Related Experiment Video
Updated: Jun 14, 2025
Real-Time Monitoring of Neurocritical Patients with Diffuse Optical Spectroscopies
Published on: November 19, 2020
Construction of a nomogram model for predicting delayed cerebral ischemia in aneurysmal subarachnoid hemorrhage
Minyun Mao1, Rimei Zhou2, Yishu Chen1
1Dept. Neurology, The Affiliated Hospital of Guilin Medical University, Guilin, 541001, Guangxi, China.
Aneurysmal subarachnoid hemorrhage (aSAH) is a severe cerebrovascular disease.This retrospective two-center cohort study aimed to construct a nomogram model for predicting delayed cerebral ischemia (DCI) in aSAH patients using LASSO- logistic regression. A total of 604 aSAH patients were included. We collected serological indicators of patients at admission. Lasso and multivariate logistic regression analysis and was performed to screen variables and constructed the independent predictors into a nomogram using R language. After LASSO and multivariate logistic regression, Alcoholism, PLT, Na, and APTT were identified as independent risk factors for DCI. A nomogram model was then developed based on these factors. The model showed good predictive performance in both the training set (AUC = 0.703) and the validation set (AUC = 0.633), along with stable calibration and favorable clinical benefits. Alcoholism, PLT, Na, and APTT may be independent predictors of DCI in aSAH patients. This nomogram can potentially help clinicians assess the risk of DCI in aSAH patients at an early stage and implement timely preventive and treatment measures.
Aneurysmal subarachnoid hemorrhage (aSAH) is a severe cerebrovascular disease.This retrospective two-center cohort study aimed to construct a nomogram model for predicting delayed cerebral ischemia (DCI) in aSAH patients using LASSO- logistic regression. A total of 604 aSAH patients were included. We collected serological indicators of patients at admission. Lasso and multivariate logistic regression analysis and was performed to screen variables and constructed the independent predictors into a nomogram using R language. After LASSO and multivariate logistic regression, Alcoholism, PLT, Na, and APTT were identified as independent risk factors for DCI. A nomogram model was then developed based on these factors. The model showed good predictive performance in both the training set (AUC = 0.703) and the validation set (AUC = 0.633), along with stable calibration and favorable clinical benefits. Alcoholism, PLT, Na, and APTT may be independent predictors of DCI in aSAH patients. This nomogram can potentially help clinicians assess the risk of DCI in aSAH patients at an early stage and implement timely preventive and treatment measures.
