Leveraging Machine Learning for a Comprehensive Assessment of PFAS Nephrotoxicity

Leveraging Machine Learning for a Comprehensive Assessment of PFAS
Nephrotoxicity

Volume 9, Issue 3, Page No 62-71, 2024

Author’s Name: Anirudh Mazumder,  Kapil Panda

View Affiliations

University of North Texas, Texas Academy of Mathematics and Science, Denton, 76203, United States of America

a)whom correspondence should be addressed. E-mail: kapilpanda@my.unt.edu

Adv. Sci. Technol. Eng. Syst. J. 9(3), 62-71(2024); a  DOI: 10.25046/aj090306

Keywords: Machine Learning, Kidneys, Polyfluoro-Alkyl Substances, Toxicokinetics

Share
Download Now!

41 Downloads

Export Citations

Abstract

Polyfluoroalkyl substances (PFAS) are persistent chemicals that accumulate in the body and environment. Although recent studies have indicated that PFAS may disrupt kidney function, the underlying mechanisms and overall effects on the organ remain unclear. Therefore, this study aims to elucidate the impact of PFAS on kidney health using machine learning techniques. Utilizing a dataset containing PFAS chemical features and kidney parameters, dimensionality reduction and clustering were performed to identify patterns. Machine learning models, including XGBoost classifier, regressor, and Random Forest regressor, were then developed to predict kidney type from PFAS descriptors, estimate PFAS accumulation in the body, and predict the ratio of glomerular surface area to proximal tubule volume, which indicates kidney filtration efficiency. The kidney type classifier achieved 100% accuracy, confirming that PFAS exposure alters kidney morphology. The PFAS accumulation model attained an R2 of 1.00, providing a tool to identify at-risk individuals. The ratio prediction model reached an R2 of 1.00, offering insights into PFAS effects on kidney function. Furthermore, PFAS descriptors and anatomical variables were identified through analyses using feature importance, demonstrating discernible links between PFAS and kidney health, offering further biological significance. Overall, this study can significantly contribute to the current findings on the effect of PFAS while offering machine learning as a contributive tool for similar studies.

Received: 04 March, 2024, Revised: 18 May, 2024, Accepted: 19 May, 2024, Published Online: 12 June, 2024

References (53)

