PMID- 36416734
OWN - NLM
STAT- MEDLINE
DCOM- 20221125
LR  - 20221220
IS  - 1552-9924 (Electronic)
IS  - 0091-6765 (Print)
IS  - 0091-6765 (Linking)
VI  - 130
IP  - 11
DP  - 2022 Nov
TI  - Principal Component Pursuit for Pattern Identification in Environmental Mixtures.
PG  - 117008
LID - 10.1289/EHP10479 [doi]
LID - 117008
AB  - BACKGROUND: Environmental health researchers often aim to identify sources or 
      behaviors that give rise to potentially harmful environmental exposures. 
      OBJECTIVE: We adapted principal component pursuit (PCP)-a robust and 
      well-established technique for dimensionality reduction in computer vision and 
      signal processing-to identify patterns in environmental mixtures. PCP decomposes 
      the exposure mixture into a low-rank matrix containing consistent patterns of 
      exposure across pollutants and a sparse matrix isolating unique or extreme 
      exposure events. METHODS: We adapted PCP to accommodate nonnegative data, missing 
      data, and values below a given limit of detection (LOD). We simulated data to 
      represent environmental mixtures of two sizes with increasing proportions  < LOD 
      and three noise structures. We applied PCP-LOD to evaluate its performance in 
      comparison with principal component analysis (PCA). We next applied principal 
      component pursuit with limit of detection (PCP-LOD) to an exposure mixture of 21 
      persistent organic pollutants (POPs) measured in 1,000 U.S. adults from the 
      2001-2002 National Health and Nutrition Examination Survey (NHANES). We applied 
      singular value decomposition to the estimated low-rank matrix to characterize the 
      patterns. RESULTS: PCP-LOD recovered the true number of patterns through 
      cross-validation for all simulations; based on an a priori specified criterion, 
      PCA recovered the true number of patterns in 32% of simulations. PCP-LOD achieved 
      lower relative predictive error than PCA for all simulated data sets with up to 
      50% of the data  < LOD. When 75% of values were  < LOD, PCP-LOD outperformed PCA 
      only when noise was low. In the POP mixture, PCP-LOD identified a rank-three 
      underlying structure and separated 6% of values as extreme events. One pattern 
      represented comprehensive exposure to all POPs. The other patterns grouped 
      chemicals based on known structure and toxicity. DISCUSSION: PCP-LOD serves as a 
      useful tool to express multidimensional exposures as consistent patterns that, if 
      found to be related to adverse health, are amenable to targeted public health 
      messaging. https://doi.org/10.1289/EHP10479.
FAU - Gibson, Elizabeth A
AU  - Gibson EA
AUID- ORCID: 0000-0001-5119-5133
AD  - Department of Environmental Health Sciences, Columbia University Mailman School 
      of Public Health, New York, New York, USA.
FAU - Zhang, Junhui
AU  - Zhang J
AD  - Department of Applied Physics and Applied Mathematics, Columbia University, New 
      York, New York, USA.
FAU - Yan, Jingkai
AU  - Yan J
AUID- ORCID: 0000-0002-2094-2092
AD  - Department of Electrical Engineering, Columbia University Data Science Institute, 
      New York, New York, USA.
FAU - Chillrud, Lawrence
AU  - Chillrud L
AUID- ORCID: 0000-0003-0727-0161
AD  - Department of Environmental Health Sciences, Columbia University Mailman School 
      of Public Health, New York, New York, USA.
FAU - Benavides, Jaime
AU  - Benavides J
AUID- ORCID: 0000-0002-1851-5155
AD  - Department of Environmental Health Sciences, Columbia University Mailman School 
      of Public Health, New York, New York, USA.
FAU - Nunez, Yanelli
AU  - Nunez Y
AD  - Department of Environmental Health Sciences, Columbia University Mailman School 
      of Public Health, New York, New York, USA.
FAU - Herbstman, Julie B
AU  - Herbstman JB
AD  - Department of Environmental Health Sciences, Columbia University Mailman School 
      of Public Health, New York, New York, USA.
FAU - Goldsmith, Jeff
AU  - Goldsmith J
AD  - Department of Biostatistics, Columbia University Mailman School of Public Health, 
      New York, New York, USA.
FAU - Wright, John
AU  - Wright J
AD  - Department of Electrical Engineering, Columbia University Data Science Institute, 
      New York, New York, USA.
FAU - Kioumourtzoglou, Marianthi-Anna
AU  - Kioumourtzoglou MA
AD  - Department of Environmental Health Sciences, Columbia University Mailman School 
      of Public Health, New York, New York, USA.
LA  - eng
GR  - F31 ES030263/ES/NIEHS NIH HHS/United States
GR  - R01 ES028805/ES/NIEHS NIH HHS/United States
GR  - P30 ES009089/ES/NIEHS NIH HHS/United States
PT  - Journal Article
PT  - Research Support, N.I.H., Extramural
DEP - 20221123
PL  - United States
TA  - Environ Health Perspect
JT  - Environmental health perspectives
JID - 0330411
RN  - 0 (Environmental Pollutants)
SB  - IM
MH  - Nutrition Surveys
MH  - *Environmental Pollutants/toxicity
MH  - Environmental Exposure/analysis
MH  - Principal Component Analysis
MH  - Public Health
PMC - PMC9683097
EDAT- 2022/11/24 06:00
MHDA- 2022/11/26 06:00
PMCR- 2022/11/23
CRDT- 2022/11/23 10:33
PHST- 2022/11/23 10:33 [entrez]
PHST- 2022/11/24 06:00 [pubmed]
PHST- 2022/11/26 06:00 [medline]
PHST- 2022/11/23 00:00 [pmc-release]
AID - EHP10479 [pii]
AID - 10.1289/EHP10479 [doi]
PST - ppublish
SO  - Environ Health Perspect. 2022 Nov;130(11):117008. doi: 10.1289/EHP10479. Epub 
      2022 Nov 23.