Predictive value of machine learning models for lymph node metastasis in gastric cancer: A two-center study

BACKGROUND Gastric cancer is one of the most common malignant tumors in the digestive system,ranking sixth in incidence and fourth in mortality worldwide.Since 42.5%of metastatic lymph nodes in gastric cancer belong to nodule type and peripheral type,the application of imaging diagnosis is restricted.AIM To establish models for predicting the risk of lymph node metastasis in gastric cancer patients using machine learning(ML)algorithms and to evaluate their pre-dictive performance in clinical practice.METHODS Data of a total of 369 patients who underwent radical gastrectomy at the Depart-ment of General Surgery of Affiliated Hospital of Xuzhou Medical University(Xuzhou,China)from March 2016 to November 2019 were collected and retro-spectively analyzed as the training group.In addition,data of 123 patients who underwent radical gastrectomy at the Department of General Surgery of Jining First People’s Hospital(Jining,China)were collected and analyzed as the verifi-cation group.Seven ML models,including decision tree,random forest,support vector machine(SVM),gradient boosting machine,naive Bayes,neural network,and logistic regression,were developed to evaluate the occurrence of lymph node metastasis in patients with gastric cancer.The ML models were established fo-llowing ten cross-validation iterations using the training dataset,and subsequently,each model was assessed using the test dataset.The models’performance was evaluated by comparing the area under the receiver operating characteristic curve of each model.RESULTS Among the seven ML models,except for SVM,the other ones exhibited higher accuracy and reliability,and the influences of various risk factors on the models are intuitive.CONCLUSION The ML models developed exhibit strong predictive capabilities for lymph node metastasis in gastric cancer,which can aid in personalized clinical diagnosis and treatment.

Robotic-assisted retroperitoneal lymph node dissection for stage II testicular cancer

Objective:To evaluate the perioperative as well as early oncological outcomes of patients undergoing robotic retroperitoneal lymph node dissection for treatment of testicular cancer.Methods:We conducted a prospective consecutive case series of patients undergoing robotic assisted retroperitoneal lymph node dissection for metastatic testicular cancer between May 2018 and July 2021 at our institution.Data were collected on patient and tumour characteristics,intraoperative and postoperative parameters,and functional and oncological outcomes.Descriptive statistics are presented.Results:Nineteen patients were identified;18(94.7%)completed the procedure robotically and one was converted to open surgery;78.9%of patients had stage≥IIB and 12(63.2%)patients had undergone prior chemotherapy.The median operative time was 300(interquartile range[IQR]240-315)min.Median blood loss was 100(IQR 50-175)mL.Median length of stay was 2(range 1-11)days.All robotically completed patients commenced diet and passed flatus on Day 1 and were discharged by Day 3.The median lymph node yield was 40.5(IQR 38-51)nodes.All patients undergoing nerve-sparing procedures recovered antegrade ejaculatory function.One patient had a Clavien-Dindo III complication(chylous ascites requiring drainage).At a median follow-up of 22.3(IQR 16.3-24.9)months,one patient developed retroperitoneal recurrence,which was successfully treated with second-line chemotherapy;no other patients have had recurrences.Conclusion:Robotic retroperitoneal lymph node dissection is a safe and feasible alternative to open surgery in appropriately selected patients,offering low morbidity.Early oncological outcomes are promising.Larger cohorts and longer follow-ups are required to validate our institution's findings.

Magnetic resonance imaging-based lymph node radiomics for predicting the metastasis of evaluable lymph nodes in rectal cancer

BACKGROUND Lymph node(LN)staging in rectal cancer(RC)affects treatment decisions and patient prognosis.For radiologists,the traditional preoperative assessment of LN metastasis(LNM)using magnetic resonance imaging(MRI)poses a challenge.AIM To explore the value of a nomogram model that combines Conventional MRI and radiomics features from the LNs of RC in assessing the preoperative metastasis of evaluable LNs.METHODS In this retrospective study,270 LNs(158 nonmetastatic,112 metastatic)were randomly split into training(n=189)and validation sets(n=81).LNs were classified based on pathology-MRI matching.Conventional MRI features[size,shape,margin,T2-weighted imaging(T2WI)appearance,and CE-T1-weighted imaging(T1WI)enhancement]were evaluated.Three radiomics models used 3D features from T1WI and T2WI images.Additionally,a nomogram model combining conventional MRI and radiomics features was developed.The model used univariate analysis and multivariable logistic regression.Evaluation employed the receiver operating characteristic curve,with DeLong test for comparing diagnostic performance.Nomogram performance was assessed using calibration and decision curve analysis.RESULTS The nomogram model outperformed conventional MRI and single radiomics models in evaluating LNM.In the training set,the nomogram model achieved an area under the curve(AUC)of 0.92,which was significantly higher than the AUCs of 0.82(P<0.001)and 0.89(P<0.001)of the conventional MRI and radiomics models,respectively.In the validation set,the nomogram model achieved an AUC of 0.91,significantly surpassing 0.80(P<0.001)and 0.86(P<0.001),respectively.CONCLUSION The nomogram model showed the best performance in predicting metastasis of evaluable LNs.

Predictive value of positive lymph node ratio in patients with locally advanced gastric remnant cancer

BACKGROUND Traditional lymph node stage(N stage)has limitations in advanced gastric remnant cancer(GRC)patients;therefore,establishing a new predictive stage is necessary.AIM To explore the predictive value of positive lymph node ratio(LNR)according to clinicopathological characteristics and prognosis of locally advanced GRC.METHODS Seventy-four patients who underwent radical gastrectomy and lymphadenectomy for locally advanced GRC were retrospectively reviewed.The relationship between LNR and clinicopathological characteristics was analyzed.The survival analysis was performed using Kaplan-Meier survival curves and Cox regression model.RESULTS Number of metastatic LNs,tumor diameter,depth of tumor invasion,Borrmann type,serum tumor biomarkers,and tumor-node-metastasis(TNM)stage were correlated with LNR stage and N stage.Univariate analysis revealed that the factors affecting survival included tumor diameter,anemia,serum tumor biomarkers,vascular or neural invasion,combined resection,LNR stage,N stage,and TNM stage(all P<0.05).The median survival time for those with LNR0,LNR1,LNR2 and LNR3 stage were 61,31,23 and 17 mo,respectively,and the differences were significant(P=0.000).Anemia,tumor biomarkers and LNR stage were independent prognostic factors for survival in multivariable analysis(all P<0.05).CONCLUSION The new LNR stage is uniquely based on number of metastatic LNs,with significant prognostic value for locally advanced GRC,and could better differentiate overall survival,compared with N stage.

Nomogram established using risk factors of early gastric cancer for predicting the lymph node metastasis

BACKGROUND For the prognosis of patients with early gastric cancer(EGC),lymph node metastasis(LNM)plays a crucial role.A thorough and precise evaluation of the patient for LNM is now required.AIM To determine the factors influencing LNM and to construct a prediction model of LNM for EGC patients.METHODS Clinical information and pathology data of 2217 EGC patients downloaded from the Surveillance,Epidemiology,and End Results database were collected and analyzed.Based on a 7:3 ratio,1550 people were categorized into training sets and 667 people were assigned to testing sets,randomly.Based on the factors influencing LNM determined by the training sets,the nomogram was drawn and verified.RESULTS Based on multivariate analysis,age at diagnosis,histology type,grade,T-stage,and size were risk factors of LNM for EGC.Besides,nomogram was drawn to predict the risk of LNM for EGC patients.Among the categorical variables,the effect of grade(well,moderate,and poor)was the most significant prognosis factor.For training sets and testing sets,respectively,area under the receiver-operating characteristic curve of nomograms were 0.751[95%confidence interval(CI):0.721-0.782]and 0.786(95%CI:0.742-0.830).In addition,the calibration curves showed that the prediction model of LNM had good consistency.CONCLUSION Age at diagnosis,histology type,grade,T-stage,and tumor size were independent variables for LNM in EGC.Based on the above risk factors,prediction model may offer some guiding implications for the choice of subsequent therapeutic approaches for EGC.

