Nomograms for Predicting the Lymph Node Metastasis in Early Gastric Cancer by Gender: A Retrospective Multicentric Study

Latest guideline of endoscopic submucosal dissection of early gastric cancer may not be suitable for Chinese patients: retrospective study findings from two centers

BACKGROUND

To analyze the diagnostic efficiency of the four absolute endoscopic submucosal dissection (ESD) indications for lymph node metastasis (LNM) of Chinese patients with early gastric cancer (EGC).

METHODS

We retrospectively analyzed EGC patients who underwent radical D2 gastrectomy from January 2019 to December 2022. We evaluated the rate of LNM, false-negative rate, and negative predictive value of the four ESD indications.

RESULTS

Of enrolled 2722 EGC patients, 388 (14.3%) patients presented LNM. Tumor size > 2 cm, ulceration, submucosal invasion, undifferentiated type, and lymphovascular invasion were independent risk factors of LNM in patients with EGC. 1062 (39%) cases of EGC conformed to the four EDS indications; however, 4% of them had LNM. 451 cases were fully in accord with the fourth ESD indication (undifferentiated intramucosal carcinoma without ulceration and a maximum lesion diameter of ≤ 2 cm), and 35 of them had LNM, with a false-negative rate (FNR) of 9.02% and a negative predictive value (NPV) of 92.24%. There was significant difference among the four indications in terms of the rate of LNM (1.0% vs 1.5% vs 1.3% vs 7.8%, P < 0.001), FNR (1.03% vs 0.52% vs 0.26% vs 9.02%, P < 0.001), and NPV (98.99% vs 98.53% vs 98.75% vs 92.24%, P < 0.001).

CONCLUSION

Overall, the fourth ESD indication was associated with a high rate of LNM compared to the other three indications. Thus, it might not be safe to classify it as an absolute indication in Chinese patients with EGC.

An artificial intelligence system for comprehensive pathologic outcome prediction in early gastric cancer through endoscopic image analysis (with video)

BACKGROUND

Accurate prediction of pathologic results for early gastric cancer (EGC) based on endoscopic findings is essential in deciding between endoscopic and surgical resection. This study aimed to develop an artificial intelligence (AI) model to assess comprehensive pathologic characteristics of EGC using white-light endoscopic images and videos.

METHODS

To train the model, we retrospectively collected 4,336 images and prospectively included 153 videos from patients with EGC who underwent endoscopic or surgical resection. The performance of the model was tested and compared to that of 16 endoscopists (nine experts and seven novices) using a mutually exclusive set of 260 images and 10 videos. Finally, we conducted external validation using 436 images and 89 videos from another institution.

RESULTS

After training, the model achieved predictive accuracies of 89.7% for undifferentiated histology, 88.0% for submucosal invasion, 87.9% for lymphovascular invasion (LVI), and 92.7% for lymph node metastasis (LNM), using endoscopic videos. The area under the curve values of the model were 0.992 for undifferentiated histology, 0.902 for submucosal invasion, 0.706 for LVI, and 0.680 for LNM in the test. In addition, the model showed significantly higher accuracy than the experts in predicting undifferentiated histology (92.7% vs. 71.6%), submucosal invasion (87.3% vs. 72.6%), and LNM (87.7% vs. 72.3%). The external validation showed accuracies of 75.6% and 71.9% for undifferentiated histology and submucosal invasion, respectively.

CONCLUSIONS

AI may assist endoscopists with high predictive performance for differentiation status and invasion depth of EGC. Further research is needed to improve the detection of LVI and LNM.

A nomogram based on platelet-to-lymphocyte ratio for predicting lymph node metastasis in patients with early gastric cancer

Background

Preoperative assessment of the presence of lymph node metastasis (LNM) in patients with early gastric cancer (EGC) remains difficult. We aimed to develop a practical prediction model based on preoperative pathological data and inflammatory or nutrition-related indicators.

Methods

This study retrospectively analyzed the clinicopathological characteristics of 1,061 patients with EGC who were randomly divided into the training set and validation set at a ratio of 7:3. In the training set, we introduced the least absolute selection and shrinkage operator (LASSO) algorithm and multivariate logistic regression to identify independent risk factors and construct the nomogram. Both internal validation and external validation were performed by the area under the receiver operating characteristic curve (AUC), C-index, calibration curve, and decision curve analysis (DCA).

Results

LNM occurred in 162 of 1,061 patients, and the rate of LNM was 15.27%. In the training set, four variables proved to be independent risk factors (p < 0.05) and were incorporated into the final model, including depth of invasion, tumor size, degree of differentiation, and platelet-to-lymphocyte ratio (PLR). The AUC values were 0.775 and 0.792 for the training and validation groups, respectively. Both calibration curves showed great consistency in the predictive and actual values. The Hosmer-Lemeshow (H-L) test was carried out in two cohorts, showing excellent performance with p-value >0.05 (0.684422, 0.7403046). Decision curve analysis demonstrated a good clinical benefit in the respective set.

Conclusion

We established a preoperative nomogram including depth of invasion, tumor size, degree of differentiation, and PLR to predict LNM in EGC patients and achieved a good performance.

Sex Disparity in Patients with Gastric Cancer: A Systematic Review and Meta-Analysis

OBJECTIVE

This systematic review and meta-analysis aimed to ascertain whether sex-based differences influence clinicopathological characteristics and survival outcomes of gastric cancer patients.

BACKGROUND

Gastric cancer in females has received less attention than in males. Clinicopathological features and survival outcomes of females with gastric cancer have been reported in several studies with controversial results.

METHODS

We systematically reviewed clinical studies from PubMed, Cochrane Library, Embase, and Web of Science published up to June 2022. The effect sizes of the included studies were estimated using odds ratios (ORs). Heterogeneity was investigated using the χ2 and I ² tests, while sensitivity analyses were performed to identify the source of substantial heterogeneity. All data used in this study were obtained from previously published studies obviating the need for ethical approval and patient consent.

RESULTS

Seventy-six studies with 775,003 gastric cancer patients were included in the meta-analysis. Gastric cancer patients were less likely to be females (P < 0.00001). Female patients were younger in age (P < 0.00001) and showed a higher percentage of distal (P < 0.00001), non-cardia (P < 0.00001), undifferentiated (P < 0.00001), diffuse (P < 0.00001), and signet-ring cell carcinoma (P < 0.00001). Female patients showed better prognosis in both 3-year (P = 0.0003) and 5-year overall survival (OS) (P < 0.00001), especially White patients. However, females were associated with lower 5-year OS relative to males in the younger patients (P = 0.0001).

CONCLUSIONS

In conclusion, gender differences were observed in clinicopathological characteristics and survival outcomes of gastric cancer. Different management of therapy will become necessary for different genders.

Establishment of a nomogram for predicting lymph node metastasis in patients with early gastric cancer after endoscopic submucosal dissection

Background

Endoscopic submucosal dissection (ESD) has been accepted as the standard treatment for the appropriate indication of early gastric cancer (EGC). Determining the risk of lymph node metastasis (LNM) is critical for the following treatment selection after ESD. This study aimed to develop a predictive model to quantify the probability of LNM in EGC to help minimize the invasive procedures.

Methods

A total of 952 patients with EGC who underwent radical gastrectomy were retrospectively reviewed. LASSO regression was used to help screen the potential risk factors. Multivariate logistic regression was used to establish a predictive nomogram, which was subjected to discrimination and calibration evaluation, bootstrapping internal validation, and decision curve analysis.

Results

Results of multivariate analyses revealed that gender, fecal occult blood test, CEA, CA19-9, histologic differentiation grade, lymphovascular invasion, depth of infiltration, and Ki67 labeling index were independent prognostic factors for LNM. The nomogram had good discriminatory performance, with a concordance index of 0.816 (95% CI 0.781–0.853). The validation dataset yielded a corrected concordance index of 0.805 (95% CI 0.770–0.842). High agreements between ideal curves and calibration curves were observed.

Conclusions

The nomogram is clinically useful for predicting LNM after ESD in EGC, which is beneficial to identifying patients who are at low risk for LNM and would benefit from avoiding an unnecessary gastrectomy.

Development and validation of a predictive model combining clinical, radiomics, and deep transfer learning features for lymph node metastasis in early gastric cancer

Background

This study aims to develop and validate a predictive model combining deep transfer learning, radiomics, and clinical features for lymph node metastasis (LNM) in early gastric cancer (EGC).

Materials and methods

This study retrospectively collected 555 patients with EGC, and randomly divided them into two cohorts with a ratio of 7:3 (training cohort, n = 388; internal validation cohort, n = 167). A total of 79 patients with EGC collected from the Second Affiliated Hospital of Soochow University were used as external validation cohort. Pre-trained deep learning networks were used to extract deep transfer learning (DTL) features, and radiomics features were extracted based on hand-crafted features. We employed the Spearman rank correlation test and least absolute shrinkage and selection operator regression for feature selection from the combined features of clinical, radiomics, and DTL features, and then, machine learning classification models including support vector machine, K-nearest neighbor, random decision forests (RF), and XGBoost were trained, and their performance by determining the area under the curve (AUC) were compared.

