• Corpus ID: 221879150

Steering a Historical Disease Forecasting Model Under a Pandemic: Case of Flu and COVID-19

  title={Steering a Historical Disease Forecasting Model Under a Pandemic: Case of Flu and COVID-19},
  author={Alexander Rodr{\'i}guez and Nikhil Muralidhar and Bijaya Adhikari and Anika Tabassum and Naren Ramakrishnan and B. Aditya Prakash},
Forecasting influenza in a timely manner aids health organizations and policymakers in adequate preparation and decision making. However, effective influenza forecasting still remains a challenge despite increasing research interest. It is even more challenging amidst the COVID pandemic, when the influenza-like illness (ILI) counts is affected by various factors such as symptomatic similarities with COVID-19 and shift in healthcare seeking patterns of the general population. We term the ILI… 

Figures and Tables from this paper

CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting
This work proposes a general probabilistic multi-view forecasting framework CAMUL, that can learn representations and uncertainty from diverse data sources and uses it for multiple domains with varied sources and modalities and shows that CAMUL outperforms other state-of-art probabilism forecasting models by over 25% in accuracy and calibration.
A Brief Summary on Covid-19 Pandemic & Machine Learning Approaches
Beginning in 2019 the world has been under the effect of a global pandemic caused by SARS-CoV2 infecting over 134 million people, resulting in approximately three million deaths globally, several
Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future
This paper construct a detailed dataset composed of relevant signals over the past year of the pandemic, and systematically characterize several patterns in backfill dynamics and leverage the observations for formulating a novel problem and neural framework Back2Future that refines a given model’s predictions in real-time.
COVID-19 Outbreak Prediction and Analysis using Self Reported Symptoms
The findings reaffirm the predictive value of symptoms, such as anosmia and ageusia, and forecast that % of the population having COVID-19-like illness and those tested positive as 0.15% and 1.14% absolute error respectively could help aid faster development of the public health policy, particularly in areas with low levels of testing and having a greater reliance on self-reported symptoms.
Multiwave COVID-19 Prediction via Social Awareness-Based Graph Neural Networks using Mobility and Web Search Data
A Social Awareness-Based Graph Neural Network (SAB-GNN) is proposed that considers the decay of symptom-related web search frequency to capture the changes in public awareness across multiple waves of pandemic outbreaks.
When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting
This work model the forecasting task as a probabilistic generative process and proposes a functional neural process model called EPIFNP, which directly models the probability density of the forecast value and significantly outperforms previous state-of-the-art models in both accuracy and calibration metrics.


Dynamic Bayesian Influenza Forecasting in the United States with Hierarchical Discrepancy (with Discussion)
Timely and accurate forecasts of seasonal influenza would assist public health decision-makers in planning intervention strategies, efficiently allocating resources, and possibly saving lives. For
A Collaborative Multi-Model Ensemble for Real-Time Influenza Season Forecasting in the U.S
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.
DEFSI: Deep Learning Based Epidemic Forecasting with Synthetic Information
This work proposes DEFSI (Deep Learning Based Epidemic Forecasting with Synthetic Information), an epidemic forecasting framework that integrates the strengths of artificial neural networks and causal methods that significantly outperforms the other methods for short-term ILI forecasting at the state level.
EpiDeep: Exploiting Embeddings for Epidemic Forecasting
EpiDeep, a novel deep neural network approach for epidemic forecasting which tackles all of these issues by learning meaningful representations of incidence curves in a continuous feature space and accurately predicting future incidences, peak intensity, peak time, and onset of the upcoming season is proposed.
Flexible Modeling of Epidemics with an Empirical Bayes Framework
A framework for in-season forecasts of epidemics using a semiparametric Empirical Bayes framework was developed and applied to predict the weekly percentage of outpatient doctors visits for influenza-like illness, and the season onset, duration, peak time, and peak height, with and without using Google Flu Trends data.
Accuracy of real-time multi-model ensemble forecasts for seasonal influenza in the U.S.
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.
Forecasting Seasonal Influenza Fusing Digital Indicators and a Mechanistic Disease Model
The first seasonal influenza forecast framework based on a stochastic, spatially structured mechanistic model (individual level microsimulation) initialized with geo-localized microblogging data is proposed, which provides reliable results with leads of up to 6 weeks that became more stable and accurate with progression of the season.
Nonmechanistic forecasts of seasonal influenza with iterative one-week-ahead distributions
A novel approach to probabilistic modeling of surveillance time series based on “delta densities”, and an optimization scheme for combining output from multiple forecasting methods into an adaptively weighted ensemble.
Real-time numerical forecast of global epidemic spreading: case study of 2009 A/H1N1pdm
The results show that large-scale models can be used to provide valuable real-time forecasts of influenza spreading, but they require high-performance computing.
Forecasting influenza-like illness dynamics for military populations using neural networks and social media
This work builds and evaluates the predictive power of neural network architectures based on Long Short Term Memory units capable of nowcasting and forecasting influenza-like illness (ILI) dynamics from various linguistic signals extracted from social media data and combines ILI and social media signals to build a joint neural network model.