ΑΙhub.org
 

#ICLR2023 invited talk: Data, history and equality with Elaine Nsoesie


by
11 May 2023



share this:

city data split by region on a white to blue colour scaleFigure from Use of Deep Learning to Examine the Association of the Built Environment With Prevalence of Neighborhood Adult Obesity, Adyasha Maharana and Elaine Okanyene Nsoesie. Image on the right represents actual obesity prevalence; on the left, cross-validated estimates of obesity prevalence based on features of the built environment extracted from satellite images. Figure reproduced under CC-BY licence.

The 11th International Conference on Learning Representations (ICLR) took place last week in Kigali, Rwanda, the first time a major AI conference has taken place in-person in Africa. The program included workshops, contributed talks, affinity group events, and socials. In addition, a total of six invited talks covered a broad range of topics. Following on from our post summarising the first two invited talks, we give a flavour of the presentation from Elaine Nsoesie.

Elaine Nsoesie – Data, History and Equity

Elaine Nsoesie’s research is primarily focused on the use of data and technology to advance health equity. One research direction is concerned with improving data, and increasing involvement, for under-represented communities in the development of AI models for health research. She also heads a project (the racial data tracker) which collects, analyses and disseminates racial data that point to the structural nature of racism in the USA. The results of this effort (which will be released later this month) take the form of interactive visualisations and infographics that citizens can use, either for advocacy, or for policy making.

One particular area that Elaine has focused on is the study of the links between neighbourhood and the health outcomes of its residents. Life expectancy is closely linked to the neighbourhood in which you live. As an example, Elaine highlighted Boston, and two neighbourhoods that are located just a few miles apart. In the neighbourhood North Roxbury (which consists of 50.3% Black population and 30.7% Hispanic population), the life expectancy is 59.8 years, whereas in Back Bay (with 73.4% white population) this figure is 84.5. These disparities can be linked to past governmental policies.

A specific policy that Elaine highlighted is “redlining“. Introduced in the 1930s, the US Government categorised neighbourhoods in cities across the country, with each given a grade based on how risky that area was deemed for investment. This led to residents of areas labelled as “hazardous” being denied services. The areas most frequently discriminated against were Black inner city neighbourhoods. The lasting effects of this policy continue to impact health to this day.

In her work, Elaine studies how racist policies, such as redlining, have created inequities in the built environment. In one study, she used deep learning (specifically a convolutional neural network (CNN)) to examine the association of environs with the prevalence of adult obesity. Using satellite images and obesity data from six US cities, Elaine, and colleague Adyasha Maharana, showed that physical characteristics of a neighbourhood (such as the presence of parks, highways, green streets, crosswalks, housing types) can be associated with variations in obesity prevalence across different neighbourhoods.

As a next step, Elaine and her team looked at street view images. Once again using a CNN, they classified the images according the physical characteristics of the built environment. Their aim was to investigate the association among neighbourhood racial and ethnic composition, the built environment, and health outcomes across urban areas in the US. They found significant differences (in terms of the built environment) between predominantly white neighbourhoods and neighbourhoods with predominantly Black, or other minoritized racial or ethnic group, residents. In terms of health outcomes, poor-quality housing was strongly associated with the prevalence of asthma and sleep problems.

Elaine closed her presentation by stressing that historical policies continue to impact our lives today. By studying, measuring, and quantifying these impacts, her objective is to provide concrete evidence of disparities to inform policy makers.

You can read more about this research, and Elaine’s other projects and published work here.



tags:


Lucy Smith is Senior Managing Editor for AIhub.
Lucy Smith is Senior Managing Editor for AIhub.




            AIhub is supported by:



Related posts :



Machine learning for atomic-scale simulations: balancing speed and physical laws

How much underlying physics can we safely “shortcut” without breaking a simulation?

Policy design for two-sided platforms with participation dynamics: Interview with Haruka Kiyohara

  09 Oct 2025
Studying the long-term impacts of decision-making algorithms on two-sided platforms such as e-commerce or music streaming apps.

The Machine Ethics podcast: What excites you about AI? Vol.2

This is a bonus episode looking back over answers to our question: What excites you about AI?

Interview with Janice Anta Zebaze: using AI to address energy supply challenges

  07 Oct 2025
Find out more about research combining renewable energy systems, tribology, and artificial intelligence.

How does AI affect how we learn? A cognitive psychologist explains why you learn when the work is hard

  06 Oct 2025
Early research is only beginning to scratch the surface of how AI technology will truly affect learning and cognition in the long run.

Interview with Zahra Ghorrati: developing frameworks for human activity recognition using wearable sensors

  03 Oct 2025
Find out more about research developing scalable and adaptive deep learning frameworks.

Diffusion beats autoregressive in data-constrained settings

  03 Oct 2025
How can we trade off more compute for less data?

Forthcoming machine learning and AI seminars: October 2025 edition

  02 Oct 2025
A list of free-to-attend AI-related seminars that are scheduled to take place between 3 October and 30 November 2025.



 

AIhub is supported by:






 












©2025.05 - Association for the Understanding of Artificial Intelligence