Department of Radiotherapy, Policlinico Umberto I "Sapienza" University of Rome, Rome, Italy;
Department of Oral and Maxillo Facial Sciences, Policlinico Umberto I, "Sapienza" University of Rome, Rome, Italy.
In Vivo. 2021 Nov-Dec;35(6):3355-3360. doi: 10.21873/invivo.12633.
BACKGROUND/AIM: To investigate survival outcomes and recurrence patterns using machine learning in patients with salivary gland malignant tumor (SGMT) undergoing adjuvant chemoradiotherapy (CRT).
Consecutive SGMT patients were identified, and a data set included nine predictor variables and a dependent variable [disease-free survival (DFS) event] was standardized. The open-source R software was used. Survival outcomes were estimated by the Kaplan-Meier method. The random forest approach was used to select the important explanatory variables. A classification tree that optimally partitioned SGMT patients with different DFS rates was built.
In total, 54 SGMT patients were included in the final analysis. Five-year DFS was 62.1%. The top two important variables identified were pathologic node (pN) and pathologic tumor (pT). Based on these explanatory variables, patients were partitioned in three groups, including pN0, pT1-2 pN+ and pT3-4 pN+ with 26%, 38% and 75% probability of recurrence, respectively. Accordingly, 5-year DFS rates were 73.7%, 57.1% and 34.3%, respectively.
The proposed decision tree algorithm is an appropriate tool to partition SGMT patients. It can guide decision-making and future research in the SGMT field.
背景/目的：利用机器学习研究接受辅助放化疗（CRT）的涎腺癌（SGMT）患者的生存结果和复发模式。
连续纳入 SGMT 患者，建立一个包含九个预测变量和一个因变量（无病生存（DFS）事件）的数据集并进行标准化。使用开源 R 软件。采用 Kaplan-Meier 法估计生存结果。采用随机森林法选择重要的解释变量。构建一个分类树，以最优方式划分具有不同 DFS 率的 SGMT 患者。
共纳入 54 例 SGMT 患者进行最终分析。5 年 DFS 率为 62.1%。确定的前两个重要变量是病理淋巴结（pN）和病理肿瘤（pT）。基于这些解释变量，患者被分为三组，包括 pN0、pT1-2 pN+和 pT3-4 pN+，复发概率分别为 26%、38%和 75%。相应地，5 年 DFS 率分别为 73.7%、57.1%和 34.3%。
提出的决策树算法是一种划分 SGMT 患者的合适工具。它可以为 SGMT 领域的决策和未来研究提供指导。
