Sign in Subscribe
Cancer

Personalized Medicine Breakthrough: Predicting Neoadjuvant Chemotherapy Response in Locally Advanced Gastric Cancer

Strategic Insights

— 1 min read

Researchers from Guangxi, People's Republic of China, have made a significant discovery in the field of personalized medicine. By integrating radiomic features with clinical biomarkers through machine learning approaches, they were able to develop a hybrid model that predicts neoadjuvant chemotherapy response in patients with locally advanced gastric cancer (LAGC) undergoing surgical resection. This breakthrough has the potential to provide personalized treatment insights for patients with LAGC, improving clinical outcomes and enhancing resection rates.

Key Takeaways:

  • The study analyzed a cohort of 255 patients with LAGC who underwent neoadjuvant chemotherapy (NAC) prior to surgical resection at the Affiliated Cancer Hospital of Guangxi Medical University.
  • Among the patients, 57 (22.4%) were classified as responders (TRG 0-1), and 198 (77.6%) were identified as non-responders (TRG 2-3).
  • The researchers extracted 1130 radiomic features via the OnekeyAI platform software from pre-treatment portal venous-phase computed tomography scans.
  • The hybrid model developed by the researchers, using a random forest model combining radiomics and clinical biomarkers, outperformed the radiomics and clinical models, achieving an area under the curve (AUC) of 0.814.
  • The study concluded that the developed RF-based hybrid model provides personalized treatment insights for patients with LAGC undergoing surgical resection.

Statistics:

  • 255 patients with locally advanced gastric cancer were analyzed in the study.
  • 57 (22.4%) patients were classified as responders (TRG 0-1).
  • 198 (77.6%) patients were identified as non-responders (TRG 2-3).
  • The radiomics score was generated linearly combining 1130 radiomic features.
  • The AUC achieved by the hybrid model was 0.814.
  • The AUC achieved by the radiomics model was 0.755.
  • The AUC achieved by the clinical model was 0.682.

Sources:

  • Predicting neoadjuvant chemotherapy response in locally advanced gastric cancer using a machine learning model combining radiomics and clinical biomarkers. Digital Health, 2025, 11. (Digital Health - http://dhj.sagepub.com/)
  • Citation for this news report: NewsRx. New Personalized Medicine Study Findings Reported from Guangxi (Predicting neoadjuvant chemotherapy response in locally advanced gastric cancer using a machine learning model combining radiomics and clinical biomarkers). Cancer Weekly. May 27, 2025; p 535.

Read more