HAVE YOUR SAY.
Join us in The Bullpen, where the members of the Scientific Inquirer community get to shape the site’s editorial decision making. We’ll be discussing people and companies to profile on the site. On Wednesday, April 12 at 5:30pm EST, join us on Discord and let’s build the best Scientific Inquirer possible.
A detailed analysis of consumed food showed there is a need to improve diets in long-term care (LTC) homes to make them healthier for residents.
The analysis found that eating more whole grains, plant-based proteins, and plain fruits and vegetables would help residents meet government guidelines and reduce their risk of inflammation.
Researchers at the University of Waterloo developed new artificial intelligence (AI) technology to examine data on food and fluids consumed by more than 600 residents over three days at 32 LTC homes.
Results were compared to recommendations in the 2019 Canada’s Food Guide on healthy eating and expert information on foods that could cause inflammation, contributing to chronic diseases including diabetes, cardiovascular disease, arthritis and dementia.
“These food analytics can support LTC menu planning and provide data-driven insights to support nutritional interventions geared at improving clinical outcomes and quality of life,” said Dr. Kaylen Pfisterer, an adjunct assistant engineering professor at Waterloo and a scientific associate at the Centre for Digital Therapeutics within the University Health Network.
Although they identified room for improvement in diet quality, the researchers acknowledged several challenges when changing food in LTC homes.
One is that older adult residents must enjoy the food and drinks they consume since it affects their quality of life.
Another is that most LTC residents are at risk of malnutrition, so simply ensuring they receive enough calories can be difficult. Budgetary constraints and the seasonal availability of certain foods can also come into play.
The new AI tool the researchers developed automated a process that has long been a time-consuming manual task subject to bias and error.
“The ability to do such massive categorization using AI in an automated fashion allowed us to get much deeper, much more comprehensive insights into the inflammatory potential of what is currently eaten in LTC,” said Dr. Alexander Wong, a professor of systems design engineering at Waterloo.
IMAGE CREDIT: NASA.