1. Development and Validation of a Nomogram for Predicting Lacunar Infarction in Patients with Hypertension
- Author
-
Lu J, Pan H, Xing J, Wang B, Xu L, and Ye S
- Subjects
lacunar infarction ,nomogram ,hypertension ,lasso regression ,predictive model ,Medicine (General) ,R5-920 - Abstract
Jun Lu,1,* Huiqing Pan,1,* Jingjing Xing,1 Bing Wang,1 Li Xu,2 Sheng Ye1,3 1Emergency Department, The Second Affiliated Hospital of Wannan Medical College, Wuhu, Anhui, People’s Republic of China; 2Neurology Department, The Second Affiliated Hospital of Wannan Medical College, Wuhu, Anhui, People’s Republic of China; 3School of Clinical Medicine, Wannan Medical College, Wuhu, Anhui, People’s Republic of China*These authors contributed equally to this workCorrespondence: Sheng Ye, Emergency Department, The Second Affiliated Hospital of Wannan Medical College, 10 Kangfu Road, Jinghu District, Wuhu, Anhui, People’s Republic of China, Email yesheng0553@163.comBackground: A considerable proportion of hypertensive patients may experience lacunar infarction. Therefore, early identification of the risk for lacunar infarction in hypertensive patients is particularly important. This study aimed to develop and validate a concise nomogram for predicting lacunar infarction in hypertensive patients.Methods: Retrospectively analyzed the clinical data of 314 patients with accurate history of hypertension in the Second Affiliated Hospital of Wannan Medical College from January 2021 to December 2022. All the patients were randomly assigned to the training set (n=220) and the validation set (n=94) with 7:3. The diagnosis of lacunar infarction in patients was confirmed using cranial CT or MRI. The independent risk factors of lacunar infarction were determined by Least absolute shrinkage and selection operator (LASSO) regression and multivariable logistic regression analysis. The nomogram was built based on the independent risk factors. The nomogram’s discrimination, calibration, and clinical usefulness were evaluated by receiver operating characteristics (ROC) curve, calibration curve, and decision curve analysis (DCA) analysis, respectively.Results: The incidence of lacunar infarction was 34.50% and 33.00% in the training and validation sets, respectively. Five independent predictors were made up of the nomogram, including age (OR=1.142, 95% CI: 1.089– 1.198, P< 0.001), diabetes mellitus (OR=3.058, 95% CI: 1.396– 6.697, P=0.005), atrial fibrillation (OR=3.103, 95% CI: 1.328– 7.250, P=0.009), duration of hypertension (OR=1.130, 95% CI: 1.045– 1.222, P=0.002), and low-density lipoprotein (OR=2.147, 95% CI: 1.250– 3.688, P=0.006). The discrimination with area under the curve (AUC) was 0.847 (95% CI: 0.789– 0.905) in the training set and was a slight increase to 0.907 (95% CI: 0.838– 0.976) in the validation set. The calibration curve showed high coherence between the predicted and actual probability of lacunar infarction. Moreover, the DCA analysis indicated that the nomogram had a higher overall net benefit of the threshold probability range in both two sets.Conclusion: Age, diabetes mellitus, atrial fibrillation, duration of hypertension, and low-density lipoprotein were significant predictors of lacunar infarction in hypertensive patients. The nomogram based on the clinical data was constructed, which was a useful visualized tool for clinicians to assess the risk of the lacunar infarction in hypertensive patients.Keywords: lacunar infarction, nomogram, hypertension, lasso regression, predictive model
- Published
- 2024