Ning-Hui Zhao, Ling-Ran Zhao, Jia Yao, Ling-Yun Niu, Long-Jun Yang, Yu-Jia Lin, Mei Liu
{"title":"Development and validation of a risk prediction model for small intestinal mucosal injury in nonsteroidal anti-inflammatory drug users.","authors":"Ning-Hui Zhao, Ling-Ran Zhao, Jia Yao, Ling-Yun Niu, Long-Jun Yang, Yu-Jia Lin, Mei Liu","doi":"10.4240/wjgs.v18.i2.115830","DOIUrl":"10.4240/wjgs.v18.i2.115830","url":null,"abstract":"<p><strong>Background: </strong>Despite the enhanced detection capability of capsule endoscopy for small intestinal lesions, the independent risk factors and distinct clinical-endoscopic characteristics in high-risk populations remain incompletely elucidated.</p><p><strong>Aim: </strong>To investigate the risk factors for small intestinal mucosal injury (SIMI) in nonsteroidal anti-inflammatory drug (NSAID) users and to establish a corresponding predictive model.</p><p><strong>Methods: </strong>We conducted a retrospective analysis of clinical data from patients undergoing capsule endoscopy at our institution and Shanxi Bethune Hospital from August 2012 to January 2025. Multivariate analysis was performed to identify independent risk factors for SIMI. A nomogram was subsequently developed to predict the risk of SIMI in NSAID users. Receiver operating characteristic curve analysis, calibration curve and decision curve analysis were performed to evaluate the predictive accuracy of the nomogram.</p><p><strong>Results: </strong>In the primary cohort, SIMI was identified in 114 out of 181 NSAID users. Multivariate analysis revealed that advanced age, smoking, proton pump inhibitor use, elevated body mass index, high triglyceride levels, and increased low-density lipoprotein were independent risk factors for SIMI. The research team developed a risk prediction model for estimating the risk of mucosal injury, which achieved an area under the curve of 0.775 (95% confidence interval: 0.700-0.849) in the derivation set. The model exhibited an area under the curve of 0.797 (95% confidence interval: 0.643-0.952) in the validation cohort.</p><p><strong>Conclusion: </strong>We identified risk factors for SIMI in NSAID users and established a predictive model, which may facilitate early identification of high-risk populations and guide clinical interventions.</p>","PeriodicalId":23759,"journal":{"name":"World Journal of Gastrointestinal Surgery","volume":"18 2","pages":"115830"},"PeriodicalIF":2.1,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12968674/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147435824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Maryam Hassanesfahani, Dimitrios Giannis, Nana Marfo, Manpreet Kaur, Camille Mai-Phuong Tran Quang, Andrew Miele, Martine A Louis, Nageswara Rao Mandava
{"title":"Defining endpoints in percutaneous cholecystostomy: Catheter management, patient survival, and long-term outcomes from a twelve-year retrospective study.","authors":"Maryam Hassanesfahani, Dimitrios Giannis, Nana Marfo, Manpreet Kaur, Camille Mai-Phuong Tran Quang, Andrew Miele, Martine A Louis, Nageswara Rao Mandava","doi":"10.4240/wjgs.v18.i2.115744","DOIUrl":"10.4240/wjgs.v18.i2.115744","url":null,"abstract":"<p><strong>Background: </strong>Percutaneous cholecystostomy (PCT) is widely used for high-risk acute cholecystitis as an alternative to emergent cholecystectomy. Despite its effectiveness, the optimal timing, catheter management, and long-term outcomes remain to be elucidated.</p><p><strong>Aim: </strong>To characterize timing, catheter management, survival, and follow-up outcomes after PCT in a high-risk cohort.</p><p><strong>Methods: </strong>This single center retrospective cohort study included consecutive adult patients undergoing PCT placement for acute cholecystitis at a community hospital setting in New York between January 2012 and December 2024. The study population was grouped according to type of acute cholecystitis (calculous <i>vs</i> acalculous), according to the timing of PCT placement since diagnosis [early (≤ 4 days) <i>vs</i> late (> 4 days)], and according to level of care [intensive care unit (ICU) <i>vs</i> non-ICU patients]. Cox proportional hazards models were used to examine effects of PCT placement interval on mortality rates, after accounting for potential confounding factors (age, Charlson Comorbidity Index, cholecystitis type, ICU status, bile culture and blood culture data).