Development and Validation of a Website to Guide Decision-Making for Disorders of Consciousness

Abstract

Background: This study aimed to develop and validate a nomogram and present it on a website to be used to predict the overall survival at 16, 32, and 48 months in patients with prolonged disorder of consciousness (pDOC).

Methods: We retrospectively analyzed the data of 381 patients with pDOC at two centers. The data were randomly divided into training and validation sets using a ratio of 6:4. On the training set, Cox proportional hazard analyses were used to identify the predictive variables. In the training set, two models were screened by COX regression analysis, and based on clinical evidence, model 2 was eventually selected in the nomogram after comparing the receiver operating characteristic (ROC) of the two models. In the training and validation sets, ROC curves, calibration curves, and decision curve analysis (DCA) curves were utilized to measure discrimination, calibration, and clinical efficacy, respectively.

Results: The final model included age, Glasgow coma scale (GCS) score, serum albumin level, and computed tomography (CT) midline shift, all of which had a significant effect on survival after DOCs. For the 16-, 32-, and 48-month survival on the training set, the model had good discriminative power, with areas under the curve (AUCs) of 0.791, 0.760, and 0.886, respectively. For the validation set, the AUCs for the 16-, 32-, and 48-month survival predictions were 0.806, 0.789, and 0.867, respectively. Model performance was good for both the training and validation sets according to calibration plots and DCA.

Conclusion: We developed an accurate, efficient nomogram, and a corresponding website based on four correlated factors to help clinicians improve their assessment of patient outcomes and help personalize the treatment process and clinical decisions.

Keywords: Glasgow coma scale score; clinical prediction; disorders of consciousness (DOC); nomogram; website.

Figure 1

The receiver operating characteristic (ROC) curve of the model 1 and model 2 in the training set. (A) Comparison of ROC curves of model 1 and model 2 for predicting the survival of patients with disorder of consciousness (DOC) at 16 months. (B) Comparison of ROC curves of model 1 and model 2 for predicting the survival of patients with DOC at 32 months. (C) Comparison of ROC curves of model 1 and model 2 for predicting the survival of patients with DOC at 48 months.

Figure 2

A clinical feature model was used to develop a nomogram.

Figure 3

Construction of a web-based calculator for predicting DOC's disease survival based on the model (https://kangjw.shinyapps.io/P-Doc/). (A) Web survival rate calculator. (B) 95% confidence interval (CI) of the web survival rate calculator.

Figure 4

Model performance in the training set. (A) Calibration curves of 16-, 32-, and 48-month specific survival. (B) Decision curve analyses (DCA) for predicting the survival of patients with DOC at 16, 32, and 48 months by nomogram.

Figure 5

Model discrimination and performance in the validation set. (A) ROC curves for nomogram-based prognostic prediction. (B) Calibration curve of 16-, 32-, and 48-month specific survival. (C) DCA of this nomogram in the validation set.

Figure 6

Performance of the nomogram in stratifying the risk of patients. (A) Restricted cubic spline analysis of the total risk score in the training set. (B) Kaplan–Meier survival analysis between the low- and high-risk groups in the training set. (C) Kaplan–Meier survival analysis between the low- and high-risk groups in the validation set.