Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jun 26;20(6):e0325896.
doi: 10.1371/journal.pone.0325896. eCollection 2025.

Effect of the exposure to brominated flame retardants on hyperuricemia using interpretable machine learning algorithms based on the SHAP methodology

Yu Cai  1 , Xi-Ru Huang  1 , Sheng-Jia Wang  1 , Ying-Chao Liang  1 , De-Liang Liu  2 , Shu-Fang Chu  2 , Hui-Lin Li  2
Affiliations

Effect of the exposure to brominated flame retardants on hyperuricemia using interpretable machine learning algorithms based on the SHAP methodology

Yu Cai et al. PLoS One. .

Abstract

Background: Brominated flame retardants (BFRs) are classified as important endocrine disruptors and persistent organic pollutants; nevertheless, there is no comprehensive investigation to evaluate the association between BFRs and hyperuricemia, and the available studies related to this field are exceptionally scarce.

Methods: For this study, we enrolled 3,812 individuals from NHANES 2005-2016, with nine different types of BFRs serving as the exposure. We conducted advanced machine learning techniques, along with regression analysis to validate our findings from diverse perspectives. Weighted logistic regression were employed to evaluate the association of BFRs for both continuous variables after logarithmic transformation and their quartile subgroups with hyperuricemia. Restricted cubic spline (RCS) analysis was conducted to identify whether a non-linear relationship exists. Subgroup analysis enabled us to explore potential interactions of research findings across different groups. Weighted quantile sum (WQS) regression was performed to assess collective mixture sum impact, along with contributions of each component. Nine machine-learning models were developed for hyperuricemia prediction, and six discrimination characteristics were applied to select the optimal model. SHapley Additive exPlanations (SHAP) was utilized to interpret the contributions of selected variables for model decision-making capacity.

Results: Several BFRs exhibited noticeable positive correlation with the prevalence of hyperuricemia, including PBDE28 (OR: 1.27, 95% CI: 1.05-1.54, P-value = 0.014), PBDE47 (OR: 1.19, 95% CI: 1.02-1.40, P-value = 0.032), PBDE85 (OR: 1.16, 95% CI: 1.01-1.34, P-value = 0.036), PBDE99 (OR: 1.17, 95% CI: 1.02-1.34, P-value = 0.025), and PBDE154 (OR: 1.16, 95% CI: 1.00-1.34, P-value = 0.050) after fully adjustment. The WQS analysis found that the sum effect of BFRs was positively associated with hyperuricemia, of which PBDE28 (28.70%), PBDE85 (22.10%) and PBDE47 (14.90%) were the top 3 components. XGboost exhibited superior performance across several important metrics. The SHAP analysis revealed that the PBDE85, PBDE28 and PBDE154 exhibited considerable influence, ranking after "BMI≥30", "Race-Non-Hispanic Black" and "Hypertension-Yes".

Conclusions: Combining the outcomes, our study identified PBDE28 and PBDE85 as the two major significant contributors to elevated prevalence of hyperuricemia. Other components, such as PBDE154, PBDE47, PBDE99, and PBDE100, emerged as potential pollutants. These pioneering efforts highlighted the previously underrecognized impact on this environmental and public health concern.

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. Flowchart of the selection of participants for this study from NHANES 2005–2016.
Fig 2
Fig 2. RCS analysis of nine BFRs with hyperuricemia.
Fig 3
Fig 3. Contributions of each component in WQS regression for BFRs on hyperuricemia with full covariate adjustment.
Fig 4
Fig 4. The ROC curves of nine machine-learning models.
(A) Training set. (B) Testing set.
Fig 5
Fig 5. Discriminative characteristics of nine machine-learning models.
Fig 6
Fig 6. Calibration curve of nine machine-learning models.
Fig 7
Fig 7. SHAP Summary plot based on the XGboost.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Feiteiro J, Mariana M, Cairrão E. Health toxicity effects of brominated flame retardants: From environmental to human exposure. Environ Pollut. 2021;285:117475. doi: 10.1016/j.envpol.2021.117475 - DOI - PubMed
    1. Lyche JL, Rosseland C, Berge G, Polder A. Human health risk associated with brominated flame-retardants (BFRs). Environ Int. 2015;74:170–80. doi: 10.1016/j.envint.2014.09.006 - DOI - PubMed
    1. Ezechiáš M, Covino S, Cajthaml T. Ecotoxicity and biodegradability of new brominated flame retardants: A review. Ecotoxicology Environ Safety. 2014;110:153–67. doi: 10.1016/j.ecoenv.2014.08.030 - DOI - PubMed
    1. Khalil A, Cevik SE, Hung S, Kolla S, Roy MA, Suvorov A. Developmental Exposure to 2,2′,4,4′-Tetrabromodiphenyl Ether Permanently Alters Blood-Liver Balance of Lipids in Male Mice. Front Endocrinol. 2018;9. doi: 10.3389/fendo.2018.00548 - DOI - PMC - PubMed
    1. Ongono JS, Dow C, Gambaretti J, Severi G, Boutron-Ruault M-C, Bonnet F, et al. Dietary exposure to brominated flame retardants and risk of type 2 diabetes in the French E3N cohort. Environ Int. 2019;123:54–60. doi: 10.1016/j.envint.2018.11.040 - DOI - PubMed

Substances

LinkOut - more resources