</p><p><strong>Results: </strong>The population consisted of 174 patients who underwent PCT placement for acute cholecystitis between 2012 and 2024 at a community hospital in New York. Median time to PCT was 2 days (interquartile range 1-4). Overall, mortality was 21% (36/174) and was higher with delayed PCT (> 4 days) <i>vs</i> early PCT [35% (17/49) <i>vs</i> 15% (19/125), <i>P</i> = 0.001]. Catheter removal occurred in 13% (23/174), 55% (96/174) remained catheter-dependent, and 32% (56/174) had interval cholecystectomy. ICU admission was associated with prolonged catheter duration but was not associated with mortality. Kaplan-Meier analysis demonstrated a significantly higher survival rate in the early group compared with the late group (log-rank <i>P</i> = 0.006). In both unadjusted models and models adjusted for selected covariates, patients who had catheters placed late (> 4 days) had 2.5-fold higher risk of death than patients with early placement.</p><p><strong>Conclusion: </strong>Early PCT was associated with higher survival in high-risk acute cholecystitis. High rates of catheter dependency highlight the need for standardized protocols and reassessment for definitive surgery.</p>","PeriodicalId":23759,"journal":{"name":"World Journal of Gastrointestinal Surgery","volume":"18 2","pages":"115744"},"PeriodicalIF":2.1,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12968654/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147435833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wen-Cai Luo, Yuan-Fu Yang, Yao Wang, Zhao-Hong Zhang
{"title":"Endoscopic characterization and development of a prediction model for colorectal adenomatous polyps.","authors":"Wen-Cai Luo, Yuan-Fu Yang, Yao Wang, Zhao-Hong Zhang","doi":"10.4240/wjgs.v18.i2.115902","DOIUrl":"10.4240/wjgs.v18.i2.115902","url":null,"abstract":"<p><strong>Background: </strong>Colorectal cancer carries a high mortality rate worldwide. Adenocarcinoma is its most common type, which is progressed following an adenoma-dysplasia-carcinoma sequence. Early accurate identification of individuals with a high risk for adenomas could facilitate prompt removal of adenomas and reduce colorectal cancer incidence.</p><p><strong>Aim: </strong>To investigate the endoscopic features of colorectal adenomatous polyps and develop a prediction model for their occurrence.</p><p><strong>Methods: </strong>A total of 202 individuals undergoing their first colonoscope between January 2023 and January 2024 were selected. Endoscopic characteristics, demographics, clinical information, and laboratory results were compared between individuals with or without colorectal adenomas. Logistic regression was performed to identify risk factors for colorectal adenomatous polyps and construct a prediction model. A nomogram was developed using R (v3.5.2). Internal validation was conducted with 1000 bootstrap resamples to assess calibration and discrimination. External valuation was conducted in another 240 individuals.</p><p><strong>Results: </strong>In 202 participants, 75 (37.13%) and 127 (62.87%) had or had no colorectal adenomas, respectively. These adenomas varied in shape, size, and locations. Age ≥ 60 years, smoking, alcohol, fatty liver, gallbladder polyps, and abnormal glycosylated hemoglobin (HbA1c) were risk factors and were used to construct nomogram Logit(P) = -5.602 + 1.791 × age ≥ 60 years + 1.115 × smoking + 1.894 × alcohol + 1.727 × fatty liver + 1.749 × gallbladder polyps + 1.903 × abnormal HbA1c. Internal validation demonstrated excellent agreement between apparent and bias-corrected curves, strong discriminative ability (area under the curve of 0.889, 95% confidence interval: 0.841-0.938), and high net clinical benefit (threshold probability range 0.1-0.9). External validation also suggested excellent model performance.</p><p><strong>Conclusion: </strong>Colorectal adenomas exhibit diverse characteristics. A nomogram incorporating age, smoking, alcohol, fatty liver, gallbladder polyps, and HbA1c provides a robust and accurate prediction for the risk of colorectal adenomas.