Ejso最新文献

{"title":"Machine learning prediction of perineural invasion in intrahepatic cholangiocarcinoma","authors":"Guan Tan,&nbsp;Wen-Qiang Wang,&nbsp;Tong Yuan,&nbsp;Jun-Jie Liu,&nbsp;Zhen-Hui Xie,&nbsp;Zun-Yi Zhang,&nbsp;Zhi-Yong Huang","doi":"10.1016/j.ejso.2025.110203","DOIUrl":"10.1016/j.ejso.2025.110203","url":null,"abstract":"<div><h3>Objective</h3><div>Perineural invasion (PNI) significantly influences postoperative recurrence and survival in intrahepatic cholangiocarcinoma (ICC) patients. This study aims to develop and validate an interpretable model that can be used to predict PNI in ICC cases before surgery.</div></div><div><h3>Methods</h3><div>Retrospective clinical information was gathered from ICC patients (n = 250) at our hospital, covering the period from January 2012 to January 2022. The patients were randomly assigned to the training group (n = 176, 70.4 %) and validation group (n = 74, 29.6 %). We employed four machine learning algorithms to establish prediction models, each model's performance was assessed via a receiver operating characteristic (ROC) curve. Decision Curve Analysis (DCA) was performed to evaluate the models' risks and benefits. SHapley Additive exPlanations (SHAP) were used to quantify the contributions of model features, providing both global and local interpretations.</div></div><div><h3>Results</h3><div>Significant differences in tumor size, tumor number, lymph node metastasis, CA199, distant metastasis ratio, HBsAg, PLR, and NLR were observed between the PNI[-] (n = 172, 68.8 %) and PNI[+](n = 78, 31.2 %) groups. The PFS and OS rates in the PNI[-] group were better than those in the PNI[+] group. Based on the evaluation of the validation group, the XGBoost model demonstrated the best predictive performance. SHAP analysis identified tumor number, tumor size, and lymph node metastasis as the top three factors predicting PNI in ICC patients.</div></div><div><h3>Conclusion</h3><div>We developed a reliable predictive model that effectively predicts PNI status in patients with ICC and facilitates personalized clinical decision-making.</div></div>","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 9","pages":"Article 110203"},"PeriodicalIF":3.5,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144167830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Letter to the Editor “Clinical management and oncologic outcomes of pure pleomorphic and florid lobular carcinoma in situ of the breast: Results from a large single institution experience”","authors":"Qi Xu","doi":"10.1016/j.ejso.2025.110199","DOIUrl":"10.1016/j.ejso.2025.110199","url":null,"abstract":"","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 8","pages":"Article 110199"},"PeriodicalIF":3.5,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144169922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging automated machine learning to predict colon cancer prognosis from clinical features and risk groups: a retrospective cohort study","authors":"Jakob Woerner ,&nbsp;Yonghyun Nam ,&nbsp;Sang-Hyuk Jung ,&nbsp;Manu Shivakumar ,&nbsp;Matthew Lee ,&nbsp;Eun Kyung Choe ,&nbsp;Min Jung Kim ,&nbsp;Rumi Shin ,&nbsp;Seung-Bum Ryoo ,&nbsp;Seung-Yong Jeong ,&nbsp;Kyu Joo Park ,&nbsp;Sung Chan Park ,&nbsp;Dae Kyung Sohn ,&nbsp;Jae Hwan Oh ,&nbsp;Dokyoon Kim ,&nbsp;Ji Won Park","doi":"10.1016/j.ejso.2025.110194","DOIUrl":"10.1016/j.ejso.2025.110194","url":null,"abstract":"<div><h3>Background</h3><div>Predicting colon cancer recurrence is crucial for determining the need for adjuvant therapy after curative resection. However, clinical decisions often rely on limited features, even when a large amount of data is available.</div></div><div><h3>Methods</h3><div>We assessed the clinical utility of automated machine learning (AutoML) models to predict the prognosis of colon cancer patients from a tertiary hospital using clinical features, pathologic characteristics, and blood markers. We also compared these AutoML models to manually trained and tuned models and evaluated survival predictions.</div></div><div><h3>Results</h3><div>We found comparable performance between linear and ensemble models, and the predicted prognosis was significantly associated with overall survival and disease-free survival outcomes. Interpretable machine learning models identified T and N staging as important features and highlighted the prognostic immune and nutritional index (PINI) as a meaningful biomarker. The XGBoost model predicted prognosis with an AUC of 0.798 in an independent test set from a different hospital, demonstrating the model's interoperability. Additionally, the model was able to distinguish stage IIA patients that would benefit from adjuvant chemotherapy, a complex and difficult decision for clinicians. We also showed that simplified models generally maintained predictive accuracy, and that the automated approach was equally predictive as manually curated models.