Integrating explanation and prediction in computational social science.

Computational social science is more than just large repositories of digital data and the computational methods needed to construct and analyse them. It also represents a convergence of different fields with different ways of thinking about and doing science. The goal of this Perspective is to provide some clarity around how these approaches differ from one another and to propose how they might be productively integrated. Towards this end we make two contributions. The first is a schema for thinking about research activities along two dimensions-the extent to which work is explanatory, focusing on identifying and estimating causal effects, and the degree of consideration given to testing predictions of outcomes-and how these two priorities can complement, rather than compete with, one another. Our second contribution is to advocate that computational social scientists devote more attention to combining prediction and explanation, which we call integrative modelling, and to outline some practical suggestions for realizing this goal.

Cryptic transmission of SARS-CoV-2 and the first COVID-19 wave.

Considerable uncertainty surrounds the timeline of introductions and onsets of local transmission of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) globally1-7. Although a limited number of SARS-CoV-2 introductions were reported in January and February 2020 (refs.8,9), the narrowness of the initial testing criteria, combined with a slow growth in testing capacity and porous travel screening10, left many countries vulnerable to unmitigated, cryptic transmission. Here we use a global metapopulation epidemic model to provide a mechanistic understanding of the early dispersal of infections and the temporal windows of the introduction of SARS-CoV-2 and onset of local transmission in Europe and the USA. We find that community transmission of SARS-CoV-2 was likely to have been present in several areas of Europe and the USA by January 2020, and estimate that by early March, only 1 to 4 in 100 SARS-CoV-2 infections were detected by surveillance systems. The modelling results highlight international travel as the key driver of the introduction of SARS-CoV-2, with possible introductions and transmission events as early as December 2019 to January 2020. We find a heterogeneous geographic distribution of cumulative infection attack rates by 4 July 2020, ranging from 0.78% to 15.2% across US states and 0.19% to 13.2% in European countries. Our approach complements phylogenetic analyses and other surveillance approaches and provides insights that can be used to design innovative, model-driven surveillance systems that guide enhanced testing and response strategies.

Heterogeneous changes in mobility in response to the SARS-CoV-2 Omicron BA.2 outbreak in Shanghai.

The coronavirus disease 2019 (COVID-19) pandemic and the measures taken by authorities to control its spread have altered human behavior and mobility patterns in an unprecedented way. However, it remains unclear whether the population response to a COVID-19 outbreak varies within a city or among demographic groups. Here, we utilized passively recorded cellular signaling data at a spatial resolution of 1 km × 1 km for over 5 million users and epidemiological surveillance data collected during the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) Omicron BA.2 outbreak from February to June 2022 in Shanghai, China, to investigate the heterogeneous response of different segments of the population at the within-city level and examine its relationship with the actual risk of infection. Changes in behavior were spatially heterogenous within the city and population groups and associated with both the infection incidence and adopted interventions. We also found that males and individuals aged 30 to 59 y old traveled more frequently, traveled longer distances, and their communities were more connected; the same groups were also associated with the highest SARS-CoV-2 incidence. Our results highlight the heterogeneous behavioral change of the Shanghai population to the SARS-CoV-2 Omicron BA.2 outbreak and the effect of heterogenous behavior on the spread of COVID-19, both spatially and demographically. These findings could be instrumental for the design of targeted interventions for the control and mitigation of future outbreaks of COVID-19, and, more broadly, of respiratory pathogens.

Multimodeling approach to evaluating the efficacy of layering pharmaceutical and nonpharmaceutical interventions for influenza pandemics.

When an influenza pandemic emerges, temporary school closures and antiviral treatment may slow virus spread, reduce the overall disease burden, and provide time for vaccine development, distribution, and administration while keeping a larger portion of the general population infection free. The impact of such measures will depend on the transmissibility and severity of the virus and the timing and extent of their implementation. To provide robust assessments of layered pandemic intervention strategies, the Centers for Disease Control and Prevention (CDC) funded a network of academic groups to build a framework for the development and comparison of multiple pandemic influenza models. Research teams from Columbia University, Imperial College London/Princeton University, Northeastern University, the University of Texas at Austin/Yale University, and the University of Virginia independently modeled three prescribed sets of pandemic influenza scenarios developed collaboratively by the CDC and network members. Results provided by the groups were aggregated into a mean-based ensemble. The ensemble and most component models agreed on the ranking of the most and least effective intervention strategies by impact but not on the magnitude of those impacts. In the scenarios evaluated, vaccination alone, due to the time needed for development, approval, and deployment, would not be expected to substantially reduce the numbers of illnesses, hospitalizations, and deaths that would occur. Only strategies that included early implementation of school closure were found to substantially mitigate early spread and allow time for vaccines to be developed and administered, especially under a highly transmissible pandemic scenario.