</p>","PeriodicalId":23759,"journal":{"name":"World Journal of Gastrointestinal Surgery","volume":"18 2","pages":"115902"},"PeriodicalIF":2.1,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12968667/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147435880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Serum inflammatory biomarkers can predict clinical outcomes in patients with sepsis-associated gastrointestinal dysfunction.","authors":"You-Hui Liu, Qing-Yang Chen, Fei-Yue Dai, Xin-Yu Chen","doi":"10.4240/wjgs.v18.i2.112169","DOIUrl":"10.4240/wjgs.v18.i2.112169","url":null,"abstract":"<p><strong>Background: </strong>Effective predictive indicators for clinical outcomes in septic patients with gastrointestinal dysfunction (GID) remain lacking.</p><p><strong>Aim: </strong>To evaluate the relationship between serum inflammatory biomarkers (SIBs) and clinical outcomes in patients with sepsis-induced GID.</p><p><strong>Methods: </strong>A total of 117 sepsis-induced GID patients were selected (January 2021 to January 2025). They were grouped into poor [<i>n</i> = 76; Acute Physiology and Chronic Health Evaluation II (APACHE II) score > 10] and good (<i>n</i> = 41; APACHE II ≤ 10) prognosis groups based on outcomes. Clinical variables (sex, age, body mass index, smoking history, diabetes, hypertension, and infection site) were collected. SIBs, encompassing procalcitonin (PCT), C-reactive protein (CRP), interleukin (IL)-6/10, and tumor necrosis factor (TNF)-α, were analyzed. Correlation analyses were conducted to assess the associations of SIBs with Sequential Organ Failure Assessment (SOFA) and APACHE II scores. Receiver operating characteristic curves visualized SIBs' predictive performance, and multivariate analysis identified independent outcome predictors.</p><p><strong>Results: </strong>The groups were similar in age, sex, body mass index, comorbidities, and major infection site. The poor prognosis group exhibited elevated APACHE II, SOFA, PCT, CRP, IL-6, IL-10, and TNF-α than the good prognosis cohort. SIBs correlated positively with both APACHE II and SOFA scores. When used to predict outcomes individually, SIBs yielded an area under the curve range of 0.660-0.780 in septic patients with GID, whereas combined biomarker analysis increased the area under the curve to 0.906. APACHE II, SOFA, PCT, CRP, IL-6, and TNF-α acted as independent predictors of prognosis.</p><p><strong>Conclusion: </strong>SIBs correlate intimately with clinical outcomes in sepsis-induced GID patients.</p>","PeriodicalId":23759,"journal":{"name":"World Journal of Gastrointestinal Surgery","volume":"18 2","pages":"112169"},"PeriodicalIF":2.1,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12968717/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147436143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Prediction of lymphovascular invasion in rectal cancer based on multimodal magnetic resonance imaging radiomics model.","authors":"Zheng-Hong Zhu, Yi Liang, Min Shi","doi":"10.4240/wjgs.v18.i2.113021","DOIUrl":"10.4240/wjgs.v18.i2.113021","url":null,"abstract":"<p><strong>Background: </strong>Lymphovascular invasion (LVI) is an independent prognostic factor in rectal cancer, but its assessment relies on postoperative pathology. Radiomics-based analysis of multimodal magnetic resonance imaging (MRI) can provide noninvasive preoperative prediction of LVI status, supporting precision treatment decisions.</p><p><strong>Aim: </strong>To construct a machine learning model based on multimodal MRI radiomics features for noninvasive preoperative prediction of LVI status in rectal cancer, providing decision support for individualized clinical treatment.</p><p><strong>Methods: </strong>A total of 278 patients with pathologically confirmed rectal cancer after surgery were retrospectively included and divided into training set (222 cases) and test set (56 cases) at an 8:2 ratio. Three sequences were used for scanning: Fat-suppressed T2-weighted imaging, diffusion-weighted imaging, and T1-weighted contrast-enhanced imaging. PyRadiomics software was used to extract radiomics features, which were then screened through stability assessment, variance filtering, correlation analysis, univariate screening, and least absolute shrinkage and selection operator regression for key features. Single-modal models, multimodal radiomics model, clinical model, and clinical-radiomics combined model were constructed respectively. Model performance was evaluated using receiver operating characteristic curves.</p><p><strong>Results: </strong>Among 278 patients, 121 (43.5%) were LVI-positive. Twenty-three key features were selected from initial 4200 features. Multivariate analysis showed that tumor diameter ≥ 4 cm, carcinoembryonic antigen ≥ 5 ng/mL, poor differentiation, T3-4 staging, N1-2 staging, and positive perineural invasion were independent predictors of LVI. In the test set, single-modal models achieved area under the curve (AUC) of 0.708-0.775, multimodal radiomics model achieved AUC of 0.835, clinical model achieved AUC of 0.782, and the combined model performed best (AUC = 0.867, sensitivity = 0.840, specificity = 0.806). Hosmer-Lemeshow test showed good calibration for all models (<i>P</i> > 0.05). Decision curve analysis demonstrated that the combined model had maximum net benefit within threshold probability range of 0.15-0.65.</p><p><strong>Conclusion: </strong>Machine learning models based on multimodal MRI radiomics features can effectively predict LVI status in rectal cancer, with the combined model showing optimal performance, providing a valuable quantitative tool for preoperative clinical assessment and individualized treatment decision-making.</p>","PeriodicalId":23759,"journal":{"name":"World Journal of Gastrointestinal Surgery","volume":"18 2","pages":"113021"},"PeriodicalIF":2.1,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12968679/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147436042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Application of improved π anastomosis in totally laparoscopic radical right hemicolectomy.","authors":"Jian-Zhong Wu, Peng-Fei Liu, Zhi-Gang Gu, Zhi Zhang, Zheng-Yu Zhou, Tao Shen","doi":"10.4240/wjgs.v18.i2.115978","DOIUrl":"10.4240/wjgs.v18.i2.115978","url":null,"abstract":"<p><strong>Background: </strong>The optimal anastomotic technique for total laparoscopic right hemicolectomy remains a subject of debate. Novel intracorporeal approaches may help overcome current challenges.</p><p><strong>Aim: </strong>To compare the efficacy of improved π anastomosis and overlap anastomosis.</p><p><strong>Methods: </strong>A retrospective analysis was conducted on 110 colon cancer patients who underwent total laparoscopic radical right hemicolectomy at the Department of Gastrointestinal Surgery, Suzhou Ninth People's Hospital, from January 2022 to May 2024. All patients underwent intracorporeal reconstruction, with 42 patients receiving improved π anastomosis and 68 patients undergoing overlap anastomosis. The perioperative related indicators and postoperative complications were compared between the two groups of patients.</p><p><strong>Results: </strong>No significant differences were observed between the two groups in terms of operative time, number of lymph nodes dissected, or postoperative hospital stay (<i>P</i> > 0.05). However, the anastomosis time was significantly shorter in the improved π anastomosis group (<i>P</i> < 0.001), while the time to first anal flatus was longer (<i>P</i> < 0.05). No cases of anastomotic leakage or stenosis occurred in either group, though one patient in the overlap group experienced anastomotic bleeding (hematochezia). During a follow-up period of over six months, no local recurrence or distant metastasis was detected. The learning curve analysis shows that both groups demonstrated good model fit, and improved π anastomosis achieves proficiency earlier than overlap anastomosis.</p><p><strong>Conclusion: </strong>The improved π anastomosis in total laparoscopic radical right hemicolectomy ensures high safety and favorable short-term outcomes. It offers a shorter learning curve and quicker proficiency compared to overlap anastomosis, reducing operative times and technical demands on surgeons.</p>","PeriodicalId":23759,"journal":{"name":"World Journal of Gastrointestinal Surgery","volume":"18 2","pages":"115978"},"PeriodicalIF":2.1,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12968656/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147435517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Managing reflux after tubular gastric esophageal substitution.","authors":"Li-Juan Yan, Si-Wen Shen, Ting-Ting Fang","doi":"10.4240/wjgs.v18.i2.116235","DOIUrl":"10.4240/wjgs.v18.i2.116235","url":null,"abstract":"<p><strong>Background: </strong>Tubular gastric substitution is a common procedure after esophagectomy, and postoperative reflux symptoms significantly impair the patients' quality of life and nutritional status. Effective long-term nursing strategies are crucial in managing this complication. This study aimed to evaluate the efficacy of a comprehensive follow-up approach.