A predictive model for awakening in patients with prolonged disorders of consciousness after craniocerebral injury

Abstract

This study aimed to develop and validate a nomogram to predict awakening at 1 year in patients with prolonged disorders of consciousness (pDOC). We retrospectively analyzed the data of 381 patients with pDOC at 2 centers. The data were randomly divided into training and validation sets using a ratio of 6:4. For the training set, univariate and multivariate logical regression analyses were used to identify the predictive variables. Receiver operating characteristic curves, calibration curves, and a decision curve analysis were utilized to assess the predictive accuracy, discriminative ability, and clinical utility of the model, respectively. The final model included age, Glasgow Coma Scale score, serum albumin level, and computed tomography midline shift, all of which had a significant effect on awakening after pDOC. For the 1-year awakening in the training set, the model had good discriminative power, with an area under the curve of 0.733 (95% confidence interval: 0.667–0.789). For the validation set, the area under the curve for 1-year awakening was 0.721 (95% confidence interval: 0.617–0.826). Model performance was good for both the training and validation sets according to calibration plots and decision curve analysis. We developed a precise, effective nomogram to assist clinicians in better assessing patients’ outcomes, guiding clinical judgment, and personalizing the therapeutic process.