</div></div><div><h3>Conclusion</h3><div>With extensive validation through multiple test sets and internal cross-validation, this work underscores the potential of AutoML in identifying survival-related signatures in colon cancer from routinely collected data, providing clinicians with valuable insights for personalized treatment strategies.</div></div>","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 9","pages":"Article 110194"},"PeriodicalIF":3.5,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144212625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comment on: “Risk of distant metastasis after local excision for near-complete response versus salvage surgery for local regrowth in rectal cancer: Results from an international registry”","authors":"Quoc Riccardo Bao ,&nbsp;Lorenzo Dell’Atti ,&nbsp;Marco Scarpa ,&nbsp;Daniela Rega ,&nbsp;Paolo Delrio ,&nbsp;Angelo Restivo ,&nbsp;Giuditta Chiloiro ,&nbsp;Maria Antonietta Gambacorta ,&nbsp;Salvatore Pucciarelli ,&nbsp;Gaya Spolverato","doi":"10.1016/j.ejso.2025.110177","DOIUrl":"10.1016/j.ejso.2025.110177","url":null,"abstract":"","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 7","pages":"Article 110177"},"PeriodicalIF":3.5,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144220958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Letter to Editor: Exploring the application of FNA-Tg for the diagnosis of cervical lymph node metastasis in PTC","authors":"Aleena Ahmad","doi":"10.1016/j.ejso.2025.110152","DOIUrl":"10.1016/j.ejso.2025.110152","url":null,"abstract":"","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 9","pages":"Article 110152"},"PeriodicalIF":3.5,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144212628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Does surgical margin status truly affect local recurrence in benign and borderline phyllodes tumors of the breast?","authors":"Burak Dinçer ,&nbsp;Fisun Ardıç Yükrük ,&nbsp;Sultan Çiğdem Irkkan ,&nbsp;Cemal Kaya ,&nbsp;Ramazan Uçak ,&nbsp;Cihangir Özaslan","doi":"10.1016/j.ejso.2025.110195","DOIUrl":"10.1016/j.ejso.2025.110195","url":null,"abstract":"<div><h3>Background</h3><div>Phyllodes tumors of the breast are rare and classified into three groups—benign, borderline, and malignant—based on their malignant potential. Surgical resection is the primary treatment modality; however, the necessity of clear surgical margins remains a topic of debate in the literature. This study aimed to evaluate the relationship between surgical margin status and local recurrence in benign and borderline phyllodes tumors.</div></div><div><h3>Methods</h3><div>A total of 177 patients diagnosed with phyllodes tumors from two centers were included. Patients were analyzed based on demographic, clinical, pathological, and survival data.</div></div><div><h3>Results</h3><div>The median age was 38 years (range: 15–78), and all patients were female. The most commonly performed breast surgery was wide local excision in 173 patients (97.7 %). Final pathological examination revealed that 136 patients (76.8 %) had benign phyllodes tumors, while 41 patients (23.2 %) had borderline phyllodes tumors. The median pathological tumor diameter was 35 mm (IQR: 27–55 mm). During a median follow-up of 60 months, local recurrence occurred in 12 patients (6.8 %), while no systemic metastasis or tumor-related death was observed. Patients with borderline phyllodes tumors had a higher local recurrence rate and shorter recurrence-free survival (RFS) (p = 0.022 and p = 0.013, respectively). Cox regression analysis identified tumor type as the only independent factor affecting RFS, with borderline phyllodes tumors demonstrating a shorter RFS compared to benign phyllodes tumors (p = 0.015).</div></div><div><h3>Conclusion</h3><div>Surgical margin status was not associated with local recurrence in benign and borderline phyllodes tumors. Therefore, re-excision decisions based on margin proximity or positivity should be individualized.</div></div>","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 9","pages":"Article 110195"},"PeriodicalIF":3.5,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144167751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Re: Optimizing surgical timing following neoadjuvant therapy for gastric cancer: Insights from a multicenter retrospective analysis","authors":"Amir Masoud Karimi ,&nbsp;Amirmohammad Khosravi ,&nbsp;Nima Masoudi","doi":"10.1016/j.ejso.2025.110171","DOIUrl":"10.1016/j.ejso.2025.110171","url":null,"abstract":"","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 8","pages":"Article 110171"},"PeriodicalIF":3.5,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144212764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reply