  1. J. Gl¨uge, M. Scheringer, I. T. Cousins, J. C. DeWitt, G. Goldenman, D. Herzke, R. Lohmann, C. A. Ng, X. Trier, Z. Wang, “An overview of the uses of perand polyfluoroalkyl substances (PFAS),” Environmental Science: Processes & Impacts, 22, 2345–2373, 2020, doi:10.1039/D0EM00291G.
  2.  P. Dewapriya, L. Chadwick, S. G. Gorji, B. Schulze, S. Valsecchi, S. Samanipour, K. V. Thomas, S. L. Kaserzon, “Per- and polyfluoroalkyl substances (PFAS) in consumer products: Current knowledge and research gaps,” Journal of Hazardous Materials Letters, 4, 100086, 2023, doi:10.1016/j.hazl.2023.100086.
  3. B. E. Blake, S. E. Fenton, “Early life exposure to per- and polyfluoroalkyl substances (PFAS) and latent health outcomes: A review including the placenta as a target tissue and possible driver of peri- and postnatal effects,” Toxicology, 443, 152565, 2020, doi:10.1016/j.tox.2020.152565.
  4.  D. Renfrew, T. W. Pearson, “The Social Life of the “Forever Chemical”,” Environment and Society, 12, 146–163, 2021, doi:10.3167/ares.2021.120109.
  5.  M. Kotthoff, J. M¨uller, H. J¨urling, M. Schlummer, D. Fiedler, “Perfluoroalkyl and polyfluoroalkyl substances in consumer products,” Environmental Science and Pollution Research, 22, 14546–14559, 2015, doi:10.1007/s11356-015- 4202-7.
  6.  S. A. B˘alan, V. C. Mathrani, D. F. Guo, A. M. Algazi, “Regulating PFAS as a Chemical Class under the California Safer Consumer Products Program,” Environmental Health Perspectives, 129, 2021, doi:10.1289/EHP7431.
  7. M. N. Ehsan, M. Riza, M. N. Pervez, M. M. O. Khyum, Y. Liang, V. Naddeo,“Environmental and health impacts of PFAS: Sources, distribution and sustainable management in North Carolina (USA),” Science of The Total Environment, 878, 163123, 2023, doi:10.1016/j.scitotenv.2023.163123.
  8. J. Fabregat-Palau, M. Vidal, A. Rigol, “Examining sorption of perfluoroalkyl substances (PFAS) in biochars and other carbon-rich materials,” Chemosphere, 302, 134733, 2022, doi:10.1016/j.chemosphere.2022.134733.
  9. G. Jha, V. Kankarla, E. McLennon, S. Pal, D. Sihi, B. Dari, D. Diaz, M. Nocco,“Per- and Polyfluoroalkyl Substances (PFAS) in Integrated Crop–Livestock Systems: Environmental Exposure and Human Health Risks,” International Journal of Environmental Research and Public Health, 18, 12550, 2021, doi:10.3390/ijerph182312550.
  10. B. E. Blake, S. M. Pinney, E. P. Hines, S. E. Fenton, K. K. Ferguson, “Associations between longitudinal serum perfluoroalkyl substance (PFAS) levels and measures of thyroid hormone, kidney function, and body mass index in the Fernald Community Cohort,” Environmental Pollution, 242, 894–904, 2018, doi:10.1016/j.envpol.2018.07.042.
  11. M. L. Ljubicic, A. Madsen, A. Juul, K. Almstrup, T. H. Johannsen, “The Application of Principal Component Analysis on Clinical and Biochemical Parameters Exemplified in Children With Congenital Adrenal Hyperplasia,” Frontiers in Endocrinology, 12, 2021, doi:10.3389/fendo.2021.652888.
  12. M. Bonato, F. Corr`a, M. Bellio, L. Guidolin, L. Tallandini, P. Irato, G. Santovito,“PFAS Environmental Pollution and Antioxidant Responses: An Overview of the Impact on Human Field,” International Journal of Environmental Research and Public Health, 17, 8020, 2020, doi:10.3390/ijerph17218020.
  13. K. M. Fraley, H. N. Fraley, D. Arthur, E. J. Walther, “Per- and Polyfluoroalkyl Substances ( PFAS ): Anglers May Be Exposed to Harmful Chemicals in Their Catch,” Fisheries, 45, 138–144, 2020, doi:10.1002/fsh.10389.
