Bringing spatiotemporal gait analysis into clinical practice: Instrument validation and pilot study of a commercial sensorized carpet.

BACKGROUND AND OBJECTIVE: We illustrate a low-cost platform easing the estimation of spatio-temporal parameters (GA-STP) ready for large-scale deployment in fall prevention. METHODS: We used a commercial sensorized carpet with a limited cost and a very coarse resolution. An instrument validation test was accomplished: the Wilcoxon test for paired samples and the correlation test with Spearman method were used to compare the values computed by the platform with reference ones. Hierarchical clustering using Ward's method and ROC curves have been used to assess the performance in a pilot study enrolling patients. RESULTS: Validation shows no significant difference between computed and reference values of gait speed (ρ-value:0.99; p-value:2.2E-16), step number (ρ-value:0.91; p-value:5.8E-16) and stride-length (ρ-value:0.92; p-value:7.5E-9). The clinical pilot study confirms that the platform may also be used to track the improvements occurring during a rehabilitation program. CONCLUSIONS: We believe that the use of a commercial carpet makes the solution proposed ready to be deployed on a large scale for effectively bringing GA into the clinical practice.

Permutation Entropy Applied to Fitbit Data: Long-Term Sleep Analysis on One Healthy Subject.

In this work we exploited an algorithm, already present in the literature, and based on the notion of signal permutation entropy, to analyze a very long time series of sleep data from a single subject. The aim of the work is to explore methods for personalizing alerts related to sleep anomalies, and recommendations for improving sleep quality. As a matter of fact, sleep duration and sleep quality may differently affect daily performance of different people, as well as daily activities may differently affect sleeping during the night. Data have been collected from a Fitbit Alta HR activity tracker worn by the subject for about three years. Results show that personalized inferences may be very different from the generic (population-based) ones, and that correlations found may suggest subject-specific life-style modifications useful to improve sleep quality.