Real-World Application of a Machine Learning-Based Early Recurrence Model for Guiding Adjuvant Chemotherapy Use in
Won-Gun Yun1,2, Youngmin Han1, Yoon Soo Chae1
1Department of Surgery and Cancer Research Institute, Seoul National University College of Medicine, Seoul, Korea.
Gut and Liver
|June 22, 2026
Summary
Machine learning accurately predicts recurrence risk in gallbladder cancer patients. This helps avoid unnecessary adjuvant chemotherapy in low-risk individuals, improving treatment efficiency and reducing costs.
Area of Science:
- Oncology
- Surgical Oncology
- Machine Learning in Medicine
Background:
- Adjuvant chemotherapy efficacy for resected biliary tract cancer is debated in real-world practice.
- Gallbladder cancer (GBC) management requires refined strategies beyond standard recommendations.
Purpose of the Study:
- To evaluate adjuvant chemotherapy effectiveness in resected gallbladder cancer patients.
- To employ machine learning for predicting recurrence risk and optimizing chemotherapy use.
Main Methods:
- Retrospective analysis of 395 patients with Stage 2+ gallbladder cancer (2005-2022).
- Risk stratification using a machine learning algorithm to predict early recurrence.
- Comparison of adjuvant chemotherapy versus surveillance in different risk groups.
Main Results:
- 204 patients (51.6%) had low recurrence risk, 191 (48.4%) had high risk.
- No significant survival difference between chemotherapy and surveillance in low-risk patients (5-year OS: 87.2% vs 83.3%).
- Adjuvant chemotherapy significantly improved 5-year overall survival in high-risk patients (52.1% vs 37.8%).
Conclusions:
- Machine learning-based risk prediction aids in selecting gallbladder cancer patients for adjuvant chemotherapy.
- This approach can minimize unnecessary chemotherapy in low-risk patients, potentially reducing healthcare costs.