Quantifying the importance and location of SARS-CoV-2 transmission events in large metropolitan areas.

Detailed characterization of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) transmission across different settings can help design less disruptive interventions. We used real-time, privacy-enhanced mobility data in the New York City, NY and Seattle, WA metropolitan areas to build a detailed agent-based model of SARS-CoV-2 infection to estimate the where, when, and magnitude of transmission events during the pandemic's first wave. We estimate that only 18% of individuals produce most infections (80%), with about 10% of events that can be considered superspreading events (SSEs). Although mass gatherings present an important risk for SSEs, we estimate that the bulk of transmission occurred in smaller events in settings like workplaces, grocery stores, or food venues. The places most important for transmission change during the pandemic and are different across cities, signaling the large underlying behavioral component underneath them. Our modeling complements case studies and epidemiological data and indicates that real-time tracking of transmission events could help evaluate and define targeted mitigation policies.

Potential impact of annual vaccination with reformulated COVID-19 vaccines: Lessons from the US COVID-19 scenario modeling hub.

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 (90% projection interval (PI) [1,438,000, 4,270,000]) hospitalizations and 209,000 (90% PI [139,000, 461,000]) deaths, exceeding pre-pandemic mortality of influenza and pneumonia. In high immune escape scenarios, vaccination of those aged 65+ results in 230,000 (95% confidence interval (CI) [104,000, 355,000]) fewer hospitalizations and 33,000 (95% CI [12,000, 54,000]) fewer deaths, while vaccination of all eligible individuals results in 431,000 (95% CI: 264,000-598,000) fewer hospitalizations and 49,000 (95% CI [29,000, 69,000]) fewer deaths. CONCLUSIONS: COVID-19 is projected to be a significant public health threat over the coming 2 years. Broad vaccination has the potential to substantially reduce the burden of this disease, saving tens of thousands of lives each year.

Anatomy of the first six months of COVID-19 vaccination campaign in Italy.

We analyze the effectiveness of the first six months of vaccination campaign against SARS-CoV-2 in Italy by using a computational epidemic model which takes into account demographic, mobility, vaccines data, as well as estimates of the introduction and spreading of the more transmissible Alpha variant. We consider six sub-national regions and study the effect of vaccines in terms of number of averted deaths, infections, and reduction in the Infection Fatality Rate (IFR) with respect to counterfactual scenarios with the actual non-pharmaceuticals interventions but no vaccine administration. Furthermore, we compare the effectiveness in counterfactual scenarios with different vaccines allocation strategies and vaccination rates. Our results show that, as of 2021/07/05, vaccines averted 29, 350 (IQR: [16, 454-42, 826]) deaths and 4, 256, 332 (IQR: [1, 675, 564-6, 980, 070]) infections and a new pandemic wave in the country. During the same period, they achieved a -22.2% (IQR: [-31.4%; -13.9%]) IFR reduction. We show that a campaign that would have strictly prioritized age groups at higher risk of dying from COVID-19, besides frontline workers and the fragile population, would have implied additional benefits both in terms of avoided fatalities and reduction in the IFR. Strategies targeting the most active age groups would have prevented a higher number of infections but would have been associated with more deaths. Finally, we study the effects of different vaccination intake scenarios by rescaling the number of available doses in the time period under study to those administered in other countries of reference. The modeling framework can be applied to other countries to provide a mechanistic characterization of vaccination campaigns worldwide.

Rapid review and meta-analysis of serial intervals for SARS-CoV-2 Delta and Omicron variants.

