New Study Predict How Much A Person Will Eat From Smartphone Data

Increasingly smartphones are being used be people to log various aspects of their life. Recently my group published a paper in which we analyzed data from individuals’ smartphones, to see whether we could model their dietary patterns. Rather than compare across people, we focused on the patterns that exist for specific individuals. We examined whether the portion size for each person’s meal tended to followed a routine based on time of day, whether the portion size was related to how much physical activity they engaged in before the meal, or whether the their “food environment” — the quantity, diversity, and types of food establishments around them — influenced the portion size. We also looked at the person’s mood to see it influenced their meals. All of these data were collected from a smartphone app we developed (voice-annotated video recording of meals, accelerometry for physical activity, GPS for food environments, and occasional prompts to ask about mood).

What we found was fascinating. In some cases, certain individuals exhibited fairly routine eating patterns, while for other individuals, exercise before the meal was an important factor in determining their portion sizes. However, we were surprised to find that across all of the subjects, the food environment tended to be an important factor for explaining portion sizes.

This study was based on data from a fairly small group of test subjects who were only monitored over a short period of time, but we now have hundreds of gigabytes of similar data for which we will be doing the same sort of analyses.

The work provides an early glimpse of our ability to integrate various different sorts of sensor, self-report data, contextual data to model specific individuals behavioral patterns.  Moving forward, we are interested in evaluating how well these models work for prediction, and eventual use for tailoring behavioral interventions to specific individuals to help them live healthier lives.

This study was recently published in the journal PLoS ONE:


My NIEHS Webinar: Environmental Sensors, Citizen Science, and Quantified Self

On April 5, I gave a webinar “Sensor Technologies for Improving Environmental Health: Juxtaposing the Citizen Science and Quantified Self Movements”.  Thanks to all who attended, and especially to those who provided questions/feedback on my group’s work.  Here’s the abstract:

In recent years, numerous sensor technologies have been developed that offer the ability to collect detailed data on environmental conditions and their impact on human health. These technologies will likely change how communities and individuals access environmental health information, and the amount of data that are available for improved decision-making.

An example of the potential impact of emerging sensor technology can be seen through the development of low-cost direct-reading air pollution monitors many of which are now commercially available.  While researchers continue to conduct studies to answer the fundamental question of “how well do these new devices perform?,” perhaps the more intriguing question is “if useful air pollution data could be obtained from a device that many people could afford, how would this change our understanding of air pollution-related health?”

This webinar will discuss multiple answers to this question, including how community groups, Citizen Science, epidemiologic researchers and individuals may benefit from these new sensors.

One answer to the above question is that community-based environmental groups may have better access to monitoring technologies to document environmental injustices. In some respects, this is not entirely new, as community groups have for many years documented their local knowledge of air pollution levels in much more detail than what was possible through government monitoring efforts. The difference now, is that monitors are more readily available for these groups to collect their own objective measurements. Because of the low cost of each monitor, it is not implausible to imagine entire communities blanketed with a high density of air pollution sensors. And, in fact, NIEHS-funded research is demonstrating that such community-engaged monitoring networks are possible.

Slightly different from the community-initiated and led research described above, new air pollution technologies are enabling a new form of environmental research within our communities, called Citizen Science. While there are different models for conducting Citizen Science, the more intriguing examples are those that are organized over the Internet, involve many individuals who work together to crowdsource data, and result in massive amounts of data that are shared openly. In some cases, technology-savvy Citizen Science leaders are developing and sharing their designs for new monitors, providing proof of concept for how measurements can be made with low-cost sensors.

Another possible answer to the above question is that an increasing number of environmental epidemiology studies may use sensors to conduct personal exposure assessments. Sensors are not only getting cheaper, but also battery-powered and are getting smaller in size, making them increasingly practical for use in a variety of cohort studies. An exciting example of NIH support for this is the new Pediatric Research Using Integrated Sensor Monitoring Systems (PRISMS) program, within which various research groups are developing new wearable sensors that can measure environmental exposures that can be related to health symptoms for future children’s asthma studies. An exciting aspect of the PRISMS program is the recognition that future sensors will likely need to be network-enabled, which would provide more immediate data from research subjects, as well as also enable more immediate feedback to research subjects.

While NIH programs like PRISMS are fostering future sensor technologies for epidemiologic research, the private sector is also commercializing air pollution monitors for the consumer health and wellness market. Smart technologies (e.g., smartphone apps, smart watches, fitness trackers, GPS loggers, etc.) used to be primarily marketed to the Quantified Self movement – individuals who use devices and data to track and optimize various aspects of their life – air pollution monitors being just one of latest devices that such an individual may want to use. But, there is a large group of individuals who have pre-existing health conditions and may be susceptible to air pollution exposures, which may be interested in understanding their air pollution exposures by either having a household or wearable monitor. While these individuals may be the greatest market for these new air pollution monitors, it remains unclear how people will respond to personalized air pollution exposure data (e.g., what are the best ways to communicate individual-based air pollution exposures and risks?), or whether people have practical ways to manage their exposures.

In summary, the recent developments in low-cost air pollution monitoring devices illustrate various opportunities for improving environmental health through sensor technologies. The benefits to traditional community-based and epidemiologic research studies are somewhat clear, with new monitoring devices potentially providing data for more persons, places, and times than previously possible. Less clear, but no less exciting because of the reach and numbers of people potentially involved, are the novel ways in which new air pollution monitors are being adopted into Citizen Science and consumer health and wellness applications.

More, and an eventual link to Youtube can be found here:

Seattle Seasonal Affective Disorder


Heather McAuliffe is a citizen scientist in Seattle, who I met last year. She’s collected tons of air pollution monitoring data on her bicycle, which she contributes to the Puget Sound Clean Air Agency to improve our understanding of air pollution along streets in the city.

She’s recently written about another environmental problem of Seattle — the grey skies and short days during the wintertime.

New Study to Develop Environmental Exposure Monitoring for Pediatric Asthma

My group at UW was awarded a $2M grant to work with the National Institutes of Health on a new program called Pediatric Research using Integrated Sensor Monitoring Systems (PRISMS).  The goal of this program is the “development of wearable and non-wearable sensors that can monitor pediatric environmental exposures, physiological signals, activity, and/or behavior in a natural environment to gain new insights into environmental determinants of asthma.”

This new grant will bring together researchers at UW in the Environmental Health Sciences, Pediatrics, and Engineering to develop a new environmental exposure monitoring system for PRISMS.  Research partners include Professors Novosselov, Posner, Korshin, Mamishev, Yost and Karr. The study will test the system for use in the HAPI asthma intervention study in Yakima, WA.

Close to 1 in 10 children in the U.S. suffer from asthma.  Children who have asthma are prone to acute exacerbations of airway inflammation (asthma “attacks”) that may be triggered by numerous environmental exposures, including infectious agents, pollens, smoke, mold, chemicals, etc.  The morbidity associated with children’s asthma is large. Asthma is the third most common cause for child hospitalization for those less than 15 years old. It is a leading cause of school absenteeism.  And, there are large public health disparities associated with asthma: those that are poor, and of certain races and ethnicities are more likely to suffer from asthma.  Through the technologies developed in the PRISMS program, improved understanding of the relationship between exposures and asthma symptoms may help researchers and asthmatic families manage the disease better.



New grant to use low-cost sensors in a community-based study of hazardous air pollutants associated with fracking in California’s Central Valley

We just received a grant from the New World Foundation through the 11th Hour Project’s pooled fund.  The new grant will allow us to use Internet-connected low-cost sensors to investigate hazardous air pollutants (HAPs) in California’s Central Valley.  This community-initiated study led by Clean Water Action, involves multiple partners working collectively to examine hazardous air pollution in a region where unconventional oil and gas extraction, such as fracking occurs. My research group at the University of Washington is pleased to support the project by providing the sensor technology and data analytics for the study.  By using a distributed network of real-time sensors, advanced algorithms to pinpoint air pollution episodes, and targeted measurement of multiple HAPs associated with fracking, we hope to improve understanding of exposures to toxic air in communities next to unconventional oil and gas extraction.

