{"title":"Erratum: MD2 blockage prevents the migration and invasion of hepatocellular carcinoma cells via inhibition of the EGFR signaling pathway.","authors":"","doi":"10.21037/jgo-2025b-02","DOIUrl":"10.21037/jgo-2025b-02","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.21037/jgo-21-362.].</p>","PeriodicalId":15841,"journal":{"name":"Journal of gastrointestinal oncology","volume":"16 1","pages":"333-335"},"PeriodicalIF":2.0,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11921404/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143669968","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}
Miaotian Deng, Chaobo Chen, Kun Wang, Binghua Li, Decai Yu
{"title":"Systemic treatment for recurrence of hepatocellular carcinoma after liver transplantation: a case report.","authors":"Miaotian Deng, Chaobo Chen, Kun Wang, Binghua Li, Decai Yu","doi":"10.21037/jgo-24-480","DOIUrl":"10.21037/jgo-24-480","url":null,"abstract":"<p><strong>Background: </strong>Liver transplantation (LT) is considered the optimal treatment approach for patients with cirrhosis progressing to hepatocellular carcinoma (HCC). LT not only allows for complete removal of tumors from the liver but also potentially eliminates cirrhosis. However, recurrence of HCC after LT remains a significant issue, with recurrence rates ranging from 8% to 20%. The median time to recurrence is 14 months, and the median survival after recurrence is 12.2 months. We present the first case of long-term remission following hepatic arterial infusion chemotherapy (HAIC) combined with targeted therapy in a patient with multifocal recurrence and distant metastasis of HCC after LT.</p><p><strong>Case description: </strong>A 62-year-old male experienced recurrence of HCC after LT, with metastases to the sigmoid colon. Following multidisciplinary discussions, he received HAIC combined with small molecule targeted therapy. The liver tumor lesions and hemorrhagic foci remained stable, even tending to shrink, while tumor marker levels steadily declined. The patient did not experience any serious adverse events during treatment. Unfortunately, the patient developed acute enteritis with dysbiosis following a meal in March 2024, which led to rapid onset of septic shock, ultimately resulting in death.</p><p><strong>Conclusions: </strong>This case suggests that the combination of HAIC and targeted therapy may offer a promising approach for treating recurrent HCC after LT. These findings provide valuable insights for further exploration of treatment strategies for recurrent HCC post-LT and may contribute to advancing clinical research and practice for the benefit of patients.</p>","PeriodicalId":15841,"journal":{"name":"Journal of gastrointestinal oncology","volume":"16 1","pages":"309-316"},"PeriodicalIF":2.0,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11921418/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143670055","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":"Expression of Claudin18.2 in metastatic lesions in peritoneum of gastric cancer.","authors":"Akira Saito, Hideyuki Ohzawa, Rie Kawashima, Shiro Matsumoto, Kentaro Kurashina, Shin Saito, Hideyo Miyato, Yoshinori Hosoya, Naohiro Sata, Joji Kitayama, Hironori Yamaguchi","doi":"10.21037/jgo-24-743","DOIUrl":"10.21037/jgo-24-743","url":null,"abstract":"<p><strong>Background: </strong>Patients with advanced gastric cancer (GC) with peritoneal involvement have a dismal prognosis. Recent clinical trials have shown that anti-Claudin18.2 (CLDN18.2) antibody (zolbetuximab) enhances survival in patients with GC expressing high levels of CLDN18.2. However, the effectiveness of the zolbetuximab in patients with peritoneal metastases (PMs) remains unclear. In this study, we aimed to evaluate the expression of CLDN18.2 in disseminated lesions to assess the clinical utility of zolbetuximab in the treatment of GC with PM.</p><p><strong>Methods: </strong>In 42 patients diagnosed with stage IV GC with PM, biopsy samples from the primary tumors and peritoneal metastatic nodules were collected and immunostained using the specific antibody (43-14A, Ventana). The expression of CLDN18.2 was comparatively evaluated based on staining intensity and the proportion of positive cells.</p><p><strong>Results: </strong>Positive immunoreactivity of CLDN18.2 was observed in 37 (88%) of the primary tumors. Specifically, CLDN18.2 positivity was identified in 26 (62%) or 12 (29%) patients based on moderate to strong membrane staining in at least 40% or 75% of tumor cells, respectively. In comparison, the staining intensity in tumor cells was consistently reduced in PM across all patients. CLDN18.2 expression was absent in PM of 29 (69%) patients, while 3 (7.1%) cases were determined to be CLDN18.2-positive based on a cutoff value of 40% for high staining. This trend was particularly pronounced in cases with undifferentiated type and human epidermal growth factor receptor 2 (HER-2) negative primary tumors.</p><p><strong>Conclusions: </strong>Although CLDN18.2 expression in PM mirrored that in primary lesions, the levels were generally reduced. When zolbetuximab is used for GC patients with peritoneal involvement, it is preferable to assess the expression of CLDN18.2 in the disseminated lesions.</p>","PeriodicalId":15841,"journal":{"name":"Journal of gastrointestinal oncology","volume":"16 1","pages":"67-76"},"PeriodicalIF":2.0,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11921363/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143669973","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":"Construction and validation of a nomogram model for predicting peritoneal metastasis in gastric cancer based on ferroptosis-relate genes and clinicopathological features.","authors":"Xiaotong Sun, Kaipeng Duan, Xiaochun Shen, Chao Dong, Yajing Zhou, Tao Chen, Weikang Li, Peiyuan Li, Pengbo Wang, Dongbao Li, Jin Zhou","doi":"10.21037/jgo-24-670","DOIUrl":"10.21037/jgo-24-670","url":null,"abstract":"<p><strong>Background: </strong>Gastric cancer peritoneal metastasis (GCPM) is a lethal condition. Current diagnostic methods for GCPM, such as imaging and serum tumor markers, lack specificity and sensitivity. Research suggests that utilizing gene signatures to predict GCPM shows significant predictive ability. Nonetheless, the predictability of GCPM using ferroptosis-related genes (FRGs) remains unknown. We aim to construct a nomogram based on FRGs for early diagnosis of GCPM.</p><p><strong>Methods: </strong>RNA sequencing and clinical data of patients with gastric cancer (GC) were downloaded from Gene Expression Omnibus (GEO) databases. GCPM was diagnosed through imaging, biopsy and cytology. A GCPM prediction model was developed based on six distinctively expressed FRGs, and the efficiency of the model was assessed through receiver operating characteristic (ROC) curves in both experimental and validation cohorts. Subsequently, 115 clinical samples were examined by immunohistochemistry (IHC) to validate the prediction model's accuracy.</p><p><strong>Results: </strong>Our analysis included 282 patients, among whom 54 had GCPM while 228 did not. Patients were randomly distributed into experimental and validation groups at a 3:2 ratio. Least absolute shrinkage and selection operator (LASSO) regression identified the coefficients of six FRGs, with a risk score calculated for every patient. Univariate and multivariate logistic analyses revealed that both risk score and pathological stage were significantly associated with GCPM. The area under the curve (AUC) values for the training and validating sets implied good predictability for GCPM (0.827 and 0.767, respectively). Combining the risk score with the tumor node metastasis (TNM) stage substantially improved predictability (AUCs were 0.916 and 0.848 respectively). Lastly, a nomogram incorporating the risk score and TNM stage was constructed, which shows good clinical utility through decision curve analysis (DCA). The IHC results from 115 clinical samples were consistent with these findings.</p><p><strong>Conclusions: </strong>A nomogram model based on FRGs and clinicopathological features was constructed, demonstrating impressive predictive value for GCPM. This enables timely and personalized therapeutic interventions, thereby benefiting gastric cancer patients.</p>","PeriodicalId":15841,"journal":{"name":"Journal of gastrointestinal oncology","volume":"16 1","pages":"264-280"},"PeriodicalIF":2.0,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11921409/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143670105","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}
Yi Zhou, Bin Guo, Honghao Zhou, Nan Wang, Zhenyu Xiao
{"title":"Conversion resection of initially unresectable hepatocellular carcinoma associated with steatohepatitis through hepatic artery infusion chemotherapy-transarterial chemoembolization and systemic therapy: a case report.","authors":"Yi Zhou, Bin Guo, Honghao Zhou, Nan Wang, Zhenyu Xiao","doi":"10.21037/jgo-24-640","DOIUrl":"10.21037/jgo-24-640","url":null,"abstract":"<p><strong>Background: </strong>For advanced hepatocellular carcinoma (HCC), effective treatment options remain scarce. The risks of surgery and the likelihood of tumor residue restrict the use of liver resection. However, the combination of systemic therapy with locoregional treatments has recently demonstrated promising anti-tumor efficacy, offering new avenues for advanced HCC.</p><p><strong>Case description: </strong>We detail the case of a 61-year-old male who is free of viral hepatitis and alcohol consumption, but overweight with a body mass index (BMI) of 25.2 kg/m<sup>2</sup>. A magnetic resonance imaging (MRI), ultrasound, and blood tests were conducted, leading to a diagnosis of HCC associated with steatohepatitis, along with a combined portal vein tumor thrombus. Following four rounds of hepatic artery infusion chemotherapy combined with transarterial chemoembolization (HAIC-TACE), 7 cycles of sintilimab treatment, and lenvatinib, there was marked tumor reduction and thrombus retraction to a peripheral branch. The patient subsequently underwent curative liver resection. Pathology revealed extensive necrosis within the tumor region and chronic hepatitis with steatosis in the adjacent liver tissue. No viable tumor tissue was identified. Now about 6 months after the operation, the patient is still in a tumor-free state.</p><p><strong>Conclusions: </strong>In this instance, we detail the effective transition of an HCC patient, with underlying steatohepatitis, to a treatment regimen that included HAIC-TACE along with sintilimab and lenvatinib. This approach yielded potent antitumor activity and was notably devoid of severe side effects. The outcome of this case expands the therapeutic horizon for managing HCC in the context of steatohepatitis.</p>","PeriodicalId":15841,"journal":{"name":"Journal of gastrointestinal oncology","volume":"16 1","pages":"301-308"},"PeriodicalIF":2.0,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11921234/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143670108","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":"Erratum to Construction and validation of a predictive model for the risk of three-month-postoperative malnutrition in patients with gastric cancer: a retrospective case-control study.","authors":"","doi":"10.21037/jgo-2025-01","DOIUrl":"10.21037/jgo-2025-01","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.21037/jgo-22-1307.].</p>","PeriodicalId":15841,"journal":{"name":"Journal of gastrointestinal oncology","volume":"16 1","pages":"336-341"},"PeriodicalIF":2.0,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11921223/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143669966","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":"Hyperthermic intraperitoneal chemotherapy plus SOX chemotherapy versus SOX chemotherapy alone in patients with gastric cancer and peritoneal metastasis: a phase II randomized clinical trial.","authors":"Lijie Luo, Zijing Zhang, Haiping Zeng, Yuting Xu, Yaohui Peng, Haipeng Huang, Zeyu Lin, Wenjun Xiong, Wei Wang","doi":"10.21037/jgo-24-807","DOIUrl":"10.21037/jgo-24-807","url":null,"abstract":"<p><strong>Background: </strong>The prognosis of patients with gastric cancer with peritoneal metastasis (GCPM) is exceedingly poor. This study evaluated the efficacy and safety of hyperthermic intraperitoneal chemotherapy (HIPEC) with paclitaxel combined with S-1 and oxaliplatin (SOX) in the treatment of GCPM.</p><p><strong>Methods: </strong>Patients with pathologically confirmed primary gastric adenocarcinoma and laparoscopy-confirmed peritoneal metastasis were enrolled and randomized to receive either HIPEC plus SOX (HIPEC group) or SOX alone (SOX group). The primary endpoint was progression-free survival (PFS), and the secondary endpoints were 1-year survival rate, overall survival (OS), and safety.</p><p><strong>Results: </strong>Among the included patients, 30 were assigned to the HIPEC group and 29 to the SOX group. Compared to the HIPEC group, the SOX group had a significantly higher median PFS (SOX: median 8.5 months, IQR, 3.8-21.8 months; HIPEC: median 6.1 months, IQR, 3.3-10.8 months; P=0.004) and OS (SOX: median 13.0 months, IQR, 6.3-16.6 months; HIPEC: median 10.0 months, IQR, 5.2-24.0 months; P=0.02). The 1-year survival rate was 50.0% in the SOX group and 37.9% in HIPEC group, but the difference was not statistically significant. No serious adverse events related to the protocol treatment occurred in any patients.