to: Re: Optimizing surgical timing following neoadjuvant therapy for gastric cancer: Insights from a multicenter retrospective analysis","authors":"Jie Chen,&nbsp;Fenglin Liu","doi":"10.1016/j.ejso.2025.110170","DOIUrl":"10.1016/j.ejso.2025.110170","url":null,"abstract":"","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 8","pages":"Article 110170"},"PeriodicalIF":3.5,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144480475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical contexts for Shared Decision-Making in rectal cancer: Organ preservation, sphincter-sparing surgery and tailored stoma policy","authors":"Barbara Noiret ,&nbsp;Chee Hoe Koo ,&nbsp;Manon Bacci ,&nbsp;Nathalie Bonichon Lamichhane ,&nbsp;Christophe Debelleix ,&nbsp;Hortense Franck ,&nbsp;Pauline Regnault ,&nbsp;Quentin Denost","doi":"10.1016/j.ejso.2025.110196","DOIUrl":"10.1016/j.ejso.2025.110196","url":null,"abstract":"<div><div>The management of rectal cancer has evolved into a patient-centered multidisciplinary approach emphasizing oncological safety, quality of life (QoL), and functional outcomes. Shared Decision-Making (SDM) plays a pivotal role in navigating treatment strategies that balance these aspects. Rather than reviewing existing SDM interventions, this narrative review explores clinical situations where SDM could significantly support the decision-making process.</div><div>We focus on three critical therapeutic domains: organ preservation, sphincter preservation and temporary stoma policies, where treatment decisions involve significant trade-offs and patients’ preferences. Emerging strategies like the “watch-and-wait\" approach and local excision in carefully selected patients have shown potential in preserving the rectum without compromising oncological outcomes. Sphincter-preserving techniques, including intersphincteric resection, offer alternatives to permanent stomas, though they require careful consideration of potential functional impacts such as Low Anterior Resection Syndrome (LARS). Regarding temporary stomas, innovations in closure timing and tailored risk stratification methods aim to reduce stoma-related complications and improve patient QoL.</div><div>This review examines the different therapeutic options, highlighting decision points where SDM can support individualized care and facilitate personalized treatment planning. By integrating SDM into these clinical pathways, healthcare teams and patients can collaboratively align treatment recommendations with patients’ preferences, ultimately improving outcomes and patient satisfaction.</div></div>","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 9","pages":"Article 110196"},"PeriodicalIF":3.5,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144184314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From data to Diagnosis: How artificial intelligence is revolutionizing preoperative assessment of thyroid nodules and cancer","authors":"Keyu Shen ,&nbsp;Meijuan Tan ,&nbsp;Yumeng Liu ,&nbsp;Xiequn Xu ,&nbsp;Shijie Yang","doi":"10.1016/j.ejso.2025.110191","DOIUrl":"10.1016/j.ejso.2025.110191","url":null,"abstract":"<div><h3>Background</h3><div>Thyroid nodules are frequently detected in the general population, raising concerns about the challenges of overdiagnosis and overtreatment. Artificial intelligence (AI) offers novel solutions for the preoperative evaluation of thyroid nodules. However, there has not yet been a comprehensive literature review on current applications.</div></div><div><h3>Methods</h3><div>We reviewed the preoperative assessment methodologies for thyroid nodules and delineated the latest advancements in the utilization of sophisticated AI within the preoperative evaluation framework.</div></div><div><h3>Results</h3><div>AI improves the accuracy of diagnostic procedures in preoperative evaluation of thyroid nodules by enhancing imaging, cytopathology diagnostics, and prognostic assessments. With its ability to automatically process large volumes of imaging and cytopathology data, AI minimizes reliance on clinical experience and reduces the occurrence of errors caused by subjective judgment. Furthermore, AI can integrate diverse data sources, providing a deeper understanding of the underlying value and interaction within the data, thereby enhancing comprehensive disease assessment and prognostic predictions.</div></div><div><h3>Conclusion</h3><div>The AI-assisted preoperative assessment approach improves diagnostic accuracy and robust evidence for developing individualized treatment strategies.</div></div>","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 9","pages":"Article 110191"},"PeriodicalIF":3.5,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144330692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}