08418504

March 20, 2025, 09:22

Reader’s expertise on the topic of the manuscript

Does the reader have a conflict of interest?

The overall quality of the manuscript, based on the above-listed criteria, should be evaluated and classified according to the following five categories

Language quality (style, grammar, and spelling) should be evaluated and classified according to the following five categories.

The author has constructed a predictive model with strong forecasting capabilities, designed to estimate the probability of a textbook outcome following surgery. Additionally, the study elucidates the machine learning computational process using the SHAP algorithm. This research is highly innovative, as it visualizes the otherwise opaque computational processes of machine learning, thereby enhancing its credibility. Clinicians can easily input specific clinical parameters of patients to obtain immediate, personalized risk assessments, enabling timely preventive measures and ensuring the best possible medical care for patients.This study substantiates the feasibility of explainable machine learning in future applications, marking a new direction in the research of predictive models and supervised learning.

Thank you very much for your comments.

08398088

March 15, 2025, 01:36

Reader’s expertise on the topic of the manuscript

Does the reader have a conflict of interest?

The overall quality of the manuscript, based on the above-listed criteria, should be evaluated and classified according to the following five categories

Language quality (style, grammar, and spelling) should be evaluated and classified according to the following five categories.

The clinical significance of this study lies in its innovative approach to predicting colorectal polyp recurrence using machine learning (ML), specifically the eXtreme Gradient Boosting (XGBoost) model. Colorectal cancer (CRC) remains a leading cause of cancer-related mortality worldwide, largely preventable through early detection and effective management of precancerous polyps. Endoscopic mucosal resection (EMR) is widely utilized for the removal of colorectal polyps, yet it carries a considerable risk of recurrence, highlighting the need for accurate predictive tools to guide postoperative surveillance. This study identifies critical independent risk factors for polyp recurrence one year post-EMR, such as age, family history, smoking habits, diarrhea, Helicobacter pylori infection, polyp size, number of polyps, and hazard classification. By leveraging ML algorithms, particularly XGBoost, the researchers have developed a model with superior predictive performance, evidenced by high Area Under the Curve (AUC) values exceeding 0.90 across multiple validation cohorts, including a prospective validation set, indicating robust predictive accuracy and clinical utility. Clinically, the XGBoost model offers substantial advantages. Its high sensitivity, specificity, accuracy, precision, and F1 scores suggest that it effectively stratifies patients based on recurrence risk. Such a model significantly enhances personalized patient management by informing more accurate follow-up intervals, potentially improving patient outcomes through timely interventions and reducing unnecessary colonoscopies in low-risk individuals. Additionally, the authors' development of an accessible online web calculator based on this predictive model further underscores its practical utility in routine clinical practice. Clinicians can conveniently input patient-specific clinical parameters to obtain immediate, individualized risk predictions, facilitating shared decision-making between physicians and patients. Decision Curve Analysis further underscores the practical value of this tool, demonstrating that using the XGBoost model provides superior clinical net benefit compared to standard follow-up strategies. This methodical approach not only advances clinical decision-making but also optimizes healthcare resources by prioritizing surveillance for those most at risk. Finally, the interpretability of the model via SHapley Additive exPlanations (SHAP) analysis significantly mitigates concerns about the "black box" nature commonly associated with ML models, thus increasing clinician trust and acceptability. In conclusion, this ML-based predictive model represents a critical advancement in clinical gastroenterology, providing robust, data-driven support for clinicians in making individualized recommendations for colorectal polyp surveillance and potentially reducing colorectal cancer incidence through targeted early intervention.

First, thank you very much for your professional comments on the article published in World Journal of Gastroenterology. Second, we read your comments with great interest. You are welcome to format your valuable comments into a Letter to the Editor and submit it online to World Journal of Gastroenterology at https://www.f6publishing.com. There are no restrictions on the number of words, figures (color, B/W) or authors for a Letter to the Editor. In addition, the article processing charge will be exempted for this Letter to the Editor. As with all articles published by the Baishideng Publishing Group, the Letter to the Editor will be published online after completing peer review. The guidelines for a Letter to the Editor can be found at: https://www.wjgnet.com/bpg/GerInfo/219. Finally, we look forward to receiving your high-quality Letter to the Editor, which will promote academic communication and lead the development of this discipline.