绵阳市中医医院普外科,四川 绵阳 621000
黄坤,副主任医师,主要从事普外基础与临床研究,Email:mshuangkun@163.com
何运胜,Email:hys2520856@163.com
收稿:2023-10-20,
纸质出版:2024-08-22
移动端阅览
黄坤,章慧,赵攀等.基于机器学习算法的胰腺鳞状细胞癌预后模型的构建与验证[J].腹部外科,2024,37(04):261-270.
Huang Kun,Zhang Hui,Zhao Pan,et al.Developing and validating nomograms for predicting survival in patients with pancreatic squamous cell carcinoma based upon machine learning[J].J Abdominal Surg,2024,37(04):261-270.
黄坤,章慧,赵攀等.基于机器学习算法的胰腺鳞状细胞癌预后模型的构建与验证[J].腹部外科,2024,37(04):261-270. DOI: 10.3969/j.issn.1003-5591.2024.04.006.
Huang Kun,Zhang Hui,Zhao Pan,et al.Developing and validating nomograms for predicting survival in patients with pancreatic squamous cell carcinoma based upon machine learning[J].J Abdominal Surg,2024,37(04):261-270. DOI: 10.3969/j.issn.1003-5591.2024.04.006.
目的
2
胰腺鳞状细胞癌(pancreatic squamous cell carcinoma,PSCC)预后差,缺乏个体化的预后预测工具。研究通过SEER数据库中的大样本真实世界数据,基于机器学习算法,构建PSCC病人预后列线图,旨在精准化、个体化评价PSCC病人的预后,为临床决策制定提供参考。
方法
2
提取SEER数据库中2000~2019年期间经病理学确诊的PSCC病人的临床资料,以7∶3的比例随机划分为训练集和验证集,采用多因素Cox比例风险模型、LASSO回归模型和随机生存森林模型筛选变量,构建预测3、6、12个月肿瘤特异性生存期(cancer-specific survival, CSS)和总生存期(overall survival,OS)的Nomogram模型,利用一致性指数、受试者操作特征曲线操作、校准曲线、生存曲线、决策曲线分析对模型进行验证和评估。
结果
2
本研究共纳入367例病人,其中训练集256例,验证集111例。训练集和验证集病人的中位随访时间分别为3(1,7)个月和2(1,8)个月。两组间的基线特征均衡(均
P
>0.05)。多因素Cox比例风险模型显示:肿瘤大小、T分期、M分期、手术、化疗是OS和CSS的独立影响因素(均
P
<0.05)。LASSO回归模型显示:M分期、手术、化疗和OS、CSS相关。随机生存森林模型显示,影响OS的重要性评分前4位变量分别为化疗、M分期、手术和年龄,而影响CSS的重要性评分前4位变量分别为化疗、M分期、手术和肿瘤大小。基于这些因素所构建的Nomogram用于预测病人3、6个月的OS和CSS。验证结果表明:对于OS,训练集和验证集中一致性指数分别为0.753(95%
CI
:0.720~0.790)和0.723(95%
CI
:0.660~0.780);对于CSS,两者分别为0.749(95%
CI
:0.720~0.780)和0.721(95%
CI
:0.660~0.780)。受试者操作特征曲线操作显示:对于3个月OS,训练集和验证集的曲线下面积(AUC)分别为79.8%和75.9%;对于6个月OS,训练集和验证集的AUC为78.9%和76.8%;对于12个月OS,训练集和验证集的AUC为78.7%和77.5%;对于3个月CSS,训练集和验证集的AUC为79.3%和76.3%;对于6个月CSS,训练集和验证集的AUC为78.6%和76.9%;对于12个月CSS,训练集和验证集的AUC为77.8%和77.4%。校准曲线均靠近理想的45°参考线,表现出良好的一致性。
结论
2
年龄、M分期、肿瘤部位、手术和化疗是病人预后的独立影响因素。研究构建的Nomogram预测模型具有良好的预测价值,有利于临床对PSCC病人选择个性化治疗。
Objective
2
Pancreatic Squamous Cell Carcinoma (PSCC) has a poor prognosis and it lacks individualized prognostic tools. This study aimed to construct prognostic nomograms for PSCC patients based upon machine learning and using large-scale real-world data from the database of SEER, provide precise and individualized prognostic assessments and offer valuable references for clinical decision-making.
