AI can predict a city's obesity levels from its buildings
AI can estimate obesity rates by analysing satellite imagery of urban areas
Your support helps us to tell the story
This election is still a dead heat, according to most polls. In a fight with such wafer-thin margins, we need reporters on the ground talking to the people Trump and Harris are courting. Your support allows us to keep sending journalists to the story.
The Independent is trusted by 27 million Americans from across the entire political spectrum every month. Unlike many other quality news outlets, we choose not to lock you out of our reporting and analysis with paywalls. But quality journalism must still be paid for.
Help us keep bring these critical stories to light. Your support makes all the difference.
An artificial intelligence algorithm has been trained to spot cities prone to obesity simply by analysing its buildings and infrastructure.
Researchers at the University of Washington used satellite and Street View images from Google Maps to study four urban areas in the United States: Los Angeles, California; Memphis, Tennessee; San Antonio, Texas; and Seattle, Washington.
Using neural networks, the researchers were able to discover a relationship between a location's infrastructure and its obesity prevalence.
Obesity is a major health issue in the US, with one in three adults suffering from the condition. Numerous studies have been carried out to better understand the phenomenon, with previous research linking obesity to factors including genetics, diet, physical activity and the environment.
The most recent study was unique in the tools it used to examine the link between built environments and obesity levels.
"This study illustrates that convolutional neural networks can be used to automate the extraction of features of the built environment from satellite images for studying healthy indicators," wrote the authors of the study, which was published in JAMA Network Open.
"Results in the study support the association between features of the built environment and obesity prevalence."
Further research could focus on assessing disparities based on neighbourhood racial composition and socioeconomic status, which has been linked to obesity and other health issues.
"Care must be taken in not over-interpreting any results," said biostatistician Benjamin Goldstein from Duke University, in a commentary on the study. "Even so, in the same way a biomarker may serve as a useful indicator of disease risk, these neighbourhood factors can serve as a valuable indicator of health outcomes.
"Going forward, it is likely that machine learning methods will be integral to discovering features associated with disease – likely features never previously suspected."
Eventually, the research could help public health bodies and improve community planning efforts for the purpose of fighting obesity.
The study's authors say the results could be used to make structural changes to built environments prone to obesity in order to encourage physical activity and introduce other measures to promote healthy living.
The study concludes: "Neighbourhood-level interventions to encourage physical activity and increase access to healthy food outlets could be combined with individual-level interventions to aid in curbing the obesity epidemic."
Join our commenting forum
Join thought-provoking conversations, follow other Independent readers and see their replies
Comments