Scholarlink

Background <p>Successful stoma reversal is a critical concern for patients undergoing rectal cancer surgery, yet it is often hindered by multiple risk factors. This study aimed to develop and validate a predictive model to assess the feasibility of ileostomy reversal after rectal cancer resection while concurrently investigating whether robotic surgery offers any advantage in prophylactic stoma reversal.</p> Methods <p>We retrospectively analyzed data from two large medical centers. Three machine learning algorithms (Random Forest, XGBoost, Decision Tree) and traditional logistic regression were used to construct prediction models. The dataset was divided chronologically into Cohort 1 and Cohort 2. Predictors were selected through univariate screening followed by multivariate analysis. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA).</p> Results <p>The logistic regression model outperformed the machine learning models, achieving an AUC of 0.856 in the training set and 0.831 in the internal validation set. External validation in Cohort 2 yielded an AUC of 0.780. DCA confirmed a positive net clinical benefit at threshold probabilities &gt; 0.1, and calibration curves showed excellent agreement between predicted and observed outcomes. AL, anastomotic stenosis, BMI, diabetes, tumor distance from the anal verge, neoadjuvant chemoradiotherapy, and surgical approach were identified as key risk factors for permanent stoma. Furthermore, robotic surgery demonstrated potential advantages in preserving anal function and reducing anastomotic complications, which may indirectly promote successful stoma reversal.</p> Conclusions <p>We developed and validated a clinically useful nomogram that effectively predicts the likelihood of successful stoma reversal after rectal cancer surgery. The model highlights the significant impact of anastomotic-related complications and patient-specific factors on stoma permanence. These findings can assist clinicians in preoperative counseling and personalized postoperative management. Robotic surgery may offer functional and technical benefits that support stoma reversal, though further prospective studies are warranted to confirm these observations.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Development and validation of nomogram about conversion from temporary to permanent stoma in rectal cancer based on machine learning and traditional model—does robotic surgery have competitive advantages?

  • 期刊论文

  • 发表日期：

    2026年2月24日

查看全文
  • Bing Ji,
  • Qiou Gu,
  • Andong Xu,
  • Jingwei Cui

摘要

Background

Successful stoma reversal is a critical concern for patients undergoing rectal cancer surgery, yet it is often hindered by multiple risk factors. This study aimed to develop and validate a predictive model to assess the feasibility of ileostomy reversal after rectal cancer resection while concurrently investigating whether robotic surgery offers any advantage in prophylactic stoma reversal.

Methods

We retrospectively analyzed data from two large medical centers. Three machine learning algorithms (Random Forest, XGBoost, Decision Tree) and traditional logistic regression were used to construct prediction models. The dataset was divided chronologically into Cohort 1 and Cohort 2. Predictors were selected through univariate screening followed by multivariate analysis. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA).

Results

The logistic regression model outperformed the machine learning models, achieving an AUC of 0.856 in the training set and 0.831 in the internal validation set. External validation in Cohort 2 yielded an AUC of 0.780. DCA confirmed a positive net clinical benefit at threshold probabilities > 0.1, and calibration curves showed excellent agreement between predicted and observed outcomes. AL, anastomotic stenosis, BMI, diabetes, tumor distance from the anal verge, neoadjuvant chemoradiotherapy, and surgical approach were identified as key risk factors for permanent stoma. Furthermore, robotic surgery demonstrated potential advantages in preserving anal function and reducing anastomotic complications, which may indirectly promote successful stoma reversal.

Conclusions

We developed and validated a clinically useful nomogram that effectively predicts the likelihood of successful stoma reversal after rectal cancer surgery. The model highlights the significant impact of anastomotic-related complications and patient-specific factors on stoma permanence. These findings can assist clinicians in preoperative counseling and personalized postoperative management. Robotic surgery may offer functional and technical benefits that support stoma reversal, though further prospective studies are warranted to confirm these observations.