Dataset Information

Individual-patient prediction of meningioma malignancy and survival using the Surveillance, Epidemiology, and End Results database.

ABSTRACT: Meningiomas are known to have relatively lower aggressiveness and better outcomes than other central nervous system (CNS) tumors. However, there is considerable overlap between clinical and radiological features characterizing benign, atypical, and malignant tumors. In this study, we developed methods and a practical app designed to assist with the diagnosis and prognosis of meningiomas. Statistical learning models were trained and validated on 62,844 patients from the Surveillance, Epidemiology, and End Results database. We used balanced logistic regression-random forest ensemble classifiers and proportional hazards models to learn multivariate patterns of association between malignancy, survival, and a series of basic clinical variables-such as tumor size, location, and surgical procedure. We demonstrate that our models are capable of predicting meaningful individual-specific clinical outcome variables and show good generalizability across 16 SEER registries. A free smartphone and web application is provided for readers to access and test the predictive models (www.meningioma.app). Future model improvements and prospective replication will be necessary to demonstrate true clinical utility. Rather than being used in isolation, we expect that the proposed models will be integrated into larger and more comprehensive models that integrate imaging and molecular biomarkers. Whether for meningiomas or other tumors of the CNS, the power of these methods to make individual-patient predictions could lead to improved diagnosis, patient counseling, and outcomes.

SUBMITTER: Moreau JT

PROVIDER: S-EPMC6992687 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Individual-patient prediction of meningioma malignancy and survival using the Surveillance, Epidemiology, and End Results database.

Moreau Jeremy T JT Hankinson Todd C TC Baillet Sylvain S Dudley Roy W R RWR

NPJ digital medicine 20200130

Meningiomas are known to have relatively lower aggressiveness and better outcomes than other central nervous system (CNS) tumors. However, there is considerable overlap between clinical and radiological features characterizing benign, atypical, and malignant tumors. In this study, we developed methods and a practical app designed to assist with the diagnosis and prognosis of meningiomas. Statistical learning models were trained and validated on 62,844 patients from the Surveillance, Epidemiology ...[more]

PMID: 32025573

Similar Datasets

Project description:Background:Esophageal cancer is the sixth leading cause of cancer-related deaths and the eighth most common cancer worldwide with a 5-year survival rate of less than 25%. Here we report the incidence, risk factors and treatment options that are available currently, and moving into the future. Methods:We retrospectively analyzed the Surveillance Epidemiology and End Results (SEER) database made available by the National Cancer Institute in the USA. Specifically we extracted data from the years 2004 - 2015. Results:In total we identified 23,804 patients with esophageal adenocarcinoma and 13,919 patients with esophageal squamous cell carcinoma. Males were at an increased risk of developing both types of esophageal cancer when compared to females. Most cases of adenocarcinoma were diagnosed as poorly differentiated grade III (42%), and most cases of squamous cell carcinoma were diagnosed as moderately differentiated grade II (39.5%). The most common stage of presentation for both adenocarcinoma (36.9%) and squamous cell (26.8%) carcinoma was stage IV. The worst outcomes for adenocarcinoma were noted with grade III tumors (hazard ratio (HR): 1.56, 95% confidence interval (CI): 1.44 - 1.68, P value: < 0.01), stage IV tumors (HR: 3.58, 95% CI: 3.33 - 3.85, P value: < 0.01) and those not treated with surgery (HR: 2.54, 95% CI: 2.44 - 2.65, P value: < 0.01). For squamous cell carcinoma, the worst outcomes were noted with grade III tumors (HR: 1.35, 95% CI: 1.23 - 1.49, P value: < 0.01), stage IV tumors (HR: 2.12, 95% CI: 1.94 - 2.32, P value: <0.01). Conclusions:The incidence of esophageal adenocarcinoma in the USA is steadily on the rise. Conversely, the incidence of squamous cell carcinoma has been continually declining. While white males had an increased incidence of both types of esophageal cancer, a higher proportion of African Americans suffered from squamous cell carcinoma. Despite the wide spread use of proton pump inhibitors, adenocarcinoma continues to be a major public health concern.

Project description:Most spinal meningiomas (SM) are benign lesions of the thoracic spine and are usually treated surgically. This study aimed to explore treatment strategies and construct a nomogram for SM. Data on patients with SM from 2000 to 2019 were extracted from the Surveillance, Epidemiology, and End Results database. First, the distributional properties and characteristics of the patients were descriptively evaluated, and the patients were randomly divided into training and testing groups in a 6:4 ratio. Least absolute shrinkage and selection operator (LASSO) regression was used to screen the survival predictors. Kaplan-Meier curves explained survival probability by different variables. The nomogram was constructed based on the results of LASSO regression. The predictive power of the nomogram was identified using the concordance index, time-receiver operating characteristics, decision curve analysis, and calibration curves. We recruited 1,148 patients with SM. LASSO results for the training group showed that sex (coefficient, 0.004), age (coefficient, 0.034), surgery (coefficient, -0.474), tumor size (coefficient, 0.008), and marital status (coefficient, 0.335) were prognostic factors. The nomogram prognostic model showed good diagnostic ability in both the training and testing groups, with a C-index of 0.726, 95% (0.679, 0.773); 0.827, 95% (0.777, 0.877). The calibration and decision curves suggested that the prognostic model had better diagnostic performance and good clinical benefit. In the training and testing groups, the time-receiver operating characteristic curve showed that SM had moderate diagnostic ability at different times, and the survival rate of the high-risk group was significantly lower than that of the low-risk group (training group: p = 0.0071; testing group: p = 0.00013). Our nomogram prognostic model may have a crucial role in predicting the six-month, one-year, and two-year survival outcomes of patients with SM and may be useful for surgical clinicians to formulate treatment plans.

Dataset Information

Individual-patient prediction of meningioma malignancy and survival using the Surveillance, Epidemiology, and End Results database.

Publications

Individual-patient prediction of meningioma malignancy and survival using the Surveillance, Epidemiology, and End Results database.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets