IF 3.5 2区医学 Q2 ONCOLOGY

Ejso

Pub Date : 2025-02-21 DOI: 10.1016/j.ejso.2025.109720

Shadin Ghabra , David Chang , Paul H. Sugarbaker

Background

Tumor markers are used routinely for surveillance in patients treated for colorectal cancer (CRC). However, the prognostic implications of elevated preoperative tumor markers in patients treated for CRC and peritoneal metastases (PM) has not been well defined. The utility of carcinoembryonic antigen (CEA), carbohydrate antigen 19–9 (CA19-9) and cancer antigen 125 (CA125) to predict outcome for these patients is reported.

Methods

Clinical and histologic features plus preoperative tumor markers were recorded within 1 week prior to CRS. Impact on overall survival of these factors was analyzed by univariate and multivariate analysis.

Results

Two hundred and four patients were in our database and 140 patients (75.3 %) had at least a single elevated preoperative tumor marker. In an analysis of clinical and histologic parameters preoperatively, a poorly differentiated tumor, signet ring morphology, a peritoneal cancer index (PCI) of ≥16 and an incomplete cytoreduction had a negative impact on median survival. In a multivariate analysis of clinical and histologic features together with tumor markers, an elevated CA19-9 and CA125 was independently associated with reduced overall survival (HR 2.7, p < 0.0001 and HR 2.2, p = 0.005), respectively. Quantitative assessment of CEA (HR 0.5, p = 0.0094) and CA19-9 (HR 4.9, p < 0.001) greater than x10 ULN showed reduced survival.

Conclusion

Preoperative assessment of symptoms and histopathology, PCI and a complete CRS combined with tumor markers CEA, CA19-9 and CA125 are independent prognostic indicators for selection by the multidisciplinary team of CRC PM patients for CRS and HIPEC. All three tumor markers are needed for a meaningful assessment.

{"title":"Preoperative tumor marker elevations in colorectal cancer patients with peritoneal metastases should be used to help select patients for cytoreductive surgery","authors":"Shadin Ghabra , David Chang , Paul H. Sugarbaker","doi":"10.1016/j.ejso.2025.109720","DOIUrl":"10.1016/j.ejso.2025.109720","url":null,"abstract":"<div><h3>Background</h3><div>Tumor markers are used routinely for surveillance in patients treated for colorectal cancer (CRC). However, the prognostic implications of elevated preoperative tumor markers in patients treated for CRC and peritoneal metastases (PM) has not been well defined. The utility of carcinoembryonic antigen (CEA), carbohydrate antigen 19–9 (CA19-9) and cancer antigen 125 (CA125) to predict outcome for these patients is reported.</div></div><div><h3>Methods</h3><div>Clinical and histologic features plus preoperative tumor markers were recorded within 1 week prior to CRS. Impact on overall survival of these factors was analyzed by univariate and multivariate analysis.</div></div><div><h3>Results</h3><div>Two hundred and four patients were in our database and 140 patients (75.3 %) had at least a single elevated preoperative tumor marker. In an analysis of clinical and histologic parameters preoperatively, a poorly differentiated tumor, signet ring morphology, a peritoneal cancer index (PCI) of ≥16 and an incomplete cytoreduction had a negative impact on median survival. In a multivariate analysis of clinical and histologic features together with tumor markers, an elevated CA19-9 and CA125 was independently associated with reduced overall survival (HR 2.7, p < 0.0001 and HR 2.2, p = 0.005), respectively. Quantitative assessment of CEA (HR 0.5, p = 0.0094) and CA19-9 (HR 4.9, p < 0.001) greater than x10 ULN showed reduced survival.</div></div><div><h3>Conclusion</h3><div>Preoperative assessment of symptoms and histopathology, PCI and a complete CRS combined with tumor markers CEA, CA19-9 and CA125 are independent prognostic indicators for selection by the multidisciplinary team of CRC PM patients for CRS and HIPEC. All three tumor markers are needed for a meaningful assessment.</div></div>","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 6","pages":"Article 109720"},"PeriodicalIF":3.5,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143519341","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}

引用次数: 0

Invasive Pleomorphic Lobular Carcinoma of the breast: Clinicopathological features, treatment patterns and outcomes

IF 3.5 2区医学 Q2 ONCOLOGY

Ejso

Pub Date : 2025-02-20 DOI: 10.1016/j.ejso.2025.109714

N Peradze , A Polizzi , E Pagan , E Bottazzoli , V Bagnardi , C Sangalli , C Morigi , E De Camili , P Rafaniello Raviele , G Corso , V Galimberti , M Colleoni , P Veronesi

Introduction

Pleomorphic lobular carcinoma (PLC) is a rare variant of invasive lobular carcinoma of the breast (ILC) and few studies have reported controversial data regarding its outcomes.

