|
|
基于随机生存森林的低级别脑胶质瘤复发预测模型
|
Abstract:
背景：低级别脑胶质瘤(LGG)患者在治疗后仍可能面临复发的风险。本研究旨在考虑复发与死亡相关性的基础上分析影响LGG患者复发的因素，并建立复发预测模型。方法：收集来自TCGA数据库LGG患者的临床数据，最终纳入457例LGG患者。建立联合脆弱模型分析复发危险因素，采用随机生存森林(Random Survival Forest，RSF)的方法建立LGG复发预测模型，同时建立Cox模型作为比较。结果：主要治疗结局、年龄、ICD-O-3组织学编码、首次症状持续时间、术后、肿瘤组织学分级和放射治疗作为预测因子纳入LGG复发预测模型。与Cox模型相比，RSF模型具有较好的区分度和校准度，具体表现为，基于bootstrap重抽样数据集计算1、3和、5年RSF的C指数分别为0.813、0.748和0.745，Cox分别为0.824、0.724和0.727，RSF在1、3、5年的AUC值分别为0.824、0.746和0.754，而Cox分别为0.833、0.713和0.730；校准曲线也表明RSF模型表现更优。结论：复发和死亡事件不应独立看待，RSF在复杂生存数据的预测建模方面具有优势，未来期待更多探索预测脑胶质瘤患者复发的方法和工具，且这些方法能得到在临床上的实践应用。
Background: Low-Grade Glioma (LGG) patients face risks of recurrence after treatment. Our study aims to analyze recurrence risk factors, considering the association between recurrence and death, and to develop an improved recurrence prognosis prediction model for LGG patients. Methods: We collected clinical data from TCGA, 457 LGG patients were finally included. We developed a Joint Frailty model to analyze recurrence risk factors. We employed the Random Survival Forest (RSF) model for recurrence prognosis prediction, with a Cox model for comparison. Results: Prognostic factors, including primary therapy outcome, age, ICD-O-3 histology, first presenting symptom dura-tion, postoperative, neoplasm histologic grade, and radiation therapy, were integrated into the LGG recurrence prediction model. The RSF model excelled in discrimination and calibration compared to the Cox model. RSF’s C-index for 1, 3, and 5 years on bootstrap validation was 0.813, 0.748, and 0.745, respectively, versus Cox’s 0.824, 0.724, and 0.727. RSF’s AUC values for 1, 3, and 5 years by bootstrapping were 0.824, 0.746, and 0.754, respectively, versus Cox's 0.833, 0.713, and 0.730. The calibration curve also favored the RSF model. Conclusions: Recurrence and death events should not be treated independently. RSF has advantages for predictive modeling of complex survival data. We foresee further research to enhance LGG recurrence prediction, with potential practical clinical ap-plications in the future.
| [1] | Ostrom, Q.T., Gittleman, H., Farah, P., Ondracek, A., Chen, Y., Wolinsky, Y., Stroup, N.E., Kruchko, C. and Barnholtz-Sloan, J.S. (2013) CBTRUS Statistical Report: Primary Brain and Central Nervous System Tumors Diagnosed in the United States in 2006-2010. Neuro-Oncology, 15, ii1-ii56. https://doi.org/10.1093/neuonc/not151 |
| [2] | Louis, D.N., Perry, A., Reifen-berger, G., von Deimling, A., Figarella-Branger, D., Cavenee, W.K., Ohgaki, H., Wiestler, O.D., Kleihues, P. and Ellison, D.W. (2016) The 2016 World Health Organization Classification of Tumors of the Central Nervous System: A Summary. Acta Neu-ropathologica, 131, 803-820.
https://doi.org/10.1007/s00401-016-1545-1 |
| [3] | Kumar A.A. and Abraham Koshy, A. (2017) Regression of Recurrent High-Grade Glioma with Temozolomide, Dexamethasone, and Levetiracetam: Case Report and Review of the Literature. World Neurosurgery, 108, 990.e11-990.e16.
https://doi.org/10.1016/j.wneu.2017.08.136 |
| [4] | Barnholtz-Sloan, J.S., Ostrom, Q.T. and Cote, D. (2018) Epidemiology of Brain Tumors. Neurologic Clinics, 36, 395-419. https://doi.org/10.1016/j.ncl.2018.04.001 |
| [5] | Tan, A.C., Ashley, D.M., López, G.Y., Malinzak, M., Friedman, H.S. and Khasraw, M. (2020) Management of Glioblastoma: State of the Art and Future Directions. CA: A Cancer Journal for Clinicians, 70, 299-312.
