Survival prediction in elderly patients with colorectal cancer complicated by reduced skeletal muscle mass

Wang Cuicui; Yao Junying; Li Qian; Zhu Li; Fan Min

doi:10.16689/j.cnki.cn11-9349/r.2026.01.018

PDF(4076 KB)

Electronic Journal of Metabolism and Nutrition of Cancer ›› 2026, Vol. 13 ›› Issue (1) : 134-141. DOI: 10.16689/j.cnki.cn11-9349/r.2026.01.018

Original Articles

Survival prediction in elderly patients with colorectal cancer complicated by reduced skeletal muscle mass

¹Wang Cuicui, ¹Yao Junying, ¹Li Qian, ²Zhu Li, ¹Fan Min

Author information +

History +

Abstract

Objective To develop and validate a survival prediction model for elderly patients with colorectal cancer complicated by reduced skeletal muscle mass based on an interpretable Extreme Gradient Boosting (XGBoost) algorithm. Methods A total of 528 elderly patients diagnosed with colorectal cancer complicated by reduced skeletal muscle mass at the People's Hospital of Xinjiang Uygur Autonomous Region from July 2018 to December 2023 were retrospectively enrolled. General clinical characteristics, laboratory test results, and imaging data were collected. Least absolute shrinkage and selection operator (Lasso) regression and the XGBoost algorithm were used for feature selection. Feature importance was further interpreted using SHapley Additive exPlanations (SHAP) values, and a nomogram prediction model was constructed based on a multivariable Cox proportional hazards regression model. Model performance was evaluated using the concordance index (C-index) and time-dependent receiver operating characteristic (ROC) curves along with the corresponding area under the curve (AUC). Results The final model incorporated age, prognostic nutritional index (PNI), controlling nutritional status (CONUT) score, carcinoembryonic antigen (CEA), carbohydrate antigen 242 (CA242), and C-reactive protein (CRP) as risk factors, while skeletal muscle index (SMI) was identified as a protective factor. The XGBoost model demonstrated good discrimination and robustness in both the training and validation cohorts. Calibration curves showed good agreement, and decision curve analysis indicated favorable clinical utility. Conclusion The interpretable XGBoost-based survival prediction model can effectively identify key prognostic factors associated with overall survival (OS) and cancer-specific survival (CSS) in elderly patients with colorectal cancer complicated by reduced skeletal muscle mass, providing a reference for clinical risk stratification and individualized intervention.

Key words

Elderly colorectal cancer / Reduced skeletal muscle mass / Extreme gradient boosting algorithm / Nomogram / Survival prediction model / Controlling nutritional status score / Prognostic analysis

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Wang Cuicui, Yao Junying, Li Qian, Zhu Li, Fan Min. Survival prediction in elderly patients with colorectal cancer complicated by reduced skeletal muscle mass[J]. Electronic Journal of Metabolism and Nutrition of Cancer. 2026, 13(1): 134-141 https://doi.org/10.16689/j.cnki.cn11-9349/r.2026.01.018