</p><p><strong>Conclusions: </strong>This trial failed to show the superiority of HIPEC with SOX over SOX alone. Further research into this regimen is needed.</p><p><strong>Trial registration: </strong>ClinicalTrials.gov NCT03604614.</p>","PeriodicalId":15841,"journal":{"name":"Journal of gastrointestinal oncology","volume":"16 1","pages":"17-26"},"PeriodicalIF":2.0,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11921333/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143669901","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":"The role of <i>TMSB15A</i> in gastric cancer progression and its prognostic significance.","authors":"Xiaolei Zhang, Xiang Yu, Qicheng Shen, Xiaohui Jiang, Yuan Zhou, Qiu Xue, Guangxin Cao","doi":"10.21037/jgo-2025-64","DOIUrl":"10.21037/jgo-2025-64","url":null,"abstract":"<p><strong>Background: </strong>Human thymosin β15 (<i>TMSB15A</i>) has been found to have protumorigenic effects in various malignant tumors, yet its function in gastric cancer (GC) remains unclear. This study investigated the value and function of <i>TMSB15A</i> in the diagnosis and tumorigenesis of GC, respectively.</p><p><strong>Methods: </strong>Expression data for TMSB15A in GC tissues were analyzed using The Cancer Genome Atlas (TCGA). We evaluated the prognostic significance of TMSB15A through Kaplan-Meier survival analysis, time-dependent receiver operating characteristic (ROC) curves, and Cox regression models. Gene set enrichment analysis (GSEA) was performed to identify pathways associated with TMSB15A. <i>In vitro</i> assays assessed the effects of TMSB15A knockdown on GC cell proliferation, migration, and invasion.</p><p><strong>Results: </strong>TMSB15A was significantly overexpressed in GC tissues compared to normal tissues (P<0.05). ROC analysis showed high diagnostic accuracy for TMSB15A (area under the curve =0.851, 95% confidence interval: 0.786-0.905, P<0.05). Kaplan-Meier survival analysis revealed that high TMSB15A expression was associated with poor overall survival, disease-specific survival, and progression-free survival. TMSB15A levels were correlated with advanced tumor stages (P<0.05), lymph node metastasis (P<0.01), and perineural invasion (P<0.05). GSEA showed significant enrichment of TMSB15A in inflammatory and oncogenic pathways, including interleukin-6 (IL-6)/Janus kinase (JAK)/signal transducer and activator of transcription 3 (STAT3), transforming growth factor β (TGF-β), and Hedgehog. Functional assays demonstrated that TMSB15A knockdown significantly reduced GC cell proliferation, migration, and invasion, suggesting that TMSB15A contributes to GC tumorigenesis and metastasis.</p><p><strong>Conclusions: </strong><i>TMSB15A</i> could serve as a prospective therapeutic target for GC due to its involvement in disease progression and metastasis.</p>","PeriodicalId":15841,"journal":{"name":"Journal of gastrointestinal oncology","volume":"16 1","pages":"27-40"},"PeriodicalIF":2.0,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11921194/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143669982","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}
Jiahao Zhou, Tinghan Yang, Xiangbing Deng, Ziqiang Wang
{"title":"Determining the optimal number of examined lymph nodes for prognosis in colon cancer: a population-based study stratified by tumor location and T stage.","authors":"Jiahao Zhou, Tinghan Yang, Xiangbing Deng, Ziqiang Wang","doi":"10.21037/jgo-24-576","DOIUrl":"10.21037/jgo-24-576","url":null,"abstract":"<p><strong>Background: </strong>Clinical guidelines recommend ≥12 examined lymph nodes (ELNs) for colon cancer staging, but more may be necessary for accuracy. This study utilized nodal staging scores (NSS) to identity the optimal number of ELNs based on tumor location and T stage, and to assess its prognostic impact.</p><p><strong>Methods: </strong>Data from 80,792 patients in the Surveillance, Epidemiology, and End Results (SEER) database (2004-2014) and 2,300 patients from the West China Hospital (WCH) cohort (2008-2014) with stage I-III resected colon cancer were analyzed. Optimal ELNs was estimated using a β-binomial distribution model, stratified by tumor location (left-sided, LS; right-sided, RS) and T stage. The primary outcome was overall survival (OS). The association between sufficient nodal staging and OS in node-negative patients was validated by multivariate Cox models.