Home    中文  
 
  • Search
  • lucene Search
  • Citation
  • Fig/Tab
  • Adv Search
Just Accepted  |  Current Issue  |  Archive  |  Featured Articles  |  Most Read  |  Most Download  |  Most Cited

Chinese Journal of Colorectal Diseases(Electronic Edition) ›› 2025, Vol. 14 ›› Issue (03): 242-250. doi: 10.3877/cma.j.issn.2095-3224.2025.03.005

• Original Articles • Previous Articles     Next Articles

Construction and validation of an early stoma complication prediction model for colorectal cancer patients

Yan Zhou1, Zeyang Zhou1, Xinmeng Cheng1, Yue'e He1, Xiangyong Li1,(), Yong Wu1,()   

  1. 1. Department of Gastrointestinal Surgery,the Second Affiliated Hospital of Soochow University,Suzhou 215004,China
  • Received:2024-10-28 Online:2025-06-25 Published:2025-06-26
  • Contact: Xiangyong Li, Yong Wu

Abstract:

Objective

To analyze and explore the risk factors for early stoma complications in patients with colorectal cancer after surgery and to construct a visual prediction model.

Methods

This study retrospectively collected and analyzed the clinicopathological data and related surgical information of colorectal cancer patients who underwent enterostomy in the Department of Gastrointestinal Surgery of the Second Affiliated Hospital of Soochow University from January 2018 to January 2021. The Logistic regression analyses were used to identify independent risk factors for stoma complications. Subsequently,a nomogram was constructed, and the model was validated through 1 000 bootstrap resamples based on the Bootstrap method. A receiver operating characteristic (ROC) curve was plotted, and the accuracy and clinical applicability of the nomogram prediction model were evaluated by calculating the area under the curve (AUC),Hosmer-Lemeshow goodness-of-fit test, calibration curve, and decision curve analysis (DCA).

Results

A total of 267 stoma patients were ultimately included in the analysis, among which 71 patients observed varying degrees of stoma complications. The multivariate Logistic regression results showed that age (OR=0.040,P=2.509), BMI (OR=5.119, P<0.001), serum albumin (OR=0.168, P<0.001), skin folds (OR=9.854, P<0.001),and history of abdominal surgery (OR=23.331, P<0.001) were independent predictors of early complications in stoma patients (P<0.05). A nomogram model was constructed based on these five independent predictors.The AUCs for the training set and validation set were 0.880 (95%CI: 0.820~0.940) and 0.861 (95%CI:0.770~0.953), respectively. The Hosmer-Lemeshow test showed good agreement between the prediction model and the actual incidence of stoma complications (P>0.05). The DCA curve indicated that the model had a high net benefit.

Conclusion

The predictive model demonstrates good performance, aiding healthcare providers in promptly identifying the risk of early complications in patients with intestinal stomas and facilitating timely interventions.

Key words: Colorectal neoplasms, Stoma complications, Risk factors, Nomogram model

京ICP 备07035254号-20
Copyright © Chinese Journal of Colorectal Diseases(Electronic Edition), All Rights Reserved.
Tel: 0086-010-87788026 E-mail: cjcd_editor@vip.163.com
Powered by Beijing Magtech Co. Ltd