This project builds upon other community-engaged studies that we and other organisations are conducting, which includes establishing a large-scale community-run PM2.5 and PM10 monitoring network in Imperial County, CA.  As with our other studies, active engagement and grassroots participation of community residents will likely be the key to this new project’s success.

New NIH Grant to Identify HIV MicroEpidemics in Lima, Peru

A new CFAR Supplement grant from the NIH will examine spatial-genetic clustering of HIV infections among males who have sex with other males (MSM) in Lima, Peru.

The study will make use of state of the art genetic markers to identify recent infections within the MSM population — so-called “HIV MicroEpidemics”.  Spatial analyses will be conducted to identify neighborhoods and social venues — the places that are most associated with these MicroEpidemics.  And, the study will be able to assess the role that certain risk factors, such numbers of sexual partners and alcohol and drug use, play in MicroEpidemic transmission.

Dr. Edmund Seto will serve as the new study’s director.  His research group in the Department of Environmental & Occupational Health Sciences at the University of Washington will contribute to the spatial-genetic analyses for this study. The research builds off the Center for AIDS Research (CFAR) at the University of Washington led by King Holmes,  the ongoing ¿Sabes? research study collaboration between Ann Duerr’s group at Fred Hutchinson Cancer Research Center at Manual Villaran at Impacta in Peru, as well as work on HIV genetics by Joshua Herbeck in the Department of Global Health at the University of Washington.


Breaking New Ground: A New Program in Construction Management Occupational Safety and Health (CMOSH)

Construction is one of the most dangerous industries in the United States.  Close to 10 million people work in construction in the U.S. And each year, unfortunately, there are hundreds of construction work fatalities — more than any other industry in the country.

Construction workers also face numerous risks that can cause serious injury — injuries such as falls, things falling on workers, workers being run over by motorized equipment, electrocutions, being exposed to worksite and material hazards, and musculoskeletal problems.

To help address these problems from within the industry — to better promote a culture of safety within Construction and to promote the concept of Total Worker Health within the industry, I am working with Ken-Yu Lin in the College of Built Environment. We recently announced a new degree program at the UW, called CMOSH!

Construction Management Occupational Safety and Health (CMOSH) is a new track within the Master of Science in Construction Management degree program at the University of Washington. The track aims to produce future construction management leaders who will have the knowledge and skills to integrate project management and occupational health and safety for true project success. CMOSH students will have a well-rounded and interdisciplinary learning experience covering subjects from construction management, occupational health and safety, and industry practices.

Interested in applying?  Details can be found here.

The CMOSH program is one of two new programs within the Northwest Center for Occupational Health & Safety — one of NIOSH’s Education and Research Centers (ERC).  The other new program is the Occupational Health at the Human-Animal Interface (OHHAI) research training program.



Imperial County, California Installs the First Air Quality Monitor for its Community Monitoring Network

First Community Monitor installed at Brawley High School

Yesterday, I was in Imperial County, CA installing the first of 40 new Community Air Quality Monitors as part of study funded by the NIH NIEHS Research to Action Program.

Paul English of the Public Health Institute is the Principal Investigator for this community-engaged research study. Luis Olmedo of Comite Civico Del Valle is working to organize members of the community to lead and sustain the monitoring.  And, my group at the University of Washington is responsible for the monitors.

My PhD student, Graeme Carvlin and I developed the community monitors for this project, which consist of a modified Dylos DC1700, which measures particulate matter in 4 size bins.  Each monitor uses a networked microcontroller, and has onboard data storage as well as additional sensors for temperature and relative humidity.  The data from the monitoring network will undergo quality checks and will be publicly available through the IVAN website.