The information provided appears to indicate that PLC is more aggressive and has worse outcome when compared to classical ILC (cILC); however, due to its rarity, studies with a considerable cohort of patients are lacking.

The purpose of this study was to compare the clinicopathological characteristics and disease outcomes of PLC patients to those with cILC in a large cohort from a single institution.

Methods

A retrospective comparative study was performed, including 226 patients with PLC and 2067 patients with cILC operated at the European Institute of Oncology (EIO) between 2001 and 2018. The median follow-up period for both groups was 7 years.

Results

5- and 10-years invasive disease-free survival were better in the matched classical lobular carcinoma patients compared to the pleomorphic variant.

The 5- and 10-years overall survival confirmed the trend previously seen in favor of the classical variant, with a 5-year survival of 98.4% vs 83.6% and a 10-year survival of 93.4% vs 69.5%, respectively.

Conclusions

The pleomorphic variant has been confirmed to be characterized by worse clinicopathological characteristics and worse clinical outcomes than the classical variant.

{"title":"Invasive Pleomorphic Lobular Carcinoma of the breast: Clinicopathological features, treatment patterns and outcomes","authors":"N Peradze , A Polizzi , E Pagan , E Bottazzoli , V Bagnardi , C Sangalli , C Morigi , E De Camili , P Rafaniello Raviele , G Corso , V Galimberti , M Colleoni , P Veronesi","doi":"10.1016/j.ejso.2025.109714","DOIUrl":"10.1016/j.ejso.2025.109714","url":null,"abstract":"<div><h3>Introduction</h3><div>Pleomorphic lobular carcinoma (PLC) is a rare variant of invasive lobular carcinoma of the breast (ILC) and few studies have reported controversial data regarding its outcomes.</div><div>The information provided appears to indicate that PLC is more aggressive and has worse outcome when compared to classical ILC (cILC); however, due to its rarity, studies with a considerable cohort of patients are lacking.</div><div>The purpose of this study was to compare the clinicopathological characteristics and disease outcomes of PLC patients to those with cILC in a large cohort from a single institution.</div></div><div><h3>Methods</h3><div>A retrospective comparative study was performed, including 226 patients with PLC and 2067 patients with cILC operated at the European Institute of Oncology (EIO) between 2001 and 2018. The median follow-up period for both groups was 7 years.</div></div><div><h3>Results</h3><div>5- and 10-years invasive disease-free survival were better in the matched classical lobular carcinoma patients compared to the pleomorphic variant.</div><div>The 5- and 10-years overall survival confirmed the trend previously seen in favor of the classical variant, with a 5-year survival of 98.4% vs 83.6% and a 10-year survival of 93.4% vs 69.5%, respectively.</div></div><div><h3>Conclusions</h3><div>The pleomorphic variant has been confirmed to be characterized by worse clinicopathological characteristics and worse clinical outcomes than the classical variant.</div></div>","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 6","pages":"Article 109714"},"PeriodicalIF":3.5,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143508096","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}

引用次数: 0

Artificial intelligence-based model to predict recurrence after local excision in T1 rectal cancer

IF 3.5 2区医学 Q2 ONCOLOGY

Ejso

Pub Date : 2025-02-20 DOI: 10.1016/j.ejso.2025.109717

Jiarui Su , Zhiyuan Liu , Haiming Li , Li Kang , Kaihong Huang , Jiawei Wu , Han Huang , Fei Ling , Xueqing Yao , Chengzhi Huang

Background

According to current guideline, patients with resected specimens showing high-risk features are recommended additional surgery after local excision (LE) of T1 colorectal cancer, despite the low incidence of recurrence. However, surgical resection in patients with low rectal cancer (RC) is challenging and may compromise anal function, leading to a low quality of life. To reduce unnecessary surgical resection in these patients, we used artificial intelligence (AI) to develop and validate a prediction model for the risk of recurrence after LE.

Materials and methods

We constructed an artificial neural network (ANN) to predict recurrence using pathological images from endoscopically or transanal surgically resected T1 RC specimens. Data were retrospectively obtained from two hospitals between 2001 and 2015. The model was constructed using 496 images obtained from the Guangdong Provincial People's Hospital (GDPH), and then validated using independent external datasets (150 images from Sun Yat-sen Memorial Hospital [SYSMH]) to verify its generalizability.

Results

The ANN model yielded good discrimination, achieving areas under the receiver operating characteristic curves (AUC) of 0.979 in the training cohort (GDPH). The AUC for the validation cohort (SYSMH) was 0.978. More importantly, the AI-based prediction model avoided more than 34.9 % of unnecessary additional surgeries compared with the current US guideline in all enrolled patients.

Conclusions

We propose a novel ANN model for the risk of recurrence prediction in patients with T1 RC to provide physicians and patients guidance for decisions after LE. Furthermore, this may lead to a reduction in unnecessary invasive surgeries in patients with T1 RC.

{"title":"Artificial intelligence-based model to predict recurrence after local excision in T1 rectal cancer","authors":"Jiarui Su , Zhiyuan Liu , Haiming Li , Li Kang , Kaihong Huang , Jiawei Wu , Han Huang , Fei Ling , Xueqing Yao , Chengzhi Huang","doi":"10.1016/j.ejso.2025.109717","DOIUrl":"10.1016/j.ejso.2025.109717","url":null,"abstract":"<div><h3>Background</h3><div>According to current guideline, patients with resected specimens showing high-risk features are recommended additional surgery after local excision (LE) of T1 colorectal cancer, despite the low incidence of recurrence. However, surgical resection in patients with low rectal cancer (RC) is challenging and may compromise anal function, leading to a low quality of life. To reduce unnecessary surgical resection in these patients, we used artificial intelligence (AI) to develop and validate a prediction model for the risk of recurrence after LE.</div></div><div><h3>Materials and methods</h3><div>We constructed an artificial neural network (ANN) to predict recurrence using pathological images from endoscopically or transanal surgically resected T1 RC specimens. Data were retrospectively obtained from two hospitals between 2001 and 2015. The model was constructed using 496 images obtained from the Guangdong Provincial People's Hospital (GDPH), and then validated using independent external datasets (150 images from Sun Yat-sen Memorial Hospital [SYSMH]) to verify its generalizability.</div></div><div><h3>Results</h3><div>The ANN model yielded good discrimination, achieving areas under the receiver operating characteristic curves (AUC) of 0.979 in the training cohort (GDPH). The AUC for the validation cohort (SYSMH) was 0.978. More importantly, the AI-based prediction model avoided more than 34.9 % of unnecessary additional surgeries compared with the current US guideline in all enrolled patients.</div></div><div><h3>Conclusions</h3><div>We propose a novel ANN model for the risk of recurrence prediction in patients with T1 RC to provide physicians and patients guidance for decisions after LE. Furthermore, this may lead to a reduction in unnecessary invasive surgeries in patients with T1 RC.</div></div>","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 6","pages":"Article 109717"},"PeriodicalIF":3.5,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143550927","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}

引用次数: 0

Additional breast lesions on MRI in patients with small early stage luminal type breast cancer: Important consequences for future thermal ablation treatment

IF 3.5 2区医学 Q2 ONCOLOGY

Ejso

Pub Date : 2025-02-19 DOI: 10.1016/j.ejso.2025.109715

Sophie M. Wooldrik , Linda Riks , Gerson M. Struik , Frank Hulsebosch , Cornelis Verhoef , Taco M.A.L. Klem

In this study, data from 50 postmenopausal women with unilateral cT1N0 breast cancer, who underwent MRI as part of the THERMAC trial for a thermal ablation protocol, were analyzed. Additional MRI findings were classified as benign or malignant based on histopathology. Results showed that 30 % of patients had additional MRI findings, with 40 % of those being malignant, which led to exclusion from the trial and altered surgical management. Malignant lesions included lobular carcinoma, NST tumors, and multifocal/multicentric disease, while benign findings were predominantly fibroadenomas, cysts, and mastopathy. Malignant lesions required changes in the treatment approach, including exclusion from the ablation protocol, wider excisions, and in some cases, mastectomy. The study highlights the significant role of MRI in patient selection and treatment planning, emphasizing the need for further investigation into the long-term oncological outcomes in early-stage breast cancer patients.

{"title":"Additional breast lesions on MRI in patients with small early stage luminal type breast cancer: Important consequences for future thermal ablation treatment","authors":"Sophie M. Wooldrik , Linda Riks , Gerson M. Struik , Frank Hulsebosch , Cornelis Verhoef , Taco M.A.L. Klem","doi":"10.1016/j.ejso.2025.109715","DOIUrl":"10.1016/j.ejso.2025.109715","url":null,"abstract":"<div><div>In this study, data from 50 postmenopausal women with unilateral cT1N0 breast cancer, who underwent MRI as part of the THERMAC trial for a thermal ablation protocol, were analyzed. Additional MRI findings were classified as benign or malignant based on histopathology. Results showed that 30 % of patients had additional MRI findings, with 40 % of those being malignant, which led to exclusion from the trial and altered surgical management. Malignant lesions included lobular carcinoma, NST tumors, and multifocal/multicentric disease, while benign findings were predominantly fibroadenomas, cysts, and mastopathy. Malignant lesions required changes in the treatment approach, including exclusion from the ablation protocol, wider excisions, and in some cases, mastectomy. The study highlights the significant role of MRI in patient selection and treatment planning, emphasizing the need for further investigation into the long-term oncological outcomes in early-stage breast cancer patients.</div></div>","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 6","pages":"Article 109715"},"PeriodicalIF":3.5,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Management strategies following recurrence of resected retroperitoneal sarcoma: A 10-year observational study

IF 3.5 2区医学 Q2 ONCOLOGY

Ejso

Pub Date : 2025-02-19 DOI: 10.1016/j.ejso.2025.109704

R.A. Young , T.M. Gilbert , A. Leppert , M. Griffin , G. Poston , R.P. Jones , H.Z. Malik

Background

In management of retroperitoneal sarcoma (RPS), radical resection remains the main facet of curative treatment. While recurrence is common, a clear consensus does not exist around optimal post-operative surveillance and post recurrence management.

Materials and methods

Patients undergoing resection for RPS over a 10 year period were identified through a prospectively maintained database. Patients underwent surveillance imaging with intensity dependant on risk of disease recurrence. Rates of recurrence, post recurrence therapeutic modalities and outcomes were recorded.

Results

105 patients underwent primary resection of RPS in the study period. 5-year survival of patients with low-risk and high-risk of disease recurrence was 74 % and 49 % respectively. Of the 58 patients that suffered disease recurrence, 29 patients with primary recurrence underwent further surgery, 10 patients with oligo-metastatic disease underwent curative intent management and 12 patients underwent chemotherapy (median survival: 6.5 vs 4.0 vs 1.7 years, 5-year survival: 71 % vs 45 % vs 12 %). The cost of surveillance imaging to identify recurrence treated with curative intent was calculated at £5434 and £2269 for low- and high-risk disease respectively.

Conclusions

Post resectional surveillance detects recurrence, allowing further intervention. Such strategies include surgical re-resection, interventional ablation or ablative radiotherapy of oligometastatic disease, and palliative chemotherapy; multifaceted therapeutic options which sit within current management guidelines. Patients with local recurrence who underwent further resection and those who underwent curative-intent management for other metastatic disease had improved outcomes compared to patients with widespread disease recurrence who underwent systemic chemotherapy. The costs of surveillance imaging fit within current UK healthcare economic policy guidelines.

{"title":"Management strategies following recurrence of resected retroperitoneal sarcoma: A 10-year observational study","authors":"R.A. Young , T.M. Gilbert , A. Leppert , M. Griffin , G. Poston , R.P. Jones , H.Z. Malik","doi":"10.1016/j.ejso.2025.109704","DOIUrl":"10.1016/j.ejso.2025.109704","url":null,"abstract":"<div><h3>Background</h3><div>In management of retroperitoneal sarcoma (RPS), radical resection remains the main facet of curative treatment. While recurrence is common, a clear consensus does not exist around optimal post-operative surveillance and post recurrence management.</div></div><div><h3>Materials and methods</h3><div>Patients undergoing resection for RPS over a 10 year period were identified through a prospectively maintained database. Patients underwent surveillance imaging with intensity dependant on risk of disease recurrence. Rates of recurrence, post recurrence therapeutic modalities and outcomes were recorded.</div></div><div><h3>Results</h3><div>105 patients underwent primary resection of RPS in the study period. 5-year survival of patients with low-risk and high-risk of disease recurrence was 74 % and 49 % respectively. Of the 58 patients that suffered disease recurrence, 29 patients with primary recurrence underwent further surgery, 10 patients with oligo-metastatic disease underwent curative intent management and 12 patients underwent chemotherapy (median survival: 6.5 vs 4.0 vs 1.7 years, 5-year survival: 71 % vs 45 % vs 12 %). The cost of surveillance imaging to identify recurrence treated with curative intent was calculated at £5434 and £2269 for low- and high-risk disease respectively.</div></div><div><h3>Conclusions</h3><div>Post resectional surveillance detects recurrence, allowing further intervention. Such strategies include surgical re-resection, interventional ablation or ablative radiotherapy of oligometastatic disease, and palliative chemotherapy; multifaceted therapeutic options which sit within current management guidelines. Patients with local recurrence who underwent further resection and those who underwent curative-intent management for other metastatic disease had improved outcomes compared to patients with widespread disease recurrence who underwent systemic chemotherapy. The costs of surveillance imaging fit within current UK healthcare economic policy guidelines.</div></div>","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 7","pages":"Article 109704"},"PeriodicalIF":3.5,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143562998","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}

引用次数: 0

Identification of a gene signature and prediction of overall survival of patients with stage IV colorectal cancer using a novel machine learning approach

IF 3.5 2区医学 Q2 ONCOLOGY

Ejso

Pub Date : 2025-02-19 DOI: 10.1016/j.ejso.2025.109718

Abdullah Altaf , Jun Kawashima , Mujtaba Khalil , Hunter Stecko , Zayed Rashid , Matthew Kalady , Timothy M. Pawlik

Objective

We sought to characterize unique gene signature patterns associated with worse overall survival (OS) among patients with stage IV colorectal cancer (CRC) using a machine learning (ML) approach.

Methods

Data from the AACR GENIE registry were analyzed for genetic variations (somatic mutations, structural variants and copy number alterations) among patients with CRC. Adult patients (≥18 years) with histologically confirmed stage IV CRC who underwent next-generation sequencing were included. An eXtreme Gradient Boosting (XGBoost) model was developed to predict OS and the relative importance of different genetic alterations was determined using SHapley Additive exPlanations (SHAP) algorithm.

Results

Among 688 patients with stage IV CRC, 54.4 % were male (n = 374) with a median age of 55 years (IQR, 46–64). An XGBoost model developed using the 200 most frequent genetic alterations demonstrated good performance to predict OS with a c-index of 0.701 (95 % CI: 0.675–0.726) on 5-fold cross-validation. The model achieved time-dependent AUC of 0.742, 0.757 and 0.793 at 12-, 24- and 36-months, respectively. The SHAP algorithm identified the top 20 genetic alterations most strongly predictive of worse OS among stage IV CRC patients. Based on the 20-gene signature, individuals at high risk had worse 12- and 36-month OS versus low-risk patients (82.6 % vs. 97.1 % and 30.1 % vs. 72.6 %, respectively; p < 0.001).

Conclusion

The XGBoost ML model identified a unique gene signature that accurately risk stratified stage IV CRC patients. ML models that incorporate molecular information represent an opportunity to predict long-term outcomes and potentially identify novel therapeutic targets for stage IV CRC patients.

{"title":"Identification of a gene signature and prediction of overall survival of patients with stage IV colorectal cancer using a novel machine learning approach","authors":"Abdullah Altaf , Jun Kawashima , Mujtaba Khalil , Hunter Stecko , Zayed Rashid , Matthew Kalady , Timothy M. Pawlik","doi":"10.1016/j.ejso.2025.109718","DOIUrl":"10.1016/j.ejso.2025.109718","url":null,"abstract":"<div><h3>Objective</h3><div>We sought to characterize unique gene signature patterns associated with worse overall survival (OS) among patients with stage IV colorectal cancer (CRC) using a machine learning (ML) approach.</div></div><div><h3>Methods</h3><div>Data from the AACR GENIE registry were analyzed for genetic variations (somatic mutations, structural variants and copy number alterations) among patients with CRC. Adult patients (≥18 years) with histologically confirmed stage IV CRC who underwent next-generation sequencing were included. An eXtreme Gradient Boosting (XGBoost) model was developed to predict OS and the relative importance of different genetic alterations was determined using SHapley Additive exPlanations (SHAP) algorithm.</div></div><div><h3>Results</h3><div>Among 688 patients with stage IV CRC, 54.4 % were male (n = 374) with a median age of 55 years (IQR, 46–64). An XGBoost model developed using the 200 most frequent genetic alterations demonstrated good performance to predict OS with a c-index of 0.701 (95 % CI: 0.675–0.726) on 5-fold cross-validation. The model achieved time-dependent AUC of 0.742, 0.757 and 0.793 at 12-, 24- and 36-months, respectively. The SHAP algorithm identified the top 20 genetic alterations most strongly predictive of worse OS among stage IV CRC patients. Based on the 20-gene signature, individuals at high risk had worse 12- and 36-month OS versus low-risk patients (82.6 % vs. 97.1 % and 30.1 % vs. 72.6 %, respectively; p < 0.001).</div></div><div><h3>Conclusion</h3><div>The XGBoost ML model identified a unique gene signature that accurately risk stratified stage IV CRC patients. ML models that incorporate molecular information represent an opportunity to predict long-term outcomes and potentially identify novel therapeutic targets for stage IV CRC patients.</div></div>","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 5","pages":"Article 109718"},"PeriodicalIF":3.5,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471170","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}

引用次数: 0

Reply to: Enhancing feature importance analysis with Spearman's correlation with p-values: Recommendations for improving PHLF prediction.

IF 3.5 2区医学 Q2 ONCOLOGY

Ejso

Pub Date : 2025-02-17 DOI: 10.1016/j.ejso.2025.109686

Simone Famularo, Flavio Milana, Matteo Donadon

引用次数: 0

Efficacy and safety of subtotal pelvic peritonectomy for colorectal cancer patients with peritoneal metastasis confined to the pelvic cavity

IF 3.5 2区医学 Q2 ONCOLOGY

Ejso

Pub Date : 2025-02-16 DOI: 10.1016/j.ejso.2025.109703

Jinghua Tang , Leen Liao , Binyi Xiao , Qiaoqi Sui , Muxu Zheng, Wu Jiang, Kai Han, Lingheng Kong, Zhizhong Pan, Peirong Ding

Background

Cytoreductive surgery has shown survival benefits for colorectal cancer (CRC) patients with peritoneal metastasis. However, the optimal extent of peritonectomy remains controversial in cases of limited peritoneal metastases. This study modified selective pelvic peritonectomy (SPP) into subtotal pelvic peritonectomy (STPP) for metastasis confined to pelvic cavity, and aimed to evaluate its feasibility, safety, and impact on survival outcomes.

Materials and methods

CRC patients with limited peritoneal metastasis confined to the pelvic cavity who underwent CC0 (no macroscopic residual cancer remained) resection were included from a prospectively collected database. Surgical complications, disease-free survival (DFS), and overall survival (OS) were analyzed.

Results

A total of 67 patients were included (26 in the STPP group and 41 in the SPP group). Clinically, STPP was found to be feasible and without increased surgical complications or mortality rates. At a median follow-up of 33.9 months, the 3-year DFS was 65.9 % and 30.7 % in STPP and SPP groups, respectively (P = 0.002). The 3-year OS was 84.1 % and 68.5 % in STPP and SPP groups, respectively (P = 0.006). Moreover, STTP was independently associated with improved DFS (HR = 0.351, 95 % CI 0.165–0.745, P = 0.006) and OS (HR = 0.324, 95 % CI 0.116–0.902, P=0.032). Female gender was also independently associated with poor DFS (HR = 2.146, 95 % CI 1.078–4.271, P = 0.031). Among 24 female patients with remaining ovaries, 9 (37.5 %) cases developed metachronous ovarian metastasis, and of these 6 underwent a second operation.

Conclusions

Subtotal pelvic peritonectomy is associated with promising long-term outcomes in CRC patients with peritoneal metastasis confined to the pelvic cavity. Prophylactic bilateral oophorectomy should be strongly considered during cytoreductive surgery.

{"title":"Efficacy and safety of subtotal pelvic peritonectomy for colorectal cancer patients with peritoneal metastasis confined to the pelvic cavity","authors":"Jinghua Tang , Leen Liao , Binyi Xiao , Qiaoqi Sui , Muxu Zheng, Wu Jiang, Kai Han, Lingheng Kong, Zhizhong Pan, Peirong Ding","doi":"10.1016/j.ejso.2025.109703","DOIUrl":"10.1016/j.ejso.2025.109703","url":null,"abstract":"<div><h3>Background</h3><div>Cytoreductive surgery has shown survival benefits for colorectal cancer (CRC) patients with peritoneal metastasis. However, the optimal extent of peritonectomy remains controversial in cases of limited peritoneal metastases. This study modified selective pelvic peritonectomy (SPP) into subtotal pelvic peritonectomy (STPP) for metastasis confined to pelvic cavity, and aimed to evaluate its feasibility, safety, and impact on survival outcomes.</div></div><div><h3>Materials and methods</h3><div>CRC patients with limited peritoneal metastasis confined to the pelvic cavity who underwent CC0 (no macroscopic residual cancer remained) resection were included from a prospectively collected database. Surgical complications, disease-free survival (DFS), and overall survival (OS) were analyzed.</div></div><div><h3>Results</h3><div>A total of 67 patients were included (26 in the STPP group and 41 in the SPP group). Clinically, STPP was found to be feasible and without increased surgical complications or mortality rates. At a median follow-up of 33.9 months, the 3-year DFS was 65.9 % and 30.7 % in STPP and SPP groups, respectively (<em>P</em> <em>=</em> 0.002). The 3-year OS was 84.1 % and 68.5 % in STPP and SPP groups, respectively (<em>P</em> <em>=</em> 0.006). Moreover, STTP was independently associated with improved DFS (<em>HR</em> = 0.351, 95 % <em>CI</em> 0.165–0.745, <em>P</em> <em>=</em> 0.006) and OS (<em>HR</em> = 0.324, 95 % <em>CI</em> 0.116–0.902, <em>P=</em>0.032). Female gender was also independently associated with poor DFS (<em>HR</em> = 2.146, 95 % <em>CI</em> 1.078–4.271, <em>P</em> <em>=</em> 0.031). Among 24 female patients with remaining ovaries, 9 (37.5 %) cases developed metachronous ovarian metastasis, and of these 6 underwent a second operation.</div></div><div><h3>Conclusions</h3><div>Subtotal pelvic peritonectomy is associated with promising long-term outcomes in CRC patients with peritoneal metastasis confined to the pelvic cavity. Prophylactic bilateral oophorectomy should be strongly considered during cytoreductive surgery.</div></div>","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 5","pages":"Article 109703"},"PeriodicalIF":3.5,"publicationDate":"2025-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143512012","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}

引用次数: 0

Machine learning model based on preoperative contrast-enhanced CT and clinical features to predict perineural invasion in gallbladder carcinoma patients

IF 3.5 2区医学 Q2 ONCOLOGY

Ejso

Pub Date : 2025-02-16 DOI: 10.1016/j.ejso.2025.109697

Hengchao Liu, Zhenqi Tang, Xue Feng, Yali Cheng, Chen Chen, Dong Zhang, Jianjun Lei, Zhimin Geng, Qi Li

Background

Perineural invasion (PNI) is an independent prognostic risk factor for gallbladder carcinoma (GBC). However, there is currently no reliable method for the preoperative noninvasive prediction of PNI.

Methods

This retrospective study included 180 patients with pathologically diagnosed GBC who underwent preoperative contrast-enhanced CT between January 2022 to December 2023 at one high-volume medical center from China. K-Nearest Neighbors (KNN), LightGBM (LGB), Logistic Regression (LR), XGBoost (XGB), Naive Bayes (NB), and Support Vector Machine (SVM) were employed to develop prediction models. The Shapley additive explanations (SHAP) were used to visualize models and rank the importance of features associated with PNI.

Results

Total bilirubin, CA19-9, imaging liver invasion, vascular invasion, T staging and N staging were identified as risk factors for PNI (P < 0.05). The LightGBM model demonstrated the improved performance in the testing set, with the AUCs of 0.886 and 0.795 in the training and testing sets, respectively. In four machine learning algorithms prediction models demonstrated improved performance included three imaging features (imaging T staging, N staging, and vascular invasion) and two clinical features (TBIL and CA19-9). When these features were employed to develop the prediction models, the LightGBM model exhibited the higher performance than other machine learning modes in the testing set, with AUCs of 0.843 and 0.802, and ACCs of 0.786 and 0.759 in the training and testing sets, respectively.

Conclusion

A machine learning-based prediction model integrating contrast-enhanced CT imaging and clinical features demonstrates good performance and stability in the noninvasive preoperative identification of PNI status in GBC patients.

{"title":"Machine learning model based on preoperative contrast-enhanced CT and clinical features to predict perineural invasion in gallbladder carcinoma patients","authors":"Hengchao Liu, Zhenqi Tang, Xue Feng, Yali Cheng, Chen Chen, Dong Zhang, Jianjun Lei, Zhimin Geng, Qi Li","doi":"10.1016/j.ejso.2025.109697","DOIUrl":"10.1016/j.ejso.2025.109697","url":null,"abstract":"<div><h3>Background</h3><div>Perineural invasion (PNI) is an independent prognostic risk factor for gallbladder carcinoma (GBC). However, there is currently no reliable method for the preoperative noninvasive prediction of PNI.</div></div><div><h3>Methods</h3><div>This retrospective study included 180 patients with pathologically diagnosed GBC who underwent preoperative contrast-enhanced CT between January 2022 to December 2023 at one high-volume medical center from China. K-Nearest Neighbors (KNN), LightGBM (LGB), Logistic Regression (LR), XGBoost (XGB), Naive Bayes (NB), and Support Vector Machine (SVM) were employed to develop prediction models. The Shapley additive explanations (SHAP) were used to visualize models and rank the importance of features associated with PNI.</div></div><div><h3>Results</h3><div>Total bilirubin, CA19-9, imaging liver invasion, vascular invasion, T staging and N staging were identified as risk factors for PNI (<em>P</em> < 0.05). The LightGBM model demonstrated the improved performance in the testing set, with the AUCs of 0.886 and 0.795 in the training and testing sets, respectively. In four machine learning algorithms prediction models demonstrated improved performance included three imaging features (imaging T staging, N staging, and vascular invasion) and two clinical features (TBIL and CA19-9). When these features were employed to develop the prediction models, the LightGBM model exhibited the higher performance than other machine learning modes in the testing set, with AUCs of 0.843 and 0.802, and ACCs of 0.786 and 0.759 in the training and testing sets, respectively.</div></div><div><h3>Conclusion</h3><div>A machine learning-based prediction model integrating contrast-enhanced CT imaging and clinical features demonstrates good performance and stability in the noninvasive preoperative identification of PNI status in GBC patients.</div></div>","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 5","pages":"Article 109697"},"PeriodicalIF":3.5,"publicationDate":"2025-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471706","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}

