AI Techniques for Forecasting Epidemic Dynamics: Theory and Practice

Forecasting epidemic dynamics has been an active area of research for at least two decades. The importance of the topic is evident: policy makers, citizens, and scientists would all like to get accurate and timely forecasts. In contrast to physical systems, the co-evolution of epidemics, individual and collective behavior, viral dynamics, and public policies make epidemic forecasting a problematic task. The situation is even more challenging during a pandemic as has become amply clear during the ongoing COVID-19 pandemic. Researchers worldwide have put in extraordinary efforts to try to forecast the time-varying evolution of the pandemic;despite their best efforts, it is fair to say that the results have been mixed. Several teams have done well on average but failed to forecast upsurges in the cases. In this chapter, we describe the state-of-the-art in epidemic forecasting, with a particular emphasis on forecasting during an ongoing pandemic. We describe a range of methods that have been developed and discuss the experience of our team in this context. We also summarize several challenges in producing accurate and timely forecasts. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Enhancing COVID-19 Ensemble Forecasting Model Performance Using Auxiliary Data Sources

Real-time forecasting of non-stationary time series is a challenging problem, especially when the time series evolves rapidly. For such cases, it has been observed that ensemble models consisting of a diverse set of model classes can perform consistently better than individual models. In order to account for the nonstationarity of the data and the lack of availability of training examples, the models are retrained in real-time using the most recent observed data samples. Motivated by the robust performance properties of ensemble models, we developed a Bayesian model averaging ensemble technique consisting of statistical, deep learning, and compartmental models for fore-casting epidemiological signals, specifically, COVID-19 signals. We observed the epidemic dynamics go through several phases (waves). In our ensemble model, we observed that different model classes performed differently during the various phases. Armed with this understanding, in this paper, we propose a modification to the ensembling method to employ this phase information and use different weighting schemes for each phase to produce improved forecasts. However, predicting the phases of such time series is a significant challenge, especially when behavioral and immunological adaptations govern the evolution of the time series. We explore multiple datasets that can serve as leading indicators of trend changes and employ transfer entropy techniques to capture the relevant indicator. We propose a phase prediction algorithm to estimate the phases using the leading indicators. Using the knowledge of the estimated phase, we selectively sample the training data from similar phases. We evaluate our proposed methodology on our currently deployed COVID-19 forecasting model and the COVID-19 ForecastHub models. The overall performance of the proposed model is consistent across the pandemic. More importantly, it is ranked second during two critical rapid growth phases in cases, regimes where the performance of most models from the ForecastHub dropped significantly. © 2022 IEEE.

CausalGNN: Causal-Based Graph Neural Networks for Spatio-Temporal Epidemic Forecasting

Infectious disease forecasting has been a key focus in the recent past owing to the COVID-19 pandemic and has proved to be an important tool in controlling the pandemic. With the advent of reliable spatiotemporal data, graph neural network models have been able to successfully model the interrelation between the cross-region signals to produce quality forecasts, but like most deep-learning models they do not explicitly incorporate the underlying causal mechanisms. In this work, we employ a causal mechanistic model to guide the learning of the graph embeddings and propose a novel learning framework - Causal-based Graph Neural Network (CausalGNN) that learns spatiotemporal embedding in a latent space where graph input features and epidemiological context are combined via a mutually learning mechanism using graph-based non-linear transformations. We design an attention-based dynamic GNN module to capture spatial and temporal disease dynamics. A causal module is added to the framework to provide epidemiological context for node embedding via ordinary differential equations. Extensive experiment son forecasting daily new cases of COVID-19 at global, US state, and US county levels show that the proposed method outperforms a broad range of baselines. The learned model which incorporates epidemiological context organizes the embedding in an efficient way by keeping the parameter size small leading to robust and accurate forecasting performance across various datasets.

Data-driven scalable pipeline using national agent-based models for real-time pandemic response and decision support

This paper describes an integrated, data-driven operational pipeline based on national agent-based models to support federal and state-level pandemic planning and response. The pipeline consists of (i) an automatic semantic-aware scheduling method that coordinates jobs across two separate high performance computing systems;(ii) a data pipeline to collect, integrate and organize national and county-level disaggregated data for initialization and post-simulation analysis;(iii) a digital twin of national social contact networks made up of 288 Million individuals and 12.6 Billion time-varying interactions covering the US states and DC;(iv) an extension of a parallel agent-based simulation model to study epidemic dynamics and associated interventions. This pipeline can run 400 replicates of national runs in less than 33 h, and reduces the need for human intervention, resulting in faster turnaround times and higher reliability and accuracy of the results. Scientifically, the work has led to significant advances in real-time epidemic sciences. © The Author(s) 2022.

Evaluating the Utility of High-Resolution Proximity Metrics in Predicting the Spread of COVID-19

High resolution mobility datasets have become increasingly available in the past few years and have enabled detailed models for infectious disease spread including those for COVID-19. However, there are open questions on how such mobility data can be used effectively within epidemic models and for which tasks they are best suited. In this paper, we extract a number of graph-based proximity metrics from high resolution cellphone trace data from X-Mode and use it to study COVID-19 epidemic spread in 50 land grant university counties in the US. We present an approach to estimate the effect of mobility on cases by fitting an ordinary differential equation based model and performing multivariate linear regression to explain the estimated time varying transmissibility. We find that, while mobility plays a significant role, the contribution is heterogeneous across the counties, as exemplified by a subsequent correlation analysis. We also evaluate the metrics' utility for case surge prediction defined as a supervised classification problem, and show that the learnt model can predict surges with 95% accuracy and an 87% F1-score.

Effective Social Network-Based Allocation of COVID-19 Vaccines

We study allocation of COVID-19 vaccines to individuals based on the structural properties of their underlying social contact network. Using a realistic representation of a social contact network for the Commonwealth of Virginia, we study how a limited number of vaccine doses can be strategically distributed to individuals to reduce the overall burden of the pandemic. We show that allocation of vaccines based on individuals' degree (number of social contacts) and total social proximity time is significantly more effective than the usually used age-based allocation strategy in reducing the number of infections, hospitalizations and deaths. The overall strategy is robust even: (i) if the social contacts are not estimated correctly;(ii) if the vaccine efficacy is lower than expected or only a single dose is given;(iii) if there is a delay in vaccine production and deployment;and (iv) whether or not non-pharmaceutical interventions continue as vaccines are deployed. For reasons of implementability, we have used degree, which is a simple structural measure and can be easily estimated using several methods, including the digital technology available today. These results are significant, especially for resource-poor countries, where vaccines are less available, have lower efficacy, and are more slowly distributed. © 2022 Owner/Author.

Human health risk assessment of heavy metal and pathogenic contamination in surface water of the Punnakayal estuary, South India.

Variation in levels of toxic heavy metals in river system during the COVID-19 pandemic lockdown might potentially assist in development of a public health risk mitigation system associated with the water consumption. The water quality of Punnakayal estuary in the Thamirabarani River system from the south India, a vital source of water for drinking and domestic purposes, industrial usage, and irrigation was assessed here. A comparitive assessment of physico-chemical variables (pH, EC, TDS, DO, BOD, turbidity and NO3), microbiological parameters (total coliform bacteria, fecal coliform bacteria, fecal streptococci and escherichia coli) and toxic metals (As, Cr, Fe, Cu, Zn, Cd, and Pb) suggested a decrease of 20% in the contaminant ratio during the lockdown period in comparison to the pre-lockdown period. The Health risk assessment models (HQ, HI, and TCR) highlighted carcinogenic and non-carcinogenic hazards for both children and adults through the ingestion and dermal adsorption exposures. The HI values for both As and Cr exceeded the acceptable limit (>1) during the lockdown period, but the potential risk for children and adults remained low in compaisio with the pre-lockdown period. Our results suggested that the Thamirabarani River system remained hostile to human health even during the lockdown period, and it requires regular monitoring through a volunteer water quality committee with private and government participations.

High Performance Agent-Based Modeling to Study Realistic Contact Tracing Protocols

Contact tracing (CT) is an important and effective intervention strategy for controlling an epidemic. Its role becomes critical when pharmaceutical interventions are unavailable. CT is resource intensive, and multiple protocols are possible, therefore the ability to evaluate strategies is important. We describe a high-performance, agent-based simulation model for studying CT during an ongoing pandemic. This work was motivated by the COVID-19 pandemic, however framework and design are generic and can be applied in other settings. This work extends our HPC-oriented ABM framework EpiHiper to efficiently represent contact tracing. The main contributions are: (i) Extension of EpiHiper to represent realistic CT processes. (ii) Realistic case study using the VA network motivated by our collaboration with the Virginia Department of Health. © 2021 IEEE.

AI-Driven Agent-Based Models to Study the Role of Vaccine Acceptance in Controlling COVID-19 Spread in the US

We study the role of vaccine acceptance in controlling the spread of COVID-19 in the US using AI-driven agent-based models. Our study uses a 288 million node social contact network spanning all 50 US states plus Washington DC, comprised of 3300 counties, with 12.59 billion daily interactions. The highly-resolved agent-based models use realistic information about disease progression, vaccine uptake, production schedules, acceptance trends, prevalence, and social distancing guidelines. Developing a national model at this resolution that is driven by realistic data requires a complex scalable workflow, model calibration, simulation, and analytics components. Our workflow optimizes the total execution time and helps in improving overall human productivity.This work develops a pipeline that can execute US-scale models and associated workflows that typically present significant big data challenges. Our results show that, when compared to faster and accelerating vaccinations, slower vaccination rates due to vaccine hesitancy cause averted infections to drop from 6.7M to 4.5M, and averted total deaths to drop from 39.4K to 28.2K nationwide. This occurs despite the fact that the final vaccine coverage is the same in both scenarios. Improving vaccine acceptance by 10% in all states increases averted infections from 4.5M to 4.7M (a 4.4% improvement) and total deaths from 28.2K to 29.9K (a 6% increase) nationwide. The analysis also reveals interesting spatio-temporal differences in COVID-19 dynamics as a result of vaccine acceptance. To our knowledge, this is the first national-scale analysis of the effect of vaccine acceptance on the spread of COVID-19, using detailed and realistic agent-based models. © 2021 IEEE.

All Models Are Useful: Bayesian Ensembling for Robust High Resolution COVID-19 Forecasting

Timely, high-resolution forecasts of infectious disease incidence are useful for policy makers in deciding intervention measures and estimating healthcare resource burden. In this paper, we consider the task of forecasting COVID-19 confirmed cases at the county level for the United States. Although multiple methods have been explored for this task, their performance has varied across space and time due to noisy data and the inherent dynamic nature of the pandemic. We present a forecasting pipeline which incorporates probabilistic forecasts from multiple statistical, machine learning and mechanistic methods through a Bayesian ensembling scheme, and has been operational for nearly 6 months serving local, state and federal policymakers in the United States. While showing that the Bayesian ensemble is at least as good as the individual methods, we also show that each individual method contributes significantly for different spatial regions and time points. We compare our model's performance with other similar models being integrated into CDC-initiated COVID-19 Forecast Hub, and show better performance at longer forecast horizons. Finally, we also describe how such forecasts are used to increase lead time for training mechanistic scenario projections. Our work demonstrates that such a real-time high resolution forecasting pipeline can be developed by integrating multiple methods within a performance-based ensemble to support pandemic response. © 2021 Owner/Author.

