A Systematic Review and Meta-Analysis of Risk Prediction Models for Cog nitive Impairment in Patients with Cerebral Small Vessel Disease

Li Ting¹xia zeng^2*Wen Shen¹yun wang¹Ping Jia²

• ¹Chengdu University of Traditional Chinese Medicine, Chengdu, China
• ²Sichuan Academy of Medical Sciences / Sichuan Provincial People's Hospital / Affiliated Hospital of University of Electronic Science and Technology of China, chendu, China

Objective This study systematically evaluates the risk prediction models for cognitive decl ine in patients with CSVD and explores the predictive factors for cognitive im pairment, to provide effective guidance for the future development of higher-qu ality prediction models. Methods A computer-based search was conducted in the following databases: Wanfang Database, China National Knowledge Infrastructure (CNKI), VIP Database, Chi na Biomedical Literature Database, EMBASE, Web of Science, PubMed, and T he Cochrane Library. The search aimed to identify studies on risk prediction m odels for cognitive impairment in patients with CSVD, covering the period fro m the inception of each database up to June 15, 2025. Meta-analysis of the pr edictive factors and the AUC values of the models was performed using RevM an 5.4 and R software, respectively. The PROBAST tool was used for screenin g, data extraction, and assessment of the risk of bias for the included studies. Results A total of 19 studies were selected for inclusion, resulting in the development of 27 risk prediction models for cognitive impairment. The AUC for all models was greater than 0.7. PROBAST assessment results indicated a high risk of bias in the studies, but the applicability of the models was relatively good. Statistical analysis using R software revealed an AUC of 0.87 (95% CI: 0.79–0.92) and 0.85 (95% CI: 0.82–0.88) for the models, indicating good predictive performance. Meta-analysis results showed that hypertension, homocysteine (Hcy), high CSVD burden, age, diabetes, and the TyG index (all with P-values < 0.05) were the major predictors of cognitive impairment. Conclusion The performance and quality of existing risk prediction models for cognitive impairment in patients with cerebral small vessel disease (CSVD) still require improvement. Most models lack external validation and appropriate calibration methods, and many are retrospective studies, which increases the overall risk of bias. Future research should focus on exploring more advanced machine learning algorithms, optimizing study designs, and emphasizing external validation to enhance the generalizability of the models. This would help build more universally applicable prediction models, thereby guiding the clinical implementation of targeted preventive measures.