Wearable technology monitoring water intake aiming to reduce kidney stone risk receives National Institutes of Health grant

AddThis

A team of UT researchers led by Edison Thomaz, an electrical and computer engineering assistant professor, received a five-year, $2.97 million grant from the National Institute of Diabetes and Digestive and Kidney Diseases to develop a water bottle, watch, and app for monitoring water intake.

Photo Credit: Courtesy of Edison Thomaz | Daily Texan Staff

A team of UT researchers received a five year, $2.97 million grant from the National Institute of Diabetes and Digestive and Kidney Diseases to develop a water bottle, watch and app for monitoring water intake.

Edison Thomaz, an electrical and computer engineering assistant professor, and his team of researchers are working to create the sipIT, wearable technology that promotes fluid intake to reduce the risk of kidney stones. 

Thomaz said they started the project with researchers from Penn State and Stanford through a 
seed grant that allowed them to determine if wearable technology could detect fluid intake. The new grant, funded through a division of the National Institutes of Health, allows them to expand the number of patients and run a larger study to perfect the technology.

“Hopefully, this research will translate into an actual system that we can potentially make available to patients within the next five to 10 years,” Thomaz said.

Thomaz said the system consists of a smart water bottle, which keeps track of the fluid level when patients are drinking water, and a smartwatch that can tell when the wearer is drinking and notifies the wearer if they are not drinking enough. 

“What's unique is that the system … can actually recognize when someone is drinking as quickly as possible, so it's running the system directly on the watch,” Thomaz said. 

Rebecca Adaimi, an electrical and computer engineering graduate student who worked on the system, said she created an algorithm that uses passive sensing technologies from wearables like smartwatches to model people’s drinking behavior.

“When people drink, there's this unique pattern they do, where you grab a cup or a bottle, then you pull it up, you drink and then you put it down,” Adaimi said. “Using these signals … we were able to observe this unique pattern and develop an algorithm that hopefully can automate detecting this signal.”

Keum San Chun, an electrical and computer engineering graduate student, said the team used commercial trackers like smartwatches so the algorithm is accessible to the general public and can help a large range of people with their diet. 

"This type of algorithm can be really helpful for patients suffering from kidney stones,” Chun said. “So when someone is having kidney stones they need to drink a lot of water, and I think this type of algorithm can potentially be very helpful for that."