Influenza forecasting for French regions combining EHR, web and climatic data sources with a machine learning ensemble approach

Poirier, Canelle; Hswen, Yulin; Bouzillé, Guillaume; Cuggia, Marc; Lavenu, Audrey; Brownstein, John S.; Brewer, Thomas G.; Santillana, Mauricio

doi:10.1371/journal.pone.0250890

Cited by 8 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Combining flu-related information from online and traditional sources has showed accurate and real-time predictions in influenza surveillance [12][13][14]. Our study found that the dedicated online medical source, PD [25], aimed at HCPs working in public primary and specialized care, could provide real-time information to be used in daily practice and in surveillance to detect influenza.…”

Section: Plos Onementioning

confidence: 99%

“…Combining information from several real-time flu predictors (e.g., hospital visits, Google Trends, Twitter posts, FluNearYou, GFT) has been shown to produce more accurate and robust real-time flu predictions [12]. Using machinelearning methods to combine these sources further improves influenza surveillance with more accurate and timely predictions [13,14]. However, little data exist on searches of dedicated online databases used by health care professionals (HCPs) when detecting influenza outbreaks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Online searches of children’s oseltamivir in public primary and specialized care: Detecting influenza outbreaks in Finland using dedicated databases for health care professionals

et al. 2022

View full text Add to dashboard Cite

Introduction Health care professionals working in primary and specialized care typically search for medical information from Internet sources. In Finland, Physician’s Databases are online portals aimed at professionals seeking medical information. As dosage errors may occur when prescribing medication to children, professionals’ need for reliable medical information has increased in public health care centers and hospitals. Influenza continues to be a public health threat, with young children at risk of developing severe illness and easily transmitting the virus. Oseltamivir is used to treat children with influenza. The objective of this study was to compare searches for children’s oseltamivir and influenza diagnoses in primary and specialized care, and to determine if the searches could aid detection of influenza outbreaks. Methods We compared searches in Physician’s Databases for children’s oral suspension of oseltamivir (6 mg/mL) for influenza diagnoses of children under 7 years and laboratory findings of influenza A and B from the National Infectious Disease Register. Searches and diagnoses were assessed in primary and specialized care across Finland by season from 2012–2016. The Moving Epidemic Method (MEM) calculated seasonal starts and ends, and paired differences in the mean compared two indicators. Correlation was tested to compare seasons. Results We found that searches and diagnoses in primary and specialized care showed visually similar patterns annually. The MEM-calculated starting weeks in searches appeared mainly in the same week. Oseltamivir searches in primary care preceded diagnoses by −1.0 weeks (95% CI: −3.0, −0.3; p = 0.132) with very high correlation (τ = 0.913). Specialized care oseltamivir searches and diagnoses correlated moderately (τ = 0.667). Conclusion Health care professionals’ searches for children’s oseltamivir in online databases linked with the registers of children’s influenza diagnoses in primary and specialized care. Therefore, database searches should be considered as supplementary information in disease surveillance when detecting influenza epidemics.

show abstract

Section: Plos Onementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Online searches of children’s oseltamivir in public primary and specialized care: Detecting influenza outbreaks in Finland using dedicated databases for health care professionals

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Its most popular application has been forecasting of seasonal influenza at the population level. 36 , 37 , 38 , 39 , 40 Many have used artificial intelligence‐based methods to forecast the arrival and intensity of seasonal influenza using social media and widely used search engines such as Google or Baidu, 39 , 40 while others have utilized prior patterns of healthcare utilization and external variables such as weather patterns to predict future outbreaks. 36 , 38 Artificial intelligence has also been used to predict influenza vaccine uptake and response.…”

Section: Discussionmentioning

confidence: 99%

Multisite development and validation of machine learning models to predict severe outcomes and guide decision‐making for emergency department patients with influenza

