Reconstruction of the respiratory signal through ECG and wrist accelerometer data.
Ontology highlight
ABSTRACT:
SUBMITTER: Leube J
PROVIDER: S-EPMC7471298 | biostudies-literature | 2020 Sep
REPOSITORIES: biostudies-literature
Publications
Reconstruction of the respiratory signal through ECG and wrist accelerometer data.
Leube Julian J Zschocke Johannes J Kluge Maria M Pelikan Luise L Graf Antonia A Glos Martin M Müller Alexander A Bartsch Ronny P RP Penzel Thomas T Kantelhardt Jan W JW
Scientific reports 20200903 1
Respiratory rate and changes in respiratory activity provide important markers of health and fitness. Assessing the breathing signal without direct respiratory sensors can be very helpful in large cohort studies and for screening purposes. In this paper, we demonstrate that long-term nocturnal acceleration measurements from the wrist yield significantly better respiration proxies than four standard approaches of ECG (electrocardiogram) derived respiration. We validate our approach by comparison ...[more]
Similar Datasets
Project description:Accurate and low-cost sleep measurement tools are needed in both clinical and epidemiological research. To this end, wearable accelerometers are widely used as they are both low in price and provide reasonably accurate estimates of movement. Techniques to classify sleep from the high-resolution accelerometer data primarily rely on heuristic algorithms. In this paper, we explore the potential of detecting sleep using Random forests. Models were trained using data from three different studies where 134 adult participants (70 with sleep disorder and 64 good healthy sleepers) wore an accelerometer on their wrist during a one-night polysomnography recording in the clinic. The Random forests were able to distinguish sleep-wake states with an F1 score of 73.93% on a previously unseen test set of 24 participants. Detecting when the accelerometer is not worn was also successful using machine learning ([Formula: see text]), and when combined with our sleep detection models on day-time data provide a sleep estimate that is correlated with self-reported habitual nap behaviour ([Formula: see text]). These Random forest models have been made open-source to aid further research. In line with literature, sleep stage classification turned out to be difficult using only accelerometer data.
| S-EPMC7794504 | biostudies-literature
Project description:Although accelerometry data are widely utilized to estimate physical activity and sedentary behavior among children age 3 years or older, for toddlers age 1 and 2 year(s), accelerometry data recorded during such behaviors have been far less examined. In particular, toddler's unique behaviors, such as riding in a stroller or being carried by an adult, have not yet been examined. The objective of this study was to describe accelerometry signal outputs recorded during participation in nine types of behaviors (i.e., running, walking, climbing up/down, crawling, riding a ride-on toy, standing, sitting, riding in a stroller/wagon, and being carried by an adult) among toddlers. Twenty-four toddlers aged 13 to 35 months (50% girls) performed various prescribed behaviors during free play in a commercial indoor playroom while wearing ActiGraph wGT3X-BT accelerometers on a hip and a wrist. Participants' performances were video-recorded. Based on the video data, accelerometer data were annotated with behavior labels to examine accelerometry signal outputs while performing the nine types of behaviors. Accelerometer data collected during 664 behavior assessments from the 21 participants were used for analysis. Hip vertical axis counts for walking were low (median = 49 counts/5 s). They were significantly lower than those recorded while a toddler was "carried" by an adult (median = 144 counts/5 s; p < 0.01). While standing, sitting, and riding in a stroller, very low hip vertical axis counts were registered (median ≤ 5 counts/5 s). Although wrist vertical axis and vector magnitude counts for "carried" were not higher than those for walking, they were higher than the cut-points for sedentary behaviors. Using various accelerometry signal features, machine learning techniques showed 89% accuracy to differentiate the "carried" behavior from ambulatory movements such as running, walking, crawling, and climbing. In conclusion, hip vertical axis counts alone may be unable to capture walking as physical activity and "carried" as sedentary behavior among toddlers. Machine learning techniques that utilize additional accelerometry signal features could help to recognize behavior types, especially to differentiate being "carried" from ambulatory movements.