</p><p><strong>Aim: </strong>To investigate the follow-up nursing interventions and clinical outcomes of reflux following tubular gastric esophageal replacement surgery.</p><p><strong>Methods: </strong>A randomized prospective trial was conducted using clinical data from 100 patients with postoperative reflux following tubular gastric esophageal replacement surgery treated at our hospital's Department of Thoracic Surgery between July 2023 and July 2025. Patients were divided into control and study groups based on differing clinical nursing approaches; the control group received routine follow-up care, while the study group underwent comprehensive follow-up care for two months. Pre- and post-intervention comparisons assessed 24-hour reflux frequency, reflux episodes lasting over five minutes, reflux symptom scores, nutritional indicators, quality of life scores, complication rates, and nursing satisfaction.</p><p><strong>Results: </strong>Pre-intervention, no significant differences existed between groups in 24-hour reflux frequency (study: 9.25 ± 1.33 <i>vs</i> control: 9.30 ± 1.28, <i>P</i> = 0.848) or episodes lasting ≥ 5 minutes (study: 4.83 ± 1.16 <i>vs</i> control: 4.78 ± 1.09, <i>P</i> = 0.825). Post-intervention, both groups showed reductions, with the study group exhibiting significantly lower rates than the control group (24-hour frequency: 2.13 ± 0.35 <i>vs</i> 4.52 ± 1.06, <i>P</i> = 0.000; episodes ≥ 5 minutes: 0.88 ± 0.17 <i>vs</i> 2.03 ± 0.44, <i>P</i> = 0.000). The assessment revealed no significant pre-intervention differences in the scores for heartburn, acid regurgitation, upper abdominal distension, or upper abdominal pain. Post-intervention, all scores decreased, with the study group showing significantly lower scores than the control group (<i>e.g.</i>, heartburn: 0.91 ± 0.12 <i>vs</i> 1.46 ± 0.26, <i>P</i> = 0.001). Pre-intervention hemoglobin (Hb), serum albumin, and prealbumin levels were not significantly different between the groups. Post-intervention, all parameters increased, with the study group significantly exceeding the control group (<i>e.g.</i>, Hb: 76.05 ± 5.19 g/L <i>vs</i> 62.19 ± 5.07 g/L, <i>P</i> = 0.001). Pre-intervention World Health Organization Quality of Life Brief total scores were comparable between groups (study: 68.15 ± 4.16 <i>vs</i> control: 68.08 ± 4.29, <i>P</i> = 0.931). Post-intervention, both groups demonstrated increased scores, with the study group significantly exceeding the control group (study: 94.02 ± 4.39 <i>vs</i> control: 81.07 ± 5.23, <i>P</i> = 0.000). At the two-month follow-up post-intervention, the complicatio","PeriodicalId":23759,"journal":{"name":"World Journal of Gastrointestinal Surgery","volume":"18 2","pages":"116235"},"PeriodicalIF":2.1,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12968713/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147435965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Development of a machine learning-based model for predicting postoperative survival in gastric cancer.","authors":"Ya-Na Lü, Dong Liu, Shuai Tao, Ju Wu, Shu-Juan Yu, Hui-Ling Yuan","doi":"10.4240/wjgs.v18.i2.114951","DOIUrl":"10.4240/wjgs.v18.i2.114951","url":null,"abstract":"<p><strong>Background: </strong>Accurate prediction of postoperative survival is crucial for the personalized management of gastric cancer. However, the development of robust predictive models is often constrained by incomplete clinical data, while their clinical utility is limited by poor interpretability and the absence of practical applications.</p><p><strong>Aim: </strong>To develop an interpretable machine learning model for predicting 3-year survival following gastric cancer surgery. A novel data imputation method was proposed to handle missing values, and a user-friendly online tool was developed to facilitate clinical decision-making.