PMID- 32041029
OWN - NLM
STAT- MEDLINE
DCOM- 20200604
LR  - 20200604
IS  - 1873-6424 (Electronic)
IS  - 0269-7491 (Linking)
VI  - 260
DP  - 2020 May
TI  - Associations between persistent organic pollutants and endometriosis: A 
      multipollutant assessment using machine learning algorithms.
PG  - 114066
LID - S0269-7491(19)35535-6 [pii]
LID - 10.1016/j.envpol.2020.114066 [doi]
AB  - Endometriosis is a gynaecological disease characterised by the presence of 
      endometriotic tissue outside of the uterus impacting a significant fraction of 
      women of childbearing age. Evidence from epidemiological studies suggests a 
      relationship between risk of endometriosis and exposure to some organochlorine 
      persistent organic pollutants (POPs). However, these chemicals are numerous and 
      occur in complex and highly correlated mixtures, and to date, most studies have 
      not accounted for this simultaneous exposure. Linear and logistic regression 
      models are constrained to adjusting for multiple exposures when variables are 
      highly intercorrelated, resulting in unstable coefficients and arbitrary 
      findings. Advanced machine learning models, of emerging use in epidemiology, 
      today appear as a promising option to address these limitations. In this study, 
      different machine learning techniques were compared on a dataset from a 
      case-control study conducted in France to explore associations between mixtures 
      of POPs and deep endometriosis. The battery of models encompassed regularised 
      logistic regression, artificial neural network, support vector machine, adaptive 
      boosting, and partial least-squares discriminant analysis with some additional 
      sparsity constraints. These techniques were applied to identify the biomarkers of 
      internal exposure in adipose tissue most associated with endometriosis and to 
      compare model classification performance. The five tested models revealed a 
      consistent selection of most associated POPs with deep endometriosis, including 
      octachlorodibenzofuran, cis-heptachlor epoxide, polychlorinated biphenyl 77 or 
      trans-nonachlor, among others. The high classification performance of all five 
      models confirmed that machine learning may be a promising complementary approach 
      in modelling highly correlated exposure biomarkers and their associations with 
      health outcomes. Regularised logistic regression provided a good compromise 
      between the interpretability of traditional statistical approaches and the 
      classification capacity of machine learning approaches. Applying a battery of 
      complementary algorithms may be a strategic approach to decipher complex 
      exposome-health associations when the underlying structure is unknown.
CI  - Copyright (c) 2020 Elsevier Ltd. All rights reserved.
FAU - Matta, Komodo
AU  - Matta K
AD  - LABERCA, Oniris, INRAE, 44307, Nantes, France.
FAU - Vigneau, Evelyne
AU  - Vigneau E
AD  - StatSC, ONIRIS, INRAE, Nantes, France.
FAU - Cariou, Veronique
AU  - Cariou V
AD  - StatSC, ONIRIS, INRAE, Nantes, France.
FAU - Mouret, Delphine
AU  - Mouret D
AD  - LABERCA, Oniris, INRAE, 44307, Nantes, France.
FAU - Ploteau, Stephane
AU  - Ploteau S
AD  - Service de Gynecologie-obstetrique, CIC FEA, Hopital Mere Enfant, CHU Hotel Dieu, 
      Nantes, France.
FAU - Le Bizec, Bruno
AU  - Le Bizec B
AD  - LABERCA, Oniris, INRAE, 44307, Nantes, France.
FAU - Antignac, Jean-Philippe
AU  - Antignac JP
AD  - LABERCA, Oniris, INRAE, 44307, Nantes, France.
FAU - Cano-Sancho, German
AU  - Cano-Sancho G
AD  - LABERCA, Oniris, INRAE, 44307, Nantes, France. Electronic address: 
      laberca@oniris-nantes.fr.
LA  - eng
PT  - Journal Article
DEP - 20200128
PL  - England
TA  - Environ Pollut
JT  - Environmental pollution (Barking, Essex : 1987)
JID - 8804476
RN  - 0 (Environmental Pollutants)
SB  - IM
MH  - *Algorithms
MH  - Case-Control Studies
MH  - Endometriosis/*epidemiology
MH  - Environmental Exposure/*statistics & numerical data
MH  - *Environmental Pollutants
MH  - Female
MH  - France
MH  - Humans
MH  - Machine Learning
OTO - NOTNLM
OT  - Endocrine disrupting chemicals
OT  - Endometriosis
OT  - Machine learning
OT  - Multipollutant modelling
OT  - Persistent organic pollutants
COIS- Declaration of competing interest Authors declare no conflicts of interest.
EDAT- 2020/02/12 06:00
MHDA- 2020/06/05 06:00
CRDT- 2020/02/12 06:00
PHST- 2019/09/25 00:00 [received]
PHST- 2019/12/17 00:00 [revised]
PHST- 2020/01/23 00:00 [accepted]
PHST- 2020/02/12 06:00 [pubmed]
PHST- 2020/06/05 06:00 [medline]
PHST- 2020/02/12 06:00 [entrez]
AID - S0269-7491(19)35535-6 [pii]
AID - 10.1016/j.envpol.2020.114066 [doi]
PST - ppublish
SO  - Environ Pollut. 2020 May;260:114066. doi: 10.1016/j.envpol.2020.114066. Epub 2020 
      Jan 28.