Construction and validation of a nomogram model for lymph node metastasis of stage II-III gastric cancer based on machine learning algorithms

Background

Gastric cancer, a pervasive malignancy globally, often presents with regional lymph node metastasis (LNM), profoundly impacting prognosis and treatment options. Existing clinical methods for determining the presence of LNM are not precise enough, necessitating the development of an accurate risk prediction model.

Objective

Our primary objective was to employ machine learning algorithms to identify risk factors for LNM and establish a precise prediction model for stage II-III gastric cancer.

Methods

A study was conducted at Renji Hospital Affiliated to Shanghai Jiao Tong University School of Medicine between May 2010 and December 2022. This retrospective study analyzed 1147 surgeries for gastric cancer and explored the clinicopathological differences between LNM and non-LNM cohorts. Utilizing univariate logistic regression and two machine learning methodologies-Least absolute shrinkage and selection operator (LASSO) and random forest (RF)-we identified vascular invasion, maximum tumor diameter, percentage of monocytes, hematocrit (HCT), and lymphocyte-monocyte ratio (LMR) as salient factors and consolidated them into a nomogram model. The area under the receiver operating characteristic (ROC) curve (AUC), calibration curves, and decision curves were used to evaluate the test efficacy of the nomogram. Shapley Additive Explanation (SHAP) values were utilized to illustrate the predictive impact of each feature on the model's output.

Results

Significant differences in tumor characteristics were discerned between LNM and non-LNM cohorts through appropriate statistical methods. A nomogram, incorporating vascular invasion, maximum tumor diameter, percentage of monocytes, HCT, and LMR, was developed and exhibited satisfactory predictive capabilities with an AUC of 0.787 (95% CI: 0.749-0.824) in the training set and 0.753 (95% CI: 0.694-0.812) in the validation set. Calibration curves and decision curves affirmed the nomogram's predictive accuracy.

Conclusion

In conclusion, leveraging machine learning algorithms, we devised a nomogram for precise LNM risk prognostication in stage II-III gastric cancer, offering a valuable tool for tailored risk assessment in clinical decision-making.

Preoperatively predicting the lymph node metastasis and prognosis for gastric cancer patients

The preoperative distinguishment of lymph nodes (LN) with metastasis plays a pivotal role in guiding the surgical extension for gastric cancer (GC). We aim to identify the preparative risk factors for LN metastasis in GC patients. We retrospectively reviewed 424 patients who underwent radical GC resection in our medical center between Jan 2011 and Dec 2018. Multivariate logistic regression was employed to identify risk factors for LN metastasis, while multivariate COX regression was utilized to evaluate prognostic factors. The median overall survival of patients with or without LN metastases was 31 and 58 months, respectively. In multivariate analysis, lower albumin (OR = 0.512; P = 0.004) and prealbumin (OR = 0.367, P = 0.001) and higher CEA (OR = 3.178, P < 0.001), CA199 (OR = 2.278, P = 0.002) and platelets (OR = 1.697, P = 0.017) were found to be significantly associated with LN metastasis. In survival analysis, older age (HR = 1.712), larger tumors (HR = 1.082), higher D-dimer (HR = 1.561) and CA199 (HR = 1.553), advanced staging (stage II, HR = 3.446; stage III-IV, HR = 11.089), lower prealbumin levels (lower level for reference, HR = 0.63), and absence of adjuvant chemotherapy (HR = 0.396) was discovered to be associated with poorer overall survival (all P < 0.05). In conclusion, our results demonstrated that preoperative prealbumin-bound tumor markers can effectively predict LN metastasis. Additionally, prealbumin was found to possess prognostic value as well.

Predictive nomogram for lymph node metastasis and survival in gastric cancer using contrast-enhanced computed tomography-based radiomics: a retrospective study

Background

Lymph node involvement significantly impacts the survival of gastric cancer patients and is a crucial factor in determining the appropriate treatment. This study aimed to evaluate the potential of enhanced computed tomography (CT)-based radiomics in predicting lymph node metastasis (LNM) and survival in patients with gastric cancer before surgery.