| S-EPMC6678133 | biostudies-literature
Project description:PurposeThe purpose of this study was to develop and validate methods for analyzing wrist accelerometer data in youth.MethodsA total of 181 youth (mean ± SD; age, 12.0 ± 1.5 yr) completed 30 min of supine rest and 8 min each of 2 to 7 structured activities, selected from a list of 25. Receiver operating characteristic (ROC) curves and regression analyses were used to develop prediction equations for energy expenditure (child-METs; measured activity V˙O2 divided by measured resting V˙O2) and cut points for computing time spent in sedentary behaviors (SB), light (LPA), moderate (MPA), and vigorous (VPA) physical activity. Both vertical axis (VA) and vector magnitude (VM) counts per 5 s were used for this purpose. The validation study included 42 youth (age, 12.6 ± 0.8 yr) who completed approximately 2 h of unstructured PA. During all measurements, activity data were collected using an ActiGraph GT3X or GT3X+, positioned on the dominant wrist. Oxygen consumption was measured using a Cosmed K4b. Repeated-measures ANOVA were used to compare measured versus predicted child-METs (regression only) and time spent in SB, LPA, MPA, and VPA.ResultsAll ROC cut points were similar for area under the curve (≥0.825), sensitivity (≥0.756), and specificity (≥0.634), and they significantly underestimated LPA and overestimated VPA (P < 0.05). The VA and VM regression models were within ±0.21 child-METs of mean measured child-METs and ±2.5 min of measured time spent in SB, LPA, MPA, and VPA, respectively (P > 0.05).ConclusionsCompared to measured values, the VA and VM regression models developed on wrist accelerometer data had insignificant mean bias for child-METs and time spent in SB, LPA, MPA, and VPA; however, they had large individual errors.
| S-EPMC4362848 | biostudies-literature
Project description:This study aimed to examine the validity and accuracy of wrist accelerometers for classifying sedentary behavior (SB) in children.Fifty-seven children (5-8 and 9-12 yr) completed an ~170-min protocol, including 15 semistructured activities and transitions. Nine ActiGraph (GT3X+) and two GENEActiv wrist cut points were evaluated. Direct observation was the criterion measure. The accuracy of wrist cut points was compared with that achieved by the ActiGraph hip cut point (?25 counts per 15 s) and the thigh-mounted activPAL3. Analyses included equivalence testing, Bland-Altman procedures, and area under the receiver operating curve (ROC-AUC).The most accurate ActiGraph wrist cut points (Kim; vector magnitude, ?3958 counts per 60 s; vertical axis, ?1756 counts per 60 s) demonstrated good classification accuracy (ROC-AUC = 0.85-0.86) and accurately estimated SB time in 5-8 yr (equivalence P = 0.02; mean bias = 4.1%, limits of agreement = -20.1% to 28.4%) and 9-12 yr (equivalence P < 0.01; -2.5%, -27.9% to 22.9%). The mean bias of SB time estimates from Kim were smaller than ActiGraph hip (5-8 yr: 15.8%, -5.7% to 37.2%; 9-12 yr: 17.8%, -3.9% to 39.5%) and similar to or smaller than activPAL3 (5-8 yr: 12.6%, -39.8% to 14.7%; 9-12 yr: -1.4%, -13.9% to 11.0%), although classification accuracy was similar to ActiGraph hip (ROC-AUC = 0.85) but lower than activPAL3 (ROC-AUC = 0.92-0.97). Mean bias (5-8 yr: 6.5%, -16.1% to 29.1%; 9-12 yr: 10.5%, -13.6% to 34.6%) for the most accurate GENEActiv wrist cut point (Schaefer: ?0.19 g) was smaller than ActiGraph hip, and activPAL3 in 5-8 yr, but larger than activPAL3 in 9-12 yr. However, SB time estimates from Schaefer were not equivalent to direct observation (equivalence P > 0.05) and classification accuracy (ROC-AUC = 0.79-0.80) was lower than for ActiGraph hip and activPAL3.The most accurate SB ActiGraph (Kim) and GENEActiv (Schaefer) wrist cut points can be applied in children with similar confidence as the ActiGraph hip cut point (?25 counts per 15 s), although activPAL3 was generally more accurate.
