EUVIMEDEUVIMED entdecken
Crossref

Integration of AHRR methylation, heavy metals, and clinical characteristics for urothelial carcinoma risk stratification: An explainable artificial intelligence approach

Chia-Min Chung, Chao-Hsiang Chang, Chin-Huai Chang, Wen-Chi Chang, Yi-Huei Chang, Po-Jen Hsiao, Chi-Shun Lien, Han Chang, Mu-Chi Chung, Chi-Jung Chung

Environmental Pollution · 2026-06 · 399 · 128196

DOI: 10.1016/j.envpol.2026.128196 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Pollution, 2026-06. Verfasst von Chia-Min Chung und 9 weiteren Autor:innen. Beteiligte Einrichtung: Graduate Institute of Biomedical Sciences, China Medical University, Taichung, Taiwan; Department of Psychiatry and Center for Addiction and Mental H…. Hauptthemen laut MEDLINE: Metals, Heavy, Artificial Intelligence, Repressor Proteins, Basic Helix-Loop-Helix Proteins. Die Arbeit nennt 47 Literaturangaben. Gefördert von: China Medical University, Ministry of Science and Technology of the People's Republic of China, National Science Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The short metabolic half-life of conventional tobacco biomarkers often limits their ability to reflect cumulative toxicological damage, which may complicate risk stratification for urothelial carcinoma (UC). This study explored an explainable artificial intelligence (XAI) framework to integrate epigenetic, environmental, and clinical factors for more refined UC risk assessment. We conducted a medical center-based case-control study of 351 UC cases and 373 controls. Data on demographics, comorbidities, and biomarkers including AHRR (cg05575921) DNA methylation, urinary cotinine, 8-OHdG, and urinary heavy metals were collected and analyzed. We used LASSO regression to manage multicollinearity of metals. Eight ML models, including XGBoost, were trained and evaluated using 5-fold cross-validation. SHAP (SHapley Additive exPlanations) and mediation analyses were employed to interpret feature importance and biological pathways. Logistic regression confirmed associations between UC risk and urinary cotinine, several metals (Cr, Co, Ni, Pb), and lower AHRR methylation (all p < 0.05). Eight supervised learning algorithms were compared, with XGBoost providing the highest discriminative performance (AUC = 0.752). SHAP analysis identified chronic kidney disease and age as primary determinants, while AHRR methylation and selected metals (Ni, Cr) contributed significant independent discriminative value. Mediation analysis suggested that AHRR methylation mediated 43.74% of the effect of long-term smoking history, whereas the influence of urinary cotinine on risk was primarily mediated through increased urinary 8-OHdG. Decision tree analysis further identified a high-risk subgroup of former smokers with persistent AHRR hypomethylation despite low cotinine levels. In conclusion, by combining clinical factors with epigenetic and environmental biomarkers, our explainable machine learning framework offers robust UC risk stratification. AHRR methylation, selected metals, and CKD status provide critical information beyond standard risk factors, supporting more effective targeted surveillance for high-risk individuals.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Metals, HeavyArtificial IntelligenceRepressor ProteinsBasic Helix-Loop-Helix ProteinsUrologic NeoplasmsHumansDNA MethylationCase-Control StudiesRisk AssessmentMaleFemaleCotinineMiddle Aged

Stichwörter der Autor:innen

AHRRDNA methylationDecision treeHeavy metalsLasso regressionLeadNickelSmokingUrothelial carcinoma

Substanzen

Metals, HeavyRepressor ProteinsBasic Helix-Loop-Helix ProteinsAHRR protein, humanCotinine

Autor:innen und Institutionen

  • Graduate Institute of Biomedical Sciences, China Medical University, Taichung, Taiwan; Department of Psychiatry and Center for Addiction and Mental Health, China Medical University Hospital, Taichung, Taiwan.
  • Department of Urology, China Medical University and Hospital, Taichung, Taiwan.
  • Department of Public Health, College of Public Health, China Medical University, Taichung, Taiwan.
  • Department of Pathology, College of Medicine, China Medical University Hospital, Taichung, Taiwan.
  • Division of Nephrology, Department of Medicine, Taichung Veterans General Hospital, Taichung, Taiwan; Division of Clinical Toxicology, Department of Medical Toxicology, Taichung Veterans General Hospital, Taichung, Taiw…
  • Department of Public Health, College of Public Health, China Medical University, Taichung, Taiwan; Department of Medical Research, China Medical University Hospital, Taichung, Taiwan. Electronic address: cjchung@mail.cm…

Förderung

  • China Medical University
  • Ministry of Science and Technology of the People&apos;s Republic of China
  • National Science Council
  • National Science and Technology Council

Zitieren

APA

Chung, C. M., Chang, C. H., Chang, C. H., Chang, W. C., Chang, Y. H., Hsiao, P. J., Lien, C. S., Chang, H., Chung, M. C., & Chung, C. J. (2026). Integration of AHRR methylation, heavy metals, and clinical characteristics for urothelial carcinoma risk stratification: An explainable artificial intelligence approach. Environmental Pollution, 399, 128196. https://doi.org/10.1016/j.envpol.2026.128196

Vancouver

Chung CM, Chang CH, Chang CH, Chang WC, Chang YH, Hsiao PJ, et al. Integration of AHRR methylation, heavy metals, and clinical characteristics for urothelial carcinoma risk stratification: An explainable artificial intelligence approach. Environmental Pollution. 2026;399:128196. doi:10.1016/j.envpol.2026.128196

BibTeX
@article{Chung2026,
  author = {Chung, Chia-Min and Chang, Chao-Hsiang and Chang, Chin-Huai and Chang, Wen-Chi and Chang, Yi-Huei and Hsiao, Po-Jen and Lien, Chi-Shun and Chang, Han and Chung, Mu-Chi and Chung, Chi-Jung},
  title = {Integration of AHRR methylation, heavy metals, and clinical characteristics for urothelial carcinoma risk stratification: An explainable artificial intelligence approach},
  journal = {Environmental Pollution},
  year = {2026},
  volume = {399},
  pages = {128196},
  doi = {10.1016/j.envpol.2026.128196}
}
Kostenlos starten →