Using mobility data in the design of optimal lockdown strategies for the COVID-19 pandemic

Human-centred artificial intelligence for mobile health sensing: challenges and opportunities

Advances in wearable sensing and mobile computing have enabled the collection of health and well-being data outside of traditional laboratory and hospital settings, paving the way for a new era of mobile health. Meanwhile, artificial intelligence (AI) has made significant strides in various domains, demonstrating its potential to revolutionize healthcare. Devices can now diagnose diseases, predict heart irregularities and unlock the full potential of human cognition. However, the application of machine learning (ML) to mobile health sensing poses unique challenges due to noisy sensor measurements, high-dimensional data, sparse and irregular time series, heterogeneity in data, privacy concerns and resource constraints. Despite the recognition of the value of mobile sensing, leveraging these datasets has lagged behind other areas of ML. Furthermore, obtaining quality annotations and ground truth for such data is often expensive or impractical. While recent large-scale longitudinal studies have shown promise in leveraging wearable sensor data for health monitoring and prediction, they also introduce new challenges for data modelling. This paper explores the challenges and opportunities of human-centred AI for mobile health, focusing on key sensing modalities such as audio, location and activity tracking. We discuss the limitations of current approaches and propose potential solutions.

How contact patterns during the COVID-19 pandemic are related to pre-pandemic contact patterns and mobility trends

BACKGROUND

Non-pharmaceutical interventions (NPIs) were adopted in Belgium in order to decrease social interactions between people and as such decrease viral transmission of SARS-CoV-2. With the aim to better evaluate the impact of NPIs on the evolution of the pandemic, an estimation of social contact patterns during the pandemic is needed when social contact patterns are not available yet in real time.

METHODS

In this paper we use a model-based approach allowing for time varying effects to evaluate whether mobility and pre-pandemic social contact patterns can be used to predict the social contact patterns observed during the COVID-19 pandemic between November 11, 2020 and July 4, 2022.

RESULTS

We found that location-specific pre-pandemic social contact patterns are good indicators for estimating social contact patterns during the pandemic. However, the relationship between both changes with time. Considering a proxy for mobility, namely the change in the number of visitors to transit stations, in interaction with pre-pandemic contacts does not explain the time-varying nature of this relationship well.

CONCLUSION

In a situation where data from social contact surveys conducted during the pandemic are not yet available, the use of a linear combination of pre-pandemic social contact patterns could prove valuable. However, translating the NPIs at a given time into appropriate coefficients remains the main challenge of such an approach. In this respect, the assumption that the time variation of the coefficients can somehow be related to aggregated mobility data seems unacceptable during our study period for estimating the number of contacts at a given time.

The lockdown and vaccination distribution in Thailand's COVID-19 epidemic: A model study

Background

Several countries used varied degrees of social isolation measures in response to the COVID-19 outbreak. In 2021, the lockdown in Thailand began on July 20 and lasted for the following six weeks. The lockdown has extremely detrimental effects on the economy and society, even though it may reduce the number of COVID-19 instances. Our goals are to assess the impact of the lockdown policy, the commencement time of lockdown, and the vaccination rate on the number of COVID-19 cases in Thailand in 2021.

Methods

We modeled the dynamics of COVID-19 in Thailand throughout 2021 using the SEIR model. The Google Mobility Index, vaccine distribution rate, and lockdown were added to the model. The Google Mobility Index represents the movement of individuals during a pandemic and shows how people react to lockdown. The model also examines the effect of vaccination rate on the incidence of COVID-19.

Results

The modeling approach demonstrates that a 6-week lockdown decreases the incidence number of COVID-19 by approximately 15.49-18.17%, depending on the timing of the lockdown compared to a non-lockdown scenario. An increasing vaccination rate potentially reduce the incidence number of COVID-19 by 5.12-18.35% without launching a lockdown.

Conclusion

Lockdowns can be an effective method to slow down the spread of COVID-19 when the vaccination program is not fully functional. When the vaccines are easily accessible on a large scale, the lockdown may terminated.

