Ajitesh Srivastava

Background Coronavirus Disease 2019 (COVID-19) continues to cause significant hospitalizations and deaths in the United States. Its continued burden and the impact of annually reformulated vaccines remain unclear. Here, we present projections of COVID-19 hospitalizations and deaths in the United States for the next 2 years under 2 plausible assumptions about immune escape (20% per year and 50% per year) and 3 possible CDC recommendations for the use of annually reformulated vaccines (no recommendation, vaccination for those aged 65 years and over, vaccination for all eligible age groups based on FDA approval). Methods and findings The COVID-19 Scenario Modeling Hub solicited projections of COVID-19 hospitalization and deaths between April 15, 2023 and April 15, 2025 under 6 scenarios representing the intersection of considered levels of immune escape and vaccination. Annually reformulated vaccines are assumed to be 65% effective against symptomatic infection with strains circulating on June 15 of each year and to become available on September 1. Age- and state-specific coverage in recommended groups was assumed to match that seen for the first (fall 2021) COVID-19 booster. State and national projections from 8 modeling teams were ensembled to produce projections for each scenario and expected reductions in disease outcomes due to vaccination over the projection period. From April 15, 2023 to April 15, 2025, COVID-19 is projected to cause annual epidemics peaking November to January. In the most pessimistic scenario (high immune escape, no vaccination recommendation), we project 2.1 million …

Indirect surveys, in which respondents provide information about other people they know, have been proposed for estimating (nowcasting) the size of a \emph{hidden population} where privacy is important or the hidden population is hard to reach. Examples include estimating casualties in an earthquake, conditions among female sex workers, and the prevalence of drug use and infectious diseases. The Network Scale-up Method (NSUM) is the classical approach to developing estimates from indirect surveys, but it was designed for one-shot surveys. Further, it requires certain assumptions and asking for or estimating the number of individuals in each respondent's network. In recent years, surveys have been increasingly deployed online and can collect data continuously (e.g., COVID-19 surveys on Facebook during much of the pandemic). Conventional NSUM can be applied to these scenarios by analyzing the data independently at each point in time, but this misses the opportunity of leveraging the temporal dimension. We propose to use the responses from indirect surveys collected over time and develop analytical tools (i) to prove that indirect surveys can provide better estimates for the trends of the hidden population over time, as compared to direct surveys and (ii) to identify appropriate temporal aggregations to improve the estimates. We demonstrate through extensive simulations that our approach outperforms traditional NSUM and direct surveying methods. We also empirically demonstrate the superiority of our approach on a real indirect survey dataset of COVID-19 cases.

During the COVID-19 pandemic, a major driver of new surges has been the emergence of new variants. When a new variant emerges in one or more countries, other nations monitor its spread in preparation for its potential arrival. The impact of the variant and the timing of epidemic peaks in a country highly depend on when the variant arrives. The current methods for predicting the spread of new variants rely on statistical modeling, however, these methods work only when the new variant has already arrived in the region of interest and has a significant prevalence. The question arises: Can we predict when (and if) a variant that exists elsewhere will arrive in a given country and reach a certain prevalence? We propose a variant-dynamics-informed Graph Neural Network (GNN) approach. First, We derive the dynamics of variant prevalence across pairs of regions (countries) that applies to a large class of epidemic models. The dynamics suggest that ratios of variant proportions lead to simpler patterns. Therefore, we use ratios of variant proportions along with some parameters estimated from the dynamics as features in a GNN. We develop a benchmarking tool to evaluate variant emergence prediction over 87 countries and 36 variants. We leverage this tool to compare our GNN-based approach against our dynamics-only model and a number of machine learning models. Results show that the proposed dynamics-informed GNN method retrospectively outperforms all the baselines, including the currently pervasive framework of Physics-Informed Neural Networks (PINNs) that incorporates the dynamics in the loss function.

The traditional methods for detecting autism spectrum disorder (ASD) are expensive, subjective, and time-consuming, often taking years for a diagnosis, with many children growing well into adolescence and even adulthood before finally confirming the disorder. Recently, graph-based learning techniques have demonstrated impressive results on resting-state functional magnetic resonance imaging (rs-fMRI) data from the Autism Brain Imaging Data Exchange (ABIDE). We introduce IMAGIN, a multI-granular, Multi-Atlas spatio-temporal attention Graph Isomorphism Network, which, which we use to learn graph representations of dynamic functional brain connectivity (chronnectome), as opposed to static connectivity (connectome). The experimental results demonstrate that IMAGIN achieves a 5-fold cross validation accuracy of 79.25%, which surpasses the current state-of-the-art by 1.5%. In addition, analysis of the …

BackgroundThe COVID-19 Scenario Modeling Hub convened nine modeling teams to project the impact of expanding SARS-CoV-2 vaccination to children aged 5–11 years on COVID-19 burden and resilience against variant strains.MethodsTeams contributed state- and national-level weekly projections of cases, hospitalizations, and deaths in the United States from September 12, 2021 to March 12, 2022. Four scenarios covered all combinations of 1) vaccination (or not) of children aged 5–11 years (starting November 1, 2021), and 2) emergence (or not) of a variant more transmissible than the Delta variant (emerging November 15, 2021). Individual team projections were linearly pooled. The effect of childhood vaccination on overall and age-specific outcomes was estimated using meta-analyses.FindingsAssuming that a new variant would not emerge, all-age COVID-19 outcomes were projected to decrease …

Our ability to forecast epidemics far into the future is constrained by the many complexities of disease systems. Realistic longer-term projections may, however, be possible under well-defined scenarios that specify the future state of critical epidemic drivers. Since December 2020, the U.S. COVID-19 Scenario Modeling Hub (SMH) has convened multiple modeling teams to make months ahead projections of SARS-CoV-2 burden, totaling nearly 1.8 million national and state-level projections. Here, we find SMH performance varied widely as a function of both scenario validity and model calibration. We show scenarios remained close to reality for 22 weeks on average before the arrival of unanticipated SARS-CoV-2 variants invalidated key assumptions. An ensemble of participating models that preserved variation between models (using the linear opinion pool method) was consistently more reliable than any single …

Background: Short-term forecasts of infectious disease burden can contribute to situational awareness and aid capacity planning. Based on best practice in other fields and recent insights in infectious disease epidemiology, one can maximise the predictive performance of such forecasts if multiple models are combined into an ensemble. Here, we report on the performance of ensembles in predicting COVID-19 cases and deaths across Europe between 08 March 2021 and 07 March 2022.Methods: We used open-source tools to develop a public European COVID-19 Forecast Hub. We invited groups globally to contribute weekly forecasts for COVID-19 cases and deaths reported by a standardised source for 32 countries over the next 1–4 weeks. Teams submitted forecasts from March 2021 using standardised quantiles of the predictive distribution. Each week we created an ensemble forecast, where each predictive quantile was calculated as the equally-weighted average (initially the mean and then from 26th July the median) of all individual models’ predictive quantiles. We measured the performance of each model using the relative Weighted Interval Score (WIS), comparing models’ forecast accuracy relative to all other models. We retrospectively explored alternative methods for ensemble forecasts, including weighted averages based on models’ past predictive performance.Results: Over 52 weeks, we collected forecasts from 48 unique models. We evaluated 29 models’ forecast scores in comparison to the ensemble model. We found a weekly ensemble had a consistently strong performance across countries over time. Across all horizons …

Measuring distance or similarity between time-series data is a fundamental aspect of many applications including classification and clustering. Existing measures may fail to capture similarities due to local trends (shapes) and may even produce misleading results. Our goal is to develop a measure that looks for similar trends occurring around similar times and is easily interpretable for researchers in applied domains. This is particularly useful for applications where time-series have a sequence of meaningful local trends that are ordered, such as in epidemics (a surge to an increase to a peak to a decrease). We propose a novel measure, DTW+S, which creates an interpretable "closeness-preserving" matrix representation of the time-series, where each column represents local trends, and then it applies Dynamic Time Warping to compute distances between these matrices. We present a theoretical analysis that supports the choice of this representation. We demonstrate the utility of DTW+S in ensemble building and clustering of epidemic curves. We also demonstrate that our approach results in better classification compared to Dynamic Time Warping for a class of datasets, particularly when local trends rather than scale play a decisive role.

This letter presents a technique to identify a certain transfer function in a dynamic network when the input and the output of the transfer function are influenced by an unmeasured confounding variable. It is assumed that in an observational framework, only a subset of the variables of the network are measured and the topology of the interconnections between the variables is partially known. The focus of this letter is the challenging scenario where it is not possible to measure any variables on the directed paths from the confounding variable to either the input or the output of the transfer function of interest. Sufficient conditions are derived to determine a set of instrumental variables and a set of auxiliary variables that guarantee consistent identification of the transfer function using an algorithm based on prediction error method for the class of acyclic networks. It is also shown that similar ideas could be applied to cyclic …

$ $Acoustic-to-articulatory inversion (AAI) involves mapping from the acoustic space to the articulatory space. Signal-processing features like the MFCCs, have been widely used for the AAI task. For subjects with dysarthric speech, AAI is challenging because of an imprecise and indistinct pronunciation. In this work, we perform AAI for dysarthric speech using representations from pre-trained self-supervised learning (SSL) models. We demonstrate the impact of different pre-trained features on this challenging AAI task, at low-resource conditions. In addition, we also condition x-vectors to the extracted SSL features to train a BLSTM network. In the seen case, we experiment with three AAI training schemes (subject-specific, pooled, and fine-tuned). The results, consistent across training schemes, reveal that DeCoAR, in the fine-tuned scheme, achieves a relative improvement of the Pearson Correlation Coefficient (CC) by 1.81\% and 4.56\% for healthy controls and patients, respectively, over MFCCs. In the unseen case, we observe similar average trends for different SSL features. Overall, SSL networks like wav2vec, APC, and DeCoAR, which are trained with feature reconstruction or future timestep prediction tasks, perform well in predicting dysarthric articulatory trajectories.

Indirect surveys, in which respondents provide information about other people they know, have been proposed for scenarios where privacy is important or where the population to be surveyed is hard to reach. As an example, during various stages of the COVID-19 pandemic surveys, including indirect surveys, have been used to estimate the number of cases or the level of vaccination. The Network Scale-up Method (NSUM) is the classical approach to developing such estimates but was designed with discrete, time-limited indirect surveys in mind. Further, it requires asking for or estimating the number of individuals in each respondent's network. In recent years, surveys are being increasingly deployed online and collecting data continuously (e.g., COVID-19 surveys on Facebook during much of the pandemic). Conventional NSUM can be applied to these scenarios by analyzing the data independently during each time interval, but this misses the opportunity of leveraging the temporal dimension. Understanding the advantage of simply smoothing NSUM results to various degrees is not trivial. We propose to use the responses from indirect surveys collected over time and develop analytical tools (i) to prove that indirect surveys can be used to provide better estimates for the size of the hidden population compared to direct surveys, and (ii) to identify appropriate aggregations over time to further improve the estimates. We demonstrate through simulations that our approach outperforms traditional NSUM and direct surveying methods to estimate the size of a time-varying hidden population. We also demonstrate the superiority of our approach on an …

Background Collaborative comparisons and combinations of multiple epidemic models are used as policy-relevant evidence during epidemic outbreaks. Typically, each modeller summarises their own distribution of simulated trajectories using descriptive statistics at each modelled time step. We explored information losses compared to directly collecting a sample of the simulated trajectories, in terms of key epidemic quantities, ensemble uncertainty, and performance against data.Methods We compared July 2022 projections from the European COVID-19 Scenario Modelling Hub. Using shared scenario assumptions, five modelling teams contributed up to 100 simulated trajectories projecting incidence in Belgium, the Netherlands, and Spain. First, we compared epidemic characteristics including incidence, peaks, and cumulative totals. Second, we drew a set of quantiles from the sampled trajectories for each model at each time step. We created an ensemble as the median across models at each quantile, and compared this to an ensemble of quantiles drawn from all available trajectories at each time step. Third, we compared each trajectory to between 4 and 29 weeks of observed data, using the mean absolute error to weight trajectories in consecutive ensembles.Results We found that collecting models’ simulated trajectories, as opposed to collecting models’ quantiles at each time point, enabled us to show additional epidemic characteristics, a wider range of uncertainty, and performance against data. Sampled trajectories contained a right-skewed distribution which was poorly captured by an ensemble of models’ quantile intervals …

Accurate forecasts can enable more effective public health responses during seasonal influenza epidemics. Forecasting teams were asked to provide national and jurisdiction-specific probabilistic predictions of weekly confirmed influenza hospital admissions for one through four weeks ahead for the 2021-22 and 2022-23 influenza seasons. Across both seasons, 26 teams submitted forecasts, with the submitting teams varying between seasons. Forecast skill was evaluated using the Weighted Interval Score (WIS), relative WIS, and coverage. Six out of 23 models outperformed the baseline model across forecast weeks and locations in 2021-22 and 12 out of 18 models in 2022-23. Averaging across all forecast targets, the FluSight ensemble was the 2nd most accurate model measured by WIS in 2021-22 and the 5th most accurate in the 2022-23 season. Forecast skill and 95% coverage for the FluSight ensemble and most component models degraded over longer forecast horizons and during periods of rapid change. Current influenza forecasting efforts help inform situational awareness, but research is needed to address limitations, including decreased performance during periods of changing epidemic dynamics.

Our ability to forecast epidemics more than a few weeks into the future is constrained by the complexity of disease systems, our limited ability to measure the current state of an epidemic, and uncertainties in how human action will affect transmission. Realistic longer-term projections (spanning more than a few weeks) may, however, be possible under defined scenarios that specify the future state of critical epidemic drivers, with the additional benefit that such scenarios can be used to anticipate the comparative effect of control measures. Since December 2020, the US COVID-19 Scenario Modeling Hub (SMH) has convened multiple modeling teams to make 6-month ahead projections of the number of SARS-CoV-2 cases, hospitalizations and deaths. The SMH released nearly 1.8 million national and state-level projections between February 2021 and November 2022. SMH performance varied widely as a function of …

Challenges of COVID-19 Case Forecasting in the US, 2020-2021 (preprint) | medrxiv; 2023. | PREPRINT-MEDRXIV 1 2 3 +A A -A The WHO Covid-19 Research Database is a resource created in response to the Public Health Emergency of International Concern (PHEIC). Its content remains searchable and spans the time period March 2020 to June 2023. Since June 2023, manual updates to the database have been discontinued. 3.Challenges of COVID-19 Case Forecasting in the US, 2020-2021 (preprint) This article is a Preprint Preprints are preliminary research reports that have not been certified by peer review. They should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information. Preprints posted online allow authors to receive rapid feedback and the entire scientific community can appraise the work for themselves and respond …

We proposed the SIkJalpha model at the beginning of the COVID-19 pandemic (early 2020). Since then, as the pandemic evolved, more complexities were added to capture crucial factors and variables that can assist with projecting desired future scenarios. Throughout the pandemic, multi-model collaborative efforts have been organized to predict short-term outcomes (cases, deaths, and hospitalizations) of COVID-19 and long-term scenario projections. We have been participating in five such efforts. This paper presents the evolution of the SIkJalpha model and its many versions that have been used to submit to these collaborative efforts since the beginning of the pandemic. Specifically, we show that the SIkJalpha model is an approximation of a class of epidemiological models. We demonstrate how the model can be used to incorporate various complexities, including under-reporting, multiple variants, waning of …

With the rise of Big Data, there has been a significant effort in increasing compute power through GPUs, TPUs, and heterogeneous architectures. As a result, many applications are memory bound, i.e., they are bottlenecked by the movement of data from main memory to compute units. One way to address this issue is through data prefetching, which relies on accurate prediction of memory accesses. While recent deep learning models have performed well on sequence prediction problems, they are far too heavy in terms of model size and inference latency to be practical for data prefetching. Here, we propose clustering-driven compact LSTM models that can predict the next memory access with high accuracy. We introduce a novel clustering approach called Delegated model that can reliably cluster the applications. For each cluster, we train a compact meta-LSTM model that can quickly adapt to any application in …

Robotic comedians (and social robots generally) need to recognize and adapt to human responses during playful dialog. To support this ability, we determined design guidelines via a survey of 20 human comedians and developed a machine learning pipeline to support comedian-like behaviors by our robotic system. Based on comedian input, we identified that discerning laughter vs. no laughter during a joke setup and big laugh vs. so-so response vs. no laugh after a punchline were important skills for a comedian. To enable these abilities in a robotic system, we used an existing dataset of robot comedy performance audio to train classifiers for audience responses during the setup and after the punchline of jokes. Top-performing models for the above types of discernment performed similarly to human raters who completed the same classification task. Comparison of the current results to our past efforts of a similar …

In Spring 2021, the highly transmissible SARS-CoV-2 Delta variant began to cause increases in cases, hospitalizations, and deaths in parts of the United States. At the time, with slowed vaccination uptake, this novel variant was expected to increase the risk of pandemic resurgence in the US in summer and fall 2021. As part of the COVID-19 Scenario Modeling Hub, an ensemble of nine mechanistic models produced 6-month scenario projections for July–December 2021 for the United States. These projections estimated substantial resurgences of COVID-19 across

Forecasting the hospitalizations caused by the Influenza virus is vital for public health planning so that hospitals can be better prepared for an influx of patients. Many forecasting methods have been used in real-time during the Influenza seasons and submitted to the CDC for public communication. The forecasting models range from mechanistic models, and auto-regression models to machine learning models. We hypothesize that we can improve forecasting by using multiple mechanistic models to produce potential trajectories and use machine learning to learn how to combine those trajectories into an improved forecast. We propose a Tree Ensemble model design that utilizes the individual predictors of our baseline model SIkJalpha to improve its performance. Each predictor is generated by changing a set of hyper-parameters. We compare our prospective forecasts deployed for the FluSight challenge (2022) to all the other submitted approaches. Our approach is fully automated and does not require any manual tuning. We demonstrate that our Random Forest-based approach is able to improve upon the forecasts of the individual predictors in terms of mean absolute error, coverage, and weighted interval score. Our method outperforms all other models in terms of the mean absolute error and the weighted interval score based on the mean across all weekly submissions in the current season (2022). Explainability of the Random Forest (through analysis of the trees) enables us to gain insights into how it improves upon the individual predictors.