Methods
2
From 2000 to 2019, the relevant clinical data of 367 pathologically diagnosed PSCC patients were extracted from the database of SEER. They were randomized by a ratio of 7∶3 into training (
n
=256) and verification (
n
=111) sets. Multivariate Cox proportional hazard model, LASSO regression and random survival forest model were utilized for identifying independent prognostic factors for patient survival. These factors were utilized for constructing nomograms for predicting cancer specific survival (CSS) and total survival (OS) at Month 3/6. Subsequently, the models were internally and externally validated in training and validation sets by concordance index (C-index), receiver operating characteristic (ROC) and calibration curves for assessing their accuracy and predictive capacity.
Results
2
The median follow-up period in training and verification sets were 3(1,7) and 2(1,8) month. Baseline profiles were comparable between two groups (all
P
>
0.05). Multivariate Cox proportional hazard model analysis indicated that tumor size, M/N stage, surgery and chemotherapy were independent influencing factors for OS/CSS. LASSO regression analysis revealed that M stage, surgery and chemotherapy were associated with OS/CSS. For OS, top four scoring variables for via random survival forest model were chemotherapy, M stage, surgery and age; For CSS, chemotherapy, M stage, surgery and tumor size. Nomograms for predicting OS/CS
S at Month 3/6 were developed based upon these independent prognostic factors. Validation results showed that C-index for OS in training and verification sets were 0.753(95%
CI
:0.720-0.790) and 0.723(95%
CI
:0.660-0.780) and for CSS 0.749(95%
CI
:0.720-0.780) and 0.721(95%
CI
:0.660-0.780). ROC curve analysis indicated that AUC values for OS in training and verification sets were 79.8% and 75.9% at Month 3, 78.9% and 76.8% at Month 6 and 78.7% and 77.5% at Month 12; for CSS, 79.3% and 76.3% at Month 3, 78.6% and 76.9% at Month 6 and 77.4% and 78.4% at Month 12 respectively. Calibration curve analysis demonstrated a decent agreement between predicted and actual OS/CSS. Both were closely situated near ideal 45° reference line, demonstrating a high consistency.
Conclusion
2
Age, M stage, tumor size, surgery and chemotherapy are independent prognostic factors for PSCC patients. And the above constructed nomogram prediction models exhibit favorable predictive value and facilitate personalized therapeutics for PSCC patients in clinical practices.
王健力 , 俞泽元 , 陈志涛 , 等 . TRIM21与胰腺癌临床病理特征及免疫浸润的相关性分析 [J]. 重庆医科大学学报 , 2022 , 47 ( 2 ): 201 - 208 . DOI: 10.13406/j.cnki.cyxb.002737 http://dx.doi.org/10.13406/j.cnki.cyxb.002737 .
Timmer FEF , Geboers B , Nieuwenhuizen S , et al . Locoregional treatment of metastatic pancreatic cancer utilizing resection,ablation and embolization:a systematic review [J]. Cancers , 2021 , 13 ( 7 ): 1608 . DOI: 10.3390/cancers13071608 http://dx.doi.org/10.3390/cancers13071608 .
Zhou WT , Wang DS , Lou WH . Current role of surgery in pancreatic cancer with synchronous liver metastasis [J]. Cancer Control , 2020 , 27 ( 1 ): 1073274820976593 . DOI: 10.1177/1073274820976593 http://dx.doi.org/10.1177/1073274820976593 .
Siegel RL , Miller KD , Jemal A . Cancer statistics,2016 [J]. CA Cancer J Clin , 2016 , 66 ( 1 ): 7 - 30 . DOI: 10.3322/caac.21332 http://dx.doi.org/10.3322/caac.21332 .
肖文博 , 朱广涵 , 朱云 , 等 . 1990-2019年中国主要消化系统恶性肿瘤发病变化分析 [J]. 中国肿瘤 , 2022 , 31 ( 9 ): 693 - 700 . DOI: 10.11735/j.issn.1004-0242.2022.09.A003 http://dx.doi.org/10.11735/j.issn.1004-0242.2022.09.A003 .