引用次数: 0

Association between ERAS protocol and major postoperative complications and reasons for non-compliance in patients with esophageal cancer

IF 3.5 2区医学 Q2 ONCOLOGY

Ejso

Pub Date : 2025-02-16 DOI: 10.1016/j.ejso.2025.109707

Christian Geroin , Jacopo Weindelmayer , Serena Camozzi , Barbara Leone , Cecilia Turolo , Maria Bencivenga , Michele Sacco , Carlo Alberto De Pasqual , Ermes Vedovi , Simone Priolo , Simone Giacopuzzi

Introduction

The association between each Enhanced Recovery After Surgery (ERAS) component and the incidence of major postoperative complications following Ivor Lewis or McKeown surgery is understudied. Therefore, we wanted to determine the association between ERAS components, major postoperative complications, and the reasons for non-compliance with the ERAS program.

Methods

Data were extracted from the prospective ERAS Registry managed by the University of Verona, Italy. We searched and compared the data for postoperative major complications (Clavien-Dindo Classification ≥3B) and reasons for non-compliance with 15 ERAS items in patients undergoing Ivor Lewis or McKeown surgery with radical intent for esophageal or esophagogastric junction cancer.

Results

The study sample was 346 patients: 43 (12.4 %) experienced one or more postoperative major complications. When stratified by type of surgery, complications were more frequent after McKeown surgery than after Ivor Lewis surgery (15.5 % and 11.5 %, respectively). Organizational setbacks were the most common reason for non-compliance with the ERAS program. We identified several associations between clinical and patient demographic characteristics and 90-day postsurgical complications. The multivariate model indicated an association between fewer major postoperative complications after Ivor Lewis surgery and adherence to the protocol items “soft diet intake” (adjusted odds ratio [OR], 0.23; 95 % confidence interval [CI], 0.08–0.63) and “urinary catheter removal” (adjusted OR, 0.26; 95 % CI, 0.10–0.63).

Discussion/conclusions

Major complications are relatively frequent, especially after McKeown surgery. What remains uncertain is whether ERAS items can predict the occurrence of postoperative complications. Adherence to the protocol may be influenced by the co-occurrence of complications, comorbidities, and organizational setbacks.

{"title":"Association between ERAS protocol and major postoperative complications and reasons for non-compliance in patients with esophageal cancer","authors":"Christian Geroin , Jacopo Weindelmayer , Serena Camozzi , Barbara Leone , Cecilia Turolo , Maria Bencivenga , Michele Sacco , Carlo Alberto De Pasqual , Ermes Vedovi , Simone Priolo , Simone Giacopuzzi","doi":"10.1016/j.ejso.2025.109707","DOIUrl":"10.1016/j.ejso.2025.109707","url":null,"abstract":"<div><h3>Introduction</h3><div>The association between each Enhanced Recovery After Surgery (ERAS) component and the incidence of major postoperative complications following Ivor Lewis or McKeown surgery is understudied. Therefore, we wanted to determine the association between ERAS components, major postoperative complications, and the reasons for non-compliance with the ERAS program.</div></div><div><h3>Methods</h3><div>Data were extracted from the prospective ERAS Registry managed by the University of Verona, Italy. We searched and compared the data for postoperative major complications (Clavien-Dindo Classification ≥3B) and reasons for non-compliance with 15 ERAS items in patients undergoing Ivor Lewis or McKeown surgery with radical intent for esophageal or esophagogastric junction cancer.</div></div><div><h3>Results</h3><div>The study sample was 346 patients: 43 (12.4 %) experienced one or more postoperative major complications. When stratified by type of surgery, complications were more frequent after McKeown surgery than after Ivor Lewis surgery (15.5 % and 11.5 %, respectively). Organizational setbacks were the most common reason for non-compliance with the ERAS program. We identified several associations between clinical and patient demographic characteristics and 90-day postsurgical complications. The multivariate model indicated an association between fewer major postoperative complications after Ivor Lewis surgery and adherence to the protocol items “soft diet intake” (adjusted odds ratio [OR], 0.23; 95 % confidence interval [CI], 0.08–0.63) and “urinary catheter removal” (adjusted OR, 0.26; 95 % CI, 0.10–0.63).</div></div><div><h3>Discussion/conclusions</h3><div>Major complications are relatively frequent, especially after McKeown surgery. What remains uncertain is whether ERAS items can predict the occurrence of postoperative complications. Adherence to the protocol may be influenced by the co-occurrence of complications, comorbidities, and organizational setbacks.</div></div>","PeriodicalId":11522,"journal":{"name":"Ejso","volume":"51 5","pages":"Article 109707"},"PeriodicalIF":3.5,"publicationDate":"2025-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0