A Korean research team has developed an AI-based technology capable of predicting prognosis in patients with gallbladder cancer.
As predicting patient-specific outcomes is considered the first step toward personalized treatment, the development is expected to help improve survival rates.
Samsung Medical Center (SMC) said Wednesday that its research team had demonstrated that AI-based spatial analysis technology can analyze the tumor microenvironment of gallbladder cancer patients and predict cancer recurrence and survival outcomes.
From left, Professors Park Joo-kyung, Kim Hong-beom, Lee Kyu-taek and Choi Young-hoon, and Dr. Kim Hye-min (Courtesy of SMC)
The research was led by Professors Park Joo-kyung, Lee Kyu-taek and Choi Young-hoon of the Department of Gastroenterology, Professor Kim Hong-beom of the Department of Hepatobiliary and Pancreatic Surgery, and Dr. Kim Hye-min of the Refractory Cancer Early Diagnosis Team at the Institute for Future Medicine.
According to the study, the prognostic model for gallbladder cancer was developed using data from 225 patients who underwent surgery for gallbladder cancer, along with an external validation cohort of 41 patients. The AI model quantified and incorporated key indicators of the tumor microenvironment, including tumor-infiltrating lymphocyte (TIL) density, the number of tertiary lymphoid structures (TLSs), and fibroblast density surrounding cancer cells.
The research team identified three major prognostic determinants in the model: low TIL density, low TLS count and high fibroblast density. The presence of additional risk factors was associated with a sharp decline in both overall survival (OS) and disease-free survival (DFS).
Compared with patients with all three risk factors, those with none showed an 87 percent lower risk of recurrence and an 80 percent lower risk of death. The researchers added that as the number of risk factors increased, the gap in recurrence and mortality risk compared with the highest-risk group gradually narrowed.
Professor Kim Hong-beom said, “Gallbladder cancer is particularly difficult to predict in terms of prognosis among biliary tract cancers and is known for its poor outcomes. This study opens the door to more precise prognostic analysis of gallbladder cancer using AI technology.”
Professor Park Joo-kyung added, “This study confirmed the potential of AI as a ‘digital biomarker’ capable of deeply analyzing the biological characteristics of cancer to predict patient prognosis. We expect it will greatly help guide personalized treatment for individual patients after gallbladder cancer surgery.”
Kim Kyoung-Won
댓글
0