  14. L. Anderko, E. Pennea, “Exposures to per-and polyfluoroalkyl substances (PFAS): Potential risks to reproductive and children’s health,” Current Problems in Pediatric and Adolescent Health Care, 50, 100760, 2020, doi:10.1016/j.cppeds.2020.100760.
  15. S. H. Baker, A. Kinde, “The Pathway to a Green New Deal: Synthesizing Transdisciplinary Literatures and Activist Frameworks to Achieve a Just Energy Transition,” Environs: Environmental Law and Policy Journal, 44, 1–40.
  16. P.-I. D. Lin, A. Cardenas, R. Hauser, D. R. Gold, K. P. Kleinman, M.-F. Hivert, A. M. Calafat, T. F. Webster, E. S. Horton, E. Oken, “Per- and polyfluoroalkyl substances and kidney function: Follow-up results from the Diabetes Prevention Program trial,” Environment International, 148, 106375, 2021, doi:10.1016/j.envint.2020.106375.
  17.  W. PFALLER, M. RITTINGER, QUANTITATIVE MORPHOLOGY OF THE RAT KIDNEY, 17–22, Elsevier, 1980, doi:10.1016/B978-0-08-025517- 0.50011-4.
  18. J. Yun, E.-C. Jang, S.-C. Kwon, Y.-S. Min, Y.-J. Lee, “The association of perfluoroalkyl substances (PFAS) exposure and kidney function in Korean adolescents using data from Korean National Environmental Health Survey (KoNEHS) cycle 4 (2018–2020): a cross-sectional study,” Annals of Occupational and Environmental Medicine, 35, 2023, doi:10.35371/aoem.2023.35.e5.
  19.  J. W. Stanifer, H. M. Stapleton, T. Souma, A. Wittmer, X. Zhao, L. E. Boulware,“Perfluorinated Chemicals as Emerging Environmental Threats to Kidney Health,” Clinical Journal of the American Society of Nephrology, 13, 1479– 1492, 2018, doi:10.2215/CJN.04670418.
  20.  B. Conway, A. Badders, T. Costacou, J. Arthur, K. Innes, “Perfluoroalkyl substances and kidney function in chronic kidney disease, anemia, and diabetes,”Diabetes, Metabolic Syndrome and Obesity: Targets and Therapy, Volume 11, 707–716, 2018, doi:10.2147/DMSO.S173809.
  21.  F. Coperchini, L. Croce, G. Ricci, F. Magri, M. Rotondi, M. Imbriani, L. Chiovato,“Thyroid Disrupting Effects of Old and New Generation PFAS,” Frontiers in Endocrinology, 11, 2021, doi:10.3389/fendo.2020.612320.
  22.  A. Raza, S. Bardhan, L. Xu, S. S. R. K. C. Yamijala, C. Lian, H. Kwon, B. M. Wong, “A Machine Learning Approach for Predicting Defluorination of Per- and Polyfluoroalkyl Substances (PFAS) for Their Efficient Treatment and Removal,” Environmental Science & Technology Letters, 6, 624–629, 2019, doi:10.1021/acs.estlett.9b00476.
  23.  C.-W. Huang, R. Lu, U. Iqbal, S.-H. Lin, P. A. Nguyen, H.-C. Yang, C.-F. Wang, J. Li, K.-L. Ma, Y.-C. Li, W.-S. Jian, “A richly interactive exploratory data analysis and visualization tool using electronic medical records,” BMC Medical Informatics and Decision Making, 15, 92, 2015, doi:10.1186/s12911- 015-0218-7.
  24.  D. E. Dawson, C. Lau, P. Pradeep, R. R. Sayre, R. S. Judson, R. Tornero-Velez, J. F. Wambaugh, “A Machine Learning Model to Estimate Toxicokinetic Half- Lives of Per- and Polyfluoro-Alkyl Substances (PFAS) in Multiple Species,” Toxics, 11, 2023, doi:10.3390/toxics11020098.
  25. R. Paul, A. S. M. L. Hoque, “Clustering medical data to predict the likelihood of diseases,” in 2010 Fifth International Conference on Digital Information Management (ICDIM), 44–49, 2010, doi:10.1109/ICDIM.2010.5664638.
  26. X. Gong, L. Liu, S. Fong, Q. Xu, T. Wen, Z. Liu, “Comparative Research of Swarm Intelligence Clustering Algorithms for Analyzing Medical Data,” IEEE Access, 7, 137560–137569, 2019, doi:10.1109/ACCESS.2018.2881020.
  27. J. Ma, Z. Yu, Y. Qu, J. Xu, Y. Cao, “Application of the XGBoost Machine Learning Method in PM2.5 Prediction: A Case Study of Shanghai,” Aerosol and Air Quality Research, 20, 128–138, 2020, doi:10.4209/aaqr.2019.08.0408.
  28. H. Liang, K. Jiang, T.-A. Yan, G.-H. Chen, “XGBoost: An Optimal Machine Learning Model with Just Structural Features to Discover MOF Adsorbents of Xe/Kr,” ACS Omega, 6, 9066–9076, 2021, doi:10.1021/acsomega.1c00100.
  29. J. Li, X. An, Q. Li, C. Wang, H. Yu, X. Zhou, Y. ao Geng, “Application of XGBoost algorithm in the optimization of pollutant concentration,” Atmospheric Research, 276, 106238, 2022, doi:10.1016/j.atmosres.2022.106238.
  30. A. Ogunleye, Q.-G.Wang, “XGBoost Model for Chronic Kidney Disease Diagnosis,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, 17(6), 2131–2140, 2020, doi:10.1109/TCBB.2019.2911071.
  31.  X. Zhang, C. Yan, C. Gao, B. A. Malin, Y. Chen, “Predicting Missing Values in Medical Data Via XGBoost Regression,” Journal of Healthcare Informatics Research, 4, 383–394, 2020, doi:10.1007/s41666-020-00077-1.
  32. R. Sapir-Pichhadze, B. Kaplan, “Seeing the Forest for the Trees: Random Forest Models for Predicting Survival in Kidney Transplant Recipients,” Transplantation, 104, 905–906, 2020, doi:10.1097/TP.0000000000002923.
  33. A. Subasi, E. Alickovic, J. Kevric, Diagnosis of Chronic Kidney Disease by Using Random Forest, 589–594, 2017, doi:10.1007/978-981-10-4166-2 89.
  34. M. Z. Alam, M. S. Rahman, M. S. Rahman, “A Random Forest based predictor for medical data classification using feature ranking,” Informatics in Medicine Unlocked, 15, 100180, 2019, doi:10.1016/j.imu.2019.100180.
  35. P. G. Polishchuk, E. N. Muratov, A. G. Artemenko, O. G. Kolumbin, N. N. Muratov, V. E. Kuz’min, “Application of Random Forest Approach to QSAR Prediction of Aquatic Toxicity,” Journal of Chemical Information and Modeling, 49, 2481–2488, 2009, doi:10.1021/ci900203n.
  36. E. Gorrochategui, S. Lacorte, R. Tauler, F. L. Martin, “Perfluoroalkylated Substance Effects in Xenopus laevis A6 Kidney Epithelial Cells Determined by ATR-FTIR Spectroscopy and Chemometric Analysis,” Chemical Research in Toxicology, 29, 924–932, 2016, doi:10.1021/acs.chemrestox.6b00076.
  37. J. Zhao, P. Hinton, J. Chen, J. Jiang, “Causal inference for the effect of environmental chemicals on chronic kidney disease,” Computational and Structural Biotechnology Journal, 18, 93–99, 2020, doi:10.1016/j.csbj.2019.12.001.
  38. R. B. Jain, A. Ducatman, “Associations between the concentrations of α-klotho and selected perfluoroalkyl substances in the presence of eGFR based kidney function and albuminuria: Data for US adults aged 40–79 years,” Science of The Total Environment, 838, 155994, 2022, doi:10.1016/j.scitotenv.2022.155994.
  39. B. M. Brenner, J. L. Troy, T. M. Daugharty, I. F. Ueki, D. P. Nicholas, C. F. Wong, “On the Mechanism of Inhibition in Fluid Reabsorption by the Renal Proximal Tubule of the Volume-Expanded Rat,” Journal of Clinical Investigation, 50, 1596–1602, 1971, doi:10.1172/JCI106647.
  40. R. Quigley, “Androgens stimulate proximal tubule transport,” Gender Medicine, 5, S114–S120, 2008, doi:10.1016/j.genm.2008.03.011.
  41. A. Quan, S. Chakravarty, J.-K. Chen, J.-C. Chen, S. Loleh, N. Saini, R. C. Harris, J. Capdevila, R. Quigley, “Androgens augment proximal tubule transport,” American Journal of Physiology-Renal Physiology, 287, F452–F459, 2004, doi:10.1152/ajprenal.00188.2003.
