Hueman Matthew, Wang Huan, Liu Zhenqiu, Henson Donald, Nguyen Cuong, Park Dean, Sheng Li, Chen Dechang
Department of Surgical Oncology, John P. Murtha Cancer Center, Walter Reed National Military Medical Center, Bethesda, Maryland, USA.
Department of Biostatistics, George Washington University, Washington, District of Columbia, USA.
Thorac Cancer. 2021 May;12(9):1423-1430. doi: 10.1111/1759-7714.13926. Epub 2021 Mar 13.
Expanding the tumor, lymph node, metastasis (TNM) staging system by accommodating new prognostic and predictive factors for cancer will improve patient stratification and survival prediction. Here, we introduce machine learning for incorporating additional prognostic factors into the conventional TNM for stratifying patients with lung cancer and evaluating survival.
Data were extracted from SEER. A total of 77 953 patients were analyzed using factors including primary tumor (T), regional lymph node (N), distant metastasis (M), age, and histology type. Ensemble algorithm for clustering cancer data (EACCD) and C-index were applied to generate prognostic groups and expand the current staging system.
With T, N, and M, EACCD stratified patients into 11 groups, resulting in a significantly higher accuracy in survival prediction than the 10 AJCC stages (C-index = 0.7346 vs. 0.7247, increase in C-index = 0.0099, 95% CI: 0.0091-0.0106, p-value = 9.2 × 10 ). There nevertheless remained a strong association between the EACCD grouping and AJCC staging (rank correlation = 0.9289; p-value = 6.7 × 10 ). A further analysis demonstrated that age and histological tumor could be integrated with the TNM. Data were stratified into 12 prognostic groups with an even higher prediction accuracy (C-index = 0.7468 vs. 0.7247, increase in C-index = 0.0221, 95% CI: 0.0212-0.0231, p-value <5 × 10 ).
EACCD can be successfully applied to integrate additional factors with T, N, M for lung cancer patients.
通过纳入新的癌症预后和预测因素来扩展肿瘤、淋巴结、转移（TNM）分期系统，将改善患者分层和生存预测。在此，我们引入机器学习，将额外的预后因素纳入传统TNM，以对肺癌患者进行分层并评估生存情况。
数据从监测、流行病学和最终结果（SEER）数据库中提取。共77953例患者使用包括原发肿瘤（T）、区域淋巴结（N）、远处转移（M）、年龄和组织学类型等因素进行分析。应用癌症数据聚类集成算法（EACCD）和C指数来生成预后组并扩展当前分期系统。
结合T、N和M，EACCD将患者分为11组，在生存预测方面的准确性显著高于10个美国癌症联合委员会（AJCC）分期（C指数=0.7346对0.7247，C指数增加=0.0099，95%置信区间：0.0091-0.0106，p值=9.2×10 ）。然而，EACCD分组与AJCC分期之间仍存在强关联（等级相关性=0.9289；p值=6.7×10 ）。进一步分析表明，年龄和组织学肿瘤类型可与TNM相结合。数据被分为12个预后组，预测准确性更高（C指数=0.7468对0.7247，C指数增加=0.0221，95%置信区间：0.0212-0.0231，p值<5×10 ）。
EACCD可成功应用于将额外因素与肺癌患者的T、N、M相结合。
