Linking the main modifiable brain stroke risk factors with human movements features

This paper investigates the assessment of brain stroke susceptibility using human movement analyses. It is supported by the knowledge that 1) many stroke risk factors are correlated with human movement characteristics and 2) the anecdotal reports of motor control disturbance (e.g. in handwritten signatures and handwriting) prior to some cerebrovascular accidents. Thus, to investigate the potential plus-value of human movement information for the development of tools dedicated to stroke prevention, we analyzed the relationship between human motor control and brain stroke risk factors. Hundred and twenty subjects with or without stoke risk factors have performed a neuromuscular test battery. The kinematic of the movements was analyzed using a computational neuromuscular model and predictive characteristics were extracted. Logistic regression and linear discriminant analysis with leave-one-out cross-validation was used to infer, from movements characteristics, the probability of presence of brain stroke risk factors. The clinical potential value of movement information for stroke prevention was assessed by computing area under the receiver operating characteristic curve (AUC) for the diagnostic of risk factors based on motion analysis. AUC mostly varying between 0.6-0.9 are obtained, depending on the neuromuscular test and the risk factor investigated (obesity, diabetes, hypertension, hypercholesterolemia, cigarette smoking, and cardiac disease). Our results support the feasibility of the proposed methodology and its potential application for the development of brain stroke prevention tools. Considering the novelty of this topic, these results are promising. Further research is needed to improve this methodology and its outcome.