Fifty-five cases of hepatic alveolar echinococcosis combined with lymph node metastasis:A retrospective study

BACKGROUND Lymph node metastasis is a specific type of metastasis in hepatic alveolar echinococcosis(AE).Currently,there is a scarcity of describing the clinical characteristics and lymph node metastasis rules of patients with hepatic AE combined with lymph node metastasis and its mechanism and management are still controversial.Radical hepatectomy combined with regional lymph node dissection is a better treatment.AIM To analyse the clinical features of hepatic AE combined with lymph node metastasis to explore its treatment and efficacy.METHODS A total of 623 patients with hepatic AE admitted to the First Affiliated Hospital of Xinjiang Medical University from 1 January 2012 to 1 January 2022 were retrospectively analysed.Fifty-five patients with combined lymph node metastasis were analysed for their clinical data,diagnosis and treatment methods,follow-up efficacy,and characteristics of lymph node metastasis.Finally,we comparatively analysed the lymph node metastasis rates at different sites.Categorical variables are expressed as frequencies and percentages,and the analysis of difference was performed using theχ2 test.The Bonferroni method was used for pairwise comparisons when statistical differences existed between multiple categorical variables.RESULTS A lymph node metastasis rate of 8.8%(55/623)was reported in patients with hepatic AE,with a female predilection(69.1%)and a statistically significant sex difference(χ2=8.018,P=0.005).Of the 55 patients with lymph node metastasis,72.7%had a parasite lesion,neighbouring organ invasion,and metastasis stage of P3N1M0 and above,of which 67.3%,78.2%,and 34.5%of hepatic AE lesions invaded the bile ducts,blood vessels,and distant metastases,respectively.Detection rates of lymph node metastasis of 16.4%,21.7%,and 34.2%were reported for a preoperative abdominal ultrasound,magnetic resonance imaging,and computed tomography examinations.All patients were intraoperatively suspected with enlarged lymph nodes and underwent radical hepatectomy combined with regional lymph node dissection.After surgery,a routine pathological examination was conducted on the resected lymph nodes.A total of 106 positive lymph nodes were detected in six groups at various sites,including 51 single-group metastasis cases and four multi-group metastasis cases.When the metastasis rates at different sites were statistically analysed,we observed that the metastasis rate in the para-hepatoduodenal ligament lymph nodes was significantly higher than that of the other sites(χ^(2)=128.089,P=0.000<0.05).No statistical difference was observed in the metastasis rate between the five other groups.Clavien-Dindo grade IIIa complication occurred in 14 cases,which improved after administering symptomatic treatment.Additionally,lymph node dissection-related complications were not observed.Recurrence after 2 years was observed in one patient.CONCLUSION Lymph node metastasis is a rare form of metastasis in hepatic AE,which is more frequent in women.Parahepatoduodenal ligament lymph nodes are commonly observed.Radical hepatectomy combined with regional lymph node dissection is a safe,effective,and feasible treatment for liver AE combined with lymph node metastasis.

Assessment of programmed death-ligand 1 expression in primary tumors and paired lymph node metastases of gastric adenocarcinoma

BACKGROUND Anti-programmed death-1/programmed death-ligand 1(PD-1/PD-L1)immuno-therapy has demonstrated promising results on gastric cancer(GC).However,PD-L1 can express differently between metastatic sites and primary tumors(PT).AIM To compare PD-L1 status in PT and matched lymph node metastases(LNM)of GC patients and to determine the correlation between the PD-L1 status and clinicopathological characteristics.METHODS We retrospectively reviewed 284 GC patients who underwent D2-gastrectomy.PD-L1 was evaluated by immunohistochemistry(clone SP142)using the com-bined positive score.All PD-L1+PT staged as pN+were also tested for PD-L1 expression in their LNM.PD-L1(-)GC with pN+served as the comparison group.RESULTS Among 284 GC patients included,45 had PD-L1+PT and 24 of them had pN+.For comparison,44 PD-L1(-)cases with pN+were included(sample loss of 4 cases).Of the PD-L1+PT,54.2%(13/24 cases)were also PD-L1+in the LNM.Regarding PD-L1(-)PT,9.1%(4/44)had PD-L1+in the LNM.The agreement between PT and LNM had a kappa value of 0.483.Larger tumor size and moderate/severe peritumoral inflammatory response were associated with PD-L1 positivity in both sites.There was no statistical difference in overall survival for PT and LNM according to the PD-L1 status(P=0.166 and P=0.837,respectively).CONCLUSION Intra-patient heterogeneity in PD-L1 expression was observed between the PT and matched LNM.This disagreement in PD-L1 status may emphasize the importance of considering different tumor sites for analyses to select patients for immunotherapy.

Management of lateral pelvic lymph nodes in rectal cancer:Is it time to reach an Agreement?

