本期胸小星将为大家带来机器学习预测T1期食管鳞癌淋巴结转移:一项多中心研究;局部晚期食管鳞癌新辅助免疫化疗的围手术期结局和生存,一起来看看吧!
2017·EATTS
01
Machine learning to predict lymph node metastasis in T1 esophageal squamous cell carcinoma:a multicenter study
Xu Huang1, Qingle Wang2, Wenyi Xu1, Fangyi Liu3, Liangwei Pan1, Heng Jiao1, Jun Yin1, Hongbo Xu4, Han Tang1, Lijie Tan1
1 Department of Thoracic Surgery, Zhongshan Hospital, Fudan University, Shanghai, China.
2 Departments of Radiology, Zhongshan Hospital, Fudan University, Shanghai, China.
3 The School of Basic Medical Sciences, Fudan University, Shanghai, China.
4 Department of Cardiothoracic Surgery, Lu'an Affiliated Hospital of Anhui Medical University, Lu'an, China.
Background:
Existing models do poorly when it comes to quantifying the risk of Lymph node metastases (LNM). This study aimed to develop a machine learning model for LNM in patients with T1 esophageal squamous cell carcinoma (ESCC).
Methods and results:
The study is multicenter, and population based. Elastic net regression (ELR), random forest (RF), extreme gradient boosting (XGB), and a combined (ensemble) model of these was generated. The contribution to the model of each factor was calculated. The models all exhibited potent discriminating power. The Elastic net regression performed best with externally validated AUC of 0.803, whereas the NCCN guidelines identified patients with LNM with an AUC of 0.576 and logistic model with an AUC of 0. 670. The most important features were lymphatic and vascular invasion and depth of tumor invasion.
Conclusions:
Models created utilizing machine learning approaches had excellent performance estimating the likelihood of LNM in T1 ESCC.
[CITATION]: Huang X, Wang Q, Xu W, et al. Machine learning to predict lymph node metastasis in T1 esophageal squamous cell carcinoma:a multicenter study. Int J Surg. 2024 Jun 21.
[DOI]: 10.1097/JS9.0000000000001694.
[IF]: 12.5
向下滑动查看所有内容
机器学习预测T1期食管鳞癌淋巴结转移:一项多中心研究
胸“星”外科学术团队兴趣小队成员 杨尚坤 译
背景
现有的模型在量化淋巴结转移(lymph node metastasis, LNM)风险方面表现不佳。本研究旨在开发一种预测T1期食管鳞癌(esophageal squamous cell carcinoma, ESCC)患者LNM的机器学习模型。
方法
本研究是一项以人群为基础的多中心研究,生成了弹性网络回归(elastic net regression, ELR)、随机森林(random forest, RF)、极端梯度提升(extreme gradient boosting , XGB)以及这些模型的组合(集成)模型,计算了每个因素对模型的贡献。
结果
结论
Figure 1. ROC curve of Elastic Net(A), Random Forest(B), XGBoost(C) and Ensemble(D) in the internal-external valid cohort.
Figure 2. the variable importance of Elastic Net(A), Random Forest(B), XGBoost(C)
and Ensemble(D)
2017·EATTS
02
Perioperative Outcomes and Survival after Neoadjuvant Immunochemotherapy for Locally Advanced Esophageal Squamous Cell Carcinoma
Xinyu Yang1,2 MD, Hao Yin1,2 MD, Shaoyuan Zhang1,2MD, Tian Jiang1,2 PhD, Jianmin Gu1,2 MD, Heng Jiao1,2MD, Hao Wang1,2 MD, Fei Liang1,3 MD, Songtao Xu1,2,4MD, Hong Fan1,2,5 MD, Jianyong Ding1,2 MD, Di Ge1,2MD, Qun Wang1,2 MD, Jun Yin1,2 PhD, Lijie Tan 1,2MD
1 Department of Thoracic Surgery, Zhongshan Hospital, Fudan University, Shanghai, China, 200000.
2 Cancer Center, Zhongshan Hospital, Fudan University, Shanghai, China,200000.
3 Clinical Statistics Center, Zhongshan Hospital, Fudan University, Shanghai, China, 200000.
4 Department of Thoracic Surgery, Shanghai Geriatric Medical Center, Shanghai, China, 200000.
5 Department of Thoracic Surgery, Xiamen Branch, Zhongshan Hospital, Fudan University, Fujian, China, 350000;
Objective:
This study aimed to compare the difference in perioperative outcomes and prognosis between neoadjuvant immunochemotherapy (nICT) and neoadjuvant chemoradiotherapy (nCRT) for locally advanced esophageal squamous cell carcinoma (LA-ESCC).
Methods:
The LA-ESCC patients receiving nICT or nCRT were identified from a prospectively maintained database at Zhongshan Hospital of Fudan University between Jan 2018 and March 2022. Propensity score matching (PSM) was performed to balance the two groups.
Results:
A total of 124 patient pairs were enrolled in the final analysis.The complete pathological response rate (20.2% vs. 29.0%, P = 0.140) was similar in the two groups while the lower major pathological response rate (44.4% vs. 61.3%, P = 0.011) was observed in the nICT group. nICT was associated with a lower rate of adverse events (42.7% vs. 55.6%, P = 0.047) without additional postoperative complications (38.7% vs. 35.5%, P = 0.693). The nICT group had lower distant metastasis (6.5% vs. 16.1%, P = 0.027) and overall recurrence (11.3% vs. 23.4%, P = 0.019) in the postoperative 1 year. Also, nICT was associated with better progression-free survival (HR=0.50; 95% CI: 0.32-0.77; P = 0.002). Cox proportional hazard analysis showed that nICT (univariable: HR=0.55; 95% CI: 0.37-0.82; P = 0.003; multivariable: HR=0.44; 95% CI: 0.29-0.65; P < 0.001) was one of the independent prognostic factors for progression-free survival. The two groups had similar overall survival (HR=0.62; 95% CI: 0.36-1.09; P = 0.094) at the latest follow-up.
Conclusion:
This retrospective study showed that nICT was safe and effective for LA-ESCC patients.Further verification is needed in the randomized controlled trials.
[CITATION]: Yang X, Yin H, Zhang S, et al. Perioperative Outcomes and Survival after Neoadjuvant Immunochemotherapy for Locally Advanced Esophageal Squamous Cell Carcinoma. J Thorac Cardiovasc Surg. 2024 Jun 27.
[DOI]: 10.1016/j.jtcvs.2024.06.020
[IF]: 4.9
向下滑动查看所有内容
局部晚期食管鳞癌新辅助免疫化疗的围手术期结局和生存
胸“星”外科学术团队兴趣小队成员 杨凯越 译
目的
方法
结果
结论
Figure 2. Recurrence and
overall survival between the two groups after PSM(A) PFS; (B) locoregional
progression-free survival; (C) distant metastasis-free survival; (D) OS. (CI
95%)nICT, neoadjuvant immunochemotherapy; nCRT, neoadjuvant chemoradiotherapy;
PSM, propensity-score matching; PFS, progression-free survival; OS, overall
survival; HR, hazard ratio
Supplementary Figure 2. Progression-free survival of subgroup populations between the two groups after PSM. (CI 95) (A) with cT2-4N0-1M0; (B) without pCR; (C) with pCR; (D) with cN2-3. HR, hazard ratio; nICT, neoadjuvant immunochemotherapy; nCRT, neoadjuvant chemoradiotherapy; PFS, progression-free survival; pCR, pathological complete response.
2017·EATTS