Real Time Influenza Monitoring Using Hospital Big Data in Combination with Machine Learning Methods: Comparison Study

Poirier, Canelle; Lavenu, Audrey; Bertaud, Valérie; Campillo‐Gimenez, Boris; Chazard, Emmanuel; Cuggia, Marc; Bouzillé, Guillaume

doi:10.2196/11361

Cited by 26 publications

(24 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“… Similar results were observed for both approaches and they can be used in parallel. Poirier et al [93 ] Influenza RF, SVR and ENET Compared internet and electronic health records data and by statistical models to identify the best approach for influenza estimates in real time. For national and Brittany region influenza incidence rate, SVR model is the best approach.…”

Section: Resultsmentioning

confidence: 99%

Multi-step ahead meningitis case forecasting based on decomposition and multi-objective optimization methods

Ribeiro

Mariani

Coelho

2020

Journal of Biomedical Informatics

View full text Add to dashboard Cite

Epidemiological time series forecasting plays an important role in health public systems, due to its ability to allow managers to develop strategic planning to avoid possible epidemics. In this paper, a hybrid learning framework is developed to forecast multi-step-ahead (one, two, and three-month-ahead) meningitis cases in four states of Brazil. First, the proposed approach applies an ensemble empirical mode decomposition (EEMD) to decompose the data into intrinsic mode functions and residual components. Then, each component is used as the input of five different forecasting models, and, from there, forecasted results are obtained. Finally, all combinations of models and components are developed, and for each case, the forecasted results are weighted integrated (WI) to formulate a heterogeneous ensemble forecaster for the monthly meningitis cases. In the final stage, a multi-objective optimization (MOO) using the Non-Dominated Sorting Genetic Algorithm – version II is employed to find a set of candidates’ weights, and then the Technique for Order of Preference by similarity to Ideal Solution (TOPSIS) is applied to choose the adequate set of weights. Next, the most adequate model is the one with the best generalization capacity out-of-sample in terms of performance criteria including mean absolute error (MAE), relative root mean squared error (RRMSE), and symmetric mean absolute percentage error (sMAPE). By using MOO, the intention is to enhance the performance of the forecasting models by improving simultaneously their accuracy and stability measures. To access the model’s performance, comparisons based on metrics are conducted with: (i) EEMD, heterogeneous ensemble integrated by direct strategy, or simple sum; (ii) EEMD, homogeneous ensemble of components WI; (iii) models without signal decomposition. At this stage, MAE, RRMSE, and sMAPE criteria as well as Diebold–Mariano statistical test are adopted. In all twelve scenarios, the proposed framework was able to perform more accurate and stable forecasts, which showed, on 89.17% of the cases, that the errors of the proposed approach are statistically lower than other approaches. These results showed that combining EEMD, heterogeneous ensemble and WI with weights obtained by optimization can develop precise and stable forecasts. The modeling developed in this paper is promising and can be used by managers to support decision making.

show abstract

Section: Resultsmentioning

confidence: 99%

Multi-step ahead meningitis case forecasting based on decomposition and multi-objective optimization methods

Ribeiro

Mariani

Coelho

2020

Journal of Biomedical Informatics

View full text Add to dashboard Cite

show abstract

“…Work on epidemic/influenza forecasting has examined national/state level [16,17] and regional level [18][19][20] forecasts. The most relevant research on the hospital level we could find are [21,22] and [23], where the authors use historical data and public available data to generate hospital influenza visits.…”

Section: Literaturementioning

confidence: 99%

The development and deployment of a model for hospital-level COVID-19 associated patient demand intervals from consistent estimators (DICE)

