Development and validation of a nomogram predictive model for cerebral small vessel disease: a comprehensive retrospective analysis

Ning Li; Ying-Lei Li; Li-Tao Li

doi:10.3389/fneur.2023.1340492

Development and validation of a nomogram predictive model for cerebral small vessel disease: a comprehensive retrospective analysis

Front Neurol. 2024 Jan 8:14:1340492. doi: 10.3389/fneur.2023.1340492. eCollection 2023.

Authors

Ning Li^{1

2}, Ying-Lei Li^{1

3}, Li-Tao Li^{1

4

5}

Affiliations

¹ Department of Neurology, Hebei Medical University, Shijiazhuang, China.
² Department of Neurology, Affiliated Hospital of Hebei University, Baoding, China.
³ Department of Emergency Medicine, Baoding First Central Hospital, Baoding, China.
⁴ Department of Neurology, Hebei General Hospital, Shijiazhuang, China.
⁵ Hebei Provincial Key Laboratory of Cerebral Networks and Cognitive Disorders, Hebei General Hospital, Shijiazhuang, China.

Abstract

Background: Cerebral small vessel disease (CSVD) is a significant contributor to stroke, intracerebral hemorrhages, and vascular dementia, particularly in the elderly. Early diagnosis remains challenging. This study aimed to develop and validate a novel nomogram for the early diagnosis of cerebral small vessel disease (CSVD). We focused on integrating cerebrovascular risk factors and blood biochemical markers to identify individuals at high risk of CSVD, thus enabling early intervention.

Methods: In a retrospective study conducted at the neurology department of the Affiliated Hospital of Hebei University from January 2020 to June 2022, 587 patients were enrolled. The patients were randomly divided into a training set (70%, n = 412) and a validation set (30%, n = 175). The nomogram was developed using multivariable logistic regression analysis, with variables selected through the Least Absolute Shrinkage and Selection Operator (LASSO) technique. The performance of the nomogram was evaluated based on the area under the receiver operating characteristic curve (AUC-ROC), calibration plots, and decision curve analysis (DCA).

Results: Out of 88 analyzed biomarkers, 32 showed significant differences between the CSVD and non-CSVD groups. The LASSO regression identified 12 significant indicators, with nine being independent clinical predictors of CSVD. The AUC-ROC values of the nomogram were 0.849 (95% CI: 0.821-0.894) in the training set and 0.863 (95% CI: 0.810-0.917) in the validation set, indicating excellent discriminative ability. Calibration plots demonstrated good agreement between predicted and observed probabilities in both sets. DCA showed that the nomogram had significant clinical utility.

Conclusions: The study successfully developed a nomogram predictive model for CSVD, incorporating nine clinical predictive factors. This model offers a valuable tool for early identification and risk assessment of CSVD, potentially enhancing clinical decision-making and patient outcomes.

Keywords: blood biochemical markers; cerebral small vessel disease (CSVD); neuroimaging; nomogram; predictive model; retrospective study.

Grants and funding

The author(s) declare financial support was received for the research, authorship, and/or publication of this article. This work was supported by Hospital fund of Affiliated Hospital of Hebei University, Grant/Award Number: 2022QC43 and Hebei Medical Science Research Project, Grant/Award Number: 20230200.