the STN not only had good accuracy in forecasting performance but also indicated the spreading directions of infectious diseases among multiple regions to a certain extent. Therefore, the STN is a promising candidate to improve the surveillance work.

United States Influenza Search Patterns Since the Emergence of COVID-19: Infodemiology Study.

BackgroundThe emergence and media coverage of COVID-19 may have affected influenza search patterns, possibly affecting influenza surveillance results using Google Trends.ObjectiveWe aimed to investigate if the emergence of COVID-19 was associated with modifications in influenza search patterns in the United States.MethodsWe retrieved US Google Trends data (relative number of searches for specified terms) for the topics influenza, Coronavirus disease 2019, and symptoms shared between influenza and COVID-19. We calculated the correlations between influenza and COVID-19 search data for a 1-year period after the first COVID-19 diagnosis in the United States (January 21, 2020 to January 20, 2021). We constructed a seasonal autoregressive integrated moving average model and compared predicted search volumes, using the 4 previous years, with Google Trends relative search volume data. We built a similar model for shared symptoms data. We also assessed correlations for the past 5 years between Google Trends influenza data, US Centers for Diseases Control and Prevention influenza-like illness data, and influenza media coverage data.ResultsWe observed a nonsignificant weak correlation (ρ= –0.171; P=0.23) between COVID-19 and influenza Google Trends data. Influenza search volumes for 2020-2021 distinctly deviated from values predicted by seasonal autoregressive integrated moving average models—for 6 weeks within the first 13 weeks after the first COVID-19 infection was confirmed in the United States, the observed volume of searches was higher than the upper bound of 95% confidence intervals for predicted values. Similar results were observed for shared symptoms with influenza and COVID-19 data. The correlation between Google Trends influenza data and CDC influenza-like-illness data decreased after the emergence of COVID-19 (2020-2021: ρ=0.643; 2019-2020: ρ=0.902), while the correlation between Google Trends influenza data and influenza media coverage volume remained stable (2020-2021: ρ=0.746; 2019-2020: ρ=0.707).ConclusionsRelevant differences were observed between predicted and observed influenza Google Trends data the year after the onset of the COVID-19 pandemic in the United States. Such differences are possibly due to media coverage, suggesting limitations to the use of Google Trends as a flu surveillance tool.

Examining the Relationship Between Novel Data from Electronic Health Records (EHRs) and Traditional Public Health Surveillance Data for Influenza-like Illness among 12 U.S. Jurisdictions, 2016-2019

Examining the Relationship Between Novel Data from Electronic Health Records (EHRs) and Traditional Public Health Surveillance Data for Influenza-like Illness among 12 U.S. Jurisdictions, 2016-2019

Evaluation of IBM Watson Natural Language Processing Service to predict influenza-like illness outbreaks from Twitter data

In this work we evaluate whether Watson NLP service can be used to reliably predict infectious disease such as influenza-like illness (ILI) outbreaks using Twitter data. Watson’s performance is evaluated by computing Pearson correlation coefficient between the number of tweets classified by Watson as ILI and the number of ILI occurrences recovered from traditional epidemic surveillance system of the Centers for Disease Control and Prevention (CDC). Achieved correlation was 0.55. Furthermore, a 12-week discrepancy was found between peak occurrences of ILI predicted by Watson and CDC reported data. Additionally, we developed a scoring method for ILI prediction from a Twitter post using a simple formula with the ability to predict ILI two weeks ahead of ILI data as reported by CDC. The obtained results suggest that data found within social media can be used to supplement the traditional surveillance in epidemics of infectious diseases such as influenza or more recently COVID-19 with the help of intelligent computations

Nowcasting influenza‐like illness (ILI) via a deep learning approach using google search data: An empirical study on Taiwan ILI

Influenza outbreaks have brought increasing challenges to public health systems globally. The effective and efficient tracking of influenza can help authorities make informed and proactive decisions. In this study, we focus on nowcasting influenza epidemics at regional level. To alleviate the information lag between the release of the Centers for Disease Control's influenza-like illness (ILI) reports and real-time influenza activity, we incorporate Google search data and holiday effects to facilitate the ILI nowcasting. We develop a deep learning framework by extending the spatiotemporal residual network (ST-ResNet) to nowcast ILI rates in irregular-shaped region. We investigate the effect of temporal and spatial dependencies among irregular-shaped regions as well as external influence on ILI nowcasting. Various forecasting models, including time series models, penalized regression models, and other deep learning models, are employed for evaluating the performance of the proposed framework. Moreover, based on city-level ILI data in Taiwan, we conduct extensive experiments for methods validation. The results show that the extended ST-ResNet can effectively capture the complex spatiotemporal dependencies of ILI activity and the effects of external variables. Additionally, the strategy of incorporating Google search data and holiday effects improves the prediction. The findings may provide insights into the utility of various statistical and deep learning methods for effective ILI tracking at regional level and facilitate informed decision making for public health authorities.

Adaptively stacking ensembles for influenza forecasting.

Seasonal influenza infects between 10 and 50 million people in the United States every year. Accurate forecasts of influenza and influenza-like illness (ILI) have been named by the CDC as an important tool to fight the damaging effects of these epidemics. Multi-model ensembles make accurate forecasts of seasonal influenza, but current operational ensemble forecasts are static: they require an abundance of past ILI data and assign fixed weights to component models at the beginning of a season, but do not update weights as new data on component model performance is collected. We propose an adaptive ensemble that (i) does not initially need data to combine forecasts and (ii) finds optimal weights which are updated week-by-week throughout the influenza season. We take a regularized likelihood approach and investigate this regularizer's ability to impact adaptive ensemble performance. After finding an optimal regularization value, we compare our adaptive ensemble to an equal-weighted and static ensemble. Applied to forecasts of short-term ILI incidence at the regional and national level, our adaptive model outperforms an equal-weighted ensemble and has similar performance to the static ensemble using only a fraction of the data available to the static ensemble. Needing no data at the beginning of an epidemic, an adaptive ensemble can quickly train and forecast an outbreak, providing a practical tool to public health officials looking for a forecast to conform to unique features of a specific season.

Accurate influenza forecasts using type-specific incidence data for small geographic units.

Influenza incidence forecasting is used to facilitate better health system planning and could potentially be used to allow at-risk individuals to modify their behavior during a severe seasonal influenza epidemic or a novel respiratory pandemic. For example, the US Centers for Disease Control and Prevention (CDC) runs an annual competition to forecast influenza-like illness (ILI) at the regional and national levels in the US, based on a standard discretized incidence scale. Here, we use a suite of forecasting models to analyze type-specific incidence at the smaller spatial scale of clusters of nearby counties. We used data from point-of-care (POC) diagnostic machines over three seasons, in 10 clusters, capturing: 57 counties; 1,061,891 total specimens; and 173,909 specimens positive for Influenza A. Total specimens were closely correlated with comparable CDC ILI data. Mechanistic models were substantially more accurate when forecasting influenza A positive POC data than total specimen POC data, especially at longer lead times. Also, models that fit subpopulations of the cluster (individual counties) separately were better able to forecast clusters than were models that directly fit to aggregated cluster data. Public health authorities may wish to consider developing forecasting pipelines for type-specific POC data in addition to ILI data. Simple mechanistic models will likely improve forecast accuracy when applied at small spatial scales to pathogen-specific data before being scaled to larger geographical units and broader syndromic data. Highly local forecasts may enable new public health messaging to encourage at-risk individuals to temporarily reduce their social mixing during seasonal peaks and guide public health intervention policy during potentially severe novel influenza pandemics.