In this editorial,we proceed to comment on the article by Chua et al,addressing the management of metastatic lateral pelvic lymph nodes(mLLN)in stage II/III rectal cancer patients below the peritoneal reflection.The treatment of this nodal area sparks significant controversy due to the strategic differences followed by Eastern and Western physicians,albeit with a higher degree of convergence in recent years.The dissection of lateral pelvic lymph nodes without neoadjuvant therapy is a standard practice in Eastern countries.In contrast,in the West,preference leans towards opting for neoadjuvant therapy with chemoradiotherapy or radiotherapy,that would cover the treatment of this area without the need to add the dissection of these nodes to the total mesorectal excision.In the presence of high-risk nodal characteristics for mLLN related to radiological imaging and lack of response to neoadjuvant therapy,the risk of lateral local recurrence increases,suggesting the appropriate selection of strategies to reduce the risk of recurrence in each patient profile.Despite the heterogeneous and retrospective nature of studies addressing this area,an international consensus is necessary to approach this clinical scenario uniformly.

Feasibility and limitations of combined treatment for lateral pelvic lymph node metastases in rectal cancer

Colorectal cancer ranks among the most commonly diagnosed cancers globally,and is associated with a high rate of pelvic recurrence after surgery.In efforts to mitigate recurrence,pelvic lymph node dissection(PLND)is commonly advocated as an adjunct to radical surgery.Neoadjuvant chemoradiotherapy(NACRT)is a therapeutic approach employed in managing locally advanced rectal cancer,and has been found to increase the survival rates.Chua et al have proposed a combination of NACRT with selective PLND for addressing lateral pelvic lymph node metastases in rectal cancer patients,with the aim of reducing recurrence and improving survival outcomes.Nevertheless,certain studies have indicated that the addition of PLND to NACRT and total mesorectal excision did not yield a significant reduction in local recurrence rates or improvement in survival.Consequently,meticulous patient selection and perioperative chemotherapy may prove indispensable in ensuring the efficacy of PLND.

Nomogram based on multimodal magnetic resonance combined with B7-H3mRNA for preoperative lymph node prediction in esophagus cancer

Accurate preoperative prediction of lymph node metastasis(LNM)in esophageal cancer(EC)patients is of crucial clinical significance for treatment planning and prognosis.AIM To develop a clinical radiomics nomogram that can predict the preoperative lymph node(LN)status in EC patients.METHODS A total of 32 EC patients confirmed by clinical pathology(who underwent surgical treatment)were included.Real-time fluorescent quantitative reverse transcription-polymerase chain reaction was used to detect the expression of B7-H3 mRNA in EC tissue obtained during preoperative gastroscopy,and its correlation with LNM was analyzed.Radiomics features were extracted from multi-modal magnetic resonance imaging of EC using Pyradiomics in Python.Feature extraction,data dimensionality reduction,and feature selection were performed using XGBoost model and leave-one-out cross-validation.Multivariable logistic regression analysis was used to establish the prediction model,which included radiomics features,LN status from computed tomography(CT)reports,and B7-H3 mRNA expression,represented by a radiomics nomogram.Receiver operating characteristic area under the curve(AUC)and decision curve analysis(DCA)were used to evaluate the predictive performance and clinical application value of the model.RESULTS The relative expression of B7-H3 mRNA in EC patients with LNM was higher than in those without metastasis,and the difference was statistically significant(P<0.05).The AUC value in the receiver operating characteristic(ROC)curve was 0.718(95%CI:0.528-0.907),with a sensitivity of 0.733 and specificity of 0.706,indicating good diagnostic performance.The individualized clinical prediction nomogram included radiomics features,LN status from CT reports,and B7-H3 mRNA expression.The ROC curve demonstrated good diagnostic value,with an AUC value of 0.765(95%CI:0.598-0.931),sensitivity of 0.800,and specificity of 0.706.DCA indicated the practical value of the radiomics nomogram in clinical practice.CONCLUSION This study developed a radiomics nomogram that includes radiomics features,LN status from CT reports,and B7-H3 mRNA expression,enabling convenient preoperative individualized prediction of LNM in EC patients.

Prediction of lymph node metastasis in early gastric signet-ring cell carcinoma:A real-world retrospective cohort study

BACKGROUND Signet-ring cell carcinoma(SRCC)was previously thought to have a worse prognosis than other differentiated gastric cancer(GC),however,recent studies have shown that the prognosis of SRCC is related to pathological type.We hypothesize that patients with SRCC and with different SRCC pathological components have different probability of lymph node metastasis(LNM).AIM To establish models to predict LNM in early GC(EGC),including early gastric SRCC.METHODS Clinical data from EGC patients who had undergone gastrectomy at the First Affiliated Hospital of Nanjing Medical University from January 2012 to March 2022 were reviewed.The patients were divided into three groups based on type:Pure SRCC,mixed SRCC,and non-signet ring cell carcinoma(NSRC).The risk factors were identified through statistical tests using SPSS 23.0,R,and EmpowerStats software.RESULTS A total of 1922 subjects with EGC were enrolled in this study,and included 249 SRCC patients and 1673 NSRC patients,while 278 of the patients(14.46%)presented with LNM.Multivariable analysis showed that gender,tumor size,depth of invasion,lymphovascular invasion,ulceration,and histological subtype were independent risk factors for LNM in EGC.Establishment and analysis using prediction models of EGC showed that the artificial neural network model was better than the logistic regression model in terms of sensitivity and accuracy(98.0%vs 58.1%,P=0.034;88.4%vs 86.8%,P<0.001,respectively).Among the 249 SRCC patients,LNM was more common in mixed(35.06%)rather than in pure SRCC(8.42%,P<0.001).The area under the ROC curve of the logistic regression model for LNM in SRCC was 0.760(95%CI:0.682-0.843),while the area under the operating characteristic curve of the internal validation set was 0.734(95%CI:0.643-0.826).The subgroups analysis of pure types showed that LNM was more common in patients with a tumor size>2 cm(OR=5.422,P=0.038).CONCLUSION A validated prediction model was developed to recognize the risk of LNM in EGC and early gastric SRCC,which can aid in pre-surgical decision making of the best method of treatment for patients.

ScRNA-seq reveals the correlation between M2 phenotype of tumorassociated macrophages and lymph node metastasis of breast cancer

The process of lymphatic metastasis was proved to be associated with podoplanin-expressing macrophages in breast cancer(BC).This study aimed to investigate the role of the M2 phenotype of tumor-associated macrophages and mine the key M2 macrophages-related genes for lymph node metastasis in BC.We downloaded the GSE158399 dataset from the Gene Expression Omnibus(GEO)database,which includes transcriptomic profiles of individual cells from primary tumors,negative lymph nodes(NLNs),and positive lymph nodes(PLNs)of breast cancer patients.The cell subsets were identified by clustering analysis after quality control of the scRNA-seq using Seurat.The activation and migration capability of M2 macrophages were evaluated with R package“GSVA”.The key M2 macrophages-related genes were screened from the differential expressed genes(DEGs)and M2 macrophages activation and migration gene sets collected from MSigDB database.Our analysis identified three main cell types in primary tumors,NLNs,and PLNs:basal cells,luminal cells,and immune cell subsets.The further cell type classification of immune cell subsets indicated M2 macrophages accumulation in NLs and PLs.The GSVA enrichment scores for activation and migration capability were increased significantly in M2 macrophages from primary tumors than NLNs and PLNs(pvalue<0.001).Seven M2 macrophages activation-related and 15 M2 macrophages migration-related genes were significantly up-regulated in primary tumors than NLNs and PLNs.The proportion and GSVA enrichment scores for activation and migration of M2 macrophages may be potential markers for lymph node metastasis in breast cancer.Our study demonstrated that twenty-two up-regulated mRNA may be possible therapeutic targets for lymph node metastasis in breast cancer.

Predictive factors for lymph node metastasis and defining a subgroup treatable for laparoscopic lymph node dissection after endoscopic submucosal dissection in poorly differentiated early gastric cancer

AIM To investigate the predictive factors of lymph node metastasis(LNM)in poorly differentiated early gastric cancer(EGC);to guide the individual application of a combination of endoscopic submucosal dissection(ESD)and laparoscopic lymph node dissection(LLND)in a suitable subgroup of patients with poorly differentiated EGC.METHODS We retrospectively analyzed 138 patients with poorly differentiated EGC who underwent gastrectomy with lymphadenectomy between January 1990 and December 2015.The association between the clinicopathological factors and the presence of LNM was retrospectively analyzed by univariate and multivariate logistic regression analyses.Odds ratios(OR)with 95%confidence interval(95%CI)were calculated.We further examined the relationship between the positive number of the significant predictive factors and the LNM rate.RESULTS The tumor diameter(OR=13.438,95%CI:1.773-25.673,P=0.029),lymphatic vessel involvement(LVI)(OR=38.521,95%CI:1.975-68.212,P=0.015)and depth of invasion(OR=14.981,95%CI:1.617-52.844,P=0.024)were found to be independent risk factors for LNM by multivariate analysis.For the 138 patients diagnosed with poorly differentiated EGC,21(15.2%)had LNM.For patients with one,two and three of the risk factors,the LNM rates were 7.7%,47.6%and 64.3%,respectively.LNM was not found in 77 patients that did not have one or more of the three risk factors.CONCLUSION ESD might be sufficient treatment for intramucosal poorly differentiated EGC if the tumor is less than or equal to2 cm in size and when LVI is absent upon postoperative histological examination.ESD with LLND may lead to the elimination of unnecessary gastrectomy in poorly differentiated EGC.