Yang

Zhang

Scheinker

2021

Health Care Manag Sci

View full text Add to dashboard Cite

Hospitals commonly project demand for their services by combining their historical share of regional demand with forecasts of total regional demand. Hospital-specific forecasts of demand that provide prediction intervals, rather than point estimates, may facilitate better managerial decisions, especially when demand overage and underage are associated with high, asymmetric costs. Regional point forecasts of patient demand are commonly available, e.g., for the number of people requiring hospitalization due to an epidemic such as COVID-19. However, even in this common setting, no probabilistic, consistent, computationally tractable forecast is available for the fraction of patients in a region that a particular institution should expect. We introduce such a forecast, DICE (Demand Intervals from Consistent Estimators). We describe its development and deployment at an academic medical center in California during the 'second wave' of COVID-19 in the Unite States. We show that DICE is consistent under mild assumptions and suitable for use with perfect, biased and unbiased regional forecasts. We evaluate its performance on empirical data from a large academic medical center as well as on synthetic data.

show abstract

“…Marie Zins 1 , Marc Cuggia 2 , Marcel Goldberg 1 teurs « intelligents » sont utilisées dans des projets de recherche sur les maladies chroniques ou le vieillissement, car ces données collectées au fil de l'eau contiennent des marqueurs très spécifiques des appareils électriques utilisés à domicile [12,13]. Enfin, les données du web et des réseaux sociaux sont de plus en plus utilisées pour, par exemple, établir des modèles de surveillance épidémiologique [14,15]…”

Section: Abondantes Mais Complexesunclassified

Les données de santé en France

2021

Self Cite

View full text Add to dashboard Cite

Alors que l’application de traçage des contacts (contact tracing) StopCovid (transformée à la mi-octobre 2020 en TousAntiCovid), débattue au Parlement en raison des inquiétudes qu’elle suscitait concernant la confidentialité des données personnelles et les libertés individuelles du fait qu’elle permet d’alerter un utilisateur s’il s’est trouvé à proximité d’une personne atteinte de la COVID-19, a été adoptée par près de 12 millions de personnes, un dispositif concernant les données individuelles de santé, aux conséquences potentiellement beaucoup plus importantes pour les citoyens et leurs données personnelles, a commencé à se mettre en place suite à la Loi du 24 juillet 2019 (Loi n° 2019-774) relative à l’organisation et à la transformation du système de santé : la plateforme des données de santé, communément appelée Health Data Hub, constituée sous la forme d’un groupement d’intérêt public (GIP). Il ne s’agit plus de simplement signaler qu’on a croisé une personne anonyme infectée par le SARS-Cov-2, mais de réunir, dans une infrastructure informatique unique, un immense ensemble de données personnelles particulièrement sensibles concernant la totalité de la population française. Ce projet suscite désormais un certain intérêt médiatique et un début d’inquiétude. Mais cette inquiétude ne concerne presque uniquement que le fait que ces données sont déposées et gérées dans un cloud appartenant à une société américaine, un nuage informatique qui tombe sous le coup de la loi américaine de 2018 dite « CLOUD act », qui ouvre la possibilité d’un transfert des données personnelles vers les États-Unis, comme s’en est inquiété récemment le Conseil d’État. Cet aspect est certes très important, mais il masque également de très nombreux enjeux liés au partage des données de santé, et qui sont largement méconnus de la population. Nous nous proposons de rappeler, tout d’abord, ce que sont les données de santé, ce qu’elles apportent et la nécessité d’en faciliter le partage, mais aussi les difficultés rencontrées pour leur accès et leur utilisation. Nous expliquerons ensuite, dans un deuxième article, en quoi cette plateforme des données de santé, telle qu’elle est conçue et pilotée par les pouvoirs publics pour répondre à ces difficultés et pour promouvoir l’intelligence artificielle en santé, est un projet qui soulève de fortes inquiétudes pour les citoyens et la société dans son ensemble. Même si les problèmes posés se présentent sous une forme différente selon les pays, notre propos concernera spécifiquement la situation en France.

show abstract

Real Time Influenza Monitoring Using Hospital Big Data in Combination with Machine Learning Methods: Comparison Study

Cited by 26 publications

References 45 publications

Multi-step ahead meningitis case forecasting based on decomposition and multi-objective optimization methods

Multi-step ahead meningitis case forecasting based on decomposition and multi-objective optimization methods

The development and deployment of a model for hospital-level COVID-19 associated patient demand intervals from consistent estimators (DICE)

Les données de santé en France

Contact Info

Product

Resources

About