Composite Markers Predict Functional Outcomes in Basal Ganglia Hemorrhage in Patients with Cerebral Small Vessel Disease

Zhiwen Zha,1 Lei Zhu,1 Chuanqin Yu,1 Tong Gu,1 Chen He,1 Xuke Zhang,2 Meihai Wen2 1Department of Neurology, The First Hospital of Anhui University of Science & Technology, Huainan, Anhui Province, People’s Republic of China; 2Department of Neurology, Bengbu Medical University, Bengbu, Anhui Province, People’s Republic of ChinaCorrespondence: Lei Zhu, Email [email protected]: Although the presence of cerebral small vessel disease (CSVD) on neuroimaging closely parallels overall stroke risk, it is still uncertain whether combining these structural markers with blood-based profiles can reliably predict functional outcomes in patients suffering from acute basal ganglia hemorrhage (BGH).Methods: We enrolled 242 BGH patients admitted between January and December 2024. The least absolute shrinkage and selection operator (LASSO) with ten‑fold cross‑validation selected candidate predictors. Backward elimination in multiple logistic regression identified independent risk variables and built the final model. Discrimination was assessed by the area under the receiver operating characteristic curve (AUC), calibration by the Hosmer‑Lemeshow test and calibration plots. The DeLong test and decision curve analysis evaluated model comparison and clinical utility. A risk stratification chart enabled individualized risk assessment.Results: Multivariable analysis identified four independent predictors of poor prognosis: total load (adjusted OR = 9.25, 95% CI: 3.52– 24.28, P < 0.001), triglyceride-to-high-density lipoprotein cholesterol (TG/HDL-C) ratio (adjusted OR = 8.39, 95% CI: 3.21– 21.92, P < 0.001), non-high-density lipoprotein cholesterol ratio (NHHR) (adjusted OR = 4.95, 95% CI: 2.50– 9.82, P < 0.001), and systemic inflammation response index (SIRI) (adjusted OR = 3.35, 95% CI: 1.89– 5.93, P < 0.001). The prediction model showed excellent discrimination, with an AUC of 0.929 (95% CI: 0.89– 0.97). At a cutoff value of 0.29, sensitivity was 86% and specificity was 91%. Evaluation of the model’s calibration demonstrated a good concordance between the estimated probabilities and the actual clinical endpoints.Conclusion: Evaluating BGH patients through an integrated lens of blood-based biomarkers and neuroimaging substantially enhances prognostic clarity. Rather than being considered in isolation, systemic indices such as the TG/HDL‑C ratio, NHHR, and SIRI combine with cumulative CSVD severity to independently flag high‑risk clinical trajectories.Keywords: cerebral small vessel disease, basal ganglia hemorrhage, blood biomarkers, prognostic prediction model, total load