Hinson,

Zhao,

Klein

et al. 2024

JACEP Open

View full text Add to dashboard Cite

ObjectiveMillions of Americans are infected by influenza annually. A minority seek care in the emergency department (ED) and, of those, only a limited number experience severe disease or death. ED clinicians must distinguish those at risk for deterioration from those who can be safely discharged.MethodsWe developed random forest machine learning (ML) models to estimate needs for critical care within 24 h and inpatient care within 72 h in ED patients with influenza. Predictor data were limited to those recorded prior to ED disposition decision: demographics, ED complaint, medical problems, vital signs, supplemental oxygen use, and laboratory results. Our study population was comprised of adults diagnosed with influenza at one of five EDs in our university health system between January 1, 2017 and May 18, 2022; visits were divided into two cohorts to facilitate model development and validation. Prediction performance was assessed by the area under the receiver operating characteristic curve (AUC) and the Brier score.ResultsAmong 8032 patients with laboratory‐confirmed influenza, incidence of critical care needs was 6.3% and incidence of inpatient care needs was 19.6%. The most common reasons for ED visit were symptoms of respiratory tract infection, fever, and shortness of breath. Model AUCs were 0.89 (95% CI 0.86–0.93) for prediction of critical care and 0.90 (95% CI 0.88–0.93) for inpatient care needs; Brier scores were 0.026 and 0.042, respectively. Importantpredictors included shortness of breath, increasing respiratory rate, and a high number of comorbid diseases. ConclusionsML methods can be used to accurately predict clinical deterioration in ED patients with influenza and have potential to support ED disposition decision‐making.

show abstract

“…The developed approach can be viewed as a feasible alternative to nowcast ILI in the areas where ILI activity has no constant seasonal trend. In the future, we will evaluate different ILI predictive methods in application to other geographical regions and incorporate other available ILI-related data such as Twitter posts [18][19]. Besides, at the methodological level, we will attempt to investigate the effect of temporal and spatial dependencies on ILI nowcasting and employ deep learning-based models for evaluating the performance of our developed approach [20].…”

Section: Discussionmentioning

confidence: 99%

Nowcasting Influenza-Like Illness (ILI) via a Stacking-Based Ensemble Approach

Wang

Luo

Cao

et al. 2022

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Monitoring influenza activity can facilitate developing prevention strategies and optimizing public health resource allocation in an effective manner. Traditional influenza surveillance methods usually have a time lag of 1 to 2 weeks. This study concerns the problem of nowcasting influenza-like illness (ILI) by comprehensively incorporating historical ILI records, Internet search data, and tourist flow information. In this study, a set of predictive models are adapted for ILI prediction, including autoregressive integrated moving average (ARIMA), autoregressive with Google search data (ARGO), extreme gradient boosting (XGBoost), and linear regression (LR). To further improve prediction accuracy, a stacking-based ensemble approach is developed to integrate the prediction results from the different models. These methods are validated using the ILI-related data in Taiwan Province of China at both global and city levels. The results show that the stacking-based ensemble approach achieved the best performance in the task of nowcasting, with the least prediction errors at the global level (MAPE=5.6%; RMSE=0.16%; MAE=0.08%). The developed approach is easily tractable and computationally efficient and can be viewed as a feasible alternative to nowcast ILI in areas where influenza activity has no constant seasonal trend.

show abstract

Influenza forecasting for French regions combining EHR, web and climatic data sources with a machine learning ensemble approach

Cited by 8 publications

References 35 publications

Online searches of children’s oseltamivir in public primary and specialized care: Detecting influenza outbreaks in Finland using dedicated databases for health care professionals

Online searches of children’s oseltamivir in public primary and specialized care: Detecting influenza outbreaks in Finland using dedicated databases for health care professionals

Multisite development and validation of machine learning models to predict severe outcomes and guide decision‐making for emergency department patients with influenza

Nowcasting Influenza-Like Illness (ILI) via a Stacking-Based Ensemble Approach

Contact Info

Product

Resources

About