</p><p><strong>Methods: </strong>A retrospective analysis was conducted on a group of 304 patients with gastric adenocarcinoma. A hybrid imputation method (HDI-MF-Gower) was developed and compared against conventional techniques. Key prognostic factors were identified by integrating least absolute shrinkage and selection operator regression with the Boruta algorithm. Subsequently, ten machine learning models were trained and validated.</p><p><strong>Results: </strong>The proposed HDI-MF-Gower method demonstrated superior imputation accuracy. Seven features were selected for the final model. The extra trees classifier achieved the best performance on the independent validation set, with an area under the curve of 0.853 and an accuracy of 0.772. The optimal model was interpreted using SHapley Additive exPlanations analysis and deployed as an online prediction tool.</p><p><strong>Conclusion: </strong>A robust and interpretable predictive model integrating advanced data imputation was successfully developed. The deployed tool facilitates individualized prognostic assessment and shows potential for enhancing personalized treatment planning in gastric cancer.</p>","PeriodicalId":23759,"journal":{"name":"World Journal of Gastrointestinal Surgery","volume":"18 2","pages":"114951"},"PeriodicalIF":2.1,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12968659/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147435786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hao-Xian Gou, Chao Deng, Yi Wen, Zhi-Long Yin, Ting-Yu Yang, Tao Wang, Hao Luo, Long Cheng
{"title":"Pancreatic head resection alongside side-to-side pancreatic duct-jejunostomy for pancreatic stones: A case report and review of literature.","authors":"Hao-Xian Gou, Chao Deng, Yi Wen, Zhi-Long Yin, Ting-Yu Yang, Tao Wang, Hao Luo, Long Cheng","doi":"10.4240/wjgs.v18.i2.115072","DOIUrl":"10.4240/wjgs.v18.i2.115072","url":null,"abstract":"<p><strong>Background: </strong>Pancreatic duct stones often develop in the late stage of chronic pancreatitis. However, for complex pancreatic duct stones or stones in the pancreatic body and tail, endoscopic treatment is often ineffective and ultimately requires surgical intervention.</p><p><strong>Case summary: </strong>A young man who had been smoking for 10 years and drinking alcohol for 5 years had a history of abdominal pain for 8 years and diarrhea for 2 years. The patient was diagnosed with \"chronic pancreatitis combined with pancreatic duct stones\" in other hospitals and underwent several endoscopic treatments, but the abdominal pain still recurred. The patient presented to our hospital one week after another episode of abdominal pain. Our team arranged for computed tomography and magnetic resonance imaging examinations, which revealed a markedly atrophic pancreas and a dilated pancreatic duct, and a large number of stones. Our team convened a multidisciplinary consultation to discuss treatment options and reviewed extensive literature. Ultimately, based on the literature and consultation advice, we implemented a novel, previously unreported surgical procedure. The surgical approach we proposed combines the Beger procedure and the Frey procedure, involving complete pancreatic head resection with duodenal preservation, full-length longitudinal incision of the pancreatic duct in the body and tail, and side-to-side pancreaticojejunostomy. Postoperative follow-up revealed a favorable prognosis.</p><p><strong>Conclusion: </strong>The main contribution of this case is the development of a modified surgical procedure for chronic pancreatitis complicated by complex pancreatic duct stones. For chronic pancreatitis complicated by stones that respond poorly to pharmacotherapy or endoscopic treatment, surgery is a worthy early treatment option. Early surgical intervention can effectively drain pancreatic juice, delay pancreatic atrophy, and protect pancreatic function. Our proposed modified procedure can more thoroughly remove stones and reduce the recurrence rate of stones and pain. Although we successfully treated a patient with this procedure for the first time, its efficacy and safety in a human population are currently lacking validation.</p>","PeriodicalId":23759,"journal":{"name":"World Journal of Gastrointestinal Surgery","volume":"18 2","pages":"115072"},"PeriodicalIF":2.1,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12968710/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147435995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}