BACKGROUND: The serial interval is the period of time between symptom onset in the primary case and symptom onset in the secondary case. Understanding the serial interval is important for determining transmission dynamics of infectious diseases like COVID-19, including the reproduction number and secondary attack rates, which could influence control measures. Early meta-analyses of COVID-19 reported serial intervals of 5.2 days (95% CI: 4.9-5.5) for the original wild-type variant and 5.2 days (95% CI: 4.87-5.47) for Alpha variant. The serial interval has been shown to decrease over the course of an epidemic for other respiratory diseases, which may be due to accumulating viral mutations and implementation of more effective nonpharmaceutical interventions. We therefore aggregated the literature to estimate serial intervals for Delta and Omicron variants. METHODS: This study followed Preferred Reporting Items for Systematic Reviews and Meta-analyses guidelines. A systematic literature search was conducted of PubMed, Scopus, Cochrane Library, ScienceDirect, and preprint server medRxiv for articles published from April 4, 2021, through May 23, 2023. Search terms were: ("serial interval" or "generation time"), ("Omicron" or "Delta"), and ("SARS-CoV-2" or "COVID-19"). Meta-analyses were done for Delta and Omicron variants using a restricted maximum-likelihood estimator model with a random effect for each study. Pooled average estimates and 95% confidence intervals (95% CI) are reported. RESULTS: There were 46,648 primary/secondary case pairs included for the meta-analysis of Delta and 18,324 for Omicron. Mean serial interval for included studies ranged from 2.3-5.8 days for Delta and 2.1-4.8 days for Omicron. The pooled mean serial interval for Delta was 3.9 days (95% CI: 3.4-4.3) (20 studies) and Omicron was 3.2 days (95% CI: 2.9-3.5) (20 studies). Mean estimated serial interval for BA.1 was 3.3 days (95% CI: 2.8-3.7) (11 studies), BA.2 was 2.9 days (95% CI: 2.7-3.1) (six studies), and BA.5 was 2.3 days (95% CI: 1.6-3.1) (three studies). CONCLUSIONS: Serial interval estimates for Delta and Omicron were shorter than ancestral SARS-CoV-2 variants. More recent Omicron subvariants had even shorter serial intervals suggesting serial intervals may be shortening over time. This suggests more rapid transmission from one generation of cases to the next, consistent with the observed faster growth dynamic of these variants compared to their ancestors. Additional changes to the serial interval may occur as SARS-CoV-2 continues to circulate and evolve. Changes to population immunity (due to infection and/or vaccination) may further modify it.

Predicting seasonal influenza using supermarket retail records.

Increased availability of epidemiological data, novel digital data streams, and the rise of powerful machine learning approaches have generated a surge of research activity on real-time epidemic forecast systems. In this paper, we propose the use of a novel data source, namely retail market data to improve seasonal influenza forecasting. Specifically, we consider supermarket retail data as a proxy signal for influenza, through the identification of sentinel baskets, i.e., products bought together by a population of selected customers. We develop a nowcasting and forecasting framework that provides estimates for influenza incidence in Italy up to 4 weeks ahead. We make use of the Support Vector Regression (SVR) model to produce the predictions of seasonal flu incidence. Our predictions outperform both a baseline autoregressive model and a second baseline based on product purchases. The results show quantitatively the value of incorporating retail market data in forecasting models, acting as a proxy that can be used for the real-time analysis of epidemics.

Estimating the cumulative incidence of COVID-19 in the United States using influenza surveillance, virologic testing, and mortality data: Four complementary approaches.

Effectively designing and evaluating public health responses to the ongoing COVID-19 pandemic requires accurate estimation of the prevalence of COVID-19 across the United States (US). Equipment shortages and varying testing capabilities have however hindered the usefulness of the official reported positive COVID-19 case counts. We introduce four complementary approaches to estimate the cumulative incidence of symptomatic COVID-19 in each state in the US as well as Puerto Rico and the District of Columbia, using a combination of excess influenza-like illness reports, COVID-19 test statistics, COVID-19 mortality reports, and a spatially structured epidemic model. Instead of relying on the estimate from a single data source or method that may be biased, we provide multiple estimates, each relying on different assumptions and data sources. Across our four approaches emerges the consistent conclusion that on April 4, 2020, the estimated case count was 5 to 50 times higher than the official positive test counts across the different states. Nationally, our estimates of COVID-19 symptomatic cases as of April 4 have a likely range of 2.3 to 4.8 million, with possibly as many as 7.6 million cases, up to 25 times greater than the cumulative confirmed cases of about 311,000. Extending our methods to May 16, 2020, we estimate that cumulative symptomatic incidence ranges from 4.9 to 10.1 million, as opposed to 1.5 million positive test counts. The proposed combination of approaches may prove useful in assessing the burden of COVID-19 during resurgences in the US and other countries with comparable surveillance systems.

Modeling of Future COVID-19 Cases, Hospitalizations, and Deaths, by Vaccination Rates and Nonpharmaceutical Intervention Scenarios - United States, April-September 2021.

After a period of rapidly declining U.S. COVID-19 incidence during January-March 2021, increases occurred in several jurisdictions (1,2) despite the rapid rollout of a large-scale vaccination program. This increase coincided with the spread of more transmissible variants of SARS-CoV-2, the virus that causes COVID-19, including B.1.1.7 (1,3) and relaxation of COVID-19 prevention strategies such as those for businesses, large-scale gatherings, and educational activities. To provide long-term projections of potential trends in COVID-19 cases, hospitalizations, and deaths, COVID-19 Scenario Modeling Hub teams used a multiple-model approach comprising six models to assess the potential course of COVID-19 in the United States across four scenarios with different vaccination coverage rates and effectiveness estimates and strength and implementation of nonpharmaceutical interventions (NPIs) (public health policies, such as physical distancing and masking) over a 6-month period (April-September 2021) using data available through March 27, 2021 (4). Among the four scenarios, an accelerated decline in NPI adherence (which encapsulates NPI mandates and population behavior) was shown to undermine vaccination-related gains over the subsequent 2-3 months and, in combination with increased transmissibility of new variants, could lead to surges in cases, hospitalizations, and deaths. A sharp decline in cases was projected by July 2021, with a faster decline in the high-vaccination scenarios. High vaccination rates and compliance with public health prevention measures are essential to control the COVID-19 pandemic and to prevent surges in hospitalizations and deaths in the coming months.

The COVID-19 outbreak in Sichuan, China: Epidemiology and impact of interventions.

In January 2020, a COVID-19 outbreak was detected in Sichuan Province of China. Six weeks later, the outbreak was successfully contained. The aim of this work is to characterize the epidemiology of the Sichuan outbreak and estimate the impact of interventions in limiting SARS-CoV-2 transmission. We analyzed patient records for all laboratory-confirmed cases reported in the province for the period of January 21 to March 16, 2020. To estimate the basic and daily reproduction numbers, we used a Bayesian framework. In addition, we estimated the number of cases averted by the implemented control strategies. The outbreak resulted in 539 confirmed cases, lasted less than two months, and no further local transmission was detected after February 27. The median age of local cases was 8 years older than that of imported cases. We estimated R0 at 2.4 (95% CI: 1.6-3.7). The epidemic was self-sustained for about 3 weeks before going below the epidemic threshold 3 days after the declaration of a public health emergency by Sichuan authorities. Our findings indicate that, were the control measures be adopted four weeks later, the epidemic could have lasted 49 days longer (95% CI: 31-68 days), causing 9,216 more cases (95% CI: 1,317-25,545).

Detecting critical slowing down in high-dimensional epidemiological systems.

Despite medical advances, the emergence and re-emergence of infectious diseases continue to pose a public health threat. Low-dimensional epidemiological models predict that epidemic transitions are preceded by the phenomenon of critical slowing down (CSD). This has raised the possibility of anticipating disease (re-)emergence using CSD-based early-warning signals (EWS), which are statistical moments estimated from time series data. For EWS to be useful at detecting future (re-)emergence, CSD needs to be a generic (model-independent) feature of epidemiological dynamics irrespective of system complexity. Currently, it is unclear whether the predictions of CSD-derived from simple, low-dimensional systems-pertain to real systems, which are high-dimensional. To assess the generality of CSD, we carried out a simulation study of a hierarchy of models, with increasing structural complexity and dimensionality, for a measles-like infectious disease. Our five models included: i) a nonseasonal homogeneous Susceptible-Exposed-Infectious-Recovered (SEIR) model, ii) a homogeneous SEIR model with seasonality in transmission, iii) an age-structured SEIR model, iv) a multiplex network-based model (Mplex) and v) an agent-based simulator (FRED). All models were parameterised to have a herd-immunity immunization threshold of around 90% coverage, and underwent a linear decrease in vaccine uptake, from 92% to 70% over 15 years. We found evidence of CSD prior to disease re-emergence in all models. We also evaluated the performance of seven EWS: the autocorrelation, coefficient of variation, index of dispersion, kurtosis, mean, skewness, variance. Performance was scored using the Area Under the ROC Curve (AUC) statistic. The best performing EWS were the mean and variance, with AUC > 0.75 one year before the estimated transition time. These two, along with the autocorrelation and index of dispersion, are promising candidate EWS for detecting disease emergence.

Using simulated infectious disease outbreaks to inform site selection and sample size for individually randomized vaccine trials during an ongoing epidemic.

BACKGROUND: Novel strategies are needed to make vaccine efficacy trials more robust given uncertain epidemiology of infectious disease outbreaks, such as arboviruses like Zika. Spatially resolved mathematical and statistical models can help investigators identify sites at highest risk of future transmission and prioritize these for inclusion in trials. Models can also characterize uncertainty in whether transmission will occur at a site, and how nearby or connected sites may have correlated outcomes. A structure is needed for how trials can use models to address key design questions, including how to prioritize sites, the optimal number of sites, and how to allocate participants across sites. METHODS: We illustrate the added value of models using the motivating example of Zika vaccine trial planning during the 2015-2017 Zika epidemic. We used a stochastic, spatially resolved, transmission model (the Global Epidemic and Mobility model) to simulate epidemics and site-level incidence at 100 high-risk sites in the Americas. We considered several strategies for prioritizing sites (average site-level incidence of infection across epidemics, median incidence, probability of exceeding 1% incidence), selecting the number of sites, and allocating sample size across sites (equal enrollment, proportional to average incidence, proportional to rank). To evaluate each design, we stochastically simulated trials in each hypothetical epidemic by drawing observed cases from site-level incidence data. RESULTS: When constraining overall trial size, the optimal number of sites represents a balance between prioritizing highest-risk sites and having enough sites to reduce the chance of observing too few endpoints. The optimal number of sites remained roughly constant regardless of the targeted number of events, although it is necessary to increase the sample size to achieve the desired power. Though different ranking strategies returned different site orders, they performed similarly with respect to trial power. Instead of enrolling participants equally from each site, investigators can allocate participants proportional to projected incidence, though this did not provide an advantage in our example because the top sites had similar risk profiles. Sites from the same geographic region may have similar outcomes, so optimal combinations of sites may be geographically dispersed, even when these are not the highest ranked sites. CONCLUSION: Mathematical and statistical models may assist in designing successful vaccination trials by capturing uncertainty and correlation in future transmission. Although many factors affect site selection, such as logistical feasibility, models can help investigators optimize site selection and the number and size of participating sites. Although our study focused on trial design for an emerging arbovirus, a similar approach can be made for any infectious disease with the appropriate model for the particular disease.

Measurability of the epidemic reproduction number in data-driven contact networks.

The basic reproduction number is one of the conceptual cornerstones of mathematical epidemiology. Its classical definition as the number of secondary cases generated by a typical infected individual in a fully susceptible population finds a clear analytical expression in homogeneous and stratified mixing models. Along with the generation time (the interval between primary and secondary cases), the reproduction number allows for the characterization of the dynamics of an epidemic. A clear-cut theoretical picture, however, is hardly found in real data. Here, we infer from highly detailed sociodemographic data two multiplex contact networks representative of a subset of the Italian and Dutch populations. We then simulate an infection transmission process on these networks accounting for the natural history of influenza and calibrated on empirical epidemiological data. We explicitly measure the reproduction number and generation time, recording all individual-level transmission events. We find that the classical concept of the basic reproduction number is untenable in realistic populations, and it does not provide any conceptual understanding of the epidemic evolution. This departure from the classical theoretical picture is not due to behavioral changes and other exogenous epidemiological determinants. Rather, it can be simply explained by the (clustered) contact structure of the population. Finally, we provide evidence that methodologies aimed at estimating the instantaneous reproduction number can operationally be used to characterize the correct epidemic dynamics from incidence data.

Give more data, awareness and control to individual citizens, and they will help COVID-19 containment.

The rapid dynamics of COVID-19 calls for quick and effective tracking of virus transmission chains and early detection of outbreaks, especially in the "phase 2" of the pandemic, when lockdown and other restriction measures are progressively withdrawn, in order to avoid or minimize contagion resurgence. For this purpose, contact-tracing apps are being proposed for large scale adoption by many countries. A centralized approach, where data sensed by the app are all sent to a nation-wide server, raises concerns about citizens' privacy and needlessly strong digital surveillance, thus alerting us to the need to minimize personal data collection and avoiding location tracking. We advocate the conceptual advantage of a decentralized approach, where both contact and location data are collected exclusively in individual citizens' "personal data stores", to be shared separately and selectively (e.g., with a backend system, but possibly also with other citizens), voluntarily, only when the citizen has tested positive for COVID-19, and with a privacy preserving level of granularity. This approach better protects the personal sphere of citizens and affords multiple benefits: it allows for detailed information gathering for infected people in a privacy-preserving fashion; and, in turn this enables both contact tracing, and, the early detection of outbreak hotspots on more finely-granulated geographic scale. The decentralized approach is also scalable to large populations, in that only the data of positive patients need be handled at a central level. Our recommendation is two-fold. First to extend existing decentralized architectures with a light touch, in order to manage the collection of location data locally on the device, and allow the user to share spatio-temporal aggregates-if and when they want and for specific aims-with health authorities, for instance. Second, we favour a longer-term pursuit of realizing a Personal Data Store vision, giving users the opportunity to contribute to collective good in the measure they want, enhancing self-awareness, and cultivating collective efforts for rebuilding society.

Early Insights from Statistical and Mathematical Modeling of Key Epidemiologic Parameters of COVID-19.

We report key epidemiologic parameter estimates for coronavirus disease identified in peer-reviewed publications, preprint articles, and online reports. Range estimates for incubation period were 1.8-6.9 days, serial interval 4.0-7.5 days, and doubling time 2.3-7.4 days. The effective reproductive number varied widely, with reductions attributable to interventions. Case burden and infection fatality ratios increased with patient age. Implementation of combined interventions could reduce cases and delay epidemic peak up to 1 month. These parameters for transmission, disease severity, and intervention effectiveness are critical for guiding policy decisions. Estimates will likely change as new information becomes available.

Spread of Zika virus in the Americas.

We use a data-driven global stochastic epidemic model to analyze the spread of the Zika virus (ZIKV) in the Americas. The model has high spatial and temporal resolution and integrates real-world demographic, human mobility, socioeconomic, temperature, and vector density data. We estimate that the first introduction of ZIKV to Brazil likely occurred between August 2013 and April 2014 (90% credible interval). We provide simulated epidemic profiles of incident ZIKV infections for several countries in the Americas through February 2017. The ZIKV epidemic is characterized by slow growth and high spatial and seasonal heterogeneity, attributable to the dynamics of the mosquito vector and to the characteristics and mobility of the human populations. We project the expected timing and number of pregnancies infected with ZIKV during the first trimester and provide estimates of microcephaly cases assuming different levels of risk as reported in empirical retrospective studies. Our approach represents a modeling effort aimed at understanding the potential magnitude and timing of the ZIKV epidemic and it can be potentially used as a template for the analysis of future mosquito-borne epidemics.

Real-Time Forecasting of the COVID-19 Outbreak in Chinese Provinces: Machine Learning Approach Using Novel Digital Data and Estimates From Mechanistic Models.

BACKGROUND: The inherent difficulty of identifying and monitoring emerging outbreaks caused by novel pathogens can lead to their rapid spread; and if left unchecked, they may become major public health threats to the planet. The ongoing coronavirus disease (COVID-19) outbreak, which has infected over 2,300,000 individuals and caused over 150,000 deaths, is an example of one of these catastrophic events. OBJECTIVE: We present a timely and novel methodology that combines disease estimates from mechanistic models and digital traces, via interpretable machine learning methodologies, to reliably forecast COVID-19 activity in Chinese provinces in real time. METHODS: Our method uses the following as inputs: (a) official health reports, (b) COVID-19-related internet search activity, (c) news media activity, and (d) daily forecasts of COVID-19 activity from a metapopulation mechanistic model. Our machine learning methodology uses a clustering technique that enables the exploitation of geospatial synchronicities of COVID-19 activity across Chinese provinces and a data augmentation technique to deal with the small number of historical disease observations characteristic of emerging outbreaks. RESULTS: Our model is able to produce stable and accurate forecasts 2 days ahead of the current time and outperforms a collection of baseline models in 27 out of 32 Chinese provinces. CONCLUSIONS: Our methodology could be easily extended to other geographies currently affected by COVID-19 to aid decision makers with monitoring and possibly prevention.

Correction: Real-Time Forecasting of the COVID-19 Outbreak in Chinese Provinces: Machine Learning Approach Using Novel Digital Data and Estimates From Mechanistic Models.

[This corrects the article DOI: 10.2196/20285.].