Researchers at Mount Sinai School of Medicine have developed a new machine learning algorithm and used it to previously know toxic air pollutants that may be associated with poor asthma outcomes later in the child’s life. Identified a mixture that had not been.
Research examined Early exposure To dozens of pollutants that 151 children with mild to severe illness can experience.Some cases may be personally related, but established air Pollutants, Others appeared to be related to a mixture of pollutants that had never been associated with asthma.. The results and description of the new algorithm Clinical research journal..
“Asthma is one of the most common illnesses affecting children in the United States. In this study, air pollutants that could expose infants to long-term problems with asthma. We have created a list, “says Dr. Supinda Bunyavanich. , MPH, MPhil, Professor of Pediatrics, Genetics and Genomics, and Senior Author of Research at Icahn Mount Sinai. “Our results show that individual breathing and pollutant combinations can lead to poor asthma outcomes. One day, by taking a more comprehensive and holistic view of air pollution. I hope we can reduce the chances of children suffering from asthma. “
Asthma, which affects about 7% of children in the United States, is a lung disease that can cause wheezing, chest tightness, and coughing attacks. Some studies have shown that breathing individual toxic air pollutants, or “air poisoning,” increases the likelihood that a child will suffer from asthma, but what happens when the pollutants are mixed in. Little is known about what happens.
In this study, researchers used a new machine learning algorithm to discover that 18 individual chemicals may be associated with poor asthma outcomes in later years. Specifically, we investigated whether the child needed a drug to control asthma daily or needed a visit. emergency room Or spend time in the hospital as a result of their condition. However, they also discovered a new link between the results and 20 different pollutant mixtures. Some of the chemicals in the mixture have never been associated with long-term asthma risk.
“Like many scientists, we wanted to provide a more comprehensive picture of how air poisoning contributes to childhood asthma,” said an assistant professor of genetics and genomics and research. Senior author Dr. Gaulau Panday said. “Traditionally, for technical reasons, it was difficult to study the health effects of multiple toxic substances at once. We overcame this by harnessing the power of machine learning algorithms.”
The research and development of the algorithm was led by Dr. Yan-Chak Li, a bioinformatician engineer at Pandy Labs, and Dr. Hsiao-Hsien Leon Hsu, an assistant professor of environmental medicine and public health at Icahn Mount Sinai.
Researchers first mapped 125 known pollutant emissions to the habitat and year of birth of 151 children from the New York metropolitan area, which was part of the Sinai airway in an asthma study. Did. Emission data was obtained from the Environmental Protection Agency’s National Air Toxicity Assessment Resource.
Next, researchers applied a new algorithm called “Data-Driven ExposurE Profile (DEEP) Extraction” to increase the levels of pollutants observed early in the child’s life, about 12 years old. We tested whether it correlates with the asthma problems reported in. .. DEEP relies on a powerful machine learning algorithm called “eXtreme Gradient Boosting (EXBoost)”. This builds a way in which hundreds of “decision trees”, or each pollutant, alone or in combination with other pollutants, may be associated with later asthma problems. Patient life.
The results showed that some pollutants may have worked alone. For example, exposure to trimethylamine, an ammonia-scented waterproofing agent, increased the likelihood that children with asthma would have to spend the night in the hospital.
Other pollutants can act alone or in admixture. Most notably, exposure to acrylic acid increased the likelihood that children would need daily medication. Mixing acrylic acid with other chemicals not only increased this possibility, but also increased the chances of visiting an emergency room and staying overnight.
Interestingly, researchers also found that some pollutants, such as toluene and cobalt compounds, were associated with adverse results only when mixed with other compounds. In fact, the 16 chemicals they evaluated fell into this category.
“As a doctor treating a child with asthma, I was amazed at the number of potential air toxicities that our radar does not have,” said Dr. Bunyavanich. “These results have changed my view of the increased risk faced by some children.”
Finally, researchers have discovered that demographic factors can play an additional role. For example, exposure to a combination of hydroquinone and ethylidene dichloride was the strongest predictor of overnight hospitalization. The study found that children in this category were also younger and had lower family incomes than children who were not exposed to pollutants.
“our study This is an example of how machine learning has the potential to change medical research. We can understand various environmental factors, that is, how exposomes affect our health. In the future, we plan to use DEEP and other computer science technologies to address environmental factors associated with other complex failures. ”
Yan-Chak Li et al, Machine Learning Identifying Early Air Toxic Combinations Associated with Childhood Asthma Outcomes, Clinical research journal (2021). DOI: 10.1172 / JCI152088
Mount Sinai Hospital
Quote: The Pediatric Asthma Study was obtained from https://medicalxpress.com/news/2021-10-childhood-asthma-uncovers-risky-air.html on October 8, 2021 as a dangerous air pollutant mixture (2021). October 8, 2014) will be revealed
This document is subject to copyright. No part may be reproduced without written permission, except for fair transactions for personal investigation or research purposes. The content is provided for informational purposes only.
Childhood asthma study uncovers risky air pollutant mixtures Source link Childhood asthma study uncovers risky air pollutant mixtures
The post Childhood asthma study uncovers risky air pollutant mixtures appeared first on California News Times.