解剖淋巴结数量对基于机器学习的肺癌术后复发预测的影响:一项单医院回顾性队列研究。

IF 3.6 3区 医学 Q1 RESPIRATORY SYSTEM
Kensuke Kojima, Hironobu Samejima, Kyoichi Okishio, Toshiteru Tokunaga, Hyungeun Yoon, Shinji Atagi
{"title":"解剖淋巴结数量对基于机器学习的肺癌术后复发预测的影响:一项单医院回顾性队列研究。","authors":"Kensuke Kojima, Hironobu Samejima, Kyoichi Okishio, Toshiteru Tokunaga, Hyungeun Yoon, Shinji Atagi","doi":"10.1136/bmjresp-2023-001926","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>The optimal number of lymph nodes to be dissected during lung cancer surgery to minimise the postoperative recurrence risk remains undetermined. This study aimed to elucidate the impact of the number of dissected lymph nodes on the risk of postoperative recurrence of non-small cell lung cancer (NSCLC) using machine learning algorithms and statistical analyses.</p><p><strong>Methods: </strong>We retrospectively analysed 650 patients with NSCLC who underwent complete resection. Five machine learning models were trained using clinicopathological variables to predict postoperative recurrence. The relationship between the number of dissected lymph nodes and postoperative recurrence was investigated in the best-performing model using Shapley additive explanations values and partial dependence plots. Multivariable Cox proportional hazard analysis was performed to estimate the HR for postoperative recurrence based on the number of dissected nodes.</p><p><strong>Results: </strong>The random forest model demonstrated superior predictive performance (area under the receiver operating characteristic curve: 0.92, accuracy: 0.83, F1 score: 0.64). The partial dependence plot of this model revealed a non-linear dependence of the number of dissected lymph nodes on recurrence prediction within the range of 0-20 nodes, with the weakest dependence at 10 nodes. A linear increase in the dependence was observed for ≥20 dissected nodes. A multivariable analysis revealed a significantly elevated risk of recurrence in the group with ≥20 dissected nodes in comparison to those with <20 nodes (adjusted HR, 1.45; 95% CI 1.003 to 2.087).</p><p><strong>Conclusions: </strong>The number of dissected lymph nodes was significantly associated with the risk of postoperative recurrence of NSCLC. The risk of recurrence is minimised when approximately 10 nodes are dissected but may increase when >20 nodes are removed. Limiting lymph node dissection to approximately 20 nodes may help to preserve a favourable antitumour immune environment. These findings provide novel insights into the optimisation of lymph node dissection during lung cancer surgery.</p>","PeriodicalId":9048,"journal":{"name":"BMJ Open Respiratory Research","volume":null,"pages":null},"PeriodicalIF":3.6000,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11429344/pdf/","citationCount":"0","resultStr":"{\"title\":\"Impact of the number of dissected lymph nodes on machine learning-based prediction of postoperative lung cancer recurrence: a single-hospital retrospective cohort study.\",\"authors\":\"Kensuke Kojima, Hironobu Samejima, Kyoichi Okishio, Toshiteru Tokunaga, Hyungeun Yoon, Shinji Atagi\",\"doi\":\"10.1136/bmjresp-2023-001926\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>The optimal number of lymph nodes to be dissected during lung cancer surgery to minimise the postoperative recurrence risk remains undetermined. This study aimed to elucidate the impact of the number of dissected lymph nodes on the risk of postoperative recurrence of non-small cell lung cancer (NSCLC) using machine learning algorithms and statistical analyses.</p><p><strong>Methods: </strong>We retrospectively analysed 650 patients with NSCLC who underwent complete resection. Five machine learning models were trained using clinicopathological variables to predict postoperative recurrence. The relationship between the number of dissected lymph nodes and postoperative recurrence was investigated in the best-performing model using Shapley additive explanations values and partial dependence plots. Multivariable Cox proportional hazard analysis was performed to estimate the HR for postoperative recurrence based on the number of dissected nodes.</p><p><strong>Results: </strong>The random forest model demonstrated superior predictive performance (area under the receiver operating characteristic curve: 0.92, accuracy: 0.83, F1 score: 0.64). The partial dependence plot of this model revealed a non-linear dependence of the number of dissected lymph nodes on recurrence prediction within the range of 0-20 nodes, with the weakest dependence at 10 nodes. A linear increase in the dependence was observed for ≥20 dissected nodes. A multivariable analysis revealed a significantly elevated risk of recurrence in the group with ≥20 dissected nodes in comparison to those with <20 nodes (adjusted HR, 1.45; 95% CI 1.003 to 2.087).</p><p><strong>Conclusions: </strong>The number of dissected lymph nodes was significantly associated with the risk of postoperative recurrence of NSCLC. The risk of recurrence is minimised when approximately 10 nodes are dissected but may increase when >20 nodes are removed. Limiting lymph node dissection to approximately 20 nodes may help to preserve a favourable antitumour immune environment. These findings provide novel insights into the optimisation of lymph node dissection during lung cancer surgery.</p>\",\"PeriodicalId\":9048,\"journal\":{\"name\":\"BMJ Open Respiratory Research\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.6000,\"publicationDate\":\"2024-09-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11429344/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"BMJ Open Respiratory Research\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1136/bmjresp-2023-001926\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"RESPIRATORY SYSTEM\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMJ Open Respiratory Research","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1136/bmjresp-2023-001926","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RESPIRATORY SYSTEM","Score":null,"Total":0}
引用次数: 0