</p><p><strong>Results: </strong>The mean number of ELN was 18.75 in the SEER and 14.58 in the WCH database. There were 57.8% and 48.8% patients who had RS colon cancer in the SEER and WCH database. Fewer T3-4 tumors were observed in the SEER cohort compared to the WCH cohort (68.4% <i>vs.</i> 87.2%). Sufficient nodal staging required ≥24 ELNs for T3 tumors, ≥34 nodes for T4 LS tumors, and ≥40 nodes for T4 RS tumors. For T3 lesions, examining 20-29 ELNs were more likely to have node-positive disease [odd ratio (OR) 1.07; 95% confidence interval (CI): 1.01-1.12] compared to patients with 12-15 ELNs. In the T3N0 group, ELN ≥24 was independently associated with better OS in the SEER database [hazard ratio (HR) 0.72; 95% CI: 0.68-0.75], which was validated in the WCH cohort (HR 0.54; 95% CI: 0.38-0.76).</p><p><strong>Conclusions: </strong>Optimal ELNs for adequate colon cancer staging is related to both T stage and tumor location. We recommend that ≥24 lymph nodes be examined for T3 tumors, ≥34 for LS T4 tumors and ≥40 for RS T4 tumors for sufficient staging.</p>","PeriodicalId":15841,"journal":{"name":"Journal of gastrointestinal oncology","volume":"16 1","pages":"115-127"},"PeriodicalIF":2.0,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11921217/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143669167","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":"Predictive models of lymph node metastasis in patients with gastrointestinal stromal tumors based on machine learning algorithms: a SEER-based retrospective study.","authors":"Zheng Lin, Jianping Xiong, Caixin Feng, Shaochun Pang, Liangxue Lin, Feiran Zhang, Xun Chen, Yuandong Yuan, Peijie Xie, Ting Wu, Yanchong Li, Peihong Zheng, Haijie Xu, Ziqun Liao","doi":"10.21037/jgo-24-777","DOIUrl":"10.21037/jgo-24-777","url":null,"abstract":"<p><strong>Background: </strong>Gastrointestinal stromal tumor (GIST) is one of the most prevalent tumors in the digestive system. Due to the rarity of lymph node metastasis in patients with GISTs, there is a scarcity of related studies, which leads to ongoing debates regarding its impact on patient prognosis. This study aimed to analyze the impact of lymph node metastasis on the overall survival of GISTs patients and further building predictive models with machine learning algorithms.</p><p><strong>Methods: </strong>This is a retrospective study based on the Surveillance, Epidemiology and End Results (SEER) database. The demographic and clinicopathological characteristics of GISTs patients who underwent surgical therapy were collected from database. Five different types of machine learning algorithms were used to build the models. The ensemble models were based on the three algorithms with the highest sensitivity in the validating cohort. At last, receiver operator characteristic (ROC) curve, precision-recall curve (PRC), calibration curve, decision curve analysis (DCA) and Kaplan-Meier survival curve (KMC) were used to evaluate our models.</p><p><strong>Results: </strong>A total of 1,404 patients with GISTs were included in our study after data cleaning. Artificial Neural Network model [area under the ROC curve (AUC): 0.951, 95% confidence interval (CI): 0.901-0.992, sensitivity: 0.752] achieved the best performance in the validating cohort and was chosen to be the final model. Calibration plots showed good consistency between prediction and actual observations. Although the AUC between the final model and the baseline model showed no significant difference, the area under the PRC (PRAUC) of the final model (PRAUC =0.765) was significantly higher than that of the baseline model (PRAUC =0.455). DCA showed that the final model had high net benefit. Survival analysis indicated that the final model could distinguish the prognosis of patients significantly (all P<0.001).</p><p><strong>Conclusions: </strong>We used machine learning algorithms to build models that can accurately predict lymph node metastasis in GISTs patients.</p>","PeriodicalId":15841,"journal":{"name":"Journal of gastrointestinal oncology","volume":"16 1","pages":"53-66"},"PeriodicalIF":2.0,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11921308/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143669987","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}