Forecasting influenza activity using machine-learned mobility map

Human mobility is a primary driver of infectious disease spread. However, existing data is limited in availability, coverage, granularity, and timeliness. Data-driven forecasts of disease dynamics are crucial for decision-making by health officials and private citizens alike. In this work, we focus on a machine-learned anonymized mobility map (hereon referred to as AMM) aggregated over hundreds of millions of smartphones and evaluate its utility in forecasting epidemics. We factor AMM into a metapopulation model to retrospectively forecast influenza in the USA and Australia. We show that the AMM model performs on-par with those based on commuter surveys, which are sparsely available and expensive. We also compare it with gravity and radiation based models of mobility, and find that the radiation model’s performance is quite similar to AMM and commuter flows. Additionally, we demonstrate our model’s ability to predict disease spread even across state boundaries. Our work contributes towards developing timely infectious disease forecasting at a global scale using human mobility datasets expanding their applications in the area of infectious disease epidemiology.


Statistics
For all statistical analyses, confirm that the following items are present in the figure legend, table legend, main text, or Methods section.
n/a Confirmed The exact sample size (n) for each experimental group/condition, given as a discrete number and unit of measurement A statement on whether measurements were taken from distinct samples or whether the same sample was measured repeatedly The statistical test(s) used AND whether they are one-or two-sided Only common tests should be described solely by name; describe more complex techniques in the Methods section.
A description of all covariates tested A description of any assumptions or corrections, such as tests of normality and adjustment for multiple comparisons A full description of the statistical parameters including central tendency (e.g. means) or other basic estimates (e.g. regression coefficient) AND variation (e.g. standard deviation) or associated estimates of uncertainty (e.g. confidence intervals) For null hypothesis testing, the test statistic (e.g. F, t, r) with confidence intervals, effect sizes, degrees of freedom and P value noted

Software and code
Policy information about availability of computer code Data collection The Google Aggregated Mobility Research Dataset was collected, anonymized and aggregated by commercial code belonging to Google LLC.

Data analysis
Disease simulations were conducted using openly available code for simulation engine PatchSim (https://github.com/NSSAC/PatchSim). Custom code were developed for calibration, forecasting and evaluation and are available at https://github.com/NSSAC/AMMFluForecasting. They are provided in Code availability section of the paper with respective DOIs.
For manuscripts utilizing custom algorithms or software that are central to the research but not yet described in published literature, software must be made available to editors and reviewers. We strongly encourage code deposition in a community repository (e.g. GitHub). See the Nature Research guidelines for submitting code & software for further information.

Data
Policy information about availability of data All manuscripts must include a data availability statement. This statement should provide the following information, where applicable: Labour Market Statistics (https://www.abs.gov.au/AUSSTATS/abs@.nsf/Previousproducts/6105.0Feature%20Article1Oct%202008). County population sizes for NY and NJ were obtained from US Census Bureau (https://www.census.gov/topics/population.html). State and territory population sizes for Australia were obtained from Australian Bureau of Statistics (https://www.abs.gov.au/statistics/people/population). Preprocessed versions of the above datasets used in the simulation are provided in the code repository (https://github.com/NSSAC/AMMFluForecasting). The Google Aggregated Mobility Research Dataset used for this study is available with permission from Google LLC.

Field-specific reporting
Please select the one below that is the best fit for your research. If you are not sure, read the appropriate sections before making your selection.

Life sciences Behavioural & social sciences Ecological, evolutionary & environmental sciences
For a reference copy of the document with all sections, see nature.com/documents/nr-reporting-summary-flat.pdf

Behavioural & social sciences study design
All studies must disclose on these points even when the disclosure is negative.

Study description
The study aims to measure the utility of various aggregate mobility datasets in forecasting short-term influenza incidence trends at various spatial scales. The study is quantitative in nature and combines disease monitoring collected via public health departments and aggregate mobility flows.

Research sample
The Google Aggregated Mobility Research Dataset contains anonymized mobility flows aggregated over users who have turned on the Location History setting, which is off by default. This is similar to the data used to show how busy certain types of places are in Google Maps -helping identify when a local business tends to be the most crowded. The dataset aggregates flows of people from region to region. To produce this dataset, machine learning is applied to logs data to automatically segment it into semantic trips. To provide strong privacy guarantees, all trips were anonymized and aggregated using a differentially private mechanism to aggregate flows over time (see https://policies.google.com/technologies/anonymization). This research is done on the resulting heavily aggregated and differentially private data. No individual user data was ever manually inspected, only heavily aggregated flows of large populations were handled. We used this datasets restricted to the US states of NY, NJ and Australia, since it represents the level of connectivity within the regions of interest.

Sampling strategy
No explicit sample size calculations were performed. We add a Laplacian noise to the number of unique users for each location pair, for each week. All metrics for which the noisy number of users is lower than 100 are then removed. These are described in the Methods section of the manuscript.

Data collection
Data was collected from mobile phones of users who have turned on the Location History setting, which is off by default. During data collection, the researchers were not present with the participant and were blinded to the experimental conditions and research hypothesis.