An MRI-based pelvimetry nomogram for predicting surgical difficulty of transabdominal resection in patients with middle and low rectal cancer

Development and validation of machine learning models and nomograms for predicting the surgical difficulty of laparoscopic resection in rectal cancer

BACKGROUND

The objective of this study is to develop and validate a machine learning (ML) prediction model for the assessment of laparoscopic total mesorectal excision (LaTME) surgery difficulty, as well as to identify independent risk factors that influence surgical difficulty. Establishing a nomogram aims to assist clinical practitioners in formulating more effective surgical plans before the procedure.

METHODS

This study included 186 patients with rectal cancer who underwent LaTME from January 2018 to December 2020. They were divided into a training cohort (n = 131) versus a validation cohort (n = 55). The difficulty of LaTME was defined based on Escal's et al. scoring criteria with modifications. We utilized Lasso regression to screen the preoperative clinical characteristic variables and intraoperative information most relevant to surgical difficulty for the development and validation of four ML models: logistic regression (LR), support vector machine (SVM), random forest (RF), and decision tree (DT). The performance of the model was assessed based on the area under the receiver operating characteristic curve(AUC), sensitivity, specificity, and accuracy. Logistic regression-based column-line plots were created to visualize the predictive model. Consistency statistics (C-statistic) and calibration curves were used to discriminate and calibrate the nomogram, respectively.

RESULTS

In the validation cohort, all four ML models demonstrate good performance: SVM AUC = 0.987, RF AUC = 0.953, LR AUC = 0.950, and DT AUC = 0.904. To enhance visual evaluation, a logistic regression-based nomogram has been established. Predictive factors included in the nomogram are body mass index (BMI), distance between the tumor to the dentate line ≤ 10 cm, radiodensity of visceral adipose tissue (VAT), area of subcutaneous adipose tissue (SAT), tumor diameter >3 cm, and comorbid hypertension.

CONCLUSION

In this study, four ML models based on intraoperative and preoperative risk factors and a nomogram based on logistic regression may be of help to surgeons in evaluating the surgical difficulty before operation and adopting appropriate responses and surgical protocols.

Interpretable machine learning model to predict surgical difficulty in laparoscopic resection for rectal cancer

Background

Laparoscopic total mesorectal excision (LaTME) is standard surgical methods for rectal cancer, and LaTME operation is a challenging procedure. This study is intended to use machine learning to develop and validate prediction models for surgical difficulty of LaTME in patients with rectal cancer and compare these models' performance.

Methods

We retrospectively collected the preoperative clinical and MRI pelvimetry parameter of rectal cancer patients who underwent laparoscopic total mesorectal resection from 2017 to 2022. The difficulty of LaTME was defined according to the scoring criteria reported by Escal. Patients were randomly divided into training group (80%) and test group (20%). We selected independent influencing features using the least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression method. Adopt synthetic minority oversampling technique (SMOTE) to alleviate the class imbalance problem. Six machine learning model were developed: light gradient boosting machine (LGBM); categorical boosting (CatBoost); extreme gradient boost (XGBoost), logistic regression (LR); random forests (RF); multilayer perceptron (MLP). The area under receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity and F1 score were used to evaluate the performance of the model. The Shapley Additive Explanations (SHAP) analysis provided interpretation for the best machine learning model. Further decision curve analysis (DCA) was used to evaluate the clinical manifestations of the model.

Results

A total of 626 patients were included. LASSO regression analysis shows that tumor height, prognostic nutrition index (PNI), pelvic inlet, pelvic outlet, sacrococcygeal distance, mesorectal fat area and angle 5 (the angle between the apex of the sacral angle and the lower edge of the pubic bone) are the predictor variables of the machine learning model. In addition, the correlation heatmap shows that there is no significant correlation between these seven variables. When predicting the difficulty of LaTME surgery, the XGBoost model performed best among the six machine learning models (AUROC=0.855). Based on the decision curve analysis (DCA) results, the XGBoost model is also superior, and feature importance analysis shows that tumor height is the most important variable among the seven factors.

Conclusions

This study developed an XGBoost model to predict the difficulty of LaTME surgery. This model can help clinicians quickly and accurately predict the difficulty of surgery and adopt individualized surgical methods.

Nomogram for predicting the surgical difficulty of laparoscopic total mesorectal excision and exploring the technical advantages of robotic surgery

Background

Total mesorectal excision (TME), represents a key technique in radical surgery for rectal cancer. This study aimed to construct a preoperative nomogram for predicting the surgical difficulty of laparoscopic total mesorectal excision (L-TME) and to investigate whether there were potential benefits of robotic TME (R-TME) for patients with technically challenging rectal cancer.

Methods

Consecutive mid-low rectal cancer patients receiving total mesorectal excision were included. A preoperative nomogram to predict the surgical difficulty of L-TME was established and validated. Patients with technically challenging rectal cancer were screened by calculating the prediction score of the nomogram. Then patients with technically challenging rectal cancer who underwent different types of surgery, R-TME or L-TME, were analyzed for comparison.

Results

A total of 533 consecutive patients with mid-low rectal cancer who underwent TME at a single tertiary medical center between January 2018 and January 2021 were retrospectively enrolled. Multivariable analysis demonstrated that mesorectal fat area, intertuberous distance, tumor size, and tumor height were independent risk factors for surgical difficulty. Subsequently, these variables were used to construct the nomogram model to predict the surgical difficulty of L-TME. The area under the receiver operating characteristic curve of the nomogram was 0.827 (95% CI 0.745 - 0.909) and 0.809 (95% CI 0.674- 0.944) in the training and validation cohort, respectively. For patients with technically challenging rectal cancer, R-TME was associated with a lower diverting ileostomy rate (p = 0.003), less estimated blood loss (p < 0.043), shorter procedure time (p = 0.009) and shorter postoperative hospital stay (p = 0.037).

Conclusion

In this study, we established a preoperative nomogram to predict the surgical difficulty of L-TME. Furthermore, this study also indicated that R-TME has potential technical advantages for patients with technically challenging rectal cancer.

Advances in pelvic imaging parameters predicting surgical difficulty in rectal cancer

Due to the fixed bony structure of the pelvis, the pelvic operation space is limited, complicating the surgical operation of rectal cancer, especially middle and low rectal cancer. The closer the tumor is to the anal verge, the smaller the operative field and operating space, the longer the operative time, and the greater the incidence of intraoperative side injuries and postoperative complications. To date, there is still no clear definition of a difficult pelvis that affects the surgical operation of rectal cancer. Few related research reports exist in the literature, and views on this aspect are not the same between countries. Therefore, it is particularly important to predict the difficulty of rectal cancer surgery in a certain way before surgery and to select the surgical method most suitable for each case during the treatment of rectal cancer.