Development and Validation of a Personalized Prognostic Prediction Model for Patients With Spinal Cord Astrocytoma

Abstract

Background: The study aimed to investigate the prognostic factors of spinal cord astrocytoma (SCA) and establish a nomogram prognostic model for the management of patients with SCA.

Methods: Patients diagnosed with SCA between 1975 and 2016 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database and randomly divided into training and testing datasets (7:3). The primary outcomes of this study were overall survival (OS) and cancer-specific survival (CSS). Cox hazard proportional regression model was used to identify the prognostic factors of patients with SCA in the training dataset and feature importance was obtained. Based on the independent prognostic factors, nomograms were established for prognostic prediction. Calibration curves, concordance index (C-index), and time-dependent receiver operating characteristic (ROC) curves were used to evaluate the calibration and discrimination of the nomogram model, while Kaplan-Meier (KM) survival curves and decision curve analyses (DCA) were used to evaluate the clinical utility. Web-based online calculators were further developed to achieve clinical practicability.

Results: A total of 818 patients with SCA were included in this study, with an average age of 30.84 ± 21.97 years and an average follow-up time of 117.57 ± 113.51 months. Cox regression indicated that primary site surgery, age, insurance, histologic type, tumor extension, WHO grade, chemotherapy, and post-operation radiotherapy (PRT) were independent prognostic factors for OS. While primary site surgery, insurance, tumor extension, PRT, histologic type, WHO grade, and chemotherapy were independent prognostic factors for CSS. For OS prediction, the calibration curves in the training and testing dataset illustrated good calibration, with C-indexes of 0.783 and 0.769. The area under the curves (AUCs) of 5-year survival prediction were 0.82 and 0.843, while 10-year survival predictions were 0.849 and 0.881, for training and testing datasets, respectively. Moreover, the DCA demonstrated good clinical net benefit. The prediction performances of nomograms were verified to be superior to that of single indicators, and the prediction performance of nomograms for CSS is also excellent.

Conclusions: Nomograms for patients with SCA prognosis prediction demonstrated good calibration, discrimination, and clinical utility. This result might benefit clinical decision-making and patient management for SCA. Before further use, more extensive external validation is required for the established web-based online calculators.

Keywords: SEER; astrocytoma; nomogram; prognostic factor; spinal tumor; survival prediction.

Figure 1

Workflow of the patient selection and model development.

Figure 2

Results of the univariable and multivariable Cox regression analyses for overall survival (OS).

Figure 3

Results of the univariable and multivariable Cox regression analyses for cancer-specific survival (CSS).

Figure 4

Variable importance and nomograms of (A,B) OS and (C,D) CSS.

Figure 5

Evaluation of the nomogram on training dataset for OS. (A) 5- and 10-year calibration plots of the nomogram. (B) 5-year and (C) 10-year area under the curve (AUC) for receiver operating characteristic (ROC) curves of Nomogram, Primary site surgery, Age, and Insurance. (D) Overall concordance index (c-index) of the nomogram, primary site surgery, age, and insurance. (E) 5- and 10-year decision curve analysis (DCA) of the nomogram, primary site surgery, age, and insurance.

Figure 6

Evaluation of the nomogram on testing dataset for OS. (A) 5- and 10-year calibration plots of the nomogram. (B) 5-year and (C) 10-year AUC for ROC curves of the nomogram, primary site surgery, age, and insurance. (D) Overall c-index of the nomogram, primary site surgery, age, and insurance. (E) 5- and 10-year DCA of the nomogram, primary site surgery, age, and insurance.

Figure 7

Kaplan-Meier survival curves of patients stratified by risk for (A) Training dataset of OS. (B) Testing dataset of OS. (C) Training dataset of CSS. (D) Testing dataset of CSS.