Anonymized Cell Phone Location Data can Help Monitor COVID-19 Growth Rates

In March 2020, federal officials declared the COVID-19 outbreak a national emergency. Around the same time, most states implemented stay-at-home advisories - to different degrees and at different times. Publicly available cell phone location data - anonymized at the county-level - showed marked reductions in cell phone activity at the workplace and at retail locations, as well as increased activity in residential areas. However, it was not known whether these data correlate with the spread of COVID-19 in a given region.

In a new study published in JAMA Internal Medicine, researchers from Mount Auburn Hospital and the University of Pennsylvania analyzed anonymous, county-level cell phone location data, made publicly available via Google, and incidence of COVID-19 for more than 2,500 U.S. counties between January and May 2020. The researchers found that changes in cell phone activity in workplaces, transit stations, retail locations, and at places of residence were associated with COVID-19 incidence. The findings are among the first to demonstrate that cell phone location data can help public health officials better monitor adherence to stay-at-home advisories, as well as help identify areas at greatest risk for more rapid spread of COVID-19.

"This study demonstrates that anonymized cell phone location can help researchers and public health officials better predict the future trends in the COVID-19 pandemic," said corresponding author Shiv T. Sehra, MD, Director of the Internal Medicine Residency Program at Mount Auburn Hospital. "To our knowledge, our study is among the first to evaluate the association of cell phone activity with the rate of growth in new cases of COVID-19, while considering regional confounding factors."

Sehra and colleagues, including senior author Joshua F. Baker, MD, MSCE, of the University of Pennsylvania, incorporated publicly available cell phone location data and daily reported cases of COVID-19 per capita in majority of U.S. counties (made available by Johns Hopkins University), and adjusted the data for multiple county- and state- level characteristics including population density, obesity rates, state spending on health care, and many more. Next, the researchers looked at the change in cell phone use in six categories of places over time: workplace, retail locations, transit stations, grocery stores, parks and residences.

The location data showed marked reductions in cell phone activity in public places with an increase in activity in residences even before stay-at-home advisories were rolled out. The data also showed an increase in workplace and retail location activity as time passed after stay-at-home advisories were implemented, suggesting waning adherence to the orders over time, information that may potentially be useful at a public health level.

The study showed that urban counties with higher populations and a higher density of cases saw a larger relative decline in activity outside place of residence and a greater increase in residential activity. Higher activity at the workplace, in transit stations and retail locations was associated with a higher increase in COVID-19 cases 5, 10, and 15 days later. For example, at 15 days, counties with the highest percentage of reduction in retail location cell phone activity - reflecting greater adherence to stay-at-home advisories - demonstrated 45.5 percent lower rate of growth of new cases, compared to counties with a lesser decline in retail location activity.

"Some of the factors affecting cell phone activity are quite intuitive," said Sehra, who is also an Assistant Professor of Medicine at Harvard Medical School. "But our analysis helps demonstrate the use of anonymous county-level cell phone location data as a way to better understand future trends of the pandemic. Also, we would like to stress that these results should not be used to predict the individual risk of disease at any of these locations."

Sehra ST, George M, Wiebe DJ, Fundin S, Baker JF.
Cell Phone Activity in Categories of Places and Associations With Growth in Cases of COVID-19 in the US.
Intern Med. Published online August 31, 2020. doi: 10.1001/jamainternmed.2020.4288

Most Popular Now

AI-Powered CRISPR could Lead to Faster G…

Stanford Medicine researchers have developed an artificial intelligence (AI) tool to help scientists better plan gene-editing experiments. The technology, CRISPR-GPT, acts as a gene-editing “copilot” supported by AI to help...

Groundbreaking AI Aims to Speed Lifesavi…

To solve a problem, we have to see it clearly. Whether it’s an infection by a novel virus or memory-stealing plaques forming in the brains of Alzheimer’s patients, visualizing disease processes...

ChatGPT 4o Therapeutic Chatbot 'Ama…

One of the first randomized controlled trials assessing the effectiveness of a large language model (LLM) chatbot 'Amanda' for relationship support shows that a single session of chatbot therapy...

AI Tools Help Predict Severe Asthma Risk…

Mayo Clinic researchers have developed artificial intelligence (AI) tools that help identify which children with asthma face the highest risk of serious asthma exacerbation and acute respiratory infections. The study...

AI Model Forecasts Disease Risk Decades …

Imagine a future where your medical history could help predict what health conditions you might face in the next two decades. Researchers have developed a generative AI model that uses...

AI Distinguishes Glioblastoma from Look-…

A Harvard Medical School–led research team has developed an AI tool that can reliably tell apart two look-alike cancers found in the brain but with different origins, behaviors, and treatments. The...

Smart Device Uses AI and Bioelectronics …

As a wound heals, it goes through several stages: clotting to stop bleeding, immune system response, scabbing, and scarring. A wearable device called "a-Heal," designed by engineers at the University...

AI Model Indicates Four out of Ten Breas…

A project at Lund University in Sweden has trained an AI model to identify breast cancer patients who could be spared from axillary surgery. The model analyses previously unutilised information...

Overcoming the AI Applicability Crisis a…

Opinion Article by Harry Lykostratis, Chief Executive, Open Medical. The government’s 10 Year Health Plan makes a lot of the potential of AI-software to support clinical decision making, improve productivity, and...

Dartford and Gravesham Implements Clinis…

Dartford and Gravesham NHS Trust has taken a significant step towards a more digital future by rolling out electronic test ordering using Clinisys ICE. The trust deployed the order communications...