Combination of endoscopic submucosal dissection and laparoscopic sentinel lymph node dissection in early mucinous gastric cancer:Role of lymph node metastasis

BACKGROUND Recent evidence showed that combining endoscopic submucosal dissection(ESD)and laparoscopic sentinel lymph node dissection may avoid unnecessary gastrectomy in treating early mucinous gastric cancer(EMGC)patients with risks of positive lymph node metastasis(pLNM).AIM To explore the predictive factors for pLNM in EMGC,and to optimize the clinical application of combing ESD and sentinel lymph node dissection in a proper subgroup of patients with EMGC.METHODS Thirty-one patients with EMGC who had undergone gastrectomy with lymph node dissection were consecutively enrolled from January 1988 to December 2016.Univariate and multivariate logistic regression analyses were used to estimate the association between the rates of pLNM and clinicopathological factors,providing odds ratio(OR)with 95%confidence interval.And the association between the number of predictors and the pLNM rate was also investigated.RESULTS Depth of invasion(OR=7.342,1.127-33.256,P=0.039),tumor diameter(OR=9.158,1.348-29.133,P=0.044),and lymphatic vessel involvement(OR=27.749,1.821-33.143,P=0.019)turned out to be significant and might be the independent risk factors for predicating pLNM in the multivariate analysis.For patients with 1,2,and 3 risk factors,the pLNM rates were 9.1%,33.3%,and 75.0%,respectively.pLNM was not detected in seven patients without any of these risk factors.CONCLUSION ESD might serve as a safe and sufficient treatment for intramucosal EMGC if tumor size≤2 cm,and when lymphatic vessel involvement is absent by postoperative histological examination.Combining ESD and sentinel lymph node dissection could be recommended as a safe and effective treatment for EMGC patients with a potential risk of pLNM.

Predicting lymph node metastasis in colorectal cancer:An analysis of influencing factors to develop a risk model

BACKGROUND Colorectal cancer(CRC)is a significant global health issue,and lymph node metastasis(LNM)is a crucial prognostic factor.Accurate prediction of LNM is essential for developing individualized treatment strategies for patients with CRC.However,the prediction of LNM is challenging and depends on various factors such as tumor histology,clinicopathological features,and molecular characteristics.The most reliable method to detect LNM is the histopathological examination of surgically resected specimens;however,this method is invasive,time-consuming,and subject to sampling errors and interobserver variability.AIM To analyze influencing factors and develop and validate a risk prediction model for LNM in CRC based on a large patient queue.METHODS This study retrospectively analyzed 300 patients who underwent CRC surgery at two Peking University Shenzhen hospitals between January and December 2021.A deep learning approach was used to extract features potentially associated with LNM from primary tumor histological images while a logistic regression model was employed to predict LNM in CRC using machine-learning-derived features and clinicopathological variables as predictors.RESULTS The prediction model constructed for LNM in CRC was based on a logistic regression framework that incorporated machine learning-extracted features and clinicopathological variables.The model achieved high accuracy(0.86),sensitivity(0.81),specificity(0.87),positive predictive value(0.66),negative predictive value(0.94),area under the curve for the receiver operating characteristic(0.91),and a low Brier score(0.10).The model showed good agreement between the observed and predicted probabilities of LNM across a range of risk thresholds,indicating good calibration and clinical utility.CONCLUSION The present study successfully developed and validated a potent and effective risk-prediction model for LNM in patients with CRC.This model utilizes machine-learning-derived features extracted from primary tumor histology and clinicopathological variables,demonstrating superior performance and clinical applicability compared to existing models.The study provides new insights into the potential of deep learning to extract valuable information from tumor histology,in turn,improving the prediction of LNM in CRC and facilitate risk stratification and decision-making in clinical practice.

