P1.195. A Machine Learning Model for Predicting Anastomotic Leak in Esophageal Cancer Patients Undergoing Esophagectomy: A Single-Center Retrospective Study
The developed ML models for predicting AL after esophagectomy demonstrated acceptable discriminative ability and identified key risk factors including radiotherapy, hemoglobin drop, bleeding, and lymphocyte count and provide a data-driven foundation for risk stratification.
Abstract
Esophageal Cancer: Surgical Treatment of Esophageal Cancer – early outcomes and complications
Anastomotic leak (AL) is one of the most severe complications after esophagectomy. Early identification of high-risk patients may help optimize perioperative management and improve outcomes. Machine learning (ML) offers promising tools for clinical prediction, yet studies applying ML to predict AL risk after esophagectomy remain scarce. This study aimed to develop and compare ML-based models using single-center real-world data to identify patients at high risk for AL.
Consecutive patients undergoing esophagectomy from April 2019 to April 2023 were retrospectively enrolled. The primary outcome was AL within 30 postoperative days. Thirty-seven potential predictors covering demographics, comorbidities, laboratory values, perioperative factors, and tumor characteristics were collected. Data were split 7:3 into training and test sets. Missing continuous variables were handled by multiple imputation, categorical variables by mode imputation. All features were standardized. Univariate ANOVA (P<0.10) followed by LASSO logistic regression was used for feature selection. Eight ML models were trained and tuned via 5-fold cross-validation with grid search. Performance was evaluated using AUC, accuracy, F1 score, calibration and decision curves. SHAP analysis was performed for interpretability. All analyses were performed in Python with scikit-learn, XGBoost, and SHAP packages.
502 patients who underwent esophagectomy were included, with an overall AL rate of 19.3% (97/502). Following data preprocessing and multiple imputation, univariate analysis identified 15 candidate predictors, which were refined to 15 model-level features using LASSO logistic regression. Eight machine learning models were trained. The Stochastic Gradient Boosting Tree (SGBT) achieved the highest AUC in both the training set (0.880) and the test set (0.683, Figure A). Model calibration demonstrated good agreement between predicted and observed outcomes (Figure B). The SGBT model yielded the highest recall (0.456, Figure C), and was therefore selected as the final predictive model. SHAP analysis revealed that radiotherapy, hemoglobin difference, intraoperative bleeding volume, and lymphocyte count were the most influential features driving individual risk predictions (mean absolute SHAP values shown in Figure D; full summary in Figure E). An integrated risk map visualizing the contribution of each key feature is provided in Figure F.
This single-center study developed ML models for predicting AL after esophagectomy. The SGBT model demonstrated acceptable discriminative ability and identified key risk factors including radiotherapy, hemoglobin drop, bleeding, and lymphocyte count. Despite retrospective limitations, these findings provide a data-driven foundation for risk stratification. Future multicenter validation and prospective studies are warranted to verify clinical utility.
Background Early identification of patients at high risk of anastomotic leak (AL) following esophagectomy is essential for improving surgical outcomes. However, reliable preoperative risk stratification remains challenging. This study aimed to predict AL risk in the esophageal cancer (EC) population by developing and validating a machine learning (ML)-based model using exclusively preoperative and baseline clinical data. Methods A retrospective cohort of EC patients who underwent radical esophagectomy at the Affiliated Tumor Hospital of Xinjiang Medical University from January 2020 to May 2025 was analyzed. Feature selection was performed using the least absolute shrinkage and selection operator (LASSO) regression. Five ML algorithms, Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM), were constructed. Model performance was comprehensively evaluated using the area under the receiver operating characteristic (ROC) curve (AUC), calibration curves, and decision curve analysis (DCA). Model interpretability was enhanced via Shapley Additive Explanations (SHAP), enabling quantification of feature importance and visualization of individual prediction contributions. Results A total of 368 patients were included and randomized to training (n=258) and validation (n=110) cohorts. Among the models, RF displayed the best discriminative performance in the validation cohort (AUC: 0.803, 95% confidence interval [CI]: 0.717-0.892), followed by XGBoost (AUC: 0.723) and LightGBM (AUC: 0.713). The RF model yielded a sensitivity (SEN) of 0.879 and a specificity (SPE) of 0.571. SHAP analysis identified monocytes, carcinoembryonic antigen (CEA), neutrophil-to-lymphocyte ratio (NLR), urine creatinine (UCr), and T stage as the five most influential predictors of AL. Calibration curves for the ensemble models demonstrated good agreement between predicted probabilities and observed outcomes. Conclusions The RF model, incorporating five routinely available preoperative variables, exhibited robust discriminative performance with high SEN for predicting in-hospital AL following esophagectomy. The proposed threshold-based risk stratification approach may facilitate individualized perioperative monitoring and management.
Yueying Yang, Kayishaer Ainiwaer, Yunfei Gao et al.· Frontiers in Oncology· 0 citations
Background Esophageal cancer remains one of the leading causes of cancer-related mortality worldwide. Anastomotic leakage (AL) following esophagectomy is a major postoperative complication that significantly impacts patient outcomes, including mortality, morbidity, prolonged hospital stays, and increased healthcare costs. Despite advances in surgical techniques and adjuvant therapies, predicting the risk of AL remains a challenge. Objective This study aims to develop and validate a predictive model for assessing the risk of AL in esophageal cancer patients undergoing esophagectomy, based on comprehensive clinical and laboratory variables. Methods This retrospective cohort study included 650 esophageal cancer patients who underwent esophagectomy between January 2015 and May 2025, divided into a training set (n = 455) and a validation set (n = 195) at 7:3 ratio. Baseline demographic, clinicopathological, and laboratory data were collected, with AL as the primary outcome, defined according to the Esophagectomy Complications Consensus Group (ECCG). Univariable and multivariable logistic regression, restricted cubic splines (RCS), and nomogram development to identify predictors, with model performance assessed using receiver operating characteristic (ROC) curve, calibration plots, and decision curve analysis (DCA). Results Seven significant predictors of AL were identified in the training set: age, neoadjuvant radiotherapy, C-reactive protein-albumin-lymphocyte (CALLY) index, hypertension, neutrophil-to-lymphocyte ratio (NLR), neutrophil-to-monocyte ratio (NMR), and platelet-to-lymphocyte ratio (PLR). A nomogram model was developed, showing good discrimination (AUC = 0.813) and calibration in the training set. The validation cohort demonstrated moderate predictive accuracy (AUC = 0.763), with consistent net benefits observed across different risk thresholds in DCA. Conclusions In conclusion, this study established a potentially useful predictive model for AL risk, which may facilitate individualized risk stratification, guide perioperative decision-making, and ultimately contribute to reducing AL incidence and improving postoperative recovery.
Ruonan Tan, Lili Guo, Saitian Li et al.· Frontiers in Oncology· 0 citations
Standard preoperative variables are insufficient for individualized risk stratification of RLNP, anastomotic leak, or vocal cord palsy after esophagectomy, and improved prediction will require prospective integration of real-time intraoperative data.
Si-miao Lu, Yi Zhu, Yong-tao Han et al.· Diseases of the esophagus· 0 citations
PURPOSE
Early identification of anastomotic leakage (AL) is critical for safe discharge within enhanced recovery pathways. This study developed and prospectively validated a machine learning (ML) model to predict AL using 24-h postoperative inflammatory biomarkers.
METHODS
We analyzed 1,961 patients undergoing elective minimally invasive colorectal resection (2012-2025). Five ML architectures were developed using a 70/15/15 split. The Regularized Logistic Regression (RLB) model was selected and locked with a pre-specified threshold (0.1258). Global variable importance and directionality were assessed via SHAP analysis. Prospective temporal validation was performed on 250 consecutive patients (February 2024 - December 2025).
