Limits...
Algorithm for Turning Detection and Analysis Validated under Home-Like Conditions in Patients with Parkinson ’ s Disease and Older Adults using a 6 Degree-of-Freedom Inertial Measurement Unit at the Lower Back

View Article: PubMed Central - PubMed

ABSTRACT

Introduction: Aging and age-associated disorders such as Parkinson’s disease (PD) are often associated with turning difficulties, which can lead to falls and fractures. Valid assessment of turning and turning deficits specifically in non-standardized environments may foster specific treatment and prevention of consequences.

Methods: Relative orientation, obtained from 3D-accelerometer and 3D-gyroscope data of a sensor worn at the lower back, was used to develop an algorithm for turning detection and qualitative analysis in PD patients and controls in non-standardized environments. The algorithm was validated with a total of 2,304 turns ≥90° extracted from an independent dataset of 20 PD patients during medication ON- and OFF-conditions and 13 older adults. Video observation by two independent clinical observers served as gold standard.

Results: In PD patients under medication OFF, the algorithm detected turns with a sensitivity of 0.92, a specificity of 0.89, and an accuracy of 0.92. During medication ON, values were 0.92, 0.78, and 0.83. In older adults, the algorithm reached validation values of 0.94, 0.89, and 0.92. Turning magnitude (difference, 0.06°; SEM, 0.14°) and duration (difference, 0.004 s; SEM, 0.005 s) yielded high correlation values with gold standard. Overall accuracy for direction of turning was 0.995. Intra class correlation of the clinical observers was 0.92.

Conclusion: This wearable sensor- and relative orientation-based algorithm yields very high agreement with clinical observation for the detection and evaluation of ≥90° turns under non-standardized conditions in PD patients and older adults. It can be suggested for the assessment of turning in daily life.

No MeSH data available.


Related in: MedlinePlus

(A) Turning pattern example from a test person. Six gray rectangular regions reflect turns detected by the algorithm, with flags at the beginning and the end of the turn. The abrupt change when yaw reaches 180° (to −180°) or −180° (to 180°) does not indicate a turn (24). Flags were used to extract turn metrics (magnitude, duration, and direction). (B) The area indicated by the circle in (A) shown at higher magnification, with turning patterns as reflected by yaw angle cut into small pieces. The end of the previous turn is the beginning of the following turn, marked by flags (vertical dashed lines). (C) Turns including hesitations were identified by the algorithm and defined as one turn when ≥10° angular displacements with identical directions and ≤0.5 s separation occurred.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC5385627&req=5

Figure 3: (A) Turning pattern example from a test person. Six gray rectangular regions reflect turns detected by the algorithm, with flags at the beginning and the end of the turn. The abrupt change when yaw reaches 180° (to −180°) or −180° (to 180°) does not indicate a turn (24). Flags were used to extract turn metrics (magnitude, duration, and direction). (B) The area indicated by the circle in (A) shown at higher magnification, with turning patterns as reflected by yaw angle cut into small pieces. The end of the previous turn is the beginning of the following turn, marked by flags (vertical dashed lines). (C) Turns including hesitations were identified by the algorithm and defined as one turn when ≥10° angular displacements with identical directions and ≤0.5 s separation occurred.

Mentions: General structure of the algorithm for turning detection and analysis. A turn was defined as a yaw angle (angle change around vertical axis) with a magnitude ≥90° and a duration of 0.1–10 s (for details see Section “Methods” Figures 2 and 3).


Algorithm for Turning Detection and Analysis Validated under Home-Like Conditions in Patients with Parkinson ’ s Disease and Older Adults using a 6 Degree-of-Freedom Inertial Measurement Unit at the Lower Back
(A) Turning pattern example from a test person. Six gray rectangular regions reflect turns detected by the algorithm, with flags at the beginning and the end of the turn. The abrupt change when yaw reaches 180° (to −180°) or −180° (to 180°) does not indicate a turn (24). Flags were used to extract turn metrics (magnitude, duration, and direction). (B) The area indicated by the circle in (A) shown at higher magnification, with turning patterns as reflected by yaw angle cut into small pieces. The end of the previous turn is the beginning of the following turn, marked by flags (vertical dashed lines). (C) Turns including hesitations were identified by the algorithm and defined as one turn when ≥10° angular displacements with identical directions and ≤0.5 s separation occurred.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC5385627&req=5

Figure 3: (A) Turning pattern example from a test person. Six gray rectangular regions reflect turns detected by the algorithm, with flags at the beginning and the end of the turn. The abrupt change when yaw reaches 180° (to −180°) or −180° (to 180°) does not indicate a turn (24). Flags were used to extract turn metrics (magnitude, duration, and direction). (B) The area indicated by the circle in (A) shown at higher magnification, with turning patterns as reflected by yaw angle cut into small pieces. The end of the previous turn is the beginning of the following turn, marked by flags (vertical dashed lines). (C) Turns including hesitations were identified by the algorithm and defined as one turn when ≥10° angular displacements with identical directions and ≤0.5 s separation occurred.
Mentions: General structure of the algorithm for turning detection and analysis. A turn was defined as a yaw angle (angle change around vertical axis) with a magnitude ≥90° and a duration of 0.1–10 s (for details see Section “Methods” Figures 2 and 3).

View Article: PubMed Central - PubMed

ABSTRACT

Introduction: Aging and age-associated disorders such as Parkinson’s disease (PD) are often associated with turning difficulties, which can lead to falls and fractures. Valid assessment of turning and turning deficits specifically in non-standardized environments may foster specific treatment and prevention of consequences.

Methods: Relative orientation, obtained from 3D-accelerometer and 3D-gyroscope data of a sensor worn at the lower back, was used to develop an algorithm for turning detection and qualitative analysis in PD patients and controls in non-standardized environments. The algorithm was validated with a total of 2,304 turns ≥90° extracted from an independent dataset of 20 PD patients during medication ON- and OFF-conditions and 13 older adults. Video observation by two independent clinical observers served as gold standard.

Results: In PD patients under medication OFF, the algorithm detected turns with a sensitivity of 0.92, a specificity of 0.89, and an accuracy of 0.92. During medication ON, values were 0.92, 0.78, and 0.83. In older adults, the algorithm reached validation values of 0.94, 0.89, and 0.92. Turning magnitude (difference, 0.06°; SEM, 0.14°) and duration (difference, 0.004 s; SEM, 0.005 s) yielded high correlation values with gold standard. Overall accuracy for direction of turning was 0.995. Intra class correlation of the clinical observers was 0.92.

Conclusion: This wearable sensor- and relative orientation-based algorithm yields very high agreement with clinical observation for the detection and evaluation of ≥90° turns under non-standardized conditions in PD patients and older adults. It can be suggested for the assessment of turning in daily life.

No MeSH data available.


Related in: MedlinePlus