Social structure description of epidemic propagation with a mean-field game paradigm

As emphasized by the recent pandemic crisis, the design of coherent policies against epidemic propagation is of major importance and required to model both epidemic quantities and individuals behavior because the latter has a strong influence on the former. To address this issue, we consider the spread of infectious diseases through a mean field game version of a SIR compartmental model with social structure, in which individuals are grouped by their age class and interact together in different settings. In our game theoretical approach, individuals can choose to limit their contacts if the epidemic is too virulent, but this effort comes with a social cost. We further compare the Nash equilibrium obtained in this way with the societal optimum that would be obtained if a benevolent central planner could decide on the strategy of each individual, as well as to the more realistic situation where an approximation of this optimum is reached through social policies such as lockdown.

Responsiveness of open innovation to COVID-19 pandemic: The case of data for good

Due to the COVID-19 pandemic, countries around the world are facing one of the most severe health and economic crises of recent history and human society is called to figure out effective responses. However, as current measures have not produced valuable solutions, a multidisciplinary and open approach, enabling collaborations across private and public organizations, is crucial to unleash successful contributions against the disease. Indeed, the COVID-19 represents a Grand Challenge to which joint forces and extension of disciplinary boundaries have been recognized as main imperatives. As a consequence, Open Innovation represents a promising solution to provide a fast recovery. In this paper we present a practical application of this approach, showing how knowledge sharing constitutes one of the main drivers to tackle pressing social needs. To demonstrate this, we propose a case study regarding a data sharing initiative promoted by Facebook, the Data For Good program. We leverage a large-scale dataset provided by Facebook to the research community to offer a representation of the evolution of the Italian mobility during the lockdown. We show that this repository allows to capture different patterns of movements on the territory with increasing levels of detail. We integrate this information with Open Data provided by the Lombardy region to illustrate how data sharing can also provide insights for private businesses and local authorities. Finally, we show how to interpret Data For Good initiatives in light of the Open Innovation Framework and discuss the barriers to adoption faced by public administrations regarding these practices.

Modelling lockdown measures in epidemic outbreaks using selective socio-economic containment with uncertainty

After the introduction of drastic containment measures aimed at stopping the epidemic contagion from SARS-CoV2, many governments have adopted a strategy based on a periodic relaxation of such measures in the face of a severe economic crisis caused by lockdowns. Assessing the impact of such openings in relation to the risk of a resumption of the spread of the disease is an extremely difficult problem due to the many unknowns concerning the actual number of people infected, the actual reproduction number and infection fatality rate of the disease. In this work, starting from a SEIRD compartmental model with a social structure based on the age of individuals and stochastic inputs that account for data uncertainty, the effects of containment measures are introduced via an optimal control problem dependent on specific social activities, such as home, work, school, etc. Through a short time horizon approximation, we derive models with multiple feedback controls depending on social activities that allow us to assess the impact of selective relaxation of containment measures in the presence of uncertain data. After analyzing the effects of the various controls, results from different scenarios concerning the first wave of the epidemic in some major countries, including Germany, France, Italy, Spain, the United Kingdom and the United States, are presented and discussed. Specific contact patterns in the home, work, school and other locations have been considered for each country. Numerical simulations show that a careful strategy of progressive relaxation of containment measures, such as that adopted by some governments, may be able to keep the epidemic under control by restarting various productive activities.

Spatial spread of COVID-19 outbreak in Italy using multiscale kinetic transport equations with uncertainty

In this paper we introduce a space-dependent multiscale model to describe the spatial spread of an infectious disease under uncertain data with particular interest in simulating the onset of the COVID-19 epidemic in Italy. While virus transmission is ruled by a SEIAR type compartmental model, within our approach the population is given by a sum of commuters moving on a extra-urban scale and non commuters interacting only on the smaller urban scale. A transport dynamics of the commuter population at large spatial scales, based on kinetic equations, is coupled with a diffusion model for non commuters at the urban scale. Thanks to a suitable scaling limit, the kinetic transport model used to describe the dynamics of commuters, within a given urban area coincides with the diffusion equations that characterize the movement of non-commuting individuals. Because of the high uncertainty in the data reported in the early phase of the epidemic, the presence of random inputs in both the initial data and the epidemic parameters is included in the model. A robust numerical method is designed to deal with the presence of multiple scales and the uncertainty quantification process. In our simulations, we considered a realistic geographical domain, describing the Lombardy region, in which the size of the cities, the number of infected individuals, the average number of daily commuters moving from one city to another, and the epidemic aspects are taken into account through a calibration of the model parameters based on the actual available data. The results show that the model is able to describe correctly the main features of the spatial expansion of the first wave of COVID-19 in northern Italy.