https://doi.org/10.3322/caac.21613 |
| [6] | Weller, M., Felsberg, J., Hartmann, C., Berger, H., Steinbach, J.P., Schramm, J., Westphal, M., Schackert, G., Simon, M., Tonn, J.C., Heese, O., Krex, D., Nikkhah, G., Pietsch, T., Wiestler, O., Reifenberger, G., von Deimling, A. and Loeffler, M. (2009) Molecular Predictors of Progression-Free and Overall Survival in Patients with Newly Diagnosed Glioblastoma: A Prospective Translational Study of the German Glioma Network. Journal of Clinical On-cology, 27, 5743-5750. https://doi.org/10.1200/JCO.2009.23.0805 |
| [7] | Jiang, H., Zhu, Q., Wang, X., Li, M., Shen, S., Yang, C., Zhao, X., Li, M., Ma, G., Zhao, X., Chen, X., Yang, J. and Lin, S. (2023) Characterization and Clinical Implications of Different Malignant Transformation Patterns in Diffuse Low-Grade Gliomas. Cancer Science, 114, 3708-3718. https://doi.org/10.1111/cas.15889 |
| [8] | Teng, C., Zhu, Y., Li, Y., Dai, L., Pan, Z., Wanggou, S. and Li, X. (2022) Recur-rence- and Malignant Progression-Associated Biomarkers in Low-Grade Gliomas and Their Roles in Immunotherapy. Frontiers in Immunology, 13, Article ID: 899710. https://doi.org/10.3389/fimmu.2022.899710 |
| [9] | Mazroui, Y., Mathou-lin-Pélissier, S., Macgrogan, G., Brouste, V. and Rondeau, V. (2013) Multivariate Frailty Models for Two Types of Recurrent Events with a Dependent Terminal Event: Application to Breast Cancer Data. Biometrical Journal, 55, 866-884. https://doi.org/10.1002/bimj.201200196 |
| [10] | Pasin, O., Dirican, A., Ankarali, H., Disci, R. and Karanlik, H. (2020) As-sessment of Death Risk of Breast Cancer Patients with Joint Frailty Models. Saudi Medical Journal, 41, 491-498. https://doi.org/10.15537/smj.2020.5.25065 |
| [11] | Rahman, F. and Begum, M. (2018) Survival Analysis of Recurrent Events on Prostate Cancer: Facts from Cancer Genome. Journal of Statistical Research, 51, 145-164. https://doi.org/10.47302/jsr.2017510204 |
| [12] | Talebi-Ghane, E., Baghestani, A., Zayeri, F., Rondeau, V. and Akhavan, A. (2021) Joint Frailty Model for Recurrent Events and Death in Presence of Cure Fraction: Application to Breast Cancer Data. Biometrical Journal, 63, 725-744.
https://doi.org/10.1002/bimj.201900113 |
| [13] | Charles-Nelson, A., Katsahian, S. and Schramm, C. (2019) How to Analyze and Interpret Recurrent Events Data in the Presence of a Terminal Event: An Application on Readmission after Colorectal Cancer Surgery. Statistics in Medicine, 38, 3476-3502. https://doi.org/10.1002/sim.8168 |
| [14] | Li, G., Wu, F., Zeng, F., Zhai, Y., Feng, Y., Chang, Y., Wang, D., Jiang, T. and Zhang, W. (2021) A Novel DNA Repair-Related Nomogram Predicts Survival in Low-Grade Gliomas. CNS Neuroscience & Therapeutics, 27, 186-195.
https://doi.org/10.1111/cns.13464 |
| [15] | Du, P., Chen, H., Lv, K. and Geng, D. (2022) A Survey of Radiomics in Precision Diagnosis and Treatment of Adult Gliomas. Journal of Clinical Medicine, 11, Article 3802. https://doi.org/10.3390/jcm11133802 |
| [16] | Wei, R., Zhao, C., Li, J., Yang, F., Xue, Y. and Wei, X. (2022) Online Calcu-lator to Predict Early Mortality in Patient with Surgically Treated Recurrent Lower-Grade Glioma. BMC Cancer, 22, Article No. 114.