| S-EPMC5332065 | biostudies-literature
Project description:PurposeThis study aimed to establish physical activity (PA) intensity cutpoints for a wrist-mounted GENEActiv accelerometer (ACC) in elementary school-age children. A second purpose was to apply cutpoints to a free-living sample and examine the duration of PA based on continuous 1-s epochs.MethodsMetabolic and ACC data were collected during nine typical activities in 24 children age 6-11 yr. Measured VO2 values were divided by Schofield-estimated resting values to determine METs. ACC data were collected at 75 Hz, band pass filtered, and averaged over each 1-s interval. Receiver operator characteristic curves were used to establish cutpoints at sedentary (≤ 1.5 METs), light (1.6-2.99 METs), moderate (3.0-5.99 METs), and vigorous (≥ 6 METs) activities. These cutpoints were applied to a free-living independent data set to quantify the amount of moderate-vigorous PA (MVPA) and to examine how bout length (1, 2, 3, 5, 10, 15, and 60 s) affected the accumulation of MVPA.ResultsReceiver operator characteristic yielded areas under the curve of 0.956, 0.946, and 0.940 for sedentary, moderate, and vigorous intensities, respectively. Cutpoints for sedentary, moderate, and vigorous intensities were 0.190 g, 0.314 g, and 0.998 g, respectively. Intensity classification accuracies ranged from 27.6% (light) to 88.7% (vigorous) when cutpoints were applied to the calibration data. When applied to free-living data (n = 47 children age 6-11 yr), estimated daily MVPA was 308 min and decreased to 14.3 min when only including 1-min periods of continuous MVPA.ConclusionsCutpoints that quantify movements associated with moderate-vigorous intensity, when applied to a laboratory protocol, result in large amounts of accumulated MVPA using the 1-s epoch compared to prior studies, highlighting the need for representative calibration activities and free-living validation of cutpoints and epoch length selection.
| S-EPMC3960318 | biostudies-literature
Project description:BACKGROUND:There has been an increasing interest in understanding the usefulness of wrist-based accelerometer data for physical activity (PA) assessment due to the ease of use and higher user compliance than other body placements. PA assessment studies have relied on machine learning methods which take accelerometer data in forms of variables, or feature vectors. METHODS:In this work, we introduce automated shape feature derivation methods to transform epochs of accelerometer data into feature vectors. As the first step, recurring patterns in the collected data are identified and placed in a codebook. Similarities between epochs of accelerometer data and codebook's patterns are the basis of feature calculations. In this paper, we demonstrate supervised and unsupervised approaches to learn codebooks. We evaluated these methods and compared them with the standard statistical measures for PA assessment. The experiments were performed on 146 participants who wore an ActiGraph GT3X+ accelerometer on the right wrist and performed 33 activities of daily living. RESULTS:Our evaluations show that the shape feature derivation methods were able to perform comparably with the standard wrist model (F1-score: 0.89) for identifying sedentary PAs (F1-scores of 0.86 and 0.85 for supervised and unsupervised methods, respectively). This was also observed for identifying locomotion activities (F1-scores: 0.87, 0.83, and 0.81 for the standard wrist, supervised, unsupervised models, respectively). All the wrist models were able to estimate energy expenditure required for PAs with low error (rMSE: 0.90, 0.93, and 0.90 for the standard wrist, supervised, and unsupervised models, respectively). CONCLUSION:The automated shape feature derivation methods offer insights into the performed activities by providing a summary of repeating patterns in the accelerometer data. Furthermore, they could be used as efficient alternatives (or additions) for manually engineered features, especially important for cases where the latter fail to provide sufficient information to machine learning methods for PA assessment.
| S-EPMC6290590 | biostudies-other
Project description:Functional MRI signals can be heavily influenced by systemic physiological processes in addition to local neural activity. For example, widespread hemodynamic fluctuations across the brain have been found to correlate with natural, low-frequency variations in the depth and rate of breathing over time. Acquiring peripheral measures of respiration during fMRI scanning not only allows for modeling such effects in fMRI analysis, but also provides valuable information for interrogating brain-body physiology. However, physiological recordings are frequently unavailable or have insufficient quality. Here, we propose a computational technique for reconstructing continuous low-frequency respiration volume (RV) fluctuations from fMRI data alone. We evaluate the performance of this approach across different fMRI preprocessing strategies. Further, we demonstrate that the predicted RV signals can account for similar patterns of temporal variation in resting-state fMRI data compared to measured RV fluctuations. These findings indicate that fluctuations in respiration volume can be extracted from fMRI alone, in the common scenario of missing or corrupted respiration recordings. The results have implications for enriching a large volume of existing fMRI datasets through retrospective addition of respiratory variations information.