Methods

Retrospective analysis of clinical data from 192 patients diagnosed with gastric carcinoma was conducted. The patients were randomly divided into a training cohort (n = 128) and a validation cohort (n = 64). Radiomic features of CT images were extracted using the Pyradiomics software platform, and distinctive features were further selected using a Lasso Cox regression model. Features significantly associated with LNM were identified through univariate and multivariate analyses and combined with radiomic scores to create a nomogram model for predicting lymph node involvement before surgery. The predictive performance of radiomics features, CT-reported lymph node status, and the nomogram model for LNM were compared in the training and validation cohorts by plotting receiver operating characteristic (ROC) curves. High-risk and low-risk groups were identified in both cohorts based on the cut-off value of 0.582 within the radiomics evaluation scheme, and survival rates were compared.

Results

Seven radiomic features were identified and selected, and patients were stratified into high-risk and low-risk groups using a 0.582 cut-off radiomics score. Univariate and multivariate analyses revealed that radiomics features, diabetes mellitus, Nutrition Risk Screening (NRS) 2002 score, and CT-reported lymph node status were significant predictors of LNM in patients with gastric cancer. A predictive nomogram model was developed by combining these predictors with the radiomics score, which accurately predicted LNM in gastric cancer patients before surgery and outperformed other models in terms of accuracy and sensitivity. The AUC values for the training and validation cohorts were 0.82 and 0.722, respectively. The high-risk and low-risk groups in both the training and validation cohorts showed significant differences in survival rates.

Conclusion

The radiomics nomogram, based on contrast-enhanced computed tomography (CECT ), is a promising non-invasive tool for preoperatively predicting LNM in gastric cancer patients and postoperative survival.

Association between neutrophil-lymphocyte ratio and lymph node metastasis in gastric cancer: A meta-analysis

INTRODUCTION AND AIM

The prognostic role of neutrophil to lymphocyte ratio (NLR) has been explored extensively in the literature. The aim of this meta-analysis was to evaluate the link between NLR and lymph node metastasis in gastric cancer. A method for increasing specificity and sensitivity of pre-treatment staging has implications on treatment algorithms and survival.

SEARCH STRATEGY

The relevant databases were searched as per the Preferred Reporting Items for Systematic Reviews and Meta-Analyses flowchart. After selection, 12 full text articles that met the inclusion criteria were included for quantitative analysis. 2 × 2 squares were generated using lymph node positive/negative, and NLR high/low data. The effect size for each study was calculated using the DerSimonian-Laird random effects model. P values were calculated using the chi-square method. Finally publication bias was evaluated. All statistics were calculated using R Studio.

RESULTS

Meta-analysis showed a 1.90 times (odds ratio, with 95% CI 1.52-2.38) increase in risk of positive lymph node status with high neutrophil to lymphocyte ratio. This has significant implications for cancer screening and staging, as NLR is a highly reproducible, cost-effective, and widely available prognostic factor for gastric cancer patients. Additionally, high or low NLR values may have implications for management pathways. Patients with lymph node metastasis can be offered neoadjuvant chemotherapy, avoiding salvage therapy in the form of adjuvant chemoradiotherapy, which is poorly tolerated.

CONCLUSION

This meta-analysis shows an association between NLR and positive lymph node status in gastric cancer patients with implications for staging, as well as preoperative personalisation of therapy.

Comparison of Docetaxel + Oxaliplatin + S-1 vs Oxalipatin + S-1 as Neoadjuvant Chemotherapy for Locally Advanced Gastric Cancer: A Propensity Score Matched Analysis

Background

What is the optimal neoadjuvant chemotherapy (NAC) regimen for locally advanced gastric cancer (LAGC) remains debatable. The objective of this study was to compare the efficacy of docetaxel+oxaliplatin+S-1 (DOS) vs oxaliplatin+S-1 (SOX) as NAC for LAGC.

Methods

Data of 248 LAGC patients who received either DOS or SOX as NAC in our hospital between January 2010 and January 2018 were reviewed retrospectively. Propensity score matched (PSM) analysis was applied to minimize the selection bias in both groups. Prognostic factors were screened by univariate and multivariate Cox regression analyses.

Results

Of the 248 LAGC patients included, 180 patients were subjected to the PSM analysis. Patients in DOS group showed a better tumor response to NAC, higher radical resection rate and R0 resection rate than those in SOX group. The overall survival (OS) rate in DOS group was better than that in SOX group, although the overall incidence of Grade 3/4 NAC-related toxicity in DOS group was higher, as represented by leukopenia and neutropenia. Multivariate analysis revealed that the NAC regimen, cTNM stage and the R0 resection rate were independent prognostic factors. In addition, patients with TLND less than 16 population showed a worse OS rate. Subgroup analysis indicated that patients benefited from the addition of docetaxel regardless of the clinical T stage, but those with high clinical N stages (N2-3) did not.

Conclusion

DOS is a safe and feasible NAC regimen for LAGC, which is worth popularizing in clinical practice.

Postoperative morbidity and mortality in patients receiving neoadjuvant chemotherapy for locally advanced gastric cancers: A systematic review and meta-analysis

AIM

To investigate the postoperative morbidity and mortality for neoadjuvant chemotherapy (NAC) plus surgery compared with surgery alone.

METHODS

PubMed and Embase were searched to capture the incidence of any postoperative complications, pulmonary complications, anastomotic leakage, surgical site infections, and postoperative mortality in randomized clinical trials comparing NAC plus surgery with surgery alone. The meta-analyses were performed with a random effects model.

RESULTS

Nine relevant studies were included. Comparing NAC with surgery alone, there were no increases in any postoperative complications, pulmonary complications, anastomotic leakage, surgical site infections, or postoperative mortality attributable to NAC. Sensitivity analysis suggested a possible increased risk of any postoperative complications compared with surgery alone: the risk difference 0.056 (95% confidence interval -0.032 to 0.145). Severe complications such as anastomotic leakage and pulmonary complications were similar in the 2 groups.

CONCLUSIONS

NAC for gastric cancer does not increase the risk of postoperative morbidity and mortality compared with surgery alone.

The prognostic value of negative lymph node count for patients with gastric cancer who received preoperative radiotherapy

Negative lymph node (NLN) count provides accurate prognostic information in patients with gastric cancer. However, it is unclear whether NLN still has prognostic value for patients received preoperative radiotherapy. In this study, Surveillance, Epidemiology, and End Results Program (SEER)-registered gastric cancer patients were used for analysis. Clinicopathological characteristics and survival time were collected. Univariate and multivariate Cox proportional hazards models were used to assess the risk factors for survival. NLN count was validated as an independent prognostic factor in both univariate and mulivariate analysis (P < 0.001). X-tile plots identified 12 as the optimal cutoff value to divide the patients into high and low risk subsets in terms of survival rate. Nomogram based on cancer-specific survival was successfully established according to all significant factors. The C-index was 0.630 (95% CI: 0.605–0.655). Subgroup analysis showed that NLN count was a prognosis factor for patients with advanced gastric cancer (stage ypII and ypIII). In conclusion, our results firmly demonstrated that NLN count was an independent prognostic factor for patients with gastric cancer who received preoperative radiotherapy. It provides more accurate prognostic information especially for patients with advanced gastric cancer (stage ypII and ypIII). Nomograms based on cancer-specific survival could be recommended as practical models to evaluate prognosis.

Clinical value of peripheral blood microRNA detection in evaluation of SOX regimen as neoadjuvant chemotherapy for gastric cancer

BACKGROUND

Neoadjuvant chemotherapy has been widely applied in treating advanced gastric cancer (GC). However, little research has been conducted on evaluating the effect of neoadjuvant chemotherapy. Purpose of this study was to evaluate the effect of SOX regimen as neoadjuvant chemotherapy by detecting some microRNAs.

METHODS

Total 120 GC patients who had received neoadjuvant chemotherapy (SOX regimen) were recruited with 100 healthy participants as control contemporarily. Age and gender have no significant difference in both groups (P > .05). The effect of chemotherapy was evaluated by the results of CT scan and surgery. Also, adverse effects of chemotherapy were documented. Peripheral blood of GC patients was collected twice: one day before chemotherapy and surgery, respectively, whereas healthy controls' peripheral blood was collected once. Quantitative real-time PCR (qPCR) was utilized to detect expression of miR-145, miR-185, miR-381, and miR-195 of peripheral blood in both groups.

RESULTS

One hundred and twenty patients with advanced GC completed a total of 386 cycles of neoadjuvant chemotherapy with effective rate at 84.17% (101 of 120). Expression of miR-145, miR-185, and miR-381 of patients with GC was lower than that in the control group before chemotherapy commence (all P < .05), while the expressions of miR-145 and miR-185 elevated noticeably in CG patients after neoadjuvant chemotherapy (P < .05). The differences in the expression of miR-145 and miR-185 in advanced GC patients with different chemotherapy outcomes were detected.

CONCLUSION

Patients with GC at advanced stages had aberrant miRs expressions. Detection of miR-145 and miR-185 expression may assist to predict effectiveness and adverse effects of SOX regimen as neoadjuvant chemotherapy.