Modified AJCC staging of gastric neuroendocrine carcinoma based on T staging can improve the capacity of prognosis assessment

Machine Learning-Based Real-Time Survival Prediction for Gastric Neuroendocrine Carcinoma

BACKGROUND

This study aimed to develop a dynamic survival prediction model utilizing conditional survival (CS) analysis and machine learning techniques for gastric neuroendocrine carcinomas (GNECs).

PATIENTS AND METHODS

Data from the Surveillance, Epidemiology, and End Results (SEER) database (2004-2015) were analyzed and split into training and validation groups (7:3 ratio). CS profiles for patients with GNEC were examined in the full cohort. We utilized random survival forests (RSFs) and least absolute shrinkage and selection operator (LASSO) regression, alongside stepwise Cox regression, for variable selection. A CS-based nomogram was developed on the basis of key prognostic factors, followed by risk stratification and model validation.

RESULTS

We included 654 patients with GNEC in our study, with 457 assigned to the training set and 197 to the validation set. The CS analysis demonstrated that the probability of achieving 5-year CS improved from 48% immediately after diagnosis to 68%, 81%, 88%, and 94% after surviving an additional year (i.e., at 1, 2, 3, and 4 years, respectively). Through the use of RSFs and LASSO regression, combined with multivariable regression analysis, we identified the optimal combination of prognostic factors, which included age, tumor grade, tumor stage, surgery, and chemotherapy. Utilizing these prognostic indicators, we successfully developed a nomogram model that incorporated CS and effectively stratified these patients by risk. Subsequent performance analyses further validated the superior efficacy of the nomogram.

CONCLUSIONS

Our study highlights the value of CS in GNEC prognosis. The nomogram offers dynamic, individualized survival predictions, supporting personalized treatment strategies.

Random survival forest algorithm for risk stratification and survival prediction in gastric neuroendocrine neoplasms

This study aimed to construct and assess a machine-learning algorithm designed to forecast survival rates and risk stratification for patients with gastric neuroendocrine neoplasms (gNENs) after diagnosis. Data on patients with gNENs were extracted and randomly divided into training and validation sets using the Surveillance, Epidemiology, and End Results database. We developed a prediction model using 10 machine learning algorithms across 101 combinations to forecast cancer-related mortality in patients with gNENs, selecting the best model using the highest mean over a sequence of time-dependent area under the receiver operating characteristic (ROC) curve (AUC). The performance of the final model was assessed through time-dependent ROC curves for discrimination and calibration curves for calibration. The maximum selection rank method was used to determine the best prognostic risk score threshold for classifying patients into high- and low-risk groups. Afterward, Kaplan-Meier analysis and log-rank test were used to compare survival rates among these groups. Our study examined 775 patients with gNENs, dividing them into training and validation sets. A training set comprised 543 patients, with a median follow-up of 42 months and cumulative mortality rates of 40.0% at 1 year, 48.6% at 3 years, and 54.0% at 5 years. A validation set comprised 232 patients, with cumulative mortality rates of 29.1% at 1 year, 43.5% at 3 years, and 53.2% at 5 years. The optimal random survival forest (RSF) model (mtry = 4, node size = 5) achieved an AUC of 0.839 for survival prediction in the training set. Comprising 11 variables such as demographics, treatment details, tumor characteristics, T staging, N staging, and M staging, the RSF model revealed high predictive accuracy with AUCs of 0.92, 0.96, and 0.96 for 1-, 3-, and 5-year survival, respectively, which was consistently reflected in the validation set with AUCs of 0.88, 0.92, and 0.89, respectively. Moreover, patients were risk-stratified. Although our RSF model effectively stratified patients into different prognostic groups, it needs external validation to confirm its utility for noninvasive prognostic prediction and risk stratification in gNENs. Further research is required to verify its broader clinical applicability.

Modern Management of Gastric Neuroendocrine Neoplasms

OPINION STATEMENT

Gastric neuroendocrine neoplasms (G-NENs) are a heterogeneous group of tumors that broadly fall into two groups. The first group, driven by oversecretion of gastrin, are generally multifocal, small, and behave indolently with a low (but non-zero) risk of progression and metastatic spread. They are conventionally categorized into type 1, with endogenous gastric-based overproduction of gastrin, and type 2 G-NEN, with overproduction of gastrin from an extra-gastric gastrin-secreting tumor. The second group, termed type 3 G-NEN, occur spontaneously and are potentially more aggressive, having a clinical course analogous to other neuroendocrine tumors of the gastrointestinal tract. Type 1 G-NEN can be managed with endoscopic surveillance and resection of visible lesions with great success, reserving surgery for the rare high-risk lesion, whereas surgical resection of the causative gastrin-secreting tumor in type 2 G-NEN is usually curative. Type 3 G-NEN is usually managed with formal surgical resection but there is growing evidence that limited surgery or even endoscopic resection in appropriately selected patients with low risk is both safe and effective. A novel subtype of G-NEN, associated with long-term proton pump inhibitor usage, is increasing in incidence. The pathophysiology seems to parallel type 1 G-NEN. In the setting of metastatic disease, which can occur in any subtype but is most common by far in type 3 G-NEN, the lack of trial data unique to G-NEN results in extrapolation of strategies and agents for treatment of non-gastric neuroendocrine disease. The rapid pace of development in this area is likely to benefit the metastatic G-NEN patient as well. As treatment is predicate on type of G-NEN, establishing the etiology of the lesion is crucial but growing knowledge of G-NEN pathophysiology and close collaboration between pathologists, gastroenterologists, radiologists, surgeons, and oncologists have enabled a growing trend towards de-escalation and less-invasive treatment paradigms.

Combining lymph node ratio to develop prognostic models for postoperative gastric neuroendocrine neoplasm patients

BACKGROUND

Lymph node ratio (LNR) was demonstrated to play a crucial role in the prognosis of many tumors. However, research concerning the prognostic value of LNR in postoperative gastric neuroendocrine neoplasm (NEN) patients was limited.

AIM

To explore the prognostic value of LNR in postoperative gastric NEN patients and to combine LNR to develop prognostic models.

METHODS

A total of 286 patients from the Surveillance, Epidemiology, and End Results database were divided into the training set and validation set at a ratio of 8:2. 92 patients from the First Affiliated Hospital of Soochow University in China were designated as a test set. Cox regression analysis was used to explore the relationship between LNR and disease-specific survival (DSS) of gastric NEN patients. Random survival forest (RSF) algorithm and Cox proportional hazards (CoxPH) analysis were applied to develop models to predict DSS respectively, and compared with the 8th edition American Joint Committee on Cancer (AJCC) tumor-node-metastasis (TNM) staging.

RESULTS

Multivariate analyses indicated that LNR was an independent prognostic factor for postoperative gastric NEN patients and a higher LNR was accompanied by a higher risk of death. The RSF model exhibited the best performance in predicting DSS, with the C-index in the test set being 0.769 [95% confidence interval (CI): 0.691-0.846] outperforming the CoxPH model (0.744, 95%CI: 0.665-0.822) and the 8th edition AJCC TNM staging (0.723, 95%CI: 0.613-0.833). The calibration curves and decision curve analysis (DCA) demonstrated the RSF model had good calibration and clinical benefits. Furthermore, the RSF model could perform risk stratification and individual prognosis prediction effectively.

CONCLUSION

A higher LNR indicated a lower DSS in postoperative gastric NEN patients. The RSF model outperformed the CoxPH model and the 8th edition AJCC TNM staging in the test set, showing potential in clinical practice.

A novel nomogram and risk stratification system predicting the cancer-specific survival of patients with gastric neuroendocrine carcinoma: a study based on SEER database and external validation

BACKGROUND

Gastric neuroendocrine carcinoma (GNEC) is a rare histology of gastric cancer. The retrospective study was designed to construct and validate a nomogram for predicting the cancer-specific survival (CSS) of postoperative GNEC patients.

METHODS

Data for 28 patients from the Hangzhou TCM Hospital were identified as the external validation cohort. A total of 1493 patients were included in the SEER database and randomly assigned to the training group (1045 patients) and internal validation group (448 patients). The nomogram was constructed using the findings of univariate and multivariate Cox regression studies. The model was evaluated by consistency index (C-index), calibration plots, and clinical net benefit. Finally, the effect between the nomogram and AJCC staging system was compared by net reclassification index (NRI) and integrated discrimination improvement (IDI).

RESULTS

Age, gender, grade, T stage, N stage, metastasis, primary site, tumor size, RNE, and chemotherapy were incorporated in the nomogram. The C-indexes were 0.792 and 0.782 in the training and internal verification sets. The 1-, 3-, and 5-year CSS predicted by the nomogram and actual measurements had good agreement in calibration plots. The 1-, 3-, and 5-year NRI were 0.21, 0.29, and 0.37, respectively. The 1-, 3-, and 5-year IDI values were 0.10, 0.12, and 0.13 (P < 0.001), respectively. In 1-, 3-, and 5-year CSS prediction using DCA curves, the nomogram outperformed the AJCC staging system. The nomogram performed well in both the internal and external validation cohorts.

CONCLUSION

We developed and validated a nomogram to predict 1-, 3-, and 5-year CSS for GNEC patients after surgical resection. This well-performing model could help doctors enhance the treatment plan.

Trends of incidence and prognosis of gastric neuroendocrine neoplasms: a study based on SEER and our multicenter research

BACKGROUND

To investigate the recent epidemiological trends of gastric neuroendocrine neoplasms (GNENs) and establish a new tool to estimate the prognosis of gastric neuroendocrine carcinoma (GNEC) and gastric neuroendocrine tumor (GNET).

METHODS

Nomograms were established based on a retrospective study on patients diagnosed with GNENs from 1975 to 2016 in Surveillance, Epidemiology and End Results database. External validation was performed among 246 GNENs patients in Jiangsu province to verify the discrimination and calibration of the nomograms.

RESULTS

The age-adjusted incidence of GNENs has increased from 0.309 to 6.149 per 1,000,000 persons in the past 4 decades. Multivariate analysis indicated independent prognostic factors for both GNEC and GNET including age, distant metastasis and surgical intervention (P < 0.05). In addition, T, N staging and grade were significantly associated with survival of GNEC, while size was a predictor for GNET (P < 0.05). The C-indexes of the nomograms were 0.840 for GNEC and 0.718 for GNET, which were higher than those of the 8th AJCC staging system (0.773 and 0.599). Excellent discrimination was observed in the validation cohorts (C-index of nomogram vs AJCC staging for GNEC: 0.743 vs 0.714; GNET: 0.945 vs 0.927). Survival rates predicted by nomograms were close to the actual survival rates in the calibration plots in both training and validation sets.

CONCLUSIONS

The incidence of the GNENs is increasing steadily in the past 40 years. We established more excellent nomograms to predict the prognosis of GNENs than traditional staging system, helping clinicians to make tailored decisions.