RESULTS
AL incidence was 9.8% in the development cohort. The RLB model achieved high discrimination (AUCPR 0.859; AUC-ROC 0.819). Postoperative C-reactive protein (CRP) and the Systemic Inflammation Response Index (SIRI) at 24 h were the strongest predictors. During temporal validation, despite a 70% relative reduction in AL incidence (2.8%), the model maintained a robust negative predictive value (NPV) of 97.9% (95% CI 95.1-99.1% and an AUC of 0.73 (95% CI 0.54-0.92). Calibration was near-optimal (slope 0.987, intercept 0.505). Decision curve analysis demonstrated superior net clinical benefit across risk thresholds of 5-20%.
CONCLUSIONS
ML-based integration of early inflammatory biomarkers provides a reliable "safety filter" for postoperative surveillance. The high NPV supports objective decision-making for early discharge, even in changing clinical environments with decreasing complication rates.
J. Martín-Arévalo, Andreia Guimaraes, Irina Palomo-Lopez et al.· Surgical Endoscopy· 0 citations
Esophageal Cancer: Surgical Treatment of Esophageal Cancer – long term outcomes
Esophageal cancer is one of the most common gastrointestinal malignancies worldwide. In China, most patients are diagnosed at intermediate and advanced stages, and the treatment mainly includes neoadjuvant therapy, surgery and postoperative adjuvant therapy. Although the therapeutic effect has been greatly improved, clinical challenges still exist. Therefore, it's urgent to explore new and effective prognostic markers to identify high-risk patients at an early stage.Studies have shown that low preoperative fat-free mass index is an independent prognostic factor in several malignant tumors. However, its impact on anastomotic leakage and long-term prognosis in esophageal cancer patients remains rarely reported.
From January 2013 to December 2016, 411 patients who underwent radical resection for esophageal cancer were enrolled in this study. We divided patients into a low FFMI group and a high FFMI group by using the median values of FFMI for both males and females. To determine the discriminative ability of FFMI on the occurrence of anastomotic leakage after surgery, receiver operating characteristic curve (ROC) analysis was used. And then, area under curve (AUC) and 95% confidence interval (95% CI) were calculated. Kaplan Meier survival analysis was used to explore the impact of different FFMI groups on the overall survival (OS) and disease-free survival (DFS) of esophageal cancer patients, incorporating variables with significant differences (P<0.05) in the univariate Cox regression analysis into the multivariate Cox regression analysis.
Our cohort included 245 males (59.61%) and 166 females (40.39%), with mean FFMI of 18.14±1.35 and 15.30±1.06 kg/m2, respectively. Patients were divided into low and high FFMI groups according to gender-specific median values. The overall postoperative anastomotic leakage rate was 9.98%. The low FFMI group showed significantly higher leakage rates in both males and females (males: 16.26% vs. 4.92%, P=0.004; females: 16.87% vs. 1.20%, P=0.025). Postoperative hospital stay was significantly longer in the low FFMI group for both genders (males: 15.26±9.47 vs. 12.82±6.14 days, P=0.017; females: 14.64±10.39 vs. 11.07±3.87 days, P=0.004). Kaplan–Meier analysis revealed that low FFMI was associated with poorer 5-year OS and DFS (OS: 37.4% vs. 50.2%, P=0.002; DFS: 32.0% vs. 43.9%, P=0.008). Multivariate Cox regression demonstrated that FFMI was an independent prognostic factor for OS (HR=0.73; 95%CI: 0.58–0.92; P=0.009) and DFS (HR=0.79; 95%CI: 0.64–0.98; P=0.031).
Our study found that preoperative low FFMI is a high-risk factor for increased risk of postoperative anastomotic leakage and poor survival prognosis in esophageal cancer patients. Therefore, in clinical practice, by early identification of patients with preoperative low FFMI and adopting related nutritional support and functional exercise treatments, the occurrence of poor prognosis associated with preoperative low FFMI can be reduced.
Jiarong Zhang, Weiming Chen, Weikun Su et al.· Diseases of the esophagus· 0 citations
This interpretable 11-variable model enables early POP risk stratification after brain tumor surgery and may support timely preventive intervention in neurosurgical care.
H. Mao, Fengchun Mu, Xinyu Wang et al.· Frontiers in Cellular and In...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
