Construction and Verification of a Risk Prediction Model for the Occurrence of Delayed Cerebral Ischemia after Aneurysmal Subarachnoid Hemorrhage Requiring Mechanical Ventilation

Abstract

Objectives. Delayed cerebral ischemia (DCI) contributes to poor aneurysm prognosis. Subarachnoid hemorrhage and DCI have irreversible and severe consequences once they occur; therefore, early prediction and prevention are important. We investigated the risk factors for postoperative complications of DCI in patients with aneurysmal subarachnoid hemorrhage (aSAH) requiring mechanical ventilation in intensive care and validated a prediction model. Methods. We retrospectively analyzed patients with aSAH who were treated in a French university hospital neuro-ICU between January 2010 and December 2015. The patients were randomized into a training group (144) and verification groups (60). Nomograms were validated in the training and verification groups, where receiver operating characteristic curve analysis was used to verify model discrimination; calibration curve and Hosmer-Lemeshow test were used to determine model calibration; and decision curve analysis (DCA) was used to verify clinical validity of the model. Results. External ventricular drain (EVD), duration of mechanical ventilation, and treatment were significantly associated in the univariate analysis; EVD and rebleeding were significantly associated with the occurrence of DCI after aSAH. Binary logistic regression was used to select five clinicopathological characteristics to predict the occurrence of DCI in patients with aSAH requiring mechanical ventilation nomograms of the risk of DCI. Area under the curve values for the training and verification groups were 0.768 and 0.246, with Brier scores of 0.166 and 0.163, respectively. Hosmer-Lemeshow calibration test values for the training and verification groups were x 2 = 3.824 ( P = 0.923 ) and x 2 = 10.868 ( P = 0.285 ), respectively. Calibration curves showed good agreement. DCA indicated that the training and verification groups showed large positive returns in the broad risk range of 0-77% and 0-63%, respectively. Conclusions. The predictive model of concurrent DCI in aSAH has theoretical and practical values and can provide individualized treatment options for patients with aSAH who require mechanical ventilation.

Development of a Clinical-Radiomics Nomogram That Used Contrast-Enhanced Ultrasound Images to Anticipate the Occurrence of Preoperative Cervical Lymph Node Metastasis in Papillary Thyroid Carcinoma Patients

“…The nomogram employed a scoring system and offered a numerical probability for the occurrence of the final outcome. 16 , 17 This model could be used by clinicians to enhance their ability to anticipate the occurrence of cervical LNM in patients with PTC, thus facilitating the development of personalized treatment strategies.…”