Scalable epidemiological workflows to support COVID-19 planning and response

The COVID-19 global outbreak represents the most significant epidemic event since the 1918 influenza pandemic. Simulations have played a crucial role in supporting COVID-19 planning and response efforts. Developing scalable workflows to provide policymakers quick responses to important questions pertaining to logistics, resource allocation, epidemic forecasts and intervention analysis remains a challenging computational problem. In this work, we present scalable high performance computing-enabled workflows for COVID-19 pandemic planning and response. The scalability of our methodology allows us to run fine-grained simulations daily, and to generate county-level forecasts and other counterfactual analysis for each of the 50 states (and DC), 3140 counties across the USA. Our workflows use a hybrid cloud/cluster system utilizing a combination of local and remote cluster computing facilities, and using over 20, 000 CPU cores running for 6-9 hours every day to meet this objective. Our state (Virginia), state hospital network, our university, the DOD and the CDC use our models to guide their COVID-19 planning and response efforts. We began executing these pipelines March 25, 2020, and have delivered and briefed weekly updates to these stakeholders for over 30 weeks without interruption. © 2021 IEEE.

Cohorting to Isolate asymptomatic spreaders: An agent-based simulation study on the Mumbai Suburban Railway

This paper studies cohorting in public transit systems and its usefulness in mitigating disease transmission. The Mumbai suburban railway system is used as a case study. © 2021 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.

From 5Vs to 6Cs: Operationalizing Epidemic Data Management with COVID-19 Surveillance

The COVID-19 pandemic brought to the forefront an unprecedented need for experts, as well as citizens, to visualize spatio-temporal disease surveillance data. Web application dashboards were quickly developed to fill t his g ap, b ut a ll of these dashboards supported a particular niche view of the pandemic (ie, current status or specific r egions). I n t his paper, we describe our work developing our COVID-19 Surveillance Dashboard, which offers a unique view of the pandemic while also allowing users to focus on the details that interest them. From the beginning, our goal was to provide a simple visual tool for comparing, organizing, and tracking near-real-time surveillance data as the pandemic progresses. In developing this dashboard, we also identified 6 key metrics which we propose as a standard for the design and evaluation of real-time epidemic science dashboards. Our dashboard was one of the first released to the public, and continues to be actively visited. Our own group uses it to support federal, state and local public health authorities, and it is used by individuals worldwide to track the evolution of the COVID-19 pandemic, build their own dashboards, and support their organizations as they plan their responses to the pandemic. © 2020 IEEE.

Examining Deep Learning Models with Multiple Data Sources for COVID-19 Forecasting

The COVID-19 pandemic represents the most significant public health disaster since the 1918 influenza pandemic. During pandemics such as COVID-19, timely and reliable spatio-temporal forecasting of epidemic dynamics is crucial. Deep learning-based time series models for forecasting have recently gained popularity and have been successfully used for epidemic forecasting. Here we focus on the design and analysis of deep learning-based models for COVID-19 forecasting. We implement multiple recurrent neural network-based deep learning models and combine them using the stacking ensemble technique. In order to incorporate the effects of multiple factors in COVID-19 spread, we consider multiple sources such as COVID-19 confirmed and death case count data and testing data for better predictions. To overcome the sparsity of training data and to address the dynamic correlation of the disease, we propose clustering-based training for high-resolution forecasting. The methods help us to identify the similar trends of certain groups of regions due to various spatio-temporal effects. We examine the proposed method for forecasting weekly COVID-19 new confirmed cases at county-, state-, and country-level. A comprehensive comparison between different time series models in COVID-19 context is conducted and analyzed. The results show that simple deep learning models can achieve comparable or better performance when compared with more complicated models. We are currently integrating our methods as a part of our weekly forecasts that we provide state and federal authorities. © 2020 IEEE.

SARS-CoV-2 pandemic lockdown: Effects on air quality in the industrialized Gujarat state of India.