Yesterday, we had great support from Brawley High School’s leadership, teachers, staff, and students to install our first monitor.  The members of the school’s shop class helped us fabricate a sturdy stand to mount our monitor.  The networking admin at the school helped us pull a new Internet line just for monitor.  And, we did all this in 106 deg F heat.  It was a tremendous team effort.  Brawley High has great community spirit.  Go Wildcats!

For the launch of the monitoring site today, I prepared the following press statement:

Remarks from Dr. Edmund Seto
Department of Environmental and Occupational Health Sciences
University of Washington

Today marks an important milestone in air quality monitoring in Imperial County.

Since the establishment of the Clean Air Act and the National Ambient Air Quality Standards in the 1970s, we have improved our understanding of just how important clean air is for health.  We have also improved our standards air quality, and how we monitor air pollution to meet these standards.  Like many regions across the US, there are only a handful of air quality monitors in operation in Imperial County.  Yet, these monitors serve a very important role of documenting progress towards meeting increasingly stringent air quality standards, and help guide planning activities to reduce air pollution emissions.

But can we do better monitoring?  In some ways, yes, we can.

Lower-cost air pollution monitoring technology provides new opportunities for groups to collect their own air pollution data.  While these low-cost monitors are not meant for regulatory purposes, they can play an important role in augmenting the existing regulatory monitoring network.  Because of their lower cost we can afford to monitor many more locations that we were not able to do in the past.  And, this can potentially fill gaps in knowledge.

Over the last year, I have been fortunate to be able to work with community representatives to design a low-cost air quality monitoring system that meets the needs of Imperial County. We call it a “Community Monitor” because it is operated by the community, for the community. I am excited that the first of many Community Monitors is being installed today in Brawley.

But, this is just a start.  As more community monitors are installed, and data become increasingly available from this monitoring network, we will need to explore ways to best use this new data.  Will this data be able to help the parents of an asthmatic child know when it is safe to play outside?  Will this data be able to help identify the sources of air pollution in our communities?  Will this data be able to help us understand if air pollution is getting better or worse over time in certain communities?  And, how well will this data compare to those collected from the regulatory monitoring network?

We may not have the answers to all these questions right now.  But certainly, many people — including federal, state, and regional agencies; the scientific research community; and community groups in the US and abroad – are looking at how we answer these questions in Imperial County.  So there is both a great potential for us to learn from Imperial’s Community Monitors, as well as a lot to share about what we have learned with others.

I congratulate everyone who contributed to this project.

Congratulations — Meiling Gao Graduates

Congratulations to Meiling Gao, who’s graduating this weekend with PhD in Environmental Health Sciences at Berkeley.  Meiling’s dissertation examines the complex associations between the built environment, mixtures of different air pollutants, and both physical and mental health outcomes.  Her research was conducted in Xi’an, China, where some of the worst urban air pollution exists in the world.  In addition to time-integrated monitoring of various pollutants throughout the city, developing land use regression models, and conducting epidemiologic modeling, Meiling conducted a study using the low-cost PUWP air pollution instruments to monitor time-varying particulate matter levels during the Winter 2014 Airpocalypse in Xi’an.

NCI’s RADAR Initiative Will Release Final Report

For the last couple years, the National Cancer Institute at the National Institutes of Health has been working on an important emerging area of health research — how to improve the collection, storing, management, and sharing of data from wearable sensor devices.  Over these last two years, a team of sensor researchers, technologists, and behavioral scientists have been gathering and sharing notes, and coming up with ideas for the future.  Not only does this initiative have relevance for the FitBits, Shines, Jawbones, iWatches, etc. — all those personal fitness devices you and your friends and family are using today.  But, it has the potential to affect how the next generation of devices interact with one another, via their data and metadata, over the Cloud. This initiative is called the “Repository for Algorithm Development in Ambulatory Research — or simply RADAR. Kudos to NCI for kick-starting this effort.

I wasn’t able to make all the various conferences where the RADAR team met, but it was great to be a member of the group, and to interact with the many bright minds on the team.  NCI should be releasing the final report “any day now”.