Machine Learning-assisted Diagnosis of Gastric Cancer using Extracellular Vesicles

Strategic Insights -

Researchers from Nanjing University have reported a breakthrough in diagnosing gastric cancer using machine learning algorithms and extracellular vesicles. The study, which was funded by the National Natural Science Foundation of China and other organizations, utilized a novel washing-free detection method based on aptasensor and exonuclease I to profile EVs surface proteins. The team successfully developed an accurate diagnosis model of gastric cancer by analyzing five types of EVs surface proteins using machine learning in a retrospective study design.

Key Takeaways:

  • Researchers from Nanjing University developed a machine learning-assisted diagnosis model for gastric cancer using extracellular vesicles (EVs) as biomarkers.
  • The study utilized a washing-free detection method based on aptasensor and exonuclease I to profile EVs surface proteins.
  • The team analyzed five types of EVs surface proteins using machine learning in a retrospective study design, achieving a diagnostic accuracy of 0.8421 using the XGBoost algorithm.
  • The XGBoost-based surface protein analysis could precisely identify gastric cancer patients with an area under the curve value of 0.9347 (95% CI = 0.8590 to 1.000).
  • The study potential future application of the method for diagnosing other diseases by expanding the diagnostic scope to include different protein markers.
  • The research has been peer-reviewed and published in the journal Talanta.

Statistics:

  • Accuracy of the diagnosis model: 0.8421
  • Area under the curve value: 0.9347 (95% CI = 0.8590 to 1.000)
  • Number of EVs surface proteins analyzed: 5
  • Number of machine learning algorithms compared: 5
  • Funding sources: National Natural Science Foundation of China (NSFC), Key Research and Development Project of Jiangsu Province, Natural Science Foundation of Jiangsu Province, Nanjing Important Science & Technology Specific Projects, and others.

Sources:

  • NewsRx. Researchers from Nanjing University Provide Details of New Studies and Findings in the Area of Gastric Cancer (Machine Learning-assisted Washing-free Detection of Extracellular Vesicles By Target Recycling Amplification Based Fluorescent ...). Health & Medicine Week. May 23, 2025; p 4603.
  • Talanta. Machine Learning-assisted Washing-free Detection of Extracellular Vesicles By Target Recycling Amplification Based Fluorescent Aptasensor for Accurate Diagnosis of Gastric Cancer. 2025;287.