References

[1] FERLAY J, ERVIK M, LAM F, et al. Global cancer statistics 2022: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin,2024,74(3):229-263.
[2] XIE B, WANG J, WANG C, et al. Determining the effects of social-environmental factors on the incidence and mortality of lung cancer in China based on remote sensing and GIS technology during 2007-2016[J]. BMC Public Health,2025,25(1):1673.
[3] MIYAMOTO Y, BABA Y, SAKAMOTO Y, et al. Sarcopenia is a negative prognostic factor after curative resection of colorectal cancer[J]. Ann Surg Oncol,2015,22(8):2663-2668.
[4] HE J, LUO W, HUANG Y, et al. Sarcopenia as a prognostic indicator in colorectal cancer: An updated meta-analysis[J]. Front Oncol,2023,13:1247341.
[5] LIN W L, LIU Y, ZHANG J, et al. Sarcopenia and survival in colorectal cancer: a systematic review and meta-analysis[J]. J Gastroenterol Hepatol,2024,39(7):1598-1608.
[6] CHO H J, KANG J. Sarcopenia diagnosis in patients with colorectal cancer: a review of computed tomography-based assessments and emerging ways to enhance practicality[J]. Ann Surg Treat Res,2024,106(6):305-312.
[7] CHO H J, LEE H S, KANG J. Varying clinical relevance of sarcopenia and myosteatosis according to age among patients with postoperative colorectal cancer[J]. J Nutr Health Aging,2024,28(7):100243.
[8] VERGARA-FERNANDEZ O, TREJO-AVILA M, SALGADO-NESME N. Sarcopenia in patients with colorectal cancer: a comprehensive review[J]. World J Clin Cases,2020,8(7):1188-1202.
[9] OJIMA Y, HARANO M, SUMITANI D, et al. Impact of preoperative skeletal muscle mass and quality on the survival of elderly patients after curative resection of colorectal cancer[J]. J Anus Rectum Colon,2019,3(4):143-151.
[10] RIAD M, HASSAN M, NAIR K, et al. Impact of neoadjuvant chemotherapy on skeletal muscle mass in colorectal cancer patients undergoing curative surgical resection: a single-centre retrospective observational study[J]. Cureus, 2025, 17(8): e89389.
[11] CHANG Y Y, CHENG B. Prognostic impact of myosteatosis in patients with colorectal cancer undergoing curative surgery: an updated systematic review and meta-analysis[J]. Front Oncol,2024,14:1388001.
[12] XIAO J, CAAN B J, CESPEDES FELICIANO E M, et al. Association of low muscle mass and low muscle radiodensity with morbidity and mortality for colon cancer surgery[J]. JAMA Surg,2020,155(10):942-949.
[13] LIM J Y, KIM Y M, LEE H S, et al. Skeletal muscle gauge prediction by a machine learning model in patients with colorectal cancer[J]. Nutrition,2023,115:112146.
[14] SORIA-UTRILLA V, SáNCHEZ-TORRALVO F J, PALMAS-CANDIA F X, et al. AI-assisted body composition assessment using CT imaging in colorectal cancer patients: predictive capacity for sarcopenia and malnutrition diagnosis[J]. Nutrients,2024,16(12):1864.
[15] SEOK M, KIM W, KIM J. Machine learning for sarcopenia prediction in the elderly using socioeconomic, infrastructure, and quality-of-life data[J]. Healthcare (Basel),2023,11(21):2854.
[16] PAVÓN-PULIDO N, DOMINGUEZ L, BLASCO-GARCÍA J D, et al. Identification of predictors of sarcopenia in older adults using machine learning: English longitudinal study of ageing[J]. J Clin Med,2024,13(22):6841.
[17] PRADO C M, LIEFFERS J R, MCCARGAR L J, et al. Prevalence and clinical implications of sarcopenic obesity in patients with solid tumours of the respiratory and gastrointestinal tracts: a population-based study[J]. Lancet Oncol,2008,9(7):629-635.
[18] ISEKI Y, SHIBUTANI M, MAEDA K, et al. Impact of the preoperative controlling nutritional status (CONUT) score on the survival after curative surgery for colorectal cancer[J]. PLoS One, 2015, 10(7): e0132488.
[19] TOKUNAGA R, SAKAMOTO Y, NAKAGAWA S, et al. Conut: a novel independent predictive score for colorectal cancer patients undergoing potentially curative resection[J]. Int J Colorectal Dis,2017,32(1):99-106.
[20] HAYAMA T, OZAWA T, OKADA Y, et al. The pretreatment controlling nutritional status (CONUT) score is an independent prognostic factor in patients undergoing resection for colorectal cancer[J]. Sci Rep,2020,10(1):13239.
[21] SHANG J, WEI J. Prognostic significance of the pretreatment controlling nutritional status score in colorectal cancer patients: An updated meta-analysis with 24 cohort studies[J]. Front Nutr,2025,12:1560355.
[22] CARPELAN-HOLMSTRM M, HAGLUND C, LUNDIN J, et al. Pre-operative serum levels of CA 242 and CEA predict outcome in colorectal cancer[J]. Eur J Cancer,1996,32A(7):1156-1161.
[23] VON KLEIST S, HESSE Y, KANANEEH H. Comparative evaluation of four tumor markers, CA 242, CA 19/9, TPA and CEA in carcinomas of the colon[J]. Anticancer Res,1996,16(4B):2325-2331.
[24] CENDRA A S, PEKAREK L, OSPINO L R, et al. Predictive and prognostic biomarkers of recurrence in locoregional colorectal cancer[J]. J Cancer,2025,16(10):3024-3039.
[25] RAMPHAL W, BOEDING J R E, VAN IWAARDEN M, et al. Serum carcinoembryonic antigen to predict recurrence in the follow-up of patients with colorectal cancer[J]. Int J Biol Markers,2019,34(1):60-68.
[26] HWANG S H, SHIN S H, KIM Y J, et al. Risk factors for recurrence in stage I colorectal cancer after curative resection: a systematic review and meta-analysis[J]. Ann Surg Treat Res,2025,108(1):39-48.
[27] YANG X Q, CHEN C, PENG C W, et al. Carbohydrate antigen 242 highly consists with carbohydrate antigen 19-9 in diagnosis and prognosis of colorectal cancer: study on 185 cases[J]. Med Oncol,2012,29(2):1030-1036.
[28] KIM H G, YANG S Y, HAN Y D, et al. Association of perioperative serum carcinoembryonic antigen level and recurrence in low-risk stage IIA colon cancer[J]. PLoS One, 2021, 16(6): e0252566.
[29] KIM C W, YOON Y S, PARK I J, et al. Elevation of preoperative s-CEA concentration in stage IIA colorectal cancer can also be a high risk factor for stage II patients[J]. Ann Surg Oncol,2013,20(9):2914-2920.
[30] HUANG C S, CHEN C Y, HUANG L K, et al. Prognostic value of postoperative serum carcinoembryonic antigen levels in colorectal cancer patients who smoke[J]. PLoS One, 2020, 15(6): e0233687.
[31] KIM E S, KIM S Y, MOON A. C-reactive protein signaling pathways in tumor progression[J]. Biomol Ther (Seoul),2023,31(5):473-483.
[32] ZHOU Q P, LI X J. C-reactive protein to albumin ratio in colorectal cancer: a meta-analysis of prognostic value[J]. Dose Response,2019,17(4):1559325819889814.
[33] FURUKAWA S, HIRAKI M, KIMURA N, et al. The potential of the C-reactive protein-albumin-lymphocyte (CALLY) index as a prognostic biomarker in colorectal cancer[J]. Cancer Diagn Progn,2025,5(3):370-377.
[34] SUN J, LI Z, ZHU X. Prognostic role of prognostic nutritional index in patients with bladder cancer: a systematic review and meta-analysis[J]. Front Oncol,2024,14:1486389.
[35] YANG Y, GAO P, CHEN X, et al. Prognostic significance of preoperative prognostic nutritional index in colorectal cancer: results from a retrospective cohort study and a meta-analysis[J]. Oncotarget,2016,7(36):58543-58552.