Search

A critical challenge to using longitudinal wearable sensor biosignal data for healthcare applications and digital biomarker development is the exacerbation of the healthcare "data deluge," leading to new data storage and organization challenges and costs. Data aggregation, sampling rate minimization, and effective data compression are all methods for consolidating wearable sensor data to reduce data volumes. There has been limited research on appropriate, effective, and efficient data compression methods for biosignal data. Here, we examine the application of different data compression pipelines built using combinations of algorithmic- and encoding-based methods to biosignal data from wearable sensors and explore how these implementations affect data recoverability and storage footprint. Algorithmic methods tested include singular value decomposition, the discrete cosine transform, and the biorthogonal discrete wavelet transform. Encoding methods tested include run-length encoding and Huffman encoding. We apply these methods to common wearable sensor data, including electrocardiogram (ECG), photoplethysmography (PPG), accelerometry, electrodermal activity (EDA), and skin temperature measurements. Of the methods examined in this study and in line with the characteristics of the different data types, we recommend direct data compression with Huffman encoding for ECG, and PPG, singular value decomposition with Huffman encoding for EDA and accelerometry, and the biorthogonal discrete wavelet transform with Huffman encoding for skin temperature to maximize data recoverability after compression. We also report the best methods for maximizing the compression ratio. Finally, we develop and document open-source code and data for each compression method tested here, which can be accessed through the Digital Biomarker Discovery Pipeline as the "Biosignal Data Compression Toolbox," an open-source, accessible software platform for compressing biosignal data. [ABSTRACT FROM AUTHOR]

Glucose variability (GV) is an established risk factor for hypoglycemia and diabetes complications. Over 20 GV metrics have been identified, but there is no consensus on which metrics are most effective for determining glucose control. A1c is the clinical standard of glucose control. Two of the most common GV metrics include intraday standard deviation (iSD) and intraday coefficient of variation (iCV), which are calculated for each day and then averaged over multiple days. Thus, the current metrics of iSD and iCV are aggregate means, which are influenced by outliers and do not consider variations over multiple days. To reduce the influence of outliers and examine variation in these metrics over multiple days, we propose expanding the definition of iSD and iCV to include median and standard deviation of iSD and iCV over multiple days. We examined iSD and iCV in a population of 14 high normoglycemic or prediabetic participants (A1c 5.5-6.4%). Participants wore a continuous glucose monitor for 8-10 days. In addition to iSD and iCV, 23 metrics of glucose and GV were calculated. To determine the strength of the relationship between each GV metric and A1c, Pearson correlation coefficients (PCC) were calculated. There were higher PCC between A1c and the standard deviation of iSD and iCV than the traditional metric of iSD and iCV (traditional: 0.296, SD: -0.387). Interestingly, all metrics of iSD and iCV calculated (mean, median, and standard deviation) were more closely correlated with A1c than mean glucose (0.296, 0.138, -0.387, and 0.220, respectively). We demonstrate that expanding the definitions of iSD and iCV can provide a more comprehensive view of GV. Additionally, these metrics may provide more insight into glucose control than traditionally utilized metric, mean glucose. Disclosure: P.J. Cho: None. B.M. Bent: None. A.H. Wittmann: None. R.M. Merwin: None. C.R. Thacker: None. M.N. Feinglos: None. J.P. Dunn: None. Funding: MEDx (451-1746) [ABSTRACT FROM AUTHOR]

The dynamic time warping (DTW) algorithm is widely used in pattern matching and sequence alignment tasks, including speech recognition and time series clustering. However, DTW algorithms perform poorly when aligning sequences of uneven sampling frequencies. This makes it difficult to apply DTW to practical problems, such as aligning signals that are recorded simultaneously by sensors with different, uneven, and dynamic sampling frequencies. As multi-modal sensing technologies become increasingly popular, it is necessary to develop methods for high quality alignment of such signals. Here we propose a DTW algorithm called EventDTW which uses information propagated from defined events as basis for path matching and hence sequence alignment. We have developed two metrics, the error rate (ER) and the singularity score (SS), to define and evaluate alignment quality and to enable comparison of performance across DTW algorithms. We demonstrate the utility of these metrics on 84 publicly-available signals in addition to our own multi-modal biomedical signals. EventDTW outperformed existing DTW algorithms for optimal alignment of signals with different sampling frequencies in 37% of artificial signal alignment tasks and 76% of real-world signal alignment tasks. [ABSTRACT FROM AUTHOR]