Prediction of lymph node metastasis in early esophageal cancer

BACKGROUND Given the poor prognosis of patients with lymph node metastasis,estimating the lymph node status in patients with early esophageal cancer is crucial.Indicators that could be used to predict lymph node metastasis in early esophageal cancer have been reported in many recent studies,but no recent studies have included a review of this subject.AIM To review indicators predicting lymph node metastasis in early esophageal squamous cell carcinoma(ESCC)and early esophageal adenocarcinoma(EAC).METHODS We searched PubMed with“[early esophageal cancer(Title/Abstract)]and[lymph node(Title/Abstract)]”or“[early esophageal carcinoma(Title/Abstract)]and[lymph node(Title/Abstract)]”or“[superficial esophageal cancer(Title/Abstract)]and[lymph node(Title/Abstract)].”A total of 29 studies were eligible for analysis.RESULTS Preoperative imaging(size),serum markers(microRNA-218),postoperative pathology and immunohistochemical analysis(depth of invasion,tumor size,differentiation grade,lymphovascular invasion,neural invasion,expression of PIM-1<30%)were predictive factors for lymph node metastasis in both early ESCC and EAC.Serum markers(thymidine kinase 1≥3.38 pmol/L;cytokeratin 19 fragment antigen 21-1>3.30 ng/mL;stathmin-1)and postoperative pathology and immunohistochemical analysis(overexpression of cortactin,mixed-lineage leukaemia 2,and stanniocalcin-1)were predictive for lymph node metastasis in early ESCC.Transcription of CD69,myeloid differentiation protein 88 and toll-like receptor 4 and low expression of olfactomedin 4 were predictive of lymph node metastasis in early EAC.A total of 6 comprehensive models for early ESCC,including logistic regression model,nomogram,and artificial neural network(ANN),were reviewed.The areas under the receiver operating characteristic curve of these models reached 0.789-0.938,and the ANN performed best.As all these models relied on postoperative pathology,further models focusing on serum markers,imaging and immunohistochemical indicators are still needed.CONCLUSION Various factors were predictive of lymph node metastasis in early esophageal cancer,and present comprehensive models predicting lymph node metastasis in early ESCC mainly relied on postoperative pathology.Further studies focusing on serum markers,imaging and immunohistochemical indicators are still in need.

Establishment of Risk Prediction Model and Nomogram for Lymph Node Metastasis of Cervical Cancer: Based on SEER Database

Objective: To predict the risk factors of lymph node metastasis in cervical cancer by using large sample clinical data, and to construct and verify the nomogram for predicting lymph node metastasis. Methods: A total of 5940 patients with cervical cancer from 2004 to 2015 in the National Cancer Institute Surveillance Epidemiology and End Results database were retrospectively screened and randomly assigned to training group (n = 4172) and validation group (n = 1768). Multivariate Logistic regression analysis was used, and the optimal model was selected according to AIC or BIC and likelihood ratio test, and a nomogram was drawn. The accuracy and robustness of the prediction model were evaluated in three aspects: discrimination, calibration and clinical net benefit. Results: The prediction model based on race, tumor tissue differentiation degree, tumor histopathological type, distant metastasis of tumor, tumor diameter and other risk factors was successfully established and a nomogram was constructed. The AUCs of training group and validation group were: 0.736 and 0.714, respectively. And the p-values of the Hosmer-Lemeshow test were 0.28 and 0.11, respectively. The calibration curve was in good agreement with the ideal curve. It had high accuracy and applicability after internal verification. Conclusion: A prediction model is constructed based on the risk factors of lymph node metastasis of cervical cancer. The nomogram has a good effective prediction and can provide a theoretical basis for clinicians to assess the disease quickly before surgery.

