Colorectal polyps are precancerous diseases of colorectal cancer. Early detection and resection of colorectal polyps can effectively reduce the mortality of colorectal cancer. Endoscopic mucosal resection (EMR) is a common polypectomy procedure in clinical practice, but it has a high postoperative recurrence rate. Currently, there is no predictive model for the recurrence of colorectal polyps after EMR.

To construct and validate a machine learning (ML) model for predicting the risk of colorectal polyp recurrence one year after EMR.

This study retrospectively collected data from 1694 patients at three medical centers in Xuzhou. Additionally, a total of 166 patients were collected to form a prospective validation set. Feature variable screening was conducted using univariate and multivariate logistic regression analyses, and five ML algorithms were used to construct the predictive models. The optimal models were evaluated based on different performance metrics. Decision curve analysis (DCA) and SHapley Additive exPlanation (SHAP) analysis were performed to assess clinical applicability and predictor importance.

Multivariate logistic regression analysis identified 8 independent risk factors for colorectal polyp recurrence one year after EMR (P < 0.05). Among the models, eXtreme Gradient Boosting (XGBoost) demonstrated the highest area under the curve (AUC) in the training set, internal validation set, and prospective validation set, with AUCs of 0.909 (95%CI: 0.89-0.92), 0.921 (95%CI: 0.90-0.94), and 0.963 (95%CI: 0.94-0.99), respectively. DCA indicated favorable clinical utility for the XGBoost model. SHAP analysis identified smoking history, family history, and age as the top three most important predictors in the model.

The XGBoost model has the best predictive performance and can assist clinicians in providing individualized colonoscopy follow-up recommendations.

Microecology refers to the ecosystem formed by human and microbial communities in the process of co-evolution, the microecological imbalance is associated with occurrence and development of multiple diseases, including lung cancer. In this review, we detailedly summarized the concept and roles of microecology, the relationship between microecology and human diseases, and related techniques in microecology studies. Importantly, we specially analyzed the correlations between microecology and lung cancer by focusing on gut microbiota, oral microbiota and lower respiratory tract microbiota, and further evaluated the effects of microbiota dysbiosis on chemotherapy and immunotherapy efficacy in lung cancer. At last, we discussed the potential mechanisms by which dysregulated microbiota promotes the genesis and development of lung cancer. Microecology-centered detection and intervention will improve the early diagnosis of lung cancer and provide new targets for the treatment of lung cancer.

Helicobacter pylori (H. pylori) plays an important role in the development of gastric cancer, although its association to colorectal polyp (CP) or colorectal cancer (CRC) is unknown. In this issue of World Journal of Gastrointestinal Surgery, Zhang et al investigated the risk factors for H. pylori infection after colon polyp resection. Importantly, the researchers used R software to create a prediction model for H. pylori infection based on their findings. This editorial gives an overview of the association between H. pylori and CP/CRC, including the clinical significance of H. pylori as an independent risk factor for CP/CRC, the underlying processes of H. pylori-associated carcinogenesis, and the possible risk factors and identification of H. pylori.

To explore Helicobacter pylori (Hp) infection status and its relationship with lifestyle habits and dietary factors in patients with chronic atrophic gastritis. Six hundred thirty-eight patients with chronic atrophic gastritis, who were admitted to our hospital from March 2021 to April 2023, were selected for the study. All patients underwent the 13C urea breath test. The relationship between the detection rate of Hp infection and the clinical characteristics, lifestyle habits, and dietary factors of the patients was analyzed. Among the 638 patients with chronic atrophic gastritis, 531 patients were tested positive for Hp infection, the positive rate for Hp infection was approximately 83.23%. Analyzing the clinical characteristics of the patients, it was found that age, family history of gastric cancer, degree of chronic inflammation, degree of glandular atrophy, presence of low-grade dysplasia, and intestinal metaplasia all have an impact on the positive detection rate of patients (P < .05). Analyzing the patients' lifestyle habits, it was found that BMI, smoking history, alcohol consumption, preference for spicy food, dining location, consumption of pickled foods, frequent consumption of grilled/barbecued foods, preference for strong tea, consumption of sweets, and work-related stress had an impact on the positive rate of Hp infection in patients (P < .05). The discovery showed that the levels of total protein, albumin, hemoglobin, cholesterol, and the intake of livestock and poultry meat, seafood, dairy products, vegetables, fruits, and fats have an impact on the positivity rate of Hp infection in patients (P < .05). A multiple logistic regression analysis was performed, and it was found that patients' age, family history of gastric cancer, degree of chronic inflammation, degree of glandular atrophy, presence of low-grade dysplasia, presence of wasting or obesity, history of alcohol consumption, preference for spicy food, dining location, frequent consumption of strong tea, high work pressure, high intake of fish and seafood, low intake of dairy products, low intake of vegetables, low intake of fruits, and low intake of fats all had an impact on the occurrence of Hp infection in patients (P < .05). There is a certain correlation between patients' lifestyle habits, dietary factors, and clinical characteristics with the occurrence of Hp infection. These factors can assist in the prevention of Hp infection.