Researchers develop AI capable of detecting obesity from space

The use of AI in future city-planning could help prevent obesity-related diseases

3Sep

Researchers from the University of Washington, Seattle, have utilized artificial intelligence (AI) technology to use Google Maps images in making educated estimations into rates of obesity on Earth.

Using nearly 150,000 high-resolution satellite images of neighborhoods in US cities, the AI was able to detect obesity rates from space, without actually spotting obese individuals.

The neural network was already pre-trained using around 1.2 million images to analyze urban environments. The researchers then fed it data on adult obesity prevalence and the AI then extracted features such as the distribution of buildings and green areas in the built environment, to link to the data.

Obesity rates are due to a number of complex factors, but the researchers found that the physical environment we live in has a huge effect on rates of obesity, and that using an AI satellite images could be used to map that link.


Visit Innovation Enterprise's Big Data & Machine Learning for Pharma Summit Europe 2018 in Madrid on October 10, 2018


The researchers noted that: "The extraction of built environment showed that physical characteristics of a neighbourhood (presence of parks, highways, green streets, crosswalks, diverse housing types) can be associated with variations in obesity prevalence across different neighborhoods.

"Understanding the association between specific features of the built environment and obesity prevalence can lead to structural changes that could encourage physical activity and decreases in obesity prevalence," they added.

The research demonstrated how the built environment can dramatically influence health outcomes through the availability of resources such as activity and recreational spaces, housing and measures of community design.

According to the National Health and Nutrition Examination Survey (NHANES), one in three Americans are obese, causing an immense strain on health services. However, the researchers have established that, in the future, councils and city planners could use AI to create more green areas, ensuring that the population is more physically active, thereby reducing the risk of obesity-related illness and death.

Big data analytics market to be worth  275bn by 2023 small

Read next:

Big data analytics market to be worth $275bn by 2023

i