| S-EPMC7868104 | biostudies-literature
Project description:Motor fluctuations in Parkinson's disease are characterized by unpredictability in the timing and duration of dopaminergic therapeutic benefits on symptoms, including bradykinesia and rigidity. These fluctuations significantly impair the quality of life of many Parkinson's patients. However, current clinical evaluation tools are not designed for the continuous, naturalistic (real-world) symptom monitoring needed to optimize clinical therapy to treat fluctuations. Although commercially available wearable motor monitoring, used over multiple days, can augment neurological decision making, the feasibility of rapid and dynamic detection of motor fluctuations is unclear. So far, applied wearable monitoring algorithms are trained on group data. In this study, we investigated the influence of individual model training on short timescale classification of naturalistic bradykinesia fluctuations in Parkinson's patients using a single-wrist accelerometer. As part of the Parkinson@Home study protocol, 20 Parkinson patients were recorded with bilateral wrist accelerometers for a one hour OFF medication session and a one hour ON medication session during unconstrained activities in their own homes. Kinematic metrics were extracted from the accelerometer data from the bodyside with the largest unilateral bradykinesia fluctuations across medication states. The kinematic accelerometer features were compared over the 1 h duration of recording, and medication-state classification analyses were performed on 1 min segments of data. Then, we analyzed the influence of individual versus group model training, data window length, and total number of training patients included in group model training, on classification. Statistically significant areas under the curves (AUCs) for medication induced bradykinesia fluctuation classification were seen in 85% of the Parkinson patients at the single minute timescale using the group models. Individually trained models performed at the same level as the group trained models (mean AUC both 0.70, standard deviation respectively 0.18 and 0.10) despite the small individual training dataset. AUCs of the group models improved as the length of the feature windows was increased to 300 s, and with additional training patient datasets. We were able to show that medication-induced fluctuations in bradykinesia can be classified using wrist-worn accelerometry at the time scale of a single minute. Rapid, naturalistic Parkinson motor monitoring has the clinical potential to evaluate dynamic symptomatic and therapeutic fluctuations and help tailor treatments on a fast timescale.
| S-EPMC8659489 | biostudies-literature
Project description:Wrist-worn accelerometers are increasingly being used for the assessment of physical activity in population studies, but little is known about their value for sleep assessment. We developed a novel method of assessing sleep duration using data from 4,094 Whitehall II Study (United Kingdom, 2012-2013) participants aged 60-83 who wore the accelerometer for 9 consecutive days, filled in a sleep log and reported sleep duration via questionnaire. Our sleep detection algorithm defined (nocturnal) sleep as a period of sustained inactivity, itself detected as the absence of change in arm angle greater than 5 degrees for 5 minutes or more, during a period recorded as sleep by the participant in their sleep log. The resulting estimate of sleep duration had a moderate (but similar to previous findings) agreement with questionnaire based measures for time in bed, defined as the difference between sleep onset and waking time (kappa = 0.32, 95%CI:0.29,0.34) and total sleep duration (kappa = 0.39, 0.36,0.42). This estimate was lower for time in bed for women, depressed participants, those reporting more insomnia symptoms, and on weekend days. No such group differences were found for total sleep duration. Our algorithm was validated against data from a polysomnography study on 28 persons which found a longer time window and lower angle threshold to have better sensitivity to wakefulness, while the reverse was true for sensitivity to sleep. The novelty of our method is the use of a generic algorithm that will allow comparison between studies rather than a "count" based, device specific method.
| S-EPMC4646630 | biostudies-literature
Project description:Women's Health Study Accelerometer Data
| PRJNA601248 | ENA