We published new research: Creating a new machine learning algorithm to study the effects of air pollution on children with asthma
In a new study we published this week in The Journal of Clinical Investigation, our multidisciplinary team of computer scientists, physicians, and epidemiologists at the Icahn School of Medicine at Mount Sinai developed a novel machine-learning algorithm. We used this new machine learning method to identify previously unknown mixtures of toxic air pollutants that appear to be linked to poor asthma outcomes in children.
The issue we addressed with this investigation was that most studies assess the toxicity of pollutants one at a time. But in the real world, people are exposed to mixtures of pollutants that cause different health effects. Gaurav Pandey, PhD, Assistant Professor of Genetics and Genomic Sciences and a senior author of the study, said: "Traditionally, for technical reasons, it has been difficult to study the health effects of more than one toxic at a time. We overcame this by tapping into the power of machine learning algorithms."
To do this, we examined early exposure to dozens of pollutants to which 151 children with mild to severe asthma were potentially exposed early in their lives, as measured by the Environmental Protection Agency's National Air Toxics Assessment resource. We developed and applied a novel algorithm, named "Data-driven ExposurE Profile (DEEP) Extraction, to determine the possible ways that each pollutant, alone or in combination with others, could explain asthma outcomes in the children. The algorithm development was led by Yan-Chak Li, MPhil, a bioinformatician, and Hsiao-Hsien Leon Hsu, ScD, Assistant Professor of Environmental Medicine and Public Health.
We found that some disease cases could be linked to an individual chemical. One example of an individual chemical showing an effect was the ammonia-scented waterproofing agent trimethylamine, which raised the chances that a child with asthma would spend a night in the hospital.
Other pollutants could act alone or in mixtures. One example was acrylic acid, a chemical used in plastics, coatings, medical products, and detergents. Exposure to acrylic acid raised the chances that a child would need daily medication. Exposure to acrylic acid combined with other chemicals further increased this possibility, and in addition, it boosted the chances of emergency room visits and overnight hospitalizations among the asthmatic children who participated in the study. (See illustration)
In all, 34 individual chemicals were found to be linked to poor asthma outcomes. Importantly, some asthma cases appeared to be linked to mixtures of pollutants that had never been associated with asthma.
"As a physician who treats children with asthma, I was struck by how many potential air toxics are not on our radar," said Supinda Bunyavanich, MD, MPH, MPhil, Professor of Pediatrics, and Genetics and Genomic Sciences, and a senior author of the study. "These results changed my view of the heightened risk some children face."
"Our study is an example of how machine learning has the potential to alter medical research," said Dr. Pandey. "It is allowing us to understand how a wide variety of environmental factors—or the exposome—influences our health. In the future, we plan to use DEEP and other computer science techniques to tackle environmental factors associated with other complex disorders."
This work was supported by the Department of Genetics and Genomic Sciences at Mount Sinai, Scientific Computing at Icahn Mount Sinai, and the National Institutes of Health (AI118833, HG011407, HL147328, OD023337, and ES023515).
Citation: Li, Y.C., Hsu, H.H.L., Chun Y, Chiu PH, Arditi Z, Claudio L, Pandey G, Bunyavanich S. Machine learning-driven identification of early-life air toxic combinations associated with childhood asthma outcomes. Journal of Clinical Investigation, October 5, 2021, DOI: 10.1172/JCI152088
This section will not be visible in live published website. Below are your current settings:
Current Number Of Columns are = 1
Expand Posts Area = 1
Gap/Space Between Posts = 8px
Blog Post Style = card
Use of custom card colors instead of default colors = 1
Blog Post Card Background Color = current color
Blog Post Card Shadow Color = current color
Blog Post Card Border Color = current color
Publish the website and visit your blog page to see the results
Dr. Luz Claudio is an environmental health scientist, mother and consultant, originally from Puerto Rico. She is a tenured professor of environmental medicine and public health. Luz recently published her first book: How to Write and Publish a Scientific Paper: The Step-by-Step Guide. Dr. Claudio has internship programs and resources for young scientists. Opinions expressed in this blog are solely her own and may not reflect her employer's views.