Cerebral small vessel disease (CSVD) is a major contributor to functional decline in the elderly. However, its diagnosis largely depends on neuroimaging, which may not be readily available in routine clinical practice. Gait disturbance, a prominent clinical feature of CSVD second only to cognitive impairment, may help differentiate CSVD from normal aging. Recent advances in quantitative gait analysis allow objective measurement of CSVD-specific motor alterations, showing promise as accessible diagnostic biomarkers.

This case-control study included 417 healthy controls (total CSVD score=0) from a community-based cohort and 117 hospital-based CSVD patients (total CSVD score≥2). Spatiotemporal gait parameters were quantitatively assessed. Diagnostic factor included clinical characteristics and gait metrics. Least absolute shrinkage and selection operator (LASSO) regression was applied for variable selection, and selected variables were entered into a multivariable logistic regression model. Model performance was assessed by discrimination (area under the curve [AUC]), calibration, and clinical utility (decision curve analysis [DCA]).

The LASSO regression selected six key variables for the final model: sex, hypertension, body mass index (BMI), stride length, step frequency, and step width. The model demonstrated excellent discrimination with an AUC of 0.914 (95% CI:0.886-0.943). It also showed excellent calibration and provided a superior net benefit across a wide range of threshold probabilities on DCA compared to default strategies.

The diagnostic model developed in this study effectively identifies individuals at high risk of CSVD by leveraging quantitative spatiotemporal gait parameters alongside conventional clinical features, and might offer a reliable and convenient screening method.