Dataset Information

A Nomogram to Accurately Identify Pancreatic Neuroendocrine Tumors Metastasizing to Distant Organs: A Study Based on Two National Population-Based Cohorts From the United States and China.

ABSTRACT:

Background

Distant organ metastasis is the leading cause of death in pancreatic neuroendocrine tumor (pNET) patients. In the present study, we aimed to develop and validate a nomogram that could accurately identify pNET metastasizing to distant organs.

Methods

The cases extracted from the Surveillance, Epidemiology, and End Results (SEER) program were assigned to the training cohort and validation cohort. The cases from the Chinese Gastrointestinal Neuroendocrine Tumors program were assigned to the external validation cohort. The strategy was developed with the support of a nomogram, and the predictive value of this strategy was evaluated by the receiver operating characteristic (ROC) curve analysis.

Results

In total, 2024 American cases were involved in the present study. Besides, 1450 and 574 patients were allocated into training and internal validation cohorts, respectively. In addition, 122 Chinese patients were assigned to the external validation cohort. The results of the univariate logistic regression analysis suggested that tumor grade, tumor size, and the number of metastatic lymph nodes were the risk of metastasis to distant organs, and these 3 clinicopathological characteristics were used to develop the nomogram. We observed that the accuracy of the nomogram for predicting metastasis to distant organs was 0.797, 0.819, and 0.837 in the training cohort, internal validation cohort, and external validation cohort, respectively.

Conclusions

A predictive nomogram was developed and validated, and it showed an acceptable performance in predicting metastasis to distant organs. The results will enable clinicians to identify pNETs, metastasizing to distant organs, and develop an effective individualized therapeutic strategy for these patients.

SUBMITTER: Zhang X

PROVIDER: S-EPMC9127860 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Nomogram to Accurately Identify Pancreatic Neuroendocrine Tumors Metastasizing to Distant Organs: A Study Based on Two National Population-Based Cohorts From the United States and China.

Zhang Xianbin X Lu Lili L Liu Jun J Liu Weihan W Li Li L Wei Yushan Y Fan Jinhu J Ma Li L Gong Peng P

Clinical Medicine Insights. Oncology 20220519

<h4>Background</h4>Distant organ metastasis is the leading cause of death in pancreatic neuroendocrine tumor (pNET) patients. In the present study, we aimed to develop and validate a nomogram that could accurately identify pNET metastasizing to distant organs.<h4>Methods</h4>The cases extracted from the Surveillance, Epidemiology, and End Results (SEER) program were assigned to the training cohort and validation cohort. The cases from the Chinese Gastrointestinal Neuroendocrine Tumors program we ...[more]

PMID: 35620244

Similar Datasets

Project description:Ewing's sarcoma is a high-grade malignancy bone and soft tissue tumor that most commonly occurs in children and adolescents. Although the overall prognosis of Ewing's sarcoma has improved, the 5-year survival rate has not improved significantly. The study aimed to determine the risk factors independently associated with the prognosis of Ewing's sarcoma and to construct a nomogram to predict patient survival. Patients diagnosed with Ewing's sarcoma were collected from the Surveillance, Epidemiology, and End Results program database between 2004 and 2015 and further divided into training and validation cohort. Univariate and multivariate Cox regression analyses were used to identify meaningful independent prognostic factors. The nomogram was used to predict 3- and 5-year overall survival (OS) and cancer-specific survival (CSS). Finally, the nomogram was verified internally and externally through the training and validation cohorts, and the predictive capability was evaluated using the receiver operating characteristic (ROC) curve, C-index, and calibration curve and compared with that of the 7th TNM stage. A total of 1120 patients were divided into training (n = 713) and validation (n = 407) cohorts. Based on the multivariate analysis of the training cohort, a nomogram that integrated age, tumor size, primary site, N stage, and M stage was constructed (P < 0.05). The predicted C-indexes of OS and CSS of the training cohort were 0.744 (95% CI 0.717-0.771) and 0.743 (95% CI 0.715-0.770), respectively. However, the TNM stage had a C-index of 0.695 (95% CI 0.666-0.724) and 0.698 (95% CI 0.669-0.727) for predicting OS and CSS, respectively. The nomogram showed higher C-indexes than those in the TNM stage. Furthermore, the internal and external calibration curves showed good consistency between the predicted and observed values. Age, tumor size, primary site, N stage, and M stage are independent risk factors affecting the OS and CSS in Ewing's sarcoma patients. Compared with the 7th TNM staging, the nomogram consisting of these factors was more accurate for risk assessment and survival prediction in patients with Ewing's sarcoma, thus providing a novel reliable tool for risk assessment and survival prediction in Ewing's sarcoma patients.

Project description:To retrospectively develop and validate an interpretable deep learning model and nomogram utilizing endoscopic ultrasound (EUS) images to predict pancreatic neuroendocrine tumors (PNETs). Following confirmation via pathological examination, a retrospective analysis was performed on a cohort of 266 patients, comprising 115 individuals diagnosed with PNETs and 151 with pancreatic cancer. These patients were randomly assigned to the training or test group in a 7:3 ratio. The least absolute shrinkage and selection operator algorithm was employed to reduce the dimensionality of deep learning (DL) features extracted from pre-standardized EUS images. The retained nonzero coefficient features were subsequently applied to develop predictive eight DL models based on distinct machine learning algorithms. The optimal DL model was identified and used to establish a clinical signature, which subsequently informed the construction and evaluation of a nomogram. Gradient-weighted Class Activation Mapping (Grad-CAM) and Shapley Additive Explanations (SHAP) were implemented to interpret and visualize the model outputs. A total of 2048 DL features were initially extracted, from which only 27 features with coefficients greater than zero were retained. The support vector machine (SVM) DL model demonstrated exceptional performance, achieving area under the curve (AUC) values of 0.948 and 0.795 in the training and test groups, respectively. Additionally, a nomogram was developed, incorporating both DL and clinical signatures, and was visually represented for practical application. Finally, the calibration curves, decision curve analysis (DCA) plots, and clinical impact curves (CIC) exhibited by the DL model and nomogram indicated high accuracy. The application of Grad-CAM and SHAP enhanced the interpretability of these models. These methodologies contributed substantial net benefits to clinical decision-making processes. A novel interpretable DL model and nomogram were developed and validated using EUS images, cooperating with machine learning algorithms. This approach demonstrates significant potential for enhancing the clinical applicability of EUS in predicting PNETs from pancreatic cancer, thereby offering valuable insights for future research and implementation.

Project description:BackgroundPrimary hepatic neuroendocrine tumors (PH-NETs) are extremely rare and unknown. Because of its rarity, its prognosis features and influencing factors are not well established.MethodsData of 140 patients with PH-NETs diagnosed in the SEER database from 1975 to 2016 were collected. The demographics and clinic-pathological features were described. By using propensity-score matching (PSM) analysis, three associated cohorts were selected to describe the malignancy of PH-NETs and univariate analysis was conducted. Then, multivariate Cox analyses were performed and a predicting nomograph was constructed. C-index, receiver operating characteristic (ROC) curve and calibration curves were used to evaluate the predictive value of nomogram.ResultsThe overall survival outcomes of PH-NETs were superior to hepatocellular carcinoma (HCC) with a mean survival time 30.64 vs 25.11 months (p = 0.052), but inferior to gastrointestinal tract neuroendocrine tumors in situ (GI-NETs in situ) with a mean survival time 30.64 vs 41.62 months (p = 0.017). With reference to gastrointestinal neuroendocrine tumors with liver metastasis (GI-NETs-LM), GI-NETs-LM had better outcomes in short time (1-year survival rate: 64.75% vs 56.43%) but was worse in long time (5-year survival rate: 8. 63% vs 18.57%). Multivariate Cox analyses showed that tumor grade and surgery were two independent factors for prognosis of the patients (p < 0.00). Tumor grade and surgery were used to construct the predicting nomogram. The C-index was 0.79 (95%CI = 0.75-0.83). The area under curve (AUC) values in ROC were 0.868 in 1-year and 0.917 in 3-year survival and the calibration curves showed good consistency.ConclusionsThe overall prognosis PH-NETs is generally favorable, better than HCC and GI-NETs-LM in long term. Preoperative biopsy and complete pathological diagnosis were recommended. Radical surgical intervention including transplantation was the first choice in PH-NETs therapy.

Project description:BackgroundPancreatic neuroendocrine tumors (pNETs) and solid pseudopapillary tumors (SPTs) are two of the most common pancreatic neoplasms with different treatment procedures. However, the broad heterogeneity of pNETs and SPTs in clinical manifestations and radiological features often confuse the presurgical discrimination in clinical practice, and the clinical and molecular differentiation of the two tumors remains elusive to date. We presume that a large and comprehensive study into the multimodality features of pNETs and SPTs is necessary for precise clinical management.MethodsWe collected and analyzed the clinicopathological information and multimodality features of nonfunctional pNET and SPT patients, for a total of 631 cases from 2006 to 2021. Univariate analysis of imaging features, including contrast-enhanced computed tomography (CT), magnetic resonance imaging, endoscopic ultrasound (EUS) and nuclear medicine imaging, and clinical characteristics was performed, and CT features and clinical information were integrated to establish a nomogram model.ResultsWe recruited 354 nonfunctional pNET and 277 SPT patients in our cohort. Regarding demographic information, pNET patients had a lower female percentage (55.4% vs. 72.9%), smaller tumor size (2.8 vs. 4.8 cm), and older age (53.4 vs. 35.3 years). In CT imaging and EUS, pNETs tended to appear as solid and homogenous lesions with strong enhancement intensity. Multifocal lesions, duct dilation, and lymph node (LN) enlargement were more likely to be observed in pNETs, while calcification was more common in SPT lesions. On positron emission tomography (PET)/CT, pNETs exhibited significant sensitivity to somatostatin receptor scintigraphy (SRS), with positive rates of 81.4% and 95% on 99mTc-HYNIC-TOC and 68Ga-DOTATATE PET/CT, respectively, while SPTs were all negative on SRS. Multivariate analysis identifies tumor size, age, enhancement intensity, calcification, and LN enlargement as statistically significant variables.ConclusionsCompared to SPT patients, pNET patients exhibit an older age and smaller tumor size. CT manifestations of strong intensity, LN enlargement, and no calcification could indicate a higher possibility of pNET. Meanwhile, the similarity in the immunohistochemical profile indicates that the two tumors could potentially develop from the same origin.

Dataset Information

A Nomogram to Accurately Identify Pancreatic Neuroendocrine Tumors Metastasizing to Distant Organs: A Study Based on Two National Population-Based Cohorts From the United States and China.

Background

Methods

Results

Conclusions

Publications

A Nomogram to Accurately Identify Pancreatic Neuroendocrine Tumors Metastasizing to Distant Organs: A Study Based on Two National Population-Based Cohorts From the United States and China.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets