Nanoparticle characteristic interaction effects on pulmonary toxicity: A random forest modeling framework to compare risks of nanomaterial variants

Jeremy Michael Gernand, Elizabeth A. Casman

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Due to their unique physicochemical properties, nanomaterials have the potential to interact with living organisms in novel ways. Nanomaterial variants are too numerous to be screened for toxicity individually by traditional animal testing. Existing data on the toxicity of inhaled nanomaterials in animal models are sparse in comparison to the number of potential factors that may affect toxicity. This paper presents meta-analysis-based risk models developed with the machine-learning technique, random forests (RFs), to determine the relative contribution of different physical and chemical attributes on observed toxicity. The findings from this analysis indicate that carbon nanotube (CNT) impurities explain at most 30% of the variance in pulmonary toxicity as measured by polymorphonuclear neutrophils (PMNs) count. Titanium dioxide nanoparticle size and aggregation affected the observed toxic response by less than 10%. Differences in observed effects for a group of metal oxide nanoparticles associated with differences in Gibbs free energy on lactate dehydrogenase (LDH) concentrations amount to only 4% to the total variance.

Original languageEnglish (US)
Article number021002
JournalASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering
Volume2
Issue number2
DOIs
StatePublished - Jun 1 2016

Fingerprint

Nanostructured materials
Toxicity
animal
Nanoparticles
interaction
aggregation
energy
Animals
learning
Gibbs free energy
Group
Titanium dioxide
Learning systems
Carbon nanotubes
Agglomeration
Impurities
Oxides
Testing
Metals

All Science Journal Classification (ASJC) codes

  • Mechanical Engineering
  • Safety, Risk, Reliability and Quality
  • Safety Research

Cite this

@article{225bc8d895e8447a909e504adcc605ae,
title = "Nanoparticle characteristic interaction effects on pulmonary toxicity: A random forest modeling framework to compare risks of nanomaterial variants",
abstract = "Due to their unique physicochemical properties, nanomaterials have the potential to interact with living organisms in novel ways. Nanomaterial variants are too numerous to be screened for toxicity individually by traditional animal testing. Existing data on the toxicity of inhaled nanomaterials in animal models are sparse in comparison to the number of potential factors that may affect toxicity. This paper presents meta-analysis-based risk models developed with the machine-learning technique, random forests (RFs), to determine the relative contribution of different physical and chemical attributes on observed toxicity. The findings from this analysis indicate that carbon nanotube (CNT) impurities explain at most 30{\%} of the variance in pulmonary toxicity as measured by polymorphonuclear neutrophils (PMNs) count. Titanium dioxide nanoparticle size and aggregation affected the observed toxic response by less than 10{\%}. Differences in observed effects for a group of metal oxide nanoparticles associated with differences in Gibbs free energy on lactate dehydrogenase (LDH) concentrations amount to only 4{\%} to the total variance.",
author = "Gernand, {Jeremy Michael} and Casman, {Elizabeth A.}",
year = "2016",
month = "6",
day = "1",
doi = "10.1115/1.4031216",
language = "English (US)",
volume = "2",
journal = "ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering",
issn = "2332-9017",
publisher = "American Society of Mechanical Engineers(ASME)",
number = "2",

}

TY - JOUR

T1 - Nanoparticle characteristic interaction effects on pulmonary toxicity

T2 - A random forest modeling framework to compare risks of nanomaterial variants

AU - Gernand, Jeremy Michael

AU - Casman, Elizabeth A.

PY - 2016/6/1

Y1 - 2016/6/1

N2 - Due to their unique physicochemical properties, nanomaterials have the potential to interact with living organisms in novel ways. Nanomaterial variants are too numerous to be screened for toxicity individually by traditional animal testing. Existing data on the toxicity of inhaled nanomaterials in animal models are sparse in comparison to the number of potential factors that may affect toxicity. This paper presents meta-analysis-based risk models developed with the machine-learning technique, random forests (RFs), to determine the relative contribution of different physical and chemical attributes on observed toxicity. The findings from this analysis indicate that carbon nanotube (CNT) impurities explain at most 30% of the variance in pulmonary toxicity as measured by polymorphonuclear neutrophils (PMNs) count. Titanium dioxide nanoparticle size and aggregation affected the observed toxic response by less than 10%. Differences in observed effects for a group of metal oxide nanoparticles associated with differences in Gibbs free energy on lactate dehydrogenase (LDH) concentrations amount to only 4% to the total variance.

AB - Due to their unique physicochemical properties, nanomaterials have the potential to interact with living organisms in novel ways. Nanomaterial variants are too numerous to be screened for toxicity individually by traditional animal testing. Existing data on the toxicity of inhaled nanomaterials in animal models are sparse in comparison to the number of potential factors that may affect toxicity. This paper presents meta-analysis-based risk models developed with the machine-learning technique, random forests (RFs), to determine the relative contribution of different physical and chemical attributes on observed toxicity. The findings from this analysis indicate that carbon nanotube (CNT) impurities explain at most 30% of the variance in pulmonary toxicity as measured by polymorphonuclear neutrophils (PMNs) count. Titanium dioxide nanoparticle size and aggregation affected the observed toxic response by less than 10%. Differences in observed effects for a group of metal oxide nanoparticles associated with differences in Gibbs free energy on lactate dehydrogenase (LDH) concentrations amount to only 4% to the total variance.

UR - http://www.scopus.com/inward/record.url?scp=85027408416&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027408416&partnerID=8YFLogxK

U2 - 10.1115/1.4031216

DO - 10.1115/1.4031216

M3 - Article

AN - SCOPUS:85027408416

VL - 2

JO - ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering

JF - ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering

SN - 2332-9017

IS - 2

M1 - 021002

ER -