Prediction of risk factors for lymph node metastasis in early gastric cancer

AIM:To explore risk factors for lymph node metastases in early gastric cancer(EGC) and to confirm the appropriate range of lymph node dissection.METHODS:A total of 202 patients with EGC who underwent curative gastrectomy with lymphadenectomy in the Department of Surgery,Xinhua Hospital and Ruijin Hospital of Shanghai Jiaotong University Medical School between November 2003 and July 2009,were retrospectively reviewed.Both the surgical procedure and the extent of lymph node dissection were based on the recommendations of the Japanese gastric cancer treatment guidelines.The macroscopic type was classified as elevated(type Ⅰ or Ⅱa),flat(Ⅱb),or depressed(Ⅱc or Ⅲ).Histopathologically,papillary and tubular adenocarcinomas were grouped together as differentiated adenocarcinomas,and poorly differentiated and signet-ring cell adenocarcinomas were regarded as undifferentiated adenocarcinomas.Univariate and multivariate analyses of lymph node metastases and patient and tumor characteristics were undertaken.RESULTS:The lymph node metastases rate in patients with EGC was 14.4%.Among these,the rate for mucosal cancer was 5.4%,and 8.9% for submucosal cancer.Univariate analysis showed an obvious correlation between lymph node metastases and tumor location,depth of invasion,morphological classification and venous invasion(χ 2 = 122.901,P = 0.001;χ 2 = 7.14,P = 0.008;χ 2 = 79.523,P = 0.001;χ 2 = 8.687,P = 0.003,respectively).In patients with submucosal cancers,the lymph node metastases rate in patients with venous invasion(60%,3/5) was higher than in those without invasion(20%,15/75)(χ 2 = 4.301,P = 0.038).Multivariate logistic regression analysis revealed that the depth of invasion was the only independent risk factor for lymph node metastases in EGC [P = 0.018,Exp(B) = 2.744].Among the patients with lymph node metastases,29 cases(14.4%) were at N1,seven cases were at N2(3.5%),and two cases were at N3(1.0%).Univariate analysis of variance revealed a close relationship between the depth of invasion and lymph node metastases at pN 1(P = 0.008).CONCLUSION:The depth of invasion was the only independent risk factor for lymph node metastases.Risk factors for metastases should be considered when choosing surgery for EGC.

Gastric cancer: Current status of lymph node dissection

D2 procedure has been accepted in Far East as the standard treatment for both early(EGC) and advanced gastric cancer(AGC) for many decades. Recently EGC has been successfully treated with endoscopy by endoscopic mucosal resection or endoscopic submucosal dissection, when restricted or extended Gotoda's criteria can be applied and D1+ surgery is offered only to patients not fitted for less invasive treatment. Furthermore, two randomised controlled trials(RCTs) have been demonstrating the non inferiority of minimally invasive technique as compared to standard open surgery for the treatment of early cases and recently the feasibility of adequate D1+ dissection has been demonstrated also for the robot assisted technique. In case of AGC the debate on the extent of nodal dissection has been open for many decades. While D2 gastrectomy was performed as the standard procedure in eastern countries, mostly based on observational and retrospective studies, in the west the Medical Research Council(MRC), Dutch and Italian RCTs have been conducted to show a survival benefit of D2 over D1 with evidence based medicine. Unfortunately both the MRC and the Dutch trials failed to show a survival benefit after the D2 procedure, mostly due to the significant increase of postoperative morbidity and mortality, which was referred to splenopancreatectomy. Only 15 years after the conclusion of its accrual, the Dutch trial could report a significant decrease of recur-rence after D2 procedure. Recently the long term survival analysis of the Italian RCT could demonstrate a benefit for patients with positive nodes treated with D2 gastrectomy without splenopancreatectomy. As nowadays also in western countries D2 procedure can be done safely with pancreas preserving technique and without preventive splenectomy, it has been suggested in several national guidelines as the recommended procedure for patients with AGC.

Precision surgical approach with lymph-node dissection in early gastric cancer

The gravest prognostic factor in early gastric cancer is lymph-node metastasis,with an incidence of about 10% overall. About two-thirds of early gastric cancer patients can be diagnosed as node-negative prior to treatment based on clinicpathological data. Thus, the tumor can be resected by endoscopic submucosal dissection. In the remaining third, surgical resection is necessary because of the possibility of nodal metastasis. Nevertheless, almost all patients can be cured by gastrectomy with D1+ lymph-node dissection. Laparoscopic or robotic gastrectomy has become widespread in East Asia because perioperative and oncological safety are similar to open surgery. However, after D1+ gastrectomy,functional symptoms may still result. Physicians must strive to minimize postgastrectomy symptoms and optimize long-term quality of life after this operation.Depending on the location and size of the primary lesion, preservation of the pylorus or cardia should be considered. In addition, the extent of lymph-node dissection can be individualized, and significant gastric-volume preservation can be achieved if sentinel node biopsy is used to distinguish node-negative patients.Though the surgical treatment for early gastric cancer may be less radical than in the past, the operative method itself seems to be still in transition.