Nomogram for predicting the feasibility of natural orifice specimen extraction after laparoscopic rectal resection

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.

Sex-specific bone and muscular morphological features in ischiofemoral impingement: A three-dimensional study

The study aimed to investigate how hip bone and muscular morphology features differ between ischiofemoral impingement (IFI) patients and healthy subjects among males and females. Three-dimensional models were reconstructed based on magnetic resonance imaging images from IFI patients and healthy subjects of different sexes. Bone morphological parameters and the cross-sectional area of the hip abductors were measured. The diameter and angle of the pelvis were compared between patients and healthy subjects. Bone parameters of the hip and cross-sectional area of the hip abductors were compared between affected and healthy hips. The comparison results of some parameters were significant for females but not males. For females, the comparison results of pelvis parameters showed that the anteroposterior diameter of the pelvic inlet (p = 0.001) and intertuberous distance (p < 0.001) were both larger in IFI patients than in healthy subjects. Additionally, the comparison results of hip parameters showed that the neck shaft angle (p < 0.001) and the cross-sectional area of the gluteus medius (p < 0.001) and gluteus minimus (p = 0.005) were smaller, while the cross-sectional area of the tensor fasciae latae (p < 0.001) was significantly larger in affected hips. Morphological changes in IFI patients demonstrated sexual dimorphism, including bone and muscular morphology. Differences in the anteroposterior diameter of the pelvic inlet, intertuberous distance, neck shaft angle, gluteus medius, and gluteus minimus may explain why females are more susceptible to IFI.

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

Objective

The current work aimed to develop a nomogram comprised of MRI-based pelvimetry and clinical factors for predicting the difficulty of rectal surgery for middle and low rectal cancer (RC).

Methods

Consecutive mid to low RC cases who underwent transabdominal resection between June 2020 and August 2021 were retrospectively enrolled. Univariable and multivariable logistic regression analyses were carried out for identifying factors (clinical factors and MRI-based pelvimetry parameters) independently associated with the difficulty level of rectal surgery. A nomogram model was established with the selected parameters for predicting the probability of high surgical difficulty. The predictive ability of the nomogram model was assessed by the receiver operating characteristic (ROC) curve and decision curve analysis (DCA).

Results

A total of 122 cases were included. BMI (OR = 1.269, p = 0.006), pelvic inlet (OR = 1.057, p = 0.024) and intertuberous distance (OR = 0.938, p = 0.001) independently predicted surgical difficulty level in multivariate logistic regression analysis. The nomogram model combining these predictors had an area under the ROC curve (AUC) of 0.801 (95% CI: 0.719–0.868) for the prediction of a high level of surgical difficulty. The DCA suggested that using the nomogram to predict surgical difficulty provided a clinical benefit.

Conclusions

The nomogram model is feasible for predicting the difficulty level of rectal surgery, utilizing MRI-based pelvimetry parameters and clinical factors in mid to low RC cases.

Infections at the nexus of metabolic-associated fatty liver disease

Metabolic-associated fatty liver disease (MAFLD) is a chronic liver disease that affects about a quarter of the world population. MAFLD encompasses different disease stadia ranging from isolated liver steatosis to non-alcoholic steatohepatitis (NASH), fibrosis, cirrhosis and hepatocellular carcinoma. Although MAFLD is considered as the hepatic manifestation of the metabolic syndrome, multiple concomitant disease-potentiating factors can accelerate disease progression. Among these risk factors are diet, lifestyle, genetic traits, intake of steatogenic drugs, male gender and particular infections. Although infections often outweigh the development of fatty liver disease, pre-existing MAFLD could be triggered to progress towards more severe disease stadia. These combined disease cases might be underreported because of the high prevalence of both MAFLD and infectious diseases that can promote or exacerbate fatty liver disease development. In this review, we portray the molecular and cellular mechanisms by which the most relevant viral, bacterial and parasitic infections influence the progression of fatty liver disease and steatohepatitis. We focus in particular on how infectious diseases, including coronavirus disease-19, hepatitis C, acquired immunodeficiency syndrome, peptic ulcer and periodontitis, exacerbate MAFLD. We specifically underscore the synergistic effects of these infections with other MAFLD-promoting factors.