Predicting pathologic complete response in locally advanced rectal cancer patients after neoadjuvant therapy: a machine learning model using XGBoost.
Predicting pathologic complete response in locally advanced rectal cancer patients after neoadjuvant therapy: a machine learning model using XGBoost.
复制标题
预测局部晚期直肠癌患者新辅助治疗后的病理完全缓解：一种使用XGBoost的机器学习模型
DOI：
10.1007/s00384-022-04157-z
复制
发表时间：
2022-07
影响因子：
2.8
通讯作者：
Lian, Lei
中科院分区：
文献类型：
--
作者：
Chen, Xijie;Wang, Wenhui;Chen, Junguo;Xu, Liang;He, Xiaosheng;Lan, Ping;Hu, Jiancong;Lian, Lei
观察等待策略对于新辅助治疗（NAT）后达到病理完全缓解（pCR）的局部进展期直肠癌（LARC）患者来说，是一种安全有效的手术替代方案；目前的再分期方法无法满足临床需求。本研究旨在构建一个机器学习（ML）模型，用于术前预测pCR。
纳入接受NAT的LARC患者，以生成一个基于极端梯度提升的ML模型来预测pCR。将该组患者按7 : 3的比例分为训练集和调谐集。采用SHapley可加性解释值来量化特征重要性。将ML模型与使用常规多变量逻辑回归分析确定的独立危险因素构建的列线图模型进行比较。
与列线图模型相比，我们的ML模型在训练集中将受试者工作特征曲线下面积从0.72提高到0.95，敏感性从43%提高到82.2%，特异性从87.1%提高到91.6%，调谐集中也呈现相同趋势。新辅助放疗、术前糖类抗原125（CA125）、CA199、癌胚抗原水平以及肿瘤浸润深度在两个模型中对预测pCR都具有重要意义。
我们的ML模型是现有评估工具的一种潜在替代方案，可为患者进行分诊治疗，并为临床医生制定个体化治疗方案提供参考：对pCR患者采用观察等待策略以避免手术创伤，对非pCR患者进行手术治疗以避免错过最佳手术时间窗。
网络版包含补充材料，可在10.1007/s00384 - 022 - 04157 - z获取。
Watch and wait strategy is a safe and effective alternative to surgery in patients with locally advanced rectal cancer (LARC) who have achieved pathological complete response (pCR) after neoadjuvant therapy (NAT); present restaging methods do not meet clinical needs. This study aimed to construct a machine learning (ML) model to predict pCR preoperatively. LARC patients who received NAT were included to generate an extreme gradient boosting-based ML model to predict pCR. The group was divided into a training set and a tuning set at a 7:3 ratio. The SHapley Additive exPlanations value was used to quantify feature importance. The ML model was compared with a nomogram model developed using independent risk factors identified by conventional multivariate logistic regression analysis. Compared with the nomogram model, our ML model improved the area under the receiver operating characteristics from 0.72 to 0.95, sensitivity from 43 to 82.2%, and specificity from 87.1 to 91.6% in the training set, the same trend applied to the tuning set. Neoadjuvant radiotherapy, preoperative carbohydrate antigen 125 (CA125), CA199, carcinoembryonic antigen level, and depth of tumor invasion were significant in predicting pCR in both models. Our ML model is a potential alternative to the existing assessment tools to conduct triage treatment for patients and provides reference for clinicians in tailoring individual treatment: the watch and wait strategy is used to avoid surgical trauma in pCR patients, and non-pCR patients receive surgical treatment to avoid missing the optimal operation time window. The online version contains supplementary material available at 10.1007/s00384-022-04157-z.
登录
查看更多内容
影响因子：
6
作者：
Komura D;Ishikawa S
通讯作者：
Ishikawa S
DOI：
10.6004/jnccn.2020.0032
发表时间：
2020-07-01
影响因子：
13.4
作者：
Benson, Al B., III;Venook, Alan P.;Gurski, Lisa A.
通讯作者：
Gurski, Lisa A.
直肠癌化学放疗后完全反应和疾病复发的预测指标。
影响因子：
4.7
作者：
Bitterman DS;Resende Salgado L;Moore HG;Sanfilippo NJ;Gu P;Hatzaras I;Du KL
通讯作者：
Du KL
影响因子：
3.8
作者：
Asoglu, Oktar;Tokmak, Handan;Guven, Koray
通讯作者：
Guven, Koray
影响因子：
9.6
作者：
Borowski, D. W.;Bradburn, D. M.;Kelly, S. B.
通讯作者：
Kelly, S. B.