{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T14:25:11Z","timestamp":1779891911833,"version":"3.53.1"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T00:00:00Z","timestamp":1748908800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Rheumatoid arthritis is a chronic autoimmune disease influenced by environmental exposures, including per- and polyfluoroalkyl substances (PFAS). Although previous studies have suggested links between PFAS and rheumatoid arthritis risk, none have used interpretable machine learning models for prediction. This study aimed to develop such a model to assess risk based on PFAS exposure.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We analyzed data from 11,705 participants in the National Health and Nutrition Examination Survey (2003\u20132018). Twelve machine learning algorithms were evaluated using metrics including area under the curve (AUC), accuracy, sensitivity, specificity, and F<jats:sub>1<\/jats:sub> score. Key predictors were identified using SHapley Additive exPlanations (SHAP). Partial dependence plots and locally weighted scatterplot smoothing (LOWESS) curves were used to examine non-linear associations and exposure thresholds. A web-based risk calculator was developed to enhance clinical and public health applicability.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>CatBoost showed the best performance (AUC: 0.82; Accuracy: 74%; F<jats:sub>1<\/jats:sub> score: 0.62) and was selected for further interpretation. SHAP analysis identified perfluorooctane sulfonic acid (PFOS) and 2-(N-Methyl-perfluorooctane sulfonamido) acetic acid (MPAH) as major contributors to risk prediction. PFOS exhibited a U-shaped relationship with increased risk above 15.10 ng\/ml, while MPAH showed a risk transition at 0.22 ng\/ml. Waterfall plots illustrated the contribution of individual exposures. The interactive web-based calculator allows users to input PFAS levels and receive personalized rheumatoid arthritis risk estimates. It is freely available on Hugging Face Spaces (<jats:ext-link>https:\/\/huggingface.co\/spaces\/Machine199710\/RA_ML<\/jats:ext-link>).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>This study demonstrates the potential of machine learning to predict rheumatoid arthritis risk based on PFAS exposure. The identified non-linear patterns provide insights into environmental contributions to disease risk and may inform future prevention strategies.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fpubh.2025.1581717","type":"journal-article","created":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T05:21:54Z","timestamp":1748928114000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Exploring the relationship between per- and polyfluoroalkyl substances exposure and rheumatoid arthritis risk using interpretable machine learning"],"prefix":"10.3389","volume":"13","author":[{"given":"Zhi","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinping","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1038\/s41584-022-00827-y","article-title":"Global epidemiology of rheumatoid arthritis","volume":"18","author":"Finckh","year":"2022","journal-title":"Nat Rev Rheumatol."},{"key":"B2","doi-asserted-by":"publisher","first-page":"1316","DOI":"10.1136\/annrheumdis-2013-204627","article-title":"The global burden of rheumatoid arthritis: estimates from the Global Burden of Disease 2010 study","volume":"73","author":"Cross","year":"2014","journal-title":"Ann Rheum Dis."},{"key":"B3","doi-asserted-by":"publisher","first-page":"1463","DOI":"10.1136\/annrheumdis-2019-215920","article-title":"Global, regional and national burden of rheumatoid arthritis 1990-2017: a systematic analysis of the Global Burden of Disease study 2017","volume":"78","author":"Safiri","year":"2019","journal-title":"Ann Rheum Dis."},{"key":"B4","doi-asserted-by":"publisher","first-page":"1126647","DOI":"10.3389\/fimmu.2023.1126647","article-title":"Identification of immune-related genes in diagnosing atherosclerosis with rheumatoid arthritis through bioinformatics analysis and machine learning","volume":"14","author":"Liu","year":"2023","journal-title":"Front Immunol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"2259","DOI":"10.2174\/1386207326666230306114626","article-title":"Application of machine learning in rheumatoid arthritis diseases research: review and future directions","volume":"26","author":"Patil Kose","year":"2023","journal-title":"Comb Chem High Throughput Screen."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1204652","DOI":"10.3389\/fimmu.2023.1204652","article-title":"Platelets-related signature based diagnostic model in rheumatoid arthritis using WGCNA and machine learning","volume":"14","author":"Liu","year":"2023","journal-title":"Front Immunol."},{"key":"B7","doi-asserted-by":"publisher","first-page":"e35511","DOI":"10.1016\/j.heliyon.2024.e35511","article-title":"Identification of diagnostic biomarkers of rheumatoid arthritis based on machine learning-assisted comprehensive bioinformatics and its correlation with immune cells","volume":"10","author":"Mu","year":"2024","journal-title":"Heliyon."