https://doi.org/10.1186/s12885-022-09225-9 |
| [17] | Wang, T., Zhu, C., Zheng, S., Liao, Z., Chen, B., Liao, K., Yang, X., Zhou, Z., Bai, Y., Wang, Z., Hou, Y., Qiu, Y. and Huang, R. (2021) A Novel Nomogram for Predicting the Risk of Short-Term Recurrence After Surgery in Glioma Patients. Frontiers in Oncology, 11, Article ID: 740413. https://doi.org/10.3389/fonc.2021.740413 |
| [18] | Rondeau, V., Mathoulin-Pelissier, S., Jacqmin-Gadda, H., Brouste, V. and Soubeyran, P. (2007) Joint Frailty Models for Recurring Events and Death Using Maximum Penalized Likelihood Estimation: Application on Cancer Events. Biostatistics, 8, 708-721. https://doi.org/10.1093/biostatistics/kxl043 |
| [19] | Ishwaran, H., Kogalur, U.B., Blackstone, E.H. and Lauer, M.S. (2008) Random Survival Forests. Annals of Applied Statistics, 2, 841-860. https://doi.org/10.1214/08-AOAS169 |
| [20] | Collins, G.S., Reitsma, J.B., Altman, D.G. and Moons, K.G.M. (2015) Trans-parent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD): The TRIPOD State-ment. BMJ, 350, g7594.
https://doi.org/10.1136/bmj.g7594 |
| [21] | Zhang, M., Wang, X., Chen, X., Zhang, Q. and Hong, J. (2020) Novel Im-mune-Related Gene Signature for Risk Stratification and Prognosis of Survival in Lower-Grade Glioma. Frontiers in Genetics, 11, Article 363.
https://doi.org/10.3389/fgene.2020.00363 |
| [22] | Zhu, Q., Liang, Y., Fan, Z., Liu, Y., Zhou, C., Zhang, H., He, L., Li, T., Yang, J., Zhou, Y., Wang, J. and Wang, L. (2022) Development and Validation of a Novel Survival Prediction Model for Newly Diagnosed Lower-Grade Gliomas. Neurosurgical Focus, 52, E13. https://doi.org/10.3171/2022.1.FOCUS21596 |
| [23] | Schwartz, L.H., Litière, S., de Vries, E., Ford, R., Gwyther, S., Man-drekar, S., Shankar, L., Bogaerts, J., Chen, A., Dancey, J., Hayes, W., Hodi, F.S., Hoekstra, O.S., Huang, E.P., Lin, N., Liu, Y., Therasse, P., Wolchok, J.D. and Seymour, L. (2016) RECIST 1.1—Update and Clarification: From the RECIST Committee. European Journal of Cancer, 62, 132-137. https://doi.org/10.1016/j.ejca.2016.03.081 |
| [24] | Lin, J., Yin, M., Liu, L., Gao, J., Yu, C., Liu, X., Xu, C. and Zhu, J. (2022) The Development of a Prediction Model Based on Random Survival Forest for the Postoperative Prognosis of Pancreatic Cancer: A SEER-Based Study. Cancers, 14, Article 4667. https://doi.org/10.3390/cancers14194667 |
| [25] | Zhang, L., Huang, T., Xu, F., Li, S., Zheng, S., Lyu, J. and Yin, H. (2022) Prediction of Prognosis in Elderly Patients with Sepsis Based on Machine Learning (Random Survival Forest). BMC Emergen-cy Medicine, 22, Article No. 26.
https://doi.org/10.1186/s12873-022-00582-z |
| [26] | Roshanaei, G., Safari, M., Faradmal, J., Abbasi, M. and Khazaei, S. (2022) Factors Affecting the Survival of Patients with Colorectal Cancer Using Random Survival Forest. Journal of Gastroin-testinal Cancer, 53, 64-71.
https://doi.org/10.1007/s12029-020-00544-3 |
| [27] | Gittleman, H., Sloan, A.E. and Barnholtz-Sloan, J.S. (2020) An Inde-pendently Validated Survival Nomogram for Lower-Grade Glioma. Neuro-Oncology, 22, 665-674. https://doi.org/10.1093/neuonc/noz191 |
| [28] | Hazewinkel, A.-D., Gelderblom, H. and Fiocco, M. (2022) Prediction Models with Survival Data: A Comparison between Machine Learning and the Cox Proportional Hazards Model. Medrxiv, 1-15.
https://doi.org/10.1101/2022.03.29.22273112 |
