AbstractWhile genome-wide association studies are valuable in identifying CRC survival predictors, the benefit of adding blood DNA methylation (blood-DNAm) to clinical features, including the TNM system, remains unclear. In a multi-site population-based patient cohort study of 2116 CRC patients with baseline blood-DNAm, we analyzed survival predictions using eXtreme Gradient Boosting with a 5-fold nested leave-sites-out cross-validation across four groups: traditional and comprehensive clinical features, blood-DNAm, and their combination.

摘要虽然全基因组关联研究在确定CRC生存预测因子方面很有价值，但将血液DNA甲基化（血液DNAm）添加到临床特征（包括TNM系统）的益处仍不清楚。在一项针对2116名基线血液DNAm的CRC患者的多地点人群队列研究中，我们使用极端梯度增强分析了生存预测，并在四组中进行了5倍嵌套的离开位点交叉验证：传统和全面的临床特征，血液DNAm及其组合。

Model performance was assessed using time-dependent ROC curves and calibrations. During a median follow-up of 10.3 years, 1166 patients died. Although blood-DNAm-based predictive signatures achieved moderate performances, predictive signatures based on clinical features outperformed blood-DNAm signatures.

使用时间依赖性ROC曲线和校准评估模型性能。在中位随访10.3年期间，有1166名患者死亡。尽管基于血液DNAm的预测特征取得了中等表现，但基于临床特征的预测特征优于血液DNAm特征。

The inclusion of blood-DNAm did not improve survival prediction over clinical features. M1 stage, age at blood collection, and N2 stage were the top contributors. Despite some prognostic value, incorporating blood DNA methylation did not enhance survival prediction of CRC patients beyond clinical features..

包含血液DNAm并不能改善临床特征的生存预测。M1期，采血年龄和N2期是主要贡献者。尽管有一些预后价值，但纳入血液DNA甲基化并不能提高CRC患者的生存预测，超出临床特征。。

IntroductionColorectal cancer (CRC) is one of the most common cancers and one of the most common causes of cancer-related deaths globally, accounting for more than 9% of all cancer-related deaths1. The prognosis and therapy management of CRC rely on the TNM stage system, with a relative 5-year survival over 90% for localized-stage CRC but dropping below 15% for distant-stage CRC2.

引言结直肠癌（CRC）是全球最常见的癌症之一，也是癌症相关死亡的最常见原因之一，占所有癌症相关死亡的9%以上1。CRC的预后和治疗管理依赖于TNM分期系统，局部期CRC的相对5年生存率超过90%，而远处CRC2的相对5年生存率低于15%。

Nevertheless, the current TNM stage system is insufficient for accurately predicting survival and guiding clinical management, especially among stage II–III patients, resulting in potential over- or undertreatment3,4. Consequently, there is a growing need to establish more accurate novel prognostic signatures in predicting survival of CRC patients.DNA methylation (DNAm) is a crucial epigenetic modification whose genome-wide analysis allows exploration of potentially valuable biomarkers for predicting prognosis in CRC5,6,7.

然而，目前的TNM分期系统不足以准确预测生存率和指导临床管理，特别是在II-III期患者中，导致潜在的过度或不足治疗3,4。因此，越来越需要建立更准确的新型预后特征来预测CRC患者的生存。DNA甲基化（DNAm）是一种关键的表观遗传修饰，其全基因组分析可以探索潜在有价值的生物标志物，用于预测CRC5,6,7的预后。

Predictive signatures based on high-dimensional tumor DNAm, such as DNAm from resected tumor tissue and circulating tumor DNA (ctDNA)8, using machine-learning approaches have been increasingly proposed. However, the added value in discriminatory ability provided by tumor DNAm-derived signature to traditional clinical variables was unsatisfactory9.

越来越多地提出了使用机器学习方法基于高维肿瘤DNAm的预测特征，例如来自切除的肿瘤组织的DNAm和循环肿瘤DNA（ctDNA）8。然而，肿瘤DNAm衍生的特征对传统临床变量提供的鉴别能力的附加值并不令人满意9。

Additionally, it is not possible to examine the postoperative DNAm profile following the removal of the tumor. DNAm profiles from peripheral whole blood present alternative opportunities to develop predictive signatures and use them to monitor survival over an extended period. DNAm-based scores derived from peripheral whole blood, such as a DNAm mortality risk score and the age acceleration of PhenoAge and GrimAge, have been identified as strongly associated with all-cause mortality10.

此外，不可能在切除肿瘤后检查术后DNAm谱。来自外周全血的DNAm谱提供了开发预测特征的替代机会，并将其用于长时间监测生存。来自外周全血的基于DNAm的评分，例如DNAm死亡率风险评分以及表型和GrimAge的年龄加速，已被确定与全因死亡率密切相关10。

Given that these DNAm scores have been designe.

鉴于这些DNAm分数已被设计。

Data availability

数据可用性

The datasets generated and analyzed during the current study are not publicly available due ethical and legal restrictions but are available from the corresponding author on reasonable request.

由于道德和法律限制，当前研究期间生成和分析的数据集无法公开获得，但可根据合理要求从通讯作者处获得。

Code availability

代码可用性

The code is available from the corresponding author upon reasonable request.

应合理要求，通讯作者可提供该代码。

ReferencesSung, H. et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin. 71, 209–249 (2021).Article

ReferencesSung，H.等人，《2020年全球癌症统计：全球癌症协会对185个国家36种癌症的全球发病率和死亡率的估计》。CA Cancer J.Clin。71209-249（2021）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Siegel, R. L., Wagle, N. S., Cercek, A., Smith, R. A. & Jemal, A. Colorectal cancer statistics, 2023. CA Cancer J. Clin. 73, 233–254 (2023).Article

Siegel，R.L.，Wagle，N.S.，Cercek，A.，Smith，R.A。＆Jemal，A。结直肠癌统计，2023年。CA Cancer J.Clin。73233-254（2023）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Kim, M. J. et al. Survival paradox between stage IIB/C (T4N0) and stage IIIA (T1-2N1) colon cancer. Ann. Surg. Oncol. 22, 505–512 (2015).Article

。安。外科。Oncol。22505-512（2015）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Kannarkatt, J., Joseph, J., Kurniali, P. C., Al-Janadi, A. & Hrinczenko, B. Adjuvant chemotherapy for stage II colon cancer: a clinical dilemma. J. Oncol. Pract. 13, 233–241 (2017).Article

Kannarkatt，J.，Joseph，J.，Kurniali，P.C.，Al Janadi，A。＆Hrinczenko，B。II期结肠癌的辅助化疗：临床困境。J、 Oncol公司。实践。13233-241（2017）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Draht, M. X. G. et al. Prognostic DNA methylation markers for sporadic colorectal cancer: a systematic review. Clin. Epigenetics 10, 35 (2018).Article

Draht，M.X.G.等。散发性结直肠癌的预后DNA甲基化标志物：系统评价。临床。表观遗传学10,35（2018）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Jung, G., Hernandez-Illan, E., Moreira, L., Balaguer, F. & Goel, A. Epigenetics of colorectal cancer: biomarker and therapeutic potential. Nat. Rev. Gastroenterol. Hepatol. 17, 111–130 (2020).Article

Jung，G.，Hernandez-Illan，E.，Moreira，L.，Balaguer，F。＆Goel，A。结直肠癌的表观遗传学：生物标志物和治疗潜力。胃肠病学国家修订版。肝病。17111-130（2020）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Müller, D. & Győrffy, B. DNA methylation-based diagnostic, prognostic, and predictive biomarkers in colorectal cancer. Biochim. Biophys. Acta Rev. Cancer 1877, 188722 (2022).Article

Müller，D。＆Győrffy，B。基于DNA甲基化的结直肠癌诊断，预后和预测生物标志物。生物化学。生物物理。。文章

PubMed

PubMed

Google Scholar

谷歌学者

Luo, H. et al. Circulating tumor DNA methylation profiles enable early diagnosis, prognosis prediction, and screening for colorectal cancer. Sci. Transl. Med. 12, eaax7533 (2020).Article

Luo，H。等人。循环肿瘤DNA甲基化谱可用于结直肠癌的早期诊断，预后预测和筛查。科学。翻译。医学12，eaax7533（2020）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Yuan, T. et al. CpG-biomarkers in tumor tissue and prediction models for the survival of colorectal cancer: a systematic review and external validation study. Crit. Rev. Oncol. Hematol. 193, 104199 (2024).Article

Yuan，T。等。肿瘤组织中的CpG生物标志物和结直肠癌生存的预测模型：系统评价和外部验证研究。暴击。修订版Oncol。血液学。193104199（2024）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Gao, X. et al. Whole blood DNA methylation aging markers predict colorectal cancer survival: a prospective cohort study. Clin. Epigenetics 12, 184 (2020).Article

Gao，X。等人。全血DNA甲基化衰老标志物预测结直肠癌生存：一项前瞻性队列研究。临床。表观遗传学12184（2020）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Zhang, Y. et al. DNA methylation signatures in peripheral blood strongly predict all-cause mortality. Nat. Commun. 8, 14617 (2017).Article

Zhang，Y。等人。外周血中的DNA甲基化特征强烈预测全因死亡率。国家公社。814617（2017）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Levine, M. E. et al. An epigenetic biomarker of aging for lifespan and healthspan. Aging 10, 573–591 (2018).Article

Levine，M.E.等人。衰老对寿命和健康的表观遗传生物标志物。年龄10573-591（2018）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Lu, A. T. et al. DNA methylation GrimAge strongly predicts lifespan and healthspan. Aging 11, 303–327 (2019).Article

Lu，A.T.等人，DNA甲基化GrimAge强烈预测寿命和健康寿命。年龄11303-327（2019）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Bradshaw, T. J., Huemann, Z., Hu, J. & Rahmim, A. A guide to cross-validation for artificial intelligence in medical imaging. Radio. Artif. Intell. 5, e220232 (2023).Article

Bradshaw，T.J.，Huemann，Z.，Hu，J。＆Rahmim，A。医学成像中人工智能交叉验证指南。收音机。人工制品。因特尔。5，e220232（2023）。文章

Google Scholar

谷歌学者

Yuan, T. et al. Machine learning in the identification of prognostic DNA methylation biomarkers among patients with cancer: a systematic review of epigenome-wide studies. Artif. Intell. Med. 143, 102589 (2023).Article

袁，T。等。机器学习在癌症患者预后DNA甲基化生物标志物鉴定中的应用：表观基因组研究的系统评价。人工制品。因特尔。医学143102589（2023）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Yang, X. et al. Predicting disease-free survival in colorectal cancer by circulating tumor DNA methylation markers. Clin. Epigenetics 14, 160 (2022).Article

Yang，X。等人。通过循环肿瘤DNA甲基化标记预测结直肠癌的无病生存率。临床。表观遗传学14160（2022）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Xiong, Z. et al. EWAS Data Hub: a resource of DNA methylation array data and metadata. Nucleic Acids Res. 48, D890–d895 (2020).Article

Xiong，Z.等人。EWAS数据中心：DNA甲基化阵列数据和元数据的资源。核酸研究48，D890–d895（2020）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Symonds, E. L. et al. Circulating epigenetic biomarkers for detection of recurrent colorectal cancer. Cancer 126, 1460–1469 (2020).Article

Symonds，E.L.等人。循环表观遗传生物标志物用于检测复发性结直肠癌。癌症1261460-1469（2020）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Jin, S. et al. Efficient detection and post-surgical monitoring of colon cancer with a multi-marker DNA methylation liquid biopsy. Proc. Natl Acad. Sci. USA 118, e2017421118 (2021).Article

Jin，S.等人。通过多标记DNA甲基化液体活检对结肠癌进行有效检测和术后监测。程序。国家科学院。科学。美国118，e2017421118（2021）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Hallermayr, A. et al. Somatic copy number alteration and fragmentation analysis in circulating tumor DNA for cancer screening and treatment monitoring in colorectal cancer patients. J. Hematol. Oncol. 15, 125 (2022).Article

Hallermayr，A。等人。循环肿瘤DNA中的体细胞拷贝数改变和片段化分析，用于结直肠癌患者的癌症筛查和治疗监测。J、 血液学。Oncol公司。15125（2022）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Mo, S. et al. Early detection of molecular residual disease and risk stratification for stage I to III colorectal cancer via circulating tumor DNA methylation. JAMA Oncol. 9, 770–778 (2023).Article

Mo，S.等人。通过循环肿瘤DNA甲基化早期检测I至III期结直肠癌的分子残留疾病和风险分层。JAMA Oncol。9770-778（2023）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Bachet, J. B. et al. Circulating tumour DNA at baseline for individualised prognostication in patients with chemotherapy-naïve metastatic colorectal cancer. An AGEO prospective study. Eur. J. Cancer 189, 112934 (2023).Article

Bachet，J.B.等人。在基线时循环肿瘤DNA，用于未接受化疗的转移性结直肠癌患者的个体化预后。AGEO前瞻性研究。《欧洲癌症杂志》189112934（2023）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Yu, C. et al. Association of FOXO3 blood DNA methylation with cancer risk, cancer survival, and mortality. Cells 10, 3384 (2021).Article

Yu，C.等人。FOXO3血液DNA甲基化与癌症风险，癌症存活率和死亡率的关系。细胞103384（2021）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Auclin, E. et al. Subgroups and prognostication in stage III colon cancer: future perspectives for adjuvant therapy. Ann. Oncol. 28, 958–968 (2017).Article

Auclin，E。等。III期结肠癌的亚组和预后：辅助治疗的未来前景。安科。28958-968（2017）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Sadahiro, R. et al. Major surgery induces acute changes in measured DNA methylation associated with immune response pathways. Sci. Rep. 10, 5743 (2020).Article

Sadahiro，R。等人。大手术诱导与免疫应答途径相关的DNA甲基化的急性变化。科学。代表105743（2020）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Robinson, N. et al. Anti-cancer therapy is associated with long-term epigenomic changes in childhood cancer survivors. Br. J. Cancer 127, 288–300 (2022).Article

抗癌治疗与儿童癌症幸存者的长期表观基因组变化有关。《癌症杂志》127288-300（2022）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Fatemi, N. et al. DNA methylation biomarkers in colorectal cancer: Clinical applications for precision medicine. Int. J. Cancer 151, 2068–2081 (2022).Article

Fatemi，N。等。结直肠癌中的DNA甲基化生物标志物：精准医学的临床应用。《国际癌症杂志》1512068-2081（2022）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Bibault, J. E., Chang, D. T. & Xing, L. Development and validation of a model to predict survival in colorectal cancer using a gradient-boosted machine. Gut 70, 884–889 (2021).Article

Bibault，J.E.，Chang，D.T。＆Xing，L。使用梯度增强机器预测结直肠癌存活率的模型的开发和验证。肠道70884-889（2021）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Charlson, M. E., Pompei, P., Ales, K. L. & MacKenzie, C. R. A new method of classifying prognostic comorbidity in longitudinal studies: development and validation. J. Chronic Dis. 40, 373–383 (1987).Article

Charlson，M.E.，Pompei，P.，Ales，K.L。＆MacKenzie，C.R。纵向研究中预后合并症分类的新方法：开发和验证。J、 慢性疾病。40373-383（1987）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Hahn, E. E. et al. Understanding comorbidity profiles and their effect on treatment and survival in patients with colorectal cancer. J. Natl Compr. Cancer Netw. 16, 23–34 (2018).Article

Hahn，E。E。等人。了解结直肠癌患者的合并症概况及其对治疗和生存的影响。J、 天然压缩机。癌症网络。16,23-34（2018）。文章

Google Scholar

谷歌学者

Danielsen, S. A. et al. Phospholipase C isozymes are deregulated in colorectal cancer-insights gained from gene set enrichment analysis of the transcriptome. PLoS ONE 6, e24419 (2011).Article

Danielsen，S.A。等人，磷脂酶C同工酶在结直肠癌中失调，这是从转录组的基因集富集分析中获得的见解。《公共科学图书馆·综合》第6期，第24419页（2011年）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Hajebi Khaniki, S., Shokoohi, F., Esmaily, H. & Kerachian, M. A. Analyzing aberrant DNA methylation in colorectal cancer uncovered intangible heterogeneity of gene effects in the survival time of patients. Sci. Rep. 13, 22104 (2023).Article

Hajebi-Khaniki，S.，Shokoohi，F.，Esmaily，H。＆Kerachian，M.A。分析结直肠癌中异常的DNA甲基化揭示了患者生存时间中基因效应的无形异质性。科学。代表1322104（2023）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Brenner, H., Chang-Claude, J., Seiler, C. M., Rickert, A. & Hoffmeister, M. Protection from colorectal cancer after colonoscopy: a population-based, case-control study. Ann. Intern Med. 154, 22–30 (2011).Article

Brenner，H.，Chang-Claude，J.，Seiler，C.M.，Rickert，A。＆Hoffmeister，M。结肠镜检查后对结直肠癌的保护：一项基于人群的病例对照研究。《实习医学》154，22-30（2011）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Hoffmeister, M. et al. Statin use and survival after colorectal cancer: the importance of comprehensive confounder adjustment. J. Natl Cancer Inst. 107, djv045 (2015).Article

Hoffmeister，M.等人，《结直肠癌后他汀类药物的使用和生存：综合混杂因素调整的重要性》。J、 Natl Cancer Inst.107，djv045（2015）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Carr, P. R. et al. Estimation of absolute risk of colorectal cancer based on healthy lifestyle, genetic risk, and colonoscopy status in a population-based study. Gastroenterology 159, 129–138.e129 (2020).Article

Carr，P.R.等人。在一项基于人群的研究中，基于健康生活方式，遗传风险和结肠镜检查状况估计结直肠癌的绝对风险。胃肠病学159129–138.e129（2020）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Ritchie, M. E. et al. Limma powers differential expression analyses for RNA-sequencing and microarray studies. Nucleic Acids Res. 43, e47 (2015).Article

Ritchie，M.E.等人Limma为RNA测序和微阵列研究提供了差异表达分析的能力。核酸研究43，e47（2015）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Fortin, J. P., Triche, T. J. Jr. & Hansen, K. D. Preprocessing, normalization and integration of the Illumina HumanMethylationEPIC array with minfi. Bioinformatics 33, 558–560 (2017).Article

Fortin，J.P.，Triche，T.J.Jr。＆Hansen，K.D。Illumina HumanMethylationEPIC阵列与minfi的预处理，标准化和整合。生物信息学33558-560（2017）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Tian, Y. et al. ChAMP: updated methylation analysis pipeline for Illumina BeadChips. Bioinformatics 33, 3982–3984 (2017).Article

Tian，Y.等人ChAMP：更新了Illumina BeadChips的甲基化分析流程。生物信息学333982-3984（2017）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Zhou, W., Laird, P. W. & Shen, H. Comprehensive characterization, annotation and innovative use of Infinium DNA methylation BeadChip probes. Nucleic Acids Res. 45, e22 (2017).PubMed

Zhou，W.，Laird，P.W。＆Shen，H。Infinium DNA甲基化BeadChip探针的综合表征，注释和创新使用。核酸研究45，e22（2017）。PubMed出版社

Google Scholar

谷歌学者

Pidsley, R. et al. Critical evaluation of the Illumina MethylationEPIC BeadChip microarray for whole-genome DNA methylation profiling. Genome Biol. 17, 208 (2016).Article

Pidsley，R。等人。Illumina MethylationEPIC BeadChip微阵列用于全基因组DNA甲基化分析的关键评估。基因组生物学。17208（2016）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Alcala, N. et al. Integrative and comparative genomic analyses identify clinically relevant pulmonary carcinoid groups and unveil the supra-carcinoids. Nat. Commun. 10, 3407 (2019).Article

综合和比较基因组分析确定了临床相关的肺类癌组并揭示了超类癌。国家公社。103407（2019）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Teschendorff, A. E. et al. A beta-mixture quantile normalization method for correcting probe design bias in Illumina Infinium 450 k DNA methylation data. Bioinformatics 29, 189–196 (2013).Article

Teschendorff，A.E.等人。一种用于校正Illumina Infinium 450 k DNA甲基化数据中探针设计偏差的β混合物分位数归一化方法。生物信息学29189-196（2013）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Breheny, P. & Huang, J. Group descent algorithms for nonconvex penalized linear and logistic regression models with grouped predictors. Stat. Comput. 25, 173–187 (2015).Article

Breheny，P。＆Huang，J。具有分组预测因子的非凸惩罚线性和逻辑回归模型的组下降算法。统计计算机。。文章

PubMed

PubMed

Google Scholar

谷歌学者

Chen, T. & Guestrin, C. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 785–794 (Association for Computing Machinery, 2016). https://doi.org/10.1145/2939672.2939785Carr, P. R. et al. Healthy lifestyle factors associated with lower risk of colorectal cancer irrespective of genetic risk.

Chen，T。和Guestrin，C。在程序中。第22届ACM SIGKDD知识发现和数据挖掘国际会议785-794（计算机械协会，2016）。https://doi.org/10.1145/2939672.2939785Carr，P.R.等人。健康的生活方式因素与结直肠癌风险降低相关，而与遗传风险无关。

Gastroenterology 155, 1805–1815.e1805 (2018).Article .