张敏 , 段朝晖 , 徐杰茹 , 等 . 基于GBD数据分析与预测2000—2030年中国胰腺癌发病与死亡趋势 [J]. 中国肿瘤 , 2022 , 31 ( 11 ): 862 - 868 . DOI: 10.11735/j.issn.1004-0242.2022.11.A003 http://dx.doi.org/10.11735/j.issn.1004-0242.2022.11.A003 .
Luo GP , Fan ZY , Gong YT , et al . Characteristics and outcomes of pancreatic cancer by histological subtypes [J]. Pancreas , 2019 , 48 ( 6 ): 817 - 822 . DOI: 10.1097/MPA.0000000000001338 http://dx.doi.org/10.1097/MPA.0000000000001338 .
黎美青 , 张永俊 , 刘争进 . 胰腺原发性透明细胞鳞状细胞癌一例 [J]. 中华病理学杂志 , 2021 , 50 ( 10 ): 1186 - 1188 . DOI: 10.3760/cma.j.cn112151-20210722-00524 http://dx.doi.org/10.3760/cma.j.cn112151-20210722-00524 .
Chen MS , Liu PC , Yi JZ , et al . Development and validation of nomograms for predicting survival in patients with de novo metastatic triple-negative breast cancer [J]. Sci Rep , 2022 , 12 ( 1 ): 14659 . DOI: 10.1038/s41598-022-18727-2 http://dx.doi.org/10.1038/s41598-022-18727-2 .
Huang C , Yu QP , Li H , et al . A novel nomogram model to predict the overall survival of patients with retroperitoneal leiomyosarcoma:a large cohort retrospective study [J]. Sci Rep , 2022 , 12 ( 1 ): 11851 . DOI: 10.1038/s41598-022-16055-z http://dx.doi.org/10.1038/s41598-022-16055-z .
Zhang SL , Wang ZM , Wang WR , et al . Novel nomograms individually predict the survival of patients with soft tissue sarcomas after surgery [J]. Cancer Manag Res , 2019 , 11 : 3215 - 3225 . DOI: 10.2147/CMAR.S195123 http://dx.doi.org/10.2147/CMAR.S195123 .
Wang W , Hong JQ , Meng JH , et al . Nomograms predict cancer-specific and overall survival of patients with primary limb leiomyosarcoma [J]. J Orthop Res , 2019 , 37 ( 7 ): 1649 - 1657 . DOI: 10.1002/jor.24298 http://dx.doi.org/10.1002/jor.24298 .
刘红枝 , 林海涛 , 林昭旺 , 等 . 机器学习算法在肝细胞癌微血管侵犯术前预测中的应用价值 [J]. 中华消化外科杂志 , 2020 , 19 ( 2 ): 156 - 165 . DOI: 10.3760/cma.j.issn.1673-9752.2020.02.008 http://dx.doi.org/10.3760/cma.j.issn.1673-9752.2020.02.008 .
黄坤 , 赵平武 , 白斗 , 等 . 不同病理学类型的腹膜后脂肪肉瘤患者的预后分析及临床评价 [J]. 中国普通外科杂志 , 2021 , 30 ( 10 ): 1212 - 1228 . DOI: 10.7659/j.issn.1005-6947.2021.10.011 http://dx.doi.org/10.7659/j.issn.1005-6947.2021.10.011 .
陈茂山 , 李芳芳 , 杨宏伟 , 等 . 基于SEER数据库分析142007例乳腺癌诊断时婚姻状态与预后的关系 [J]. 重庆医科大学学报 , 2020 , 45 ( 11 ): 1567 - 1572 . DOI: 10.13406/j.cnki.cyxb.002325 http://dx.doi.org/10.13406/j.cnki.cyxb.002325 .
黄坤 , 赵平武 , 白斗 , 等 . 不同病理学类型的腹膜后脂肪肉瘤患者的预后分析及临床评价 [J]. 中国普通外科杂志 , 2021 , 7 ( 10 ): 1212 - 1228 . DOI: 10.7659/j.issn.1005-6947.2021.10.011 http://dx.doi.org/10.7659/j.issn.1005-6947.2021.10.011 .
黄坤 , 何运胜 , 张红梅 , 等 . 手术治疗对胆囊小细胞癌患者预后价值的SEER数据库分析 [J]. 中国普通外科杂志 , 2022 , 8 ( 8 ): 997 - 1005 . DOI: 10.7659/j.issn.1005-6947.2022.08.002 http://dx.doi.org/10.7659/j.issn.1005-6947.2022.08.002 .
刘千琳 , 李秋 . 肝细胞癌靶向治疗联合免疫治疗的研究剖析 [J]. 中国普外基础与临床杂志 , 2023 , 30 ( 4 ): 392 - 396 . DOI: 10.7507/1007-9424.202303055 http://dx.doi.org/10.7507/1007-9424.202303055 .
黄坤 , 何运胜 , 赵攀 , 等 . 手术治疗对直肠小细胞神经内分泌癌患者预后影响的SEER数据库分析 [J]. 中国普外基础与临床杂志 , 2023 , 30 ( 2 ): 179 - 184 . DOI: 10.7507/1007-9424.202208041 http://dx.doi.org/10.7507/1007-9424.202208041 .
程杨 , 陈小彬 , 魏志鸿 , 等 . 术前淋巴细胞与C反应蛋白比值在预测胆囊癌术后复发中的应用及其临床价值 [J]. 中国普通外科杂志 , 2023 , 32 ( 2 ): 190 - 199 . DOI: 10.7659/j.issn.1005-6947.2023.02.004 http://dx.doi.org/10.7659/j.issn.1005-6947.2023.02.004 .
王晓晓 , 陶立元 , 裴敏玥 , 等 . 连续变量转换为分类变量的几种方法 [J]. 中华儿科杂志 , 2022 , 60 ( 5 ): 420 . DOI: 10.3760/cma.j.cn112140-20220317-00212 http://dx.doi.org/10.3760/cma.j.cn112140-20220317-00212 .
黄坤 , 何运胜 , 张红梅 , 等 . 手术治疗对胆囊小细胞癌患者预后价值的SEER数据库分析 [J]. 中国普通外科杂志 , 2022 , 31 ( 8 ): 997 - 1005 . DOI: 10.7659/j.issn.1005-6947.2022.08.002 http://dx.doi.org/10.7659/j.issn.1005-6947.2022.08.002 .
Su BB , Bai DS , Yu JQ , et al . Can patients with pancreatic cancer and liver metastases obtain survival benefit from surgery?A population-based study [J]. J Cancer , 2021 , 12 ( 2 ): 539 - 552 . DOI: 10.7150/jca.51218 http://dx.doi.org/10.7150/jca.51218 .
Pu N , Chen QD , Gan W , et al . Lymph node metastatic patterns and survival predictors based on tumor size in pancreatic ductal adenocarcinoma [J]. Adv Ther , 2021 , 38 ( 8 ): 4258 - 4270 . DOI: 10.1007/s12325-021-01819-2 http://dx.doi.org/10.1007/s12325-021-01819-2 .
陈茂山 , 李芳芳 , 杨宏伟 , 等 . 基于SEER数据库分析142007乳腺癌诊断时婚姻状态与预后的关系 [J]. 2020 , 45 ( 11 ): 1567 - 1572 . DOI: 10.13406/j.cnki.cyxb.002325 http://dx.doi.org/10.13406/j.cnki.cyxb.002325 .
Kim Y , Margonis GA , Prescott JD , et al . Nomograms to predict recurrence-free and overall survival after curative resection of adrenocortical carcinoma [J]. JAMA Surg , 2016 , 151 ( 4 ): 365 - 373 . DOI: 10.1001/jamasurg.2015.4516 http://dx.doi.org/10.1001/jamasurg.2015.4516 .
陈哲 , 许恒敏 , 李哲轩 , 等 . 随机生存森林:基于机器学习算法的生存分析模型 [J]. 中华预防医学杂志 , 2021 , 55 ( 1 ): 104 - 109 . DOI: 10.3760/cma.j.cn112150-20200911-01197 http://dx.doi.org/10.3760/cma.j.cn112150-20200911-01197 .
Wang YQ , Zhou YW , Chen YY , et al . Epidemiology,treatment,and outcome of pancreatic squamous cell carcinoma and pancreatic adenocarcinoma:a propensity score-matching analysis based on SEER-database [J]. Technol Cancer Res Treat , 2022 , 21 : 15330338221106533 . DOI: 10.1177/15330338221106533 http://dx.doi.org/10.1177/15330338221106533 .
Makarova-Rusher OV , Ulahannan S , Greten TF , et al . Pancreatic squamous cell carcinoma:a population-based study of epidemiology,clinicopathologic characteristics and outcomes [J]. Pancreas , 2016 , 45 ( 10 ): 1432 - 1437 . DOI: 10.1097/MPA.0000000000000658 http://dx.doi.org/10.1097/MPA.0000000000000658 .
江珍珍 , 刘夏天 , 侯传玲 . 胰腺原发性鳞状细胞癌一例 [J]. 中华胰腺病杂志 , 2018 , 18 ( 2 ): 127 . DOI: 10.3760/cma.j.issn.1674-1935.2018.02.018 http://dx.doi.org/10.3760/cma.j.issn.1674-1935.2018.02.018 .
何睿哲 , 付学良 , 刘德军 , 等 . 胰腺鳞状细胞癌一例 [J]. 中华普通外科杂志 , 2018 , 33 ( 9 ): 741 . DOI: 10.3760/cma.j.issn.1007-631X.2018.09.008 http://dx.doi.org/10.3760/cma.j.issn.1007-631X.2018.09.008 .
金圣博 , 丁雪丽 , 于亚男 , 等 . 化疗联合经皮肝动脉化疗栓塞术治疗胰腺鳞状细胞癌并肝转移一例 [J]. 中华医学杂志 , 2019 , 99 ( 46 ): 3667 - 3668 . DOI: 10.3760/cma.j.issn.0376-2491.2019.46.015 http://dx.doi.org/10.3760/cma.j.issn.0376-2491.2019.46.015 .
Qin WX , Wu Y , Liu J , et al . Primary squamous cell carcinoma of pancreas:a population-based study [J]. Gland Surg , 2021 , 10 ( 3 ): 1029 - 1037 . DOI: 10.21037/gs-20-317 http://dx.doi.org/10.21037/gs-20-317 .
Xu L , Wen N , Qiu JJ , et al . Predicting survival benefit of sparing sentinel lymph node biopsy in low-risk elderly patients with early breast cancer:a population-based analysis [J]. Front Oncol , 2020 , 10 : 1718 . DOI: 10.3389/fonc.2020.01718 http://dx.doi.org/10.3389/fonc.2020.01718 .
Xiang JX , Zhang XF , Weiss M , et al . Multi-institutional development and external validation of a nomogram predicting recurrence after curative liver resection for neuroendocrine liver metastasis [J]. Ann Surg Oncol , 2020 , 27 ( 10 ): 3717 - 3726 . DOI: 10.1245/s10434-020-08620-5 http://dx.doi.org/10.1245/s10434-020-08620-5 .
程晨 , 吴云桦 , 徐正水 , 等 . Ⅱ~Ⅲ期结肠癌根治术后复发危险因素分析及其列线图预测模型的应用价值 [J]. 中华消化外科杂志 , 2021 , 20 ( 3 ): 331 - 338 . DOI: 10.3760/cma.j.cn115610-20210120-00034 http://dx.doi.org/10.3760/cma.j.cn115610-20210120-00034 .
邓家仲 , 荚卫东 . 肝细胞癌微血管侵犯危险因素分析及术前预测列线图模型构建 [J]. 中国普通外科杂志 , 2021 , 30 ( 7 ): 772 - 779 . DOI: 10.7659/j.issn.1005-6947.2021.07.003 http://dx.doi.org/10.7659/j.issn.1005-6947.2021.07.003 .
李吴寒 , 张营 , 潘晶晶 , 等 . 胃癌患者预后相关影响因素的列线图模型构建及验证 [J]. 中国普通外科杂志 , 2022 , 31 ( 10 ): 1381 - 1388 . DOI: 10.7659/j.issn.1005-6947.2022.10.014 http://dx.doi.org/10.7659/j.issn.1005-6947.2022.10.014 .
Peng F , Qin TT , Wang M , et al . Development and validation of a nomogram to predict survival in pancreatic head ductal adenocarcinoma after pancreaticoduodenectomy [J]. Front Oncol , 2021 , 11 : 734673 . DOI: 10.3389/fonc.2021.734673 http://dx.doi.org/10.3389/fonc.2021.734673 .
0
浏览量
2
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621