mHealth 6-minute walk test – accuracy for detecting clinically relevant differences in heart failure patients

Ziegl, Andreas; Rzepka, Angelika; Kästner, Peter; Vinatzer, Hannah; Edegger, Kurt; Hayn, Dieter; Prescher, Sandra; Moller, Volker; Schreier, Günter

doi:10.1109/embc46164.2021.9630118

Cited by 6 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We implemented and compared the following six algorithms: Alpha-Beta [ 28 ], Kalman 1D [ 29 ], Kalman 2D [ 30 ], Kalman smoothing [ 22 ], Quality-based Spatial Subsampling (QSS) [ 18 ], and a simple baseline algorithm that sums the distance between samples. The following four algorithms are based on the Kalman filter: Alpha-Beta, Kalman 1D, Kalman 2D, and Kalman smoothing.…”

Section: Methodsmentioning

confidence: 99%

“…For the algorithms that rely on Kalman filters, we used the resampled GNSS signal at 1 Hz to have a constant sampling frequency. This was performed to simplify the mathematical modelling needed in these filters and was also as suggested in some previous work [ 22 ].…”

Section: Methodsmentioning

confidence: 99%

“…Kalman smoothing: This implementation is based on the algorithm proposed by Ziegl et al [ 22 ]. Here, the Kalman filter adds a backward recursion to smooth previous samples based on newly collected measures [ 36 ].…”

Section: Methodsmentioning

confidence: 99%

“…Here, the Kalman filter adds a backward recursion to smooth previous samples based on newly collected measures [ 36 ]. In [ 22 ], the signal is resampled at

and padded where missing values are found. The initial state of the filter is selected as the first available position sample.…”

Section: Methodsmentioning

confidence: 99%

“…Research developed by Ziegl et al [ 22 ] investigated how the device positioning and filtering techniques can impact the walking distance computation. To test this, they collected data from 166 recordings using a mobile phone application, and based on this proposed an algorithm based on Kalman filter operations obtaining a 3.7% mean error.…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

Assessing the Effect of Data Quality on Distance Estimation in Smartphone-Based Outdoor 6MWT

Caramaschi,

Olsson,

Orchard

et al. 2024

Sensors

View full text Add to dashboard Cite

As a result of technological advancements, functional capacity assessments, such as the 6-minute walk test, can be performed remotely, at home and in the community. Current studies, however, tend to overlook the crucial aspect of data quality, often limiting their focus to idealised scenarios. Challenging conditions may arise when performing a test given the risk of collecting poor-quality GNSS signal, which can undermine the reliability of the results. This work shows the impact of applying filtering rules to avoid noisy samples in common algorithms that compute the walked distance from positioning data. Then, based on signal features, we assess the reliability of the distance estimation using logistic regression from the following two perspectives: error-based analysis, which relates to the estimated distance error, and user-based analysis, which distinguishes conventional from unconventional tests based on users’ previous annotations. We highlight the impact of features associated with walked path irregularity and direction changes to establish data quality. We evaluate features within a binary classification task and reach an F1-score of 0.93 and an area under the curve of 0.97 for the user-based classification. Identifying unreliable tests is helpful to clinicians, who receive the recorded test results accompanied by quality assessments, and to patients, who can be given the opportunity to repeat tests classified as not following the instructions.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

“…Here, the Kalman filter adds a backward recursion to smooth previous samples based on newly collected measures [ 36 ]. In [ 22 ], the signal is resampled at

and padded where missing values are found. The initial state of the filter is selected as the first available position sample.…”

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations