Shaojie Li, Hongjian Li, Jiani Chen, Baofang Wu, Jiayin Wang, Chaocan Hong, Changhu Yan, Weizhi Qiu, Yasong Li, Hongzhi Gao
Background and purpose: Intracerebral hemorrhage remains a significant cause of death and disability worldwide, highlighting the urgent need for accurate prognostic assessments to optimize patient management. This study aimed to develop a practical nomogram for risk prediction of poor prognosis after 90 days in patients with intracerebral hemorrhage.
Methods: A retrospective study was conducted on 638 patients with intracerebral hemorrhage in the Second Hospital of Fujian Medical University, China, who were divided into a training set ( = 446) and a test set ( = 192) by random splitting. Then the data on demographics, clinical symptoms, imaging characteristics, and laboratory findings were collected. In this study, adverse outcomes were defined as a Modified Rankin Scale (mRS) score of 3-6 at 90 days post-ICH onset, as assessed during follow-up. Later, least absolute shrinkage and selection operator (LASSO) regression and multifactorial logistic regression were used to screen the variables and construct a nomogram. Next, the evaluation was performed using the Receiver Operating Characteristic (ROC) curve, calibration curve, and decision curve analysis. Finally, the external validation was completed using the data of 496 patients with intracerebral hemorrhage from the Jinjiang Hospital of Traditional Chinese Medicine.
Results: In the training and test sets of intracerebral hemorrhage, the incidence of poor prognosis was 60.53 and 61.46%, respectively. Through variable screening, this study identified age, Glasgow Coma Scale (GCS), blood glucose, uric acid, hemoglobin, and hematoma location as independent predictors of poor prognosis in intracerebral hemorrhage. The developed dynamic nomogram was easy to use and demonstrated strong predictive performance (training set AUC: 0.87; test set AUC: 0.839; external validation set AUC: 0.774), excellent calibration, and clinical applicability.
Conclusion: The dynamic nomogram we developed using five independent risk factors serves as a practical tool for real-time risk assessment and can help facilitate early intervention and personalized patient management, thereby improving clinical outcomes in high-risk patients.
