Related Experiment Video
Updated: May 26, 2026
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
Risk stratification of oral cancer patients using a combined prognostic factor including lymph node density and
1Oral Cancer Research Institute, College of Dentistry, Yonsei University, Seoul 120-752, Republic of Korea. kky1004@yuhs.ac
Purpose:
In this study, we aimed to validate the lymph node density (LND) as an independent prognostic factor of oral squamous cell carcinoma (OSCC) and identify a combined prognostic factor including LND, predicting better performance in risk stratification.
Methods:
We reviewed the clinical, pathological variables and biomarker of 95 OSCC patients who underwent surgery. LND was calculated as the ratio of positive lymph nodes to total lymph nodes removed. Principle component analysis was performed to identify a combined predictor.
Results:
Multivariate analysis showed that variables independently prognostic overall survival were IMP3 (hazard ratio [HR] = 3.01, 95% confidence interval [95% CI] = 1.17-7.75, P = 0.022) in a model without LND and were IMP3 (HR = 3.64, 95% CI = 1.38-9.58, P = 0.008) and LND (HR = 0.57, 95% CI = 0.57-1.75, P = 0.322; HR = 2.45, 95% CI = 1.20-4.97, P = 0.013) in a model with LND. The risk stratification using the combined prognostic factor was more significant (P = 0.00117) than the conventional staging system and biomarker.
Conclusions:
The LND was shown to be an independent prognostic factor in OSCC, and a combined factor including LND may be used for risk stratification of OSCC patients, which displayed the best performance.