  42.  A. A. McDonough, “Mechanisms of proximal tubule sodium transport regulation that link extracellular fluid volume and blood pressure,” American Journal of Physiology-Regulatory, Integrative and Comparative Physiology, 298, R851–R861, 2010, doi:10.1152/ajpregu.00002.2010.
  43.  B. Kaissling, I. Hegyi, J. Loffing, M. Hir, “Morphology of interstitial cells in the healthy kidney,” Anatomy and Embryology, 193, 1996, doi:10.1007/BF00186688.
  44. P. Delanaye, R. P. Radermecker, M. Rorive, G. Depas, J. M. Krzesinski, “Indexing glomerular filtration rate for body surface area in obese patients is misleading: concept and example,” Nephrology Dialysis Transplantation, 20, 2024–2028, 2005, doi:10.1093/ndt/gfh983.
  45. J. R. Nyengaard, T. F. Bendtsen, “Glomerular number and size in relation to age, kidney weight, and body surface in normal man,” The Anatomical Record, 232, 194–201, 1992, doi:10.1002/ar.1092320205.
  46. C. C. Geddes, Y. M.Woo, S. Brady, “Glomerular filtration rate what is the rationale and justification of normalizing GFR for body surface area?” Nephrology Dialysis Transplantation, 23, 4–6, 2007, doi:10.1093/ndt/gfm662.
  47. G. Vervoort, B. Veldman, J. H. M. Berden, P. Smits, J. F. M.Wetzels, “Glomerular hyperfiltration in type 1 diabetes mellitus results from primary changes in proximal tubular sodium handling without changes in volume expansion,” European Journal of Clinical Investigation, 35, 330–336, 2005, doi:10.1111/j.1365- 2362.2005.01497.x.
  48. W.-A. S. Mula-Abed, K. A. Rasadi, D. A. Riyami, “Estimated Glomerular Filtration Rate (eGFR): A Serum Creatinine-Based Test for the Detection of Chronic Kidney Disease and its Impact on Clinical Practice,” Oman Medical Journal, 27, 108–113, 2012, doi:10.5001/omj.2012.23.
  49. S. Rayego-Mateos, R. Rodrigues-Diez, J. L. Morgado-Pascual, F. Valentijn, J. M. Valdivielso, R. Goldschmeding, M. Ruiz-Ortega, “Role of Epidermal Growth Factor Receptor (EGFR) and Its Ligands in Kidney Inflammation and Damage,” Mediators of Inflammation, 2018, 8739473, 2018, doi:10.1155/2018/8739473.
  50. J. Tang, N. Liu, E. Tolbert, M. Ponnusamy, L. Ma, R. Gong, G. Bayliss, H. Yan, S. Zhuang, “Sustained Activation of EGFR Triggers Renal Fibrogenesis after Acute Kidney Injury,” The American Journal of Pathology, 183, 160–172, 2013, doi:https://doi.org/10.1016/j.ajpath.2013.04.005.
  51.  C. A. O’Callaghan, B. Shine, D. S. Lasserson, “Chronic kidney disease: a large-scale population-based study of the effects of introducing the ¡em¿CKDEPI¡/ em¿ formula for eGFR reporting,” BMJ Open, 1, e000308, 2011, doi:10.1136/bmjopen-2011-000308.
  52. N. Richards, K. Harris, M. Whitfield, D. O’Donoghue, R. Lewis, M. Mansell, S. Thomas, J. Townend, M. Eames, D. Marcelli, “The impact of populationbased identification of chronic kidney disease using estimated glomerular filtration rate (eGFR) reporting,” Nephrology Dialysis Transplantation, 23, 556–561, 2008, doi:10.1093/ndt/gfm839.
  53. J. A. Hirst, M. D. L. A. V. Montes, C. J. Taylor, J. M. Ord´o˜nez-Mena, E. Ogburn, V. Sharma, B. Shine, T. James, F. D. R. Hobbs, “Impact of a single eGFR and eGFR-estimating equation on chronic kidney disease reclassification: a cohort study in primary care,” British Journal of General Practice, 68, e524, 2018, doi:10.3399/bjgp18X697937.

Cited By

Citations by Dimensions

Citations by PlumX

Crossref Citations

This paper is currently not cited.

Metrics

No. of Downloads Per Month

No. of Downloads Per Country