},{"key":"B8","doi-asserted-by":"publisher","first-page":"101741","DOI":"10.1016\/j.berh.2021.101741","article-title":"Prediction of treatment response: Personalized medicine in the management of rheumatoid arthritis","volume":"36","author":"Wei","year":"2022","journal-title":"Best Pract Res Clin Rheumatol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1002\/etc.4890","article-title":"Per- and polyfluoroalkyl substance toxicity and human health review: current state of knowledge and strategies for informing future research","volume":"40","author":"Fenton","year":"2021","journal-title":"Environ Toxicol Chem."},{"key":"B10","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1038\/s41370-018-0094-1","article-title":"A review of the pathways of human exposure to poly- and perfluoroalkyl substances (PFASs) and present understanding of health effects","volume":"29","author":"Sunderland","year":"2019","journal-title":"J Expo Sci Environ Epidemiol."},{"key":"B11","doi-asserted-by":"publisher","first-page":"116929","DOI":"10.1016\/j.envpol.2021.116929","article-title":"Epigenetic changes by per- and polyfluoroalkyl substances (PFAS)","volume":"279","author":"Kim","year":"2021","journal-title":"Environ Pollut."},{"key":"B12","doi-asserted-by":"publisher","first-page":"113431","DOI":"10.1016\/j.envres.2022.113431","article-title":"Health-related toxicity of emerging per- and polyfluoroalkyl substances: comparison to legacy PFOS and PFOA","volume":"212","author":"Jane","year":"2022","journal-title":"Environ Res"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1136","DOI":"10.1161\/CIRCRESAHA.124.323697","article-title":"Perfluoroalkyl\/polyfluoroalkyl substances: links to cardiovascular disease risk","volume":"134","author":"Schlezinger","year":"2024","journal-title":"Circ Res."},{"key":"B14","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1186\/s12940-024-01073-3","article-title":"Associations of per- and polyfluoroalkyl substances (PFAS) and their mixture with risk of rheumatoid arthritis in the US adult population","volume":"23","author":"Qiao","year":"2024","journal-title":"Environ Health."},{"key":"B15","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1139\/gen-2020-0131","article-title":"Machine learning for precision medicine","volume":"64","author":"MacEachern","year":"2021","journal-title":"Genome."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1422617","DOI":"10.3389\/fnut.2024.1422617","article-title":"Analyzing the impact of heavy metal exposure on osteoarthritis and rheumatoid arthritis: an approach based on interpretable machine learning","volume":"11","author":"Fan","year":"2024","journal-title":"Front Nutr."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1581","DOI":"10.1016\/j.cell.2018.05.015","article-title":"Next-generation machine learning for biological networks","volume":"173","author":"Camacho","year":"2018","journal-title":"Cell."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1409555","DOI":"10.3389\/fimmu.2024.1409555","article-title":"Advancing precision rheumatology: applications of machine learning for rheumatoid arthritis management","volume":"15","author":"Shi","year":"2024","journal-title":"Front Immunol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1038\/s41746-020-0229-3","article-title":"A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases","volume":"3","author":"Stafford","year":"2020","journal-title":"NPJ Digit Med."},{"key":"B20","doi-asserted-by":"publisher","first-page":"1280312","DOI":"10.3389\/fmed.2023.1280312","article-title":"Artificial intelligence in rheumatoid arthritis: potential applications and future implications","volume":"10","author":"Gilvaz","year":"2023","journal-title":"Front Med."},{"key":"B21","doi-asserted-by":"publisher","first-page":"3890","DOI":"10.3390\/jcm13133890","article-title":"Machine learning prediction of treatment response to biological disease-modifying antirheumatic drugs in rheumatoid arthritis","volume":"13","author":"Salehi","year":"2024","journal-title":"J Clin Med"},{"key":"B22","doi-asserted-by":"publisher","first-page":"2135","DOI":"10.1002\/alz.12948","article-title":"Interpretable machine learning for dementia: a systematic review","volume":"19","author":"Martin","year":"2023","journal-title":"Alzheimers Dement."},{"key":"B23","doi-asserted-by":"publisher","first-page":"17690","DOI":"10.1021\/acs.est.3c00653","article-title":"Advancing computational toxicology by interpretable machine learning","volume":"57","author":"Jia","year":"2023","journal-title":"Environ Sci Technol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1016\/j.tig.2020.03.005","article-title":"Opening the black box: interpretable machine learning for geneticists","volume":"36","author":"Azodi","year":"2020","journal-title":"Trends Genet."