Results

We constructed eight pre-trained transfer learning networks and extracted DTL features, respectively. The results showed that 1,048 DTL features extracted based on the pre-trained Resnet152 network combined in the predictive model had the best performance in discriminating the LNM status of EGC, with an AUC of 0.901 (95% CI: 0.847-0.956) and 0.915 (95% CI: 0.850-0.981) in the internal validation and external validation cohorts, respectively.

Conclusion

We first utilized comprehensive multidimensional data based on deep transfer learning, radiomics, and clinical features with a good predictive ability for discriminating the LNM status in EGC, which could provide favorable information when choosing therapy options for individuals with EGC.

Machine learning for lymph node metastasis prediction of in patients with gastric cancer: A systematic review and meta-analysis

Objective

To evaluate the diagnostic performance of machine learning (ML) in predicting lymph node metastasis (LNM) in patients with gastric cancer (GC) and to identify predictors applicable to the models.

Methods

PubMed, EMBASE, Web of Science, and Cochrane Library were searched from inception to March 16, 2022. The pooled c-index and accuracy were used to assess the diagnostic accuracy. Subgroup analysis was performed based on ML types. Meta-analyses were performed using random-effect models. Risk of bias assessment was conducted using PROBAST tool.

Results

A total of 41 studies (56182 patients) were included, and 33 of the studies divided the participants into a training set and a test set, while the rest of the studies only had a training set. The c-index of ML for LNM prediction in training set and test set was 0.837 [95%CI (0.814, 0.859)] and 0.811 [95%CI (0.785-0.838)], respectively. The pooled accuracy was 0.781 [(95%CI (0.756-0.805)] in training set and 0.753 [95%CI (0.721-0.783)] in test set. Subgroup analysis for different ML algorithms and staging of GC showed no significant difference. In contrast, in the subgroup analysis for predictors, in the training set, the model that included radiomics had better accuracy than the model with only clinical predictors (F = 3.546, p = 0.037). Additionally, cancer size, depth of cancer invasion and histological differentiation were the three most commonly used features in models built for prediction.

Conclusion

ML has shown to be of excellent diagnostic performance in predicting the LNM of GC. One of the models covering radiomics and its ML algorithms showed good accuracy for the risk of LNM in GC. However, the results revealed some methodological limitations in the development process. Future studies should focus on refining and improving existing models to improve the accuracy of LNM prediction.

Systematic Review Registration

https://www.crd.york.ac.uk/PROSPERO/, identifier CRD42022320752

Nomograms Involving HER2 for Predicting Lymph Node Metastasis in Early Gastric Cancer

Objective: We aimed to establish a nomogram for predicting lymph node metastasis in early gastric cancer (EGC) involving human epidermal growth factor receptor 2 (HER2). Methods: We collected clinicopathological data of patients with EGC who underwent radical gastrectomy and D2 lymphadenectomy at Ruijin Hospital, Shanghai Jiao Tong University School of Medicine between January 2012 and August 2018. Univariate and multivariate logistic regression analysis were used to examine the relationship between lymph node metastasis and clinicopathological features. A nomogram was constructed based on a multivariate prediction model. Internal validation from the training set was performed using receiver operating characteristic (ROC) and calibration plots to evaluate discrimination and calibration, respectively. External validation from the validation set was utilized to examine the external validity of the prediction model using the ROC plot. A decision curve analysis was used to evaluate the benefit of the treatment. Results: Among 1,212 patients with EGC, 210 (17.32%) presented with lymph node metastasis. Multivariable analysis showed that age, tumor size, submucosal invasion, histological subtype, and HER2 positivity were independent risk factors for lymph node metastasis in EGC. The area under the ROC curve of the model was 0.760 (95% CI: 0.719-0.800) in the training set (n = 794) and 0.771 (95% CI: 0.714-0.828) in the validation set (n = 418). A predictive nomogram was constructed based on a multivariable prediction model. The decision curve showed that using the prediction model to guide treatment had a higher net benefit than using endoscopic submucosal dissection (ESD) absolute criteria over a range of threshold probabilities. Conclusion: A clinical prediction model and an effective nomogram with an integrated HER2 status were used to predict EGC lymph node metastasis with better accuracy and clinical performance.