Sign in Subscribe
Cancer research

Early Detection of Esophageal Squamous Cell Carcinoma Improves Survival Rates

Strategic Insights

— 1 min read

Research published in the Journal of Trace Elements In Medicine and Biology has identified potential early diagnostic biomarkers for esophageal squamous cell carcinoma (ESCC) by integrating trace element and oxidative stress profiling with machine learning. The study investigated alterations in trace elements and oxidative stress-related biomarkers in cancerous and adjacent healthy esophageal tissues. The researchers found significant increases in Cu, Fe, and TOS levels and a marked decrease in Se in cancerous tissues. Machine learning models were employed to classify tissue types and identify key diagnostic markers, with the XGBoost model achieving the highest performance (91.7% accuracy, AUC = 0.97).

Key Takeaways:

  • Early detection of esophageal squamous cell carcinoma significantly improves survival rates, yet reliable biochemical biomarkers for early diagnosis remain limited.
  • The study investigated alterations in trace elements and oxidative stress-related biomarkers in cancerous and adjacent healthy esophageal tissues using ICP-MS and spectrophotometric biochemical assays.
  • Statistical analysis revealed significant increases in Cu, Fe, and TOS levels and a marked decrease in Se in cancerous tissues.
  • Strong correlations were observed among specific trace elements and antioxidant enzymes, indicating the potential for using these biomarkers for early diagnosis.
  • Machine learning models, including XGBoost, Random Forest, LightGBM, SVM, and Logistic Regression, were employed to classify tissue types and identify key diagnostic markers.
  • The XGBoost model achieved the highest performance (91.7% accuracy, AUC = 0.97), and SHAP analysis highlighted Se and Zn as the most influential variables.
  • The study concluded that the combined profiling of trace elements and oxidative stress biomarkers, enhanced with machine learning, can offer powerful tools for early ESCC diagnosis.

Statistics:

  • 28 early-stage ESCC patients were included in the study.
  • 12 trace elements were measured via ICP-MS: Al, Cr, Mn, Fe, Co, Cu, Zn, Se, Sb, Hg, and Pb.
  • 11 oxidative stress and antioxidant markers were analyzed: SOD, CAT, GPx, PON, ARE, MPO, MDA, GSH, TAS, TOS, and OSI.
  • The XGBoost model achieved 91.7% accuracy and an AUC of 0.97.

Sources:

  • NewsRx. Ataturk University Reports Findings in Esophageal Cancer (An integrated analytical approach for biomarker discovery in esophageal cancer: Combining trace element and oxidative stress profiling with machine learning). Journal of Engineering. June 16, 2025; p 213.
  • Journal of Trace Elements In Medicine and Biology. An integrated analytical approach for biomarker discovery in esophageal cancer: Combining trace element and oxidative stress profiling with machine learning. 2025;89:127678.

Read more