Mining IoT data for community public health
Waterloo lab turns remote sensor data into public health information
Waterloo lab turns remote sensor data into public health information
By University RelationsIn Mongolia’s capital city of Ulaanbaatar, air pollution data is being collected by air quality sensors.
Here in North America, many houses have smart thermostats that work with sensors to adjust the room temperatures based on whether the room is occupied.
Globally, millions of people use devices such as Fitbits to monitor heart rate during workouts. In fact, almost all of today’s devices — even blood pressure monitors or weight scales — are wirelessly transmitting a vast amount of information to servers all over the world for various applications.
It has become a treasure trove of data. But surprisingly, all of this data from our Internet of Things (IoT) has been largely untapped in terms of public health usage.
Plinio Morita wants to change that. Morita is the director of the Ubiquitous Health Technology Lab (UbiLab) at the University of Waterloo and is helping health organizations and governments find ways to use data to develop better public health services.
“Most of my projects are focused on tapping into existing data and how to leverage the wealth of data that is already out there,” Morita says.
One project, in collaboration with UNICEF Mongolia, involves working with air pollution data from sensors that have been deployed in hundreds of locations in Ulaanbaatar.
Morita’s Waterloo lab has a software platform that can send requests for information to these sensors to gather the data on air quality and then correlate it with other health information. It will help answer questions such as: How did air quality affect the use of emergency health services? How did it affect student cognitive performance in the schools? How did it affect maternal and child health?
Another project involves a partnership with Ecobee, a Canadian company that is a leader in making smart thermostats that can sense temperature and occupancy in different rooms of a house.
“We can use the occupancy data to quantify indoor motion and correlate that with levels of physical activity and quality of sleep,” Morita explains.
Anonymized data from personal wearable devices such as Fitbit could also be put to use, Morita adds. If public officials could mine that anonymous data and extract information, they could use it to assess a fitness program or develop new public health interventions.
When Morita previously worked as a research scientist at the Centre for Global eHealth Innovation, he realized that although there has been a proliferation of wearable devices to monitor heart rate, blood pressure and other vital signs in order to help individual patients stay healthy, the bigger picture of how this data can inform public health policies and services was being missed. That inspired his current research.
“We want to look at the data at the country level and take a more global view,” Morita says.
UbiLab’s software platform has typically used statistical methods to analyze the data. Recently, it has also started using machine learning, a branch of artificial intelligence.
“When you are analyzing massive amounts of real-time data, machine learning is actually a better method for working with that kind of data. So recently, I have been hiring more students with a background in machine learning.”
All of this has to be done with privacy and consent being top of mind, so Morita’s lab is also developing a consent management platform using blockchain. The goal is to more clearly enable people to see who is requesting their data, and for what purposes, so they can control what they want to share and for what purpose.
Morita says this is becoming increasingly important because the European Union (EU) has already enacted the General Data Protection Regulation that governs data protection and privacy in the EU. In the future, companies that gather this type of data will need to be in compliance with that law, and other countries may soon follow similar guidelines.
Ultimately, Morita hopes that the wealth of data in our IoT world can be used for public good by making health care systems more efficient and responsive to people’s needs.
“We want to create an impact and we want to make sure that whatever we’re developing, it will make a difference in Canada and the world,” he says.
Intelligence-driven tech supports both individuals in crisis and the officers assisting them
Waterloo researcher is using AI to make legal document review more effective and efficient
When doctors wanted the best outcomes, they called on math researchers at Waterloo
The University of Waterloo acknowledges that much of our work takes place on the traditional territory of the Neutral, Anishinaabeg, and Haudenosaunee peoples. Our main campus is situated on the Haldimand Tract, the land granted to the Six Nations that includes six miles on each side of the Grand River. Our active work toward reconciliation takes place across our campuses through research, learning, teaching, and community building, and is co-ordinated within the Office of Indigenous Relations.