Connect with us

Government

Using machine learning to estimate COVID-19’s seasonal cycle

Using machine learning to estimate COVID-19’s seasonal cycle

Published

on

Berkeley Lab scientists aim to assess the role of climate variables in disease transmission

IMAGE

Credit: Center for Systems Science and Engineering at Johns Hopkins University

One of the many unanswered scientific questions about COVID-19 is whether it is seasonal like the flu – waning in warm summer months then resurging in the fall and winter. Now scientists at Lawrence Berkeley National Laboratory (Berkeley Lab) are launching a project to apply machine-learning methods to a plethora of health and environmental datasets, combined with high-resolution climate models and seasonal forecasts, to tease out the answer.

“Environmental variables, such as temperature, humidity, and UV [ultraviolet radiation] exposure, can have an effect on the virus directly, in terms of its viability. They can also affect the transmission of the virus and the formation of aerosols,” said Berkeley Lab scientist Eoin Brodie, the project lead. “We will use state-of-the-art machine-learning methods to separate the contributions of social factors from the environmental factors to attempt to identify those environmental variables to which disease dynamics are most sensitive.”

The research team will take advantage of an abundance of health data available at the county level – such as the severity, distribution, and duration of the COVID-19 outbreak, as well as what public health interventions were implemented when – along with demographics, climate and weather factors, and, thanks to smartphone data, population mobility dynamics. The initial goal of the research is to predict – for each county in the United States – how environmental factors influence the transmission of the SARS-CoV-2 virus, which causes COVID-19.

Multidisciplinary team for a complex problem

Untangling environmental factors from social and health factors is a knotty problem with a large number of variables, all interacting in different ways. On top of that, climate and weather affect not only the virus but also human physiology and behavior. For example, people may spend more or less time indoors, depending on the weather; and their immune systems may also change with the seasons.

It’s a complex data problem similar to others tackled by Berkeley Lab’s researchers studying systems like watersheds and agriculture; the challenge involves integrating data across scales to make predictions at the local level. “Downscaling of climate information is something that we routinely do to understand how climate impacts ecosystem processes,” Brodie said. “It involves the same types of variables – temperature, humidity, solar radiation.”

Brodie, deputy director of Berkeley Lab’s Climate and Ecosystem Sciences Division, is leading a cross-disciplinary team of Lab scientists with expertise in climate modeling, data analytics, machine learning, and geospatial analytics. Ben Brown, a computational biologist in Berkeley Lab’s Biosciences Area, is leading the machine-learning analysis. One of their main aims is to understand how climate and weather interact with societal factors.

“We don’t necessarily expect climate to be a massive or dominant effect in and of itself. It’s not going to trump which city shut down when,” Brown said. “But there may be some really important interactions [between the variables]. Looking at New York and California for example, even accounting for the differences between the timing of state-instituted interventions, the death rate in New York may be four times higher than in California – though additional testing on random samples of the population is needed to know for sure. Understanding the environmental interactions may help explain why these patterns appear to be emerging. This is a quintessential problem for machine learning and AI [artificial intelligence].”

The computing work will be conducted at the National Energy Research Scientific Computing Center (NERSC), a DOE Office of Science user facility located at Berkeley Lab.

Signs of climatic influences

Already, geographical differences in how the disease behaves have been reported, the researchers point out. Temperature, humidity, and the UV Index have all been statistically associated with rates of COVID-19 transmission – although contact rates are still the dominant influence on the spread of disease. In the southern hemisphere, for example, where it’s currently fall, disease spread has been slower than in the northern hemisphere. “There’s potentially other factors associated with that,” Brodie said. “The question is, when the southern hemisphere moves into winter, will there be an increase in transmission rate, or will fall and winter 2020 lead to a resurgence across the U.S. in the absence of interventions?”

India is another place where COVID-19 does not yet appear to be as virulent. “There are cities where it behaves as if it’s the most infectious disease in recorded history. Then there are cities where it behaves more like influenza,” Brown said. “It is really critical to understand why we see those massive differences.”

Brown notes other experiments suggesting the SARS-CoV-2 virus could be seasonal. In particular, the National Biodefense Analysis and Countermeasures Center (NBACC) assessed the longevity of the virus on various surfaces. “Under sunlight and humidity, they found that the virus loses viability in under 60 minutes,” Brown said. “But in darkness and low temperatures it’s stable for eight days. There’s some really serious differences that need investigating.”

The Berkeley Lab team believes that enough data may now be available to determine what environmental factors may influence the virulence of the virus. “Now we should have enough data from around the world to really make an assessment,” Brown said.

The team hopes to have the first phase of their analysis available by late summer or early fall. The next phase will be to make projections under different scenarios, which could aid in public health decisions.

“We would use models to project forward, with different weather scenarios, different health intervention scenarios – such as continued social distancing or whether there are vaccines or some level of herd immunity – in different parts of the country. For example, we hope to be able to say, if you have kids going back to school under this type of environment, the climate and weather in this zone will influence the potential transmission by this amount,” Brodie explained. “That will be a longer-term task for us to accomplish.”

###

This research is supported by Berkeley Lab’s Laboratory Directed Research and Development (LDRD) program. Other team members include Dan Feldman, Zhao Hao, Chaincy Kuo, Haruko Wainwright, and Nicola Falco. Berkeley Lab mobilized quickly to provide LDRD funding for several research projects to address the COVID-19 pandemic, including one on text mining scientific literature and another on indoor transmission of the virus.

Media Contact
Julie Chao
JHChao@lbl.gov

Original Source

https://newscenter.lbl.gov/2020/05/20/using-machine-learning-to-estimate-covid-19s-seasonal-cycle/

Read More

Continue Reading

Spread & Containment

Sex work is real work: Global COVID-19 recovery needs to include sex workers

Societally, we need to recognize that sex workers have agency and deserve the same respect, dignity and aid as any other person selling their labour.

Published

on

Globally, sex workers have been left to fend for themselves during the pandemic with little to no support from the government. (AP Photo/Bikas Das)

During the pandemic, business shifted from in person to work-from-home, which quickly became the new normal. However, it left many workers high and dry, especially those with less “socially acceptable” occupations.

The pandemic has adversely impacted sex workers globally and substantially increased the precariousness of their profession. And public health measures put in place made it almost impossible for sex workers to provide any in-person service.

Although many people depend on sex work for survival, its criminalization and policing stigmatizes sex workers.

Research shows that globally, sex workers have been left behind and in most cases excluded from government economic support initiatives and social policies. There needs to be an intersectional approach to global COVID-19 recovery that considers everyone’s lived realities. We propose policy recommendations that treat sex work as decent work and that centre around the lived experiences and rights of those in the profession.

Sex work and the pandemic

The United Nations Population Fund (UNFPA) recently reported that apart from income-loss, the pandemic has increased pre-existing inequalities for sex workers.

In a survey conducted in Eastern and Southern Africa, the UNFPA found that during the pandemic, 49 per cent of sex workers experienced police violence (including sexual violence) while 36 per cent reported arbitrary arrests. The same survey reported that more than 50 per cent of respondents experienced food and housing crises.

Lockdowns and border closures adversely impacted Thailand’s tourism industry which relies partially on the labour of sex workers.


Read more: Sex workers are criminalized and left without government support during the coronavirus pandemic


In the Asia Pacific, sex workers reported having limited access to contraceptives and lubricants along with reduced access to harm reduction resources. Lockdowns also disrupted STI or HIV testing services, limiting sex workers’ access to necessary healthcare.

In North America, sex workers have been excluded from the government’s recovery response. And many began offering online services to sustain themselves.

A woman stands backlit next to a dimly lit bus that reads 'Thailand' with green lighting.
Sex workers stand in a largely shut-down red light area in Bangkok, Thailand on March 26, 2020. (AP Photo/Gemunu Amarasinghe)

Government vs. community response

Globally, sex workers have been left to fend for themselves during the pandemic with little to no support from the government. But communities themselves have been rallying.

Elene Lam, founder of Butterfly, an Asian migrant sex organization in Canada, talks about the resilience of sex wokers during the pandemic.

She says organizations like the Canadian Alliance for Sex Work Law Reform are working in collaboration with Amnesty International to mobilize income support and resources to help sex workers in Canada.

Organizations in the United Kingdom, Germany, India and Spain have also set up emergency support funds. And some sex worker organizations have developed community-specific resources for providing services both in person and online during the pandemic.

Global recovery needs to include sex workers

The International Labour Organization’s “Decent Work Agenda” emphasizes productive employment and decent working conditions as being the driving force behind poverty reduction.

Sociologist Cecilia Benoit explains that sex work often becomes a “livelihood strategy” in the face of income and employment instability. She says that like other personal service workers, sex workers also should be able to practice without any interference or violence.

In order to have an inclusive COVID-19 recovery for all, governments need to work to extend social guarantees to sex workers — so far they haven’t.

As pandemic restrictions disappear, it is crucial to ensure that everyone involved in sex work is protected under the law and has access to accountability measures.

A woman stands wearing a mask with a safety vest on in front of a collage of scantily clad women and a sign that reads 'nude women non stop'
A volunteer helps out at Zanzibar strip club during a low-barrier vaccination clinic for sex workers in Toronto in June 2021. THE CANADIAN PRESS/Frank Gunn

Recommendations

As feminist researchers, we propose that sex work be brought under the broader agenda of decent work so that the people offering services are protected.

  1. Governments need to have a legal mandate for preventing sexual exploitation.

  2. Law enforcement staff need to be trained in better responding to the needs of sex workers. To intervene in and address situations of abuse or violence is critical to ensure workplace safety and harm reduction.

  3. Awareness and educational campaigns need to focus on destigmatizing sex work.

  4. Policy-makers need to incorporate intersectionality as a working principle in identifying and responding to the different axes of oppression and marginalization impacting LGBTQ+ and racialized sex workers.

  5. Engagement with sex workers and human rights organizations need to happen when designing aid support to ensure that an inclusive pathway for recovery is created.

  6. Globally, there needs to be a steady commitment towards destigmatizing sex workers and their services.

Despite the gradual waning of pandemic restrictions, sex workers continue to face the dual insecurity of social discrimination and loss of income support. Many are still finding it difficult to stay afloat and sustain themselves.

Societally, we need to recognize that sex workers have agency and deserve the same respect, dignity and aid as any other person selling their labour.

The authors do not work for, consult, own shares in or receive funding from any company or organisation that would benefit from this article, and have disclosed no relevant affiliations beyond their academic appointment.

Read More

Continue Reading

Government

OU researchers award two NSF pandemic prediction and prevention projects

Two groups of researchers at the University of Oklahoma have each received nearly $1 million grants from the National Science Foundation as part of its…

Published

on

Two groups of researchers at the University of Oklahoma have each received nearly $1 million grants from the National Science Foundation as part of its Predictive Intelligence for Pandemic Prevention initiative, which focuses on fundamental research and capabilities needed to tackle grand challenges in infectious disease pandemics through prediction and prevention.

Credit: Photo provided by the University of Oklahoma.

Two groups of researchers at the University of Oklahoma have each received nearly $1 million grants from the National Science Foundation as part of its Predictive Intelligence for Pandemic Prevention initiative, which focuses on fundamental research and capabilities needed to tackle grand challenges in infectious disease pandemics through prediction and prevention.

To date, researchers from 20 institutions nationwide were selected to receive an NSF PIPP Award. OU is the only university to receive two grants to the same institution.

“The next pandemic isn’t a question of ‘if,’ but ‘when,’” said OU Vice President for Research and Partnerships Tomás Díaz de la Rubia. “Research at the University of Oklahoma is going to help society be better prepared and responsive to future health challenges.”

Next-Generation Surveillance

David Ebert, Ph.D., professor of computer science and electrical and computer engineering in the Gallogly College of Engineering, is the principal investigator on one of the projects, which explores new ways of sharing, integrating and analyzing data using new and traditional data sources. Ebert is also the director of the Data Institute for Societal Challenges at OU, which applies OU expertise in data science, artificial intelligence, machine learning and data-enabled research to solving societal challenges.

While emerging pathogens can circulate among wild or domestic animals before crossing over to humans, the delayed response to the COVID-19 pandemic has highlighted the need for new early detection methods, more effective data management, and integration and information sharing between officials in both public and animal health.

Ebert’s team, composed of experts in data science, computer engineering, public health, veterinary sciences, microbiology and other areas, will look to examine data from multiple sources, such as veterinarians, agriculture, wastewater, health departments, and outpatient and inpatient clinics, to potentially build algorithms to detect the spread of signals from one source to another. The team will develop a comprehensive animal and public health surveillance, planning and response roadmap that can be tailored to the unique needs of communities.

“Integrating and developing new sources of data with existing data sources combined with new tools for detection, localization and response planning using a One Health approach could enable local and state public health partners to respond more quickly and effectively to reduce illness and death,” Ebert said. “This planning grant will develop proof-of-concept techniques and systems in partnership with local, state and regional public health officials and create a multistate partner network and design for a center to prevent the next pandemic.”

The Centers for Disease Control and Prevention describes One Health as an approach that bridges the interconnections between people, animals, plants and their shared environment to achieve optimal health outcomes.

Co-principal investigators on the project include Michael Wimberly, Ph.D., professor in the College of Atmospheric and Geographic Sciences; Jason Vogel, Ph.D., director of the Oklahoma Water Survey and professor in the Gallogly College of Engineering School of Civil Engineering and Environmental Science; Thirumalai Venkatesan, director of the Center for Quantum Research and Technology in the Dodge Family College of Arts and Sciences; and Aaron Wendelboe, Ph.D., professor in the Hudson College of Public Health at the OU Health Sciences Center.

Predicting and Preventing the Next Avian Influenza Pandemic

Several countries have experienced deadly outbreaks of avian influenza, commonly known as bird flu, that have resulted in the loss of billions of poultry, thousands of wild waterfowl and hundreds of humans. Researchers at the University of Oklahoma are taking a unique approach to predicting and preventing the next avian influenza pandemic.

Xiangming Xiao, Ph.D., professor in the Department of Microbiology and Plant Biology and director of the Center for Earth Observation and Modeling in the Dodge Family College of Arts and Sciences, is leading a project to assemble a multi-institutional team that will explore pathways for establishing an International Center for Avian Influenza Pandemic Prediction and Prevention.

The goal of the project is to incorporate and understand the status and major challenges of data, models and decision support tools for preventing pandemics. Researchers hope to identify future possible research and pathways that will help to strengthen and improve the capability and capacity to predict and prevent avian influenza pandemics.

“This grant is a milestone in our long-term effort for interdisciplinary and convergent research in the areas of One Health (human-animal-environment health) and big data science,” Xiao said. “This is an international project with geographical coverage from North America, Europe and Asia; thus, it will enable OU faculty and students to develop greater ability, capability, capacity and leaderships in prediction and prevention of global avian influenza pandemic.”

Other researchers on Xiao’s project include co-principal investigators A. Townsend Peterson, Ph.D., professor at the University of Kansas; Diann Prosser, Ph.D., research wildlife ecologist for the U.S. Geological Survey; and Richard Webby, Ph.D., director of the World Health Organization Collaborating Centre for Studies on the Ecology of Influenza in Animals and Birds with St. Jude Children’s Research Hospital. Wayne Marcus Getz, professor at the University of California, Berkeley, is also assisting on the project.

The National Science Foundation grant for Ebert’s research is set to end Jan. 31, 2024, while Xiao’s grant will end Dec. 31, 2023.


Read More

Continue Reading

Government

GSK and IQVIA launch platform of US vaccination data, showing drop in adult rates

Throughout the Covid-19 pandemic, the issue of vaccine uptake has been a point of contention, but a new platform from GSK and IQVIA is hoping to shed more…

Published

on

Throughout the Covid-19 pandemic, the issue of vaccine uptake has been a point of contention, but a new platform from GSK and IQVIA is hoping to shed more light on vaccine data, via new transparency and general awareness.

The two companies have launched Vaccine Track, a platform intended to be used by public health officials, medical professionals and others to strengthen data transparency and display vaccination trends. According to the companies, the platform is intended to aid in increasing vaccine rates and will provide data on trends to assist public health efforts.

Judy Stewart

The platform will also allow users to identify vaccination trends for adults in the US across multiple vaccine types. Users will also be able to scan claims data nationally to track trends alongside pre-Covid metrics.

“For the first time, Vaccine Track brings quarterly data tracking and trends together in a comprehensive platform for immunization partners, decision-makers and stakeholders. Our goal for Vaccine Track is to support the return to pre-pandemic vaccination rates for adults and to go beyond by empowering the vaccine and public health community with frequently updated, actionable information to get ahead of disease together,” said Judy Stewart, GSK’s head of vaccines in a statement.

This move comes as vaccination rates in adults were already low even before the pandemic, with a CDC report stressing that vaccine coverage in adults was low across all age groups.

So far the platform’s data show a decline in adult immunizations, excluding flu vaccinations, across the country during the pandemic. The platform currently only has information from January 2019 to December 2021 on hand but will be updated every quarter.

The data itself observed that rates were especially low in minority populations, which were already showing lower rates of immunization pre-pandemic.

The platform also showed that national trends for adults aged 19 and older are still low, with an average decrease of 18% through last year in overall claims. Average monthly claims through 2021 for recommended vaccines were between 12% and 42% below 2019 rates, with nearly half of the states in the US facing greater than 30% reductions in overall claims for recommended vaccines from pre-pandemic levels.

In Medicare patients, the platform’s analysis found a more than 30% reduction in overall claims for recommended vaccines among Black and Hispanic populations between 2019 and 2021.

The information itself is sourced from medical claims data and longitudinal prescription data, the companies said.

Read More

Continue Reading

Trending