胃肠病学1551805-1815.e1805（2018）。文章。

PubMed

PubMed

Google Scholar

谷歌学者

Hoffmeister, M. et al. Colonoscopy and reduction of colorectal cancer risk by molecular tumor subtypes: a population-based case-control study. Am. J. Gastroenterol. 115, 2007–2016 (2020).Article

Hoffmeister，M.等人。结肠镜检查和分子肿瘤亚型降低结直肠癌风险：基于人群的病例对照研究。Am.J.胃肠病学。1152007–2016（2020）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Stekhoven, D. J. & Buhlmann, P. MissForest-non-parametric missing value imputation for mixed-type data. Bioinformatics 28, 112–118 (2012).Article

Stekhoven，D。J。＆Buhlmann，P。MissForest混合型数据的非参数缺失值插补。生物信息学28112-118（2012）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Lazic, S. E. Medical risk prediction models: with ties to machine learning. J. R. Stat. Soc. Ser. A 185, 425–425 (2021).Article

拉齐奇，S.E。医疗风险预测模型：与机器学习有关。J、 R.统计社会服务。A 185425-425（2021）。文章

Google Scholar

谷歌学者

Blanche, P., Kattan, M. W. & Gerds, T. A. The c-index is not proper for the evaluation of t-year predicted risks. Biostatistics 20, 347–357 (2019).Article

Blanche，P.，Kattan，M.W。和Gerds，T.A。c指数不适合评估T年预测风险。生物统计学20347-357（2019）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Just, A. C. et al. Gradient boosting machine learning to improve satellite-derived column water vapor measurement error. Atmos. Meas. Tech. 13, 4669–4681 (2020).Article

Just，A.C.等人。梯度提升机器学习，以改善卫星衍生的柱水汽测量误差。。米亚斯。《技术》134669–4681（2020）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Therneau, T. M. & Grambsch, P. M. Modeling Survival Data: Extending The Cox Model. (Springer New York, 2000).Lang, M. et al. mlr3: a modern object-oriented machine learning framework in R. J. Open Source Softw. 4, 1903 (2019).Article

Therneau，T.M。＆Grambsch，P.M。建模生存数据：扩展Cox模型。（施普林格纽约，2000）。Lang，M。et al。mlr3:R.J.开源软件中的现代面向对象机器学习框架。41903（2019）。文章

Google Scholar

谷歌学者

Mogensen, U. B., Ishwaran, H. & Gerds, T. A. Evaluating random forests for survival analysis using prediction error curves. J. Stat. Softw. 50, 1–23 (2012).Article

Mogensen，U.B.，Ishwaran，H。＆Gerds，T.A。使用预测误差曲线评估随机森林的生存分析。J、 统计软件。50，1-23（2012）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Kang, L., Chen, W., Petrick, N. A. & Gallas, B. D. Comparing two correlated C indices with right-censored survival outcome: a one-shot nonparametric approach. Stat. Med. 34, 685–703 (2015).Article

Kang，L.，Chen，W.，Petrick，N.A。和Gallas，B.D。比较两个相关的C指数与右删失生存结果：一次性非参数方法。《统计医学》34685-703（2015）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Download referencesAcknowledgementsDKFZ clinician scientist program (Z.F.). German Research Council BR 1704/6-1, BR 1704/6-3, BR 1704/6-4, CH 117/1-1, HO 5117/2-1, HO 5117/2-2, HE 5998/2-1, HE 5998/2-2, KL 2354/3-1, KL 2354 3-2, RO 2270/8-1, RO 2270/8-2, BR 1704/17-1, and BR 1704/17-2 (H.B., M.H.).

下载参考文献致谢SDKFZ临床医生科学家计划（Z.F.）。德国研究委员会BR 1704/6-1、BR 1704/6-3、BR 1704/6-4、CH 117/1-1、HO 5117/2-1、HO 5117/2-2、HE 5998/2-1、HE 5998/2-2、KL 2354/3-1、KL 2354 3-2、RO 2270/8-1、RO 2270/8-2、BR 1704/17-1和BR 1704/17-2（H.B.，M.H.）。

Interdisciplinary Research Program of the National Center for Tumor Diseases (NCT), Germany (H.B., M.H.). German Federal Ministry of Education and Research 01KH0404, 01ER0814, 01ER0815, 01ER1505A, 01ER1505B and 01KD2104A (H.B., M.H.). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

德国国家肿瘤疾病中心（NCT）的跨学科研究计划（H.B.，M.H.）。德国联邦教育与研究部01KH0404、01ER0814、01ER0815、01ER1505A、01ER1505B和01KD2104A（H.B.，M.H.）。资助者在研究设计，数据收集和分析，决定发表或准备手稿方面没有任何作用。

We thank the study participants and the interviewers who collected the data. our study team at the Division of Clinical Epidemiology, German Cancer Research Center, Heidelberg, Germany for providing technical assistance, with no compensation outside of salary. We also thank the following hospitals and cooperating institutions that recruited patients for this study: Chirurgische Universitätsklinik Heidelberg, Klinik am Gesundbrunnen Heilbronn, St Vincentiuskrankenhaus Speyer, St Josefskrankenhaus Heidelberg, Chirurgische Universitätsklinik Mannheim, Diakonissenkrankenhaus Speyer, Krankenhaus Salem Heidelberg, Kreiskrankenhaus Schwetzingen, St Marienkrankenhaus Ludwigshafen, Klinikum Ludwigshafen, Stadtklinik Frankenthal, Diakoniekrankenhaus Mannheim, Kreiskrankenhaus Sinsheim, Klinikum am Plattenwald Bad Friedrichshall, Kreiskrankenhaus Weinheim, Kreiskrankenhaus Eberbach, Kreiskrankenhaus Buchen, Kreiskrankenhaus Mosbach, Enddarmzentrum Mannheim, Kreiskrankenhaus Brackenheim and Cancer Registry of Rhineland-Palatinate, Mainz.FundingOpen Access funding enabled and organized by Projekt DEAL.Author informatio.

我们感谢研究参与者和收集数据的采访者。。我们还感谢以下医院和合作机构招募患者进行这项研究：海德堡奇鲁吉斯大学、海德堡克林克斯大学、海德堡克林克斯大学、海德堡圣文森特·克兰肯豪斯·斯派尔大学、海德堡圣约瑟夫斯克兰肯豪斯大学、曼海姆奇鲁吉斯大学、迪亚科尼森克兰肯豪斯·斯派尔大学、海德堡克兰肯豪斯·塞勒姆大学、施韦津根大学、路德维希港圣玛丽·克兰肯豪斯大学、路德维希港大学、斯塔德克林克·弗兰肯塔尔大学、迪亚科尼·克兰肯豪斯曼海姆（Mannheim）、克雷斯克兰肯豪斯（Kreiskrankenhaus Sinsheim）、克莱尼库姆（Klinikum am Plattenwald Bad Friedrichshall）、克雷斯克兰肯豪斯（Kreiskrankenhaus Weinheim）、克雷斯克兰肯豪斯（Kreiskrankenhaus Eberbach）、克雷斯克兰肯豪斯（Kreiskrankenhaus Buchen）、克雷斯克兰肯豪斯·莫斯巴赫（Kreiskrankenhaus Mosbach）、恩达姆·岑特鲁姆·曼海姆（Enddarmzentrum Mannheim）、克雷斯克兰肯豪斯·布拉肯海姆（Kreiskrankenhaus Brackenheim）和美因茨莱茵兰-帕拉提纳州癌症。资金开放获取资金由Projekt交易启用和组织。作者信息。

PubMed Google ScholarDominic EdelmannView author publicationsYou can also search for this author in

PubMed Google ScholarDominic EdelmannView作者出版物您也可以在

PubMed Google ScholarTanwei YuanView author publicationsYou can also search for this author in

PubMed Google ScholarTanwei YuanView作者出版物您也可以在

PubMed Google ScholarBruno Christian KöhlerView author publicationsYou can also search for this author in

PubMed Google ScholarBruno Christian KöhlerView作者出版物您也可以在

PubMed Google ScholarMichael HoffmeisterView author publicationsYou can also search for this author in

PubMed Google Scholarmamichael HoffmeisterView作者出版物您也可以在

PubMed Google ScholarHermann BrennerView author publicationsYou can also search for this author in

PubMed谷歌学者Hermann BrennerView作者出版物您也可以在

PubMed Google ScholarContributionsZ.F. contributed to concept and design, development of methodology, acquisition of data (acquired and managed patients, provided facilities, etc.), analysis and interpretation of data (e.g., statistical analysis, biostatistics, computational analysis), writing of the manuscript, critical review and revision of the manuscript.