Two weeks after the world health organization described the novel coronavirus (SARS-CoV-2) outbreak as pandemic, the Indian government implemented lockdown of industrial activities and traffic flows across the entire nation between March 24 and May 31, 2020. In this paper, we estimated the improvements achieved in air quality during the lockdown period (March 24, 2020 and April 20, 2020) compared to the pre-lockdown (January 1, 2020 and March 23, 2020) by analyzing PM2.5, PM10, SO2, CO, NO2 and O3 data from nine different air quality monitoring stations distributed across four different zones of the industrialized Gujarat state of western Indian. The Central Pollution Control Board (CPCB)-Air Quality Index (AQI) illustrated better air qualities during the lockdown with higher improvements in the zones 2 (Ahmedabad and Gandhinagar) and 3 (Jamnagar and Rajkot), and moderate improvements in the zones 1 (Surat, Ankleshwar and Vadodra) and 4 (Bhuj and Palanpur). The concentrations of PM2.5, PM10, and NO2 were reduced by 38-78%, 32-80% and 30-84%, respectively. Functioning of the power plants possibly led to less reduction in CO (3-55%) and the declined emission of NO helped to improve O3 (16-48%) contents. We observed an overall improvement of 58% in AQI for the first four months of 2020 compared to the same interval of previous year. This positive outcome resulted from the lockdown restrictions might help to modify the existing environmental policies of the region.

Imprints of pandemic lockdown on subsurface water quality in the coastal industrial city of Tuticorin, South India: A revival perspective.

Globally, the incidences of environmental improvements owing to seizing the anthropogenic activities during the lockdown have been reported through news articles and photographs, yet a formal scholarly study has been lacking to substantiate the imprints of lockdown. We hereby present the imprints of lockdown on water quality (both chemical and biological) parameters during the nationwide lockdown (COVID-19 epidemic) in India between 25th March to 30th May 2020. The present study describes the changes in chemical and biological water quality parameters based on twenty-two groundwater samples from the coastal industrial city of Tuticorin in Southern India, taken before (10 and 11th February 2020) and during the lockdown (19 and 20th April 2020) periods. The physico-chemical parameters compared are pH, total dissolved solids (TDS) and electrical conductivity (EC), nitrate (NO3), fluoride (F), chromium (Cr), iron (Fe), copper (Cu), zinc (Zn), cadmium (Cd), lead (Pb), arsenic (As), and selenium (Se), and the bacterial parameters are total coliforms, fecal coliforms, E. coli, and fecal streptococci. Among the metals, the significant reductions in Se (42%), As (51%), Fe (60%) and Pb (50%) were noticed probably owing to no or very less wastewater discharges from metal-based industries, seafood-based industries and thermal power plants during the lockdown. Reduction in NO3 (56%), total coliform (52%) and fecal coliforms (48%) indicated less organic sewage from the fishing industries. Contents of Cr, Cu, Zn and Cd, however, remained similar and fluoride did not show any change, probably as they were sourced from rock-water interactions. Similarly, we did not observe alterations in E. coli and fecal streptococci due to no significant change in domestic sewage production during the lockdown. The multivariate analyses aptly illustrated this and the principal component analyses helped to identify the sources that controlled water qualities of the lockdown compared to the pre-lockdown period. Our observation implies that groundwater is definitely under active interaction with surface waters and thus a quick revival could be observed following the seizing of anthropogenic activities.

Commentary on Ferguson, et al., "Impact of Non-pharmaceutical Interventions (NPIs) to Reduce COVID-19 Mortality and Healthcare Demand".

A recent manuscript (Ferguson et al. in Impact of non-pharmaceutical interventions (NPIs) to reduce COVID-19 mortality and healthcare demand, Imperial College COVID-19 Response Team, London, 2020. https://www.imperial.ac.uk/media/imperial-college/medicine/sph/ide/gida-fellowships/Imperial-College-COVID19-NPI-modelling-16-03-2020.pdf) from Imperial College modelers examining ways to mitigate and control the spread of COVID-19 has attracted much attention. In this paper, we will discuss a coarse taxonomy of models and explore the context and significance of the Imperial College and other models in contributing to the analysis of COVID-19.