摘要

背景:在肺癌手术中切除多少淋巴结才能最大限度地降低术后复发风险,目前尚无定论。本研究旨在利用机器学习算法和统计分析阐明切除淋巴结数量对非小细胞肺癌(NSCLC)术后复发风险的影响:我们回顾性分析了650例接受完全切除术的NSCLC患者。我们利用临床病理变量训练了五个机器学习模型来预测术后复发。在表现最好的模型中,使用沙普利加法解释值和偏倚图研究了切除淋巴结数量与术后复发之间的关系。进行了多变量考克斯比例危险度分析,以根据切除淋巴结的数量估算术后复发的HR:结果:随机森林模型显示出了卓越的预测性能(接收者操作特征曲线下面积:0.92,准确率:0.01):0.92,准确率:0.83,F1 评分:0.64)。该模型的部分依赖关系图显示,在 0-20 个淋巴结的范围内,切除淋巴结的数量对复发预测有非线性依赖关系,在 10 个淋巴结时依赖关系最弱。当切除淋巴结数≥20个时,依赖性呈线性增加。多变量分析显示,与得出结论的组别相比,淋巴结清扫≥20个的组别复发风险明显升高:淋巴结清扫数目与 NSCLC 术后复发风险明显相关。切除约10个淋巴结时,复发风险最小,但切除>20个淋巴结时,复发风险可能会增加。将淋巴结清扫限制在 20 个左右可能有助于保持良好的抗肿瘤免疫环境。这些发现为肺癌手术中淋巴结清扫的优化提供了新的见解。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Impact of the number of dissected lymph nodes on machine learning-based prediction of postoperative lung cancer recurrence: a single-hospital retrospective cohort study.

Background: The optimal number of lymph nodes to be dissected during lung cancer surgery to minimise the postoperative recurrence risk remains undetermined. This study aimed to elucidate the impact of the number of dissected lymph nodes on the risk of postoperative recurrence of non-small cell lung cancer (NSCLC) using machine learning algorithms and statistical analyses.

Methods: We retrospectively analysed 650 patients with NSCLC who underwent complete resection. Five machine learning models were trained using clinicopathological variables to predict postoperative recurrence. The relationship between the number of dissected lymph nodes and postoperative recurrence was investigated in the best-performing model using Shapley additive explanations values and partial dependence plots. Multivariable Cox proportional hazard analysis was performed to estimate the HR for postoperative recurrence based on the number of dissected nodes.

Results: The random forest model demonstrated superior predictive performance (area under the receiver operating characteristic curve: 0.92, accuracy: 0.83, F1 score: 0.64). The partial dependence plot of this model revealed a non-linear dependence of the number of dissected lymph nodes on recurrence prediction within the range of 0-20 nodes, with the weakest dependence at 10 nodes. A linear increase in the dependence was observed for ≥20 dissected nodes. A multivariable analysis revealed a significantly elevated risk of recurrence in the group with ≥20 dissected nodes in comparison to those with <20 nodes (adjusted HR, 1.45; 95% CI 1.003 to 2.087).

Conclusions: The number of dissected lymph nodes was significantly associated with the risk of postoperative recurrence of NSCLC. The risk of recurrence is minimised when approximately 10 nodes are dissected but may increase when >20 nodes are removed. Limiting lymph node dissection to approximately 20 nodes may help to preserve a favourable antitumour immune environment. These findings provide novel insights into the optimisation of lymph node dissection during lung cancer surgery.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
BMJ Open Respiratory Research
BMJ Open Respiratory Research RESPIRATORY SYSTEM-
CiteScore
6.60
自引率
2.40%
发文量
95
审稿时长
12 weeks
期刊介绍: BMJ Open Respiratory Research is a peer-reviewed, open access journal publishing respiratory and critical care medicine. It is the sister journal to Thorax and co-owned by the British Thoracic Society and BMJ. The journal focuses on robustness of methodology and scientific rigour with less emphasis on novelty or perceived impact. BMJ Open Respiratory Research operates a rapid review process, with continuous publication online, ensuring timely, up-to-date research is available worldwide. The journal publishes review articles and all research study types: Basic science including laboratory based experiments and animal models, Pilot studies or proof of concept, Observational studies, Study protocols, Registries, Clinical trials from phase I to multicentre randomised clinical trials, Systematic reviews and meta-analyses.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信