},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295230","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017","journal-title":"31st Conference on Neural Information Processing Systems"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e001125","DOI":"10.1136\/lupus-2023-001125","article-title":"Novel multiclass classification machine learning approach for the early-stage classification of systemic autoimmune rheumatic diseases","volume":"11","author":"Wang","year":"2024","journal-title":"Lupus Sci Med"},{"key":"B27","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1186\/s13075-021-02567-y","article-title":"Machine learning model for identifying important clinical features for predicting remission in patients with rheumatoid arthritis treated with biologics","volume":"23","author":"Koo","year":"2021","journal-title":"Arthritis Res Ther."},{"key":"B28","doi-asserted-by":"publisher","first-page":"119221","DOI":"10.1016\/j.envres.2024.119221","article-title":"Immune cell profiles associated with human exposure to perfluorinated compounds (PFAS) suggest changes in natural killer, T helper, and T cytotoxic cell subpopulations","volume":"256","author":"Tursi","year":"2024","journal-title":"Environ Res."},{"key":"B29","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1186\/s12940-022-00958-5","article-title":"Consideration of pathways for immunotoxicity of per- and polyfluoroalkyl substances (PFAS)","volume":"22","author":"Ehrlich","year":"2023","journal-title":"Environ Health."},{"key":"B30","doi-asserted-by":"publisher","first-page":"116136","DOI":"10.1016\/j.taap.2022.116136","article-title":"In vitro activity of a panel of per- and polyfluoroalkyl substances (PFAS), fatty acids, and pharmaceuticals in peroxisome proliferator-activated receptor (PPAR) alpha, PPAR gamma, and estrogen receptor assays","volume":"449","author":"Evans","year":"2022","journal-title":"Toxicol Appl Pharmacol."},{"key":"B31","doi-asserted-by":"publisher","first-page":"bqab194","DOI":"10.1210\/endocr\/bqab194","article-title":"PFAS and potential adverse effects on bone and adipose tissue through interactions with PPAR\u03b3","volume":"162","author":"Kirk","year":"2021","journal-title":"Endocrinology"},{"key":"B32","doi-asserted-by":"publisher","first-page":"7423","DOI":"10.1021\/acs.jcim.3c01384","article-title":"Binding of per- and polyfluoroalkyl substances (PFAS) to the PPAR\u03b3\/RXR\u03b1-DNA complex","volume":"63","author":"Almeida","year":"2023","journal-title":"J Chem Inf Model."},{"key":"B33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10753-022-01721-1","article-title":"Neuroinflammation in Alzheimer's disease: current progress in molecular signaling and therapeutics","volume":"46","author":"Thakur","year":"2023","journal-title":"Inflammation."},{"key":"B34","doi-asserted-by":"publisher","first-page":"176786","DOI":"10.1016\/j.scitotenv.2024.176786","article-title":"Environmentally relevant level of PFDA exacerbates intestinal inflammation by activating the cGAS\/STING\/NF-\u03baB signaling pathway","volume":"954","author":"Cui","year":"2024","journal-title":"Sci Total Environ."},{"key":"B35","doi-asserted-by":"publisher","first-page":"538","DOI":"10.4049\/immunohorizons.2300049","article-title":"Effects of perfluorohexane sulfonate exposure on immune cell populations in naive mice","volume":"8","author":"Pierpont","year":"2024","journal-title":"Immunohorizons."},{"key":"B36","doi-asserted-by":"publisher","first-page":"2371868","DOI":"10.1080\/1547691X.2024.2371868","article-title":"Systemic and immunotoxicity induced by topical application of perfluoroheptane sulfonic acid (PFHpS) or perfluorooctane sulfonic acid (PFOS) in a murine model","volume":"21","author":"Weatherly","year":"2024","journal-title":"J Immunotoxicol."},{"key":"B37","doi-asserted-by":"publisher","first-page":"8539","DOI":"10.3390\/ijms24108539","article-title":"Perfluoroalkyl Substances (PFAS) affect inflammation in lung cells and tissues","volume":"24","author":"Dragon","year":"2023","journal-title":"Int J Mol Sci"},{"key":"B38","doi-asserted-by":"publisher","first-page":"108138","DOI":"10.1016\/j.envint.2023.108138","article-title":"PPAR\u03b1\/ACOX1 as a novel target for hepatic lipid metabolism disorders induced by per- and polyfluoroalkyl substances: an integrated approach","volume":"178","author":"Yang","year":"2023","journal-title":"Environ Int."},{"key":"B39","doi-asserted-by":"publisher","first-page":"118485","DOI":"10.1016\/j.envres.2024.118485","article-title":"Reproductive toxicity of PFOA, PFOS and their substitutes: a review based on epidemiological and toxicological evidence","volume":"250","author":"Shi","year":"2024","journal-title":"Environ Res."}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1581717\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T05:21:56Z","timestamp":1748928116000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1581717\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,3]]},"references-count":39,"alternative-id":["10.3389\/fpubh.2025.1581717"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2025.1581717","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,3]]},"article-number":"1581717"}}