A novel accelerometry-based algorithm for the detection of step durations over short episodes of gait in healthy elderly

Abstract

Background: The assessment of short episodes of gait is clinically relevant and easily implemented, especially given limited space and time requirements. BFS (body-fixed-sensors) are small, lightweight and easy to wear sensors, which allow the assessment of gait at relative low cost and with low interference. Thus, the assessment with BFS of short episodes of gait, extracted from dailylife physical activity or measured in a standardised and supervised setting, may add value in the study of gait quality of the elderly. The aim of this study was to evaluate the accuracy of a novel algorithm based on acceleration signals recorded at different human locations (lower back and heels) for the detection of step durations over short episodes of gait in healthy elderly subjects.

Methods: Twenty healthy elderly subjects (73.7 ± 7.9 years old) walked twice a distance of 5 m, wearing a BFS on the lower back, and on the outside of each heel. Moreover, an optoelectronic three-dimensional (3D) motion tracking system was used to detect step durations. A novel algorithm is presented for the detection of step durations from low-back and heel acceleration signals separately. The accuracy of the algorithm was assessed by comparing absolute differences in step duration between the three methods: step detection from the optoelectronic 3D motion tracking system, step detection from the application of the novel algorithm to low-back accelerations, and step detection from the application of the novel algorithm to heel accelerations.

Results: The proposed algorithm successfully detected all the steps, without false positives and without false negatives. Absolute average differences in step duration within trials and across subjects were calculated for each comparison, between low-back accelerations and the optoelectronic system were on average 22.4 ± 7.6 ms (4.0 ± 1.3 % of average step duration), between heel accelerations and the optoelectronic system were on average 20.7 ± 11.8 ms (3.7 ± 1.9 %), and between low-back accelerations and heel accelerations were on average 27.8 ± 15.1 ms (4.9 ± 2.5 % of average step duration).

Conclusions: This study showed that the presented novel algorithm detects step durations over short episodes of gait in healthy elderly subjects with acceptable accuracy from low-back and heel accelerations, which provides opportunities to extract a range of gait parameters from short episodes of gait.

Keywords: Accelerometers; Analysis of short episodes of gait; Body-fixed-sensors; Healthy elderly; Heel accelerometry; Low-back accelerometry; Step duration detection.

Fig. 1

a Location of the LED markers of the Optotrak system on one of the heels. b Cluster of markers placed on a lightweight plate and attached to the surface of the DynaPort Hybrid, McRoberts

Fig. 2

Flowchart that represents the operations executed by the algorithm

Fig. 3

“Resegmented signal”, “Segmented signal” and “Template signal” with a sampling rate of 100 samples/s. Typical example of an AP acceleration signal collected at the lower back and segmented from shortly before the first heel-strike of the gait episode until shortly before the foremost foot reached the end of the trial (“Segmented signal”, blue). New segmentation of the raw AP acceleration signal, which contains three sections with a number of samples equivalent to the template length, one section prior to the start marker of the initial segmentation, and two sections after the end marker of the initial segmentation (“Resegmented signal”, green). “Template signal” (black) is the average of all the sections defined in step 2.3

Fig. 4

a Typical example of a “SD Difference signal” (blue) and a “Correlation signal” (green) with a sampling rate of 100 samples/s. The “SD Difference signal” was obtained from the standard deviation of the difference in amplitude between the “Template signal” and a sliding window (with a number of samples equivalent to the template length) through the “Resegmented signal”. This signal has lower values at the start of the intervals along which the “Resegmented signal” and the “Template signal” are more similar in shape and amplitude. “Correlation signal” was obtained from the calculation of correlation coefficients between the “Template signal” and a sliding window through the “Resegmented signal”, being multiplied by the ratio of ranges of the “Resegmented signal” and the “Template signal”. The resulting signal has higher values at the start of the intervals along which the “Resegmented signal” and the “Template signal” are more similar in shape and amplitude. b “Coefficient signal” (blue) and “Selected peaks” (red squares) with a sampling rate of 100 samples/s. The normalized ratio signal between the “Correlation signal” and the “SD Difference signal” permitted to obtain the “Coefficient signal”. “Selected peaks” are the peaks from the “Coefficient signal” which are found within the dimension of the “Segmented signal” and are located at a distance of at least a 60 % TL (template length) samples from each other

Fig. 5

a. Low-Back acceleration signal (with a sampling rate of 100 samples/s) and detected events. Typical example of a segmented AP acceleration signal collected at the lower back (blue), and the “Events” (magenta) detected by the algorithm applied to low-back accelerometry. These “Events” were obtained from the shift by a 15 % TL samples of the instants at which the peaks were found. The intervals between “Events” permitted to calculate step durations. b. Heel acceleration signals (with a sampling rate of 100 samples/s) and detected events. Typical example of segmented AP acceleration signals collected at the heels, left heel (red) and right heel (blue), and the respective “Events” detected by the algorithm. These “Events” were obtained from the shift by a 5 % TL samples of the instants at which the peaks were found. The intervals between “Events” calculated for each of the heel acceleration signal correspond to stride durations, and the combination of the events detected from both heel accelerometry permitted to obtain step durations

Fig. 6

Average absolute differences in step duration within trials and for each subject are presented for each pair of compared methods with a boxplot (a). Percentage of average absolute differences in step duration over the average step duration calculated with both systems within trials and for each subject are presented for each pair of compared methods with a boxplot (b). *LB = low-back accelerometry, HE = heel accelerometry, OP = Optotrak. The boxplot includes minimum, first quartile (q1, 25 %), median, third quartile (q3, 75 %), maximum and outlier values