PubMed谷歌学术贡献。F、 有助于概念和设计，方法的开发，数据的获取（获得和管理的患者，提供的设施等），数据的分析和解释（例如统计分析，生物统计学，计算分析），手稿的撰写，手稿的批判性审查和修订。

D.E. contributed to development of methodology, acquisition of data (acquired and managed patients, provided facilities, etc.), analysis and interpretation of data (e.g., statistical analysis, biostatistics, computational analysis), critical review, and revision of the manuscript. T.Y. contributed to analysis and interpretation of data (e.g., statistical analysis, biostatistics, computational analysis), critical review, and revision of the manuscript.

D、 E.有助于方法的发展，数据的获取（获得和管理的患者，提供的设施等），数据的分析和解释（例如统计分析，生物统计学，计算分析），批判性审查和手稿的修订。T、 Y.有助于数据的分析和解释（例如，统计分析，生物统计学，计算分析），批判性审查和手稿的修订。

B.C.K. contributed to analysis and interpretation of data (e.g., statistical analysis, biostatistics, computational analysis), critical review, and revision of the manuscript. M.H. contributed to analysis and interpretation of data (e.g., statistical analysis, biostatistics, computational analysis), critical review and revision of the manuscript, administrative, technical, or material support (i.e., reporting or organizing data, constructing databases).

B、 C.K.为数据的分析和解释（例如统计分析，生物统计学，计算分析），批判性审查和手稿的修订做出了贡献。M、 H.有助于数据的分析和解释（例如，统计分析，生物统计学，计算分析），稿件的批判性审查和修订，行政，技术或物质支持（即报告或组织数据，构建数据库）。

H.B. contributed to concept and design, development of methodology, acquisition of data (acquired and managed patients, provided facilities, etc.), analysis and interpretation of data (e.g., statistical analysis, biostatistics, computational analysis), writing of the manuscript, critical review and revision of the manuscript, administrative, technical, or material support (i.e., reporting or organizing data, constructing databases), study supervision.Corresponding authorCorrespondence to.

H、 B.有助于概念和设计，方法的开发，数据的获取（获得和管理的患者，提供的设施等），数据的分析和解释（例如统计分析，生物统计学，计算分析），手稿的撰写，手稿的批判性审查和修订，行政，技术或物质支持（即报告或组织数据，构建数据库），研究监督。对应作者对应。

Hermann Brenner.Ethics declarations

赫尔曼·布伦纳。道德宣言

Competing interests

相互竞争的利益

The authors declare no competing interests.

作者声明没有利益冲突。

Additional informationPublisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.Supplementary informationSupplementary InformationRights and permissions

。补充信息补充信息权限

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

开放获取本文是根据知识共享署名4.0国际许可证授权的，该许可证允许以任何媒体或格式使用，共享，改编，分发和复制，只要您对原始作者和来源给予适当的信任，提供知识共享许可证的链接，并指出是否进行了更改。

The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

本文中的图像或其他第三方材料包含在文章的知识共享许可中，除非在材料的信用额度中另有说明。如果材料未包含在文章的知识共享许可中，并且您的预期用途不受法律法规的许可或超出许可用途，则您需要直接获得版权所有者的许可。

To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/..

要查看此许可证的副本，请访问http://creativecommons.org/licenses/by/4.0/..

Reprints and permissionsAbout this articleCite this articleFan, Z., Edelmann, D., Yuan, T. et al. Developing survival prediction models in colorectal cancer using epigenome-wide DNA methylation data from whole blood.

转载和许可本文引用本文Fan，Z.，Edelmann，D.，Yuan，T。等人使用全血表观基因组DNA甲基化数据开发结直肠癌生存预测模型。

npj Precis. Onc. 8, 191 (2024). https://doi.org/10.1038/s41698-024-00689-5Download citationReceived: 17 May 2024Accepted: 28 August 2024Published: 06 September 2024DOI: https://doi.org/10.1038/s41698-024-00689-5Share this articleAnyone you share the following link with will be able to read this content:Get shareable linkSorry, a shareable link is not currently available for this article.Copy to clipboard.

npj精度。Onc。8191（2024）。https://doi.org/10.1038/s41698-024-00689-5Download引文接收日期：2024年5月17日接受日期：2024年8月28日发布日期：2024年9月6日OI：https://doi.org/10.1038/s41698-024-00689-5Share本文与您共享以下链接的任何人都可以阅读此内容：获取可共享链接对不起，本文目前没有可共享的链接。复制到剪贴板。

Provided by the Springer Nature SharedIt content-sharing initiative

由Springer Nature SharedIt内容共享计划提供