Search

Digital measures are increasingly used as objective health measures in remote-monitoring settings. In addition to their use in purely clinical research, such as in clinical trials, one promising application area for sensor-derived digital measures is in technology-assisted ageing and ageing-related research. In this context, digital measures may be used to measure the risk of certain adverse events such as falls, and also to provide novel research insights into ageing and ageing-related conditions, like cognitive impairment. While major emphasis has been placed on deriving one or more digital measures from wearable devices, a more holistic approach inspired by systems biology that leverages large, non-exhaustive sets of digital measures may prove highly beneficial. Such an approach would be useful if combined with modern big data approaches like machine learning. As such, extensive sets of digital measures, which may be referred to as digital behavioromes, could help characterise new phenotypes in deep phenotyping efforts. These measures could also assist in the discovery of novel digital biomarkers or in the creation of digital clinical outcome assessments. While clinical research into digital measures focuses primarily on measures derived from wearable devices, proven technology used for long-term remote monitoring of older adults is generally contactless, unobtrusive, and privacy-preserving. In this context, we introduce and describe a digital behaviorome: a large, non-exhaustive set of digital measures based entirely on contactless, unobtrusive, and privacy-preserving sensor technologies. We also demonstrate how such a behaviorome can be used to build digital clinical outcome assessments that are relevant to ageing and derived from machine learning. These outcomes included fall risk, frailty, mild cognitive impairment, and late-life depression. With the exception of late-life depression, all digital outcome assessments demonstrated a promising ability (ROC AUC≥0.7) to discriminate between positive and negative health outcomes, often in the range of comparable work with wearable devices. Finally, we highlight the possibility of using these digital behaviorome-based outcome assessments to discover novel potential digital biomarkers for each outcome. Here, we found reasonable contributors but also some potentially interesting new candidates regarding fall risk and mild cognitive impairment.

Background: Population aging is posing multiple social and economic challenges to society. One such challenge is the social and economic burden related to increased health care expenditure caused by early institutionalizations. The use of modern pervasive computing technology makes it possible to continuously monitor the health status of community-dwelling older adults at home. Early detection of health issues through these technologies may allow for reduced treatment costs and initiation of targeted preventive measures leading to better health outcomes. Sleep is a key factor when it comes to overall health and many health issues manifest themselves with associated sleep deteriorations. Sleep quality and sleep disorders such as sleep apnea syndrome have been extensively studied using various wearable devices at home or in the setting of sleep laboratories. However, little research has been conducted evaluating the potential of contactless and continuous sleep monitoring in detecting early signs of health problems in community-dwelling older adults., Objective: In this work we aim to evaluate which contactlessly measurable sleep parameter is best suited to monitor perceived and actual health status changes in older adults., Methods: We analyzed real-world longitudinal (up to 1 year) data from 37 community-dwelling older adults including more than 6000 nights of measured sleep. Sleep parameters were recorded by a pressure sensor placed beneath the mattress, and corresponding health status information was acquired through weekly questionnaires and reports by health care personnel. A total of 20 sleep parameters were analyzed, including common sleep metrics such as sleep efficiency, sleep onset delay, and sleep stages but also vital signs in the form of heart and breathing rate as well as movements in bed. Association with self-reported health, evaluated by EuroQol visual analog scale (EQ-VAS) ratings, were quantitatively evaluated using individual linear mixed-effects models. Translation to objective, real-world health incidents was investigated through manual retrospective case-by-case analysis., Results: Using EQ-VAS rating based self-reported perceived health, we identified body movements in bed & mdash;measured by the number toss-and-turn events & mdash;as the most predictive sleep parameter (t score=& ndash;0.435, P value [adj]=, Conclusions: Our results suggest that nightly body movements in bed could potentially be a highly relevant as well as easy to interpret and derive digital biomarker to monitor a wide range of health deteriorations in older adults. As such, it could help in detecting health deteriorations early on and provide timelier, more personalized, and precise treatment options., (JMIRMhealth Uhealth 2021;9(6):e24666) doi: 10.2196/24666

Gait analysis is an important part of assessments for a variety of health conditions, specifically neurodegenerative diseases. Currently, most methods for gait assessment are based on manual scoring of certain tasks or restrictive technologies. We present an unobtrusive sensor system based on light detection and ranging sensor technology for use in home-like environments. In our evaluation, we compared six different gait parameters, based on recordings from 25 different people performing eight different walks each, resulting in 200 unique measurements. We compared the proposed sensor system against two state-of-the art technologies, a pressure mat and a set of inertial measurement unit sensors. In addition to test usability and long-term measurement, multi-hour recordings were conducted. Our evaluation showed very high correlation (r&gt, 0.95) with the gold standards across all assessed gait parameters except for cycle time (r=0.91). Similarly, the coefficient of determination was high (R2&gt, 0.9) for all gait parameters except cycle time. The highest correlation was achieved for stride length and velocity (r≥0.98,R2≥0.95). Furthermore, the multi-hour recordings did not show the systematic drift of measurements over time. Overall, the unobtrusive gait measurement system allows for contactless, highly accurate long- and short-term assessments of gait in home-like environments.

In recent years, consumer-grade sensors that measure health relevant physiological signals have become widely available and are increasingly used by consumers and researchers alike. While this allows for multiple novel, potentially highly beneficial, large-scale health monitoring applications, quality of these data streams is oftentimes suboptimal. This makes alignment of different high-frequency data streams from multiple, non-connected sensors, a difficult task. In this work we describe a noise-robust framework to align high-frequency signals from different sensors, that share some underlying characteristic, obtained in a free-living, non-clinical, home environment. We demonstrate the approach on the basis of a single-lead, medical-grade, mobile electrocardiography device and a consumer-grade sleep sensor that allows for ballistocardiography. Both commercially available sensors measure the physiological process of a heartbeat. We show, on the basis of real-world data with multiple people and sensors, that the two highly noisy and sometimes dissimilar signals could in most cases be aligned with considerable precision. As a result, we could reduce mean heartbeat peak-to-peak difference by 58.1% on average and increase signal correlation by 0.40 on average.

BACKGROUND Population aging is posing multiple social and economic challenges to society. One such challenge is the social and economic burden related to increased health care expenditure caused by early institutionalizations. The use of modern pervasive computing technology makes it possible to continuously monitor the health status of community-dwelling older adults at home. Early detection of health issues through these technologies may allow for reduced treatment costs and initiation of targeted preventive measures leading to better health outcomes. Sleep is a key factor when it comes to overall health and many health issues manifest themselves with associated sleep deteriorations. Sleep quality and sleep disorders such as sleep apnea syndrome have been extensively studied using various wearable devices at home or in the setting of sleep laboratories. However, little research has been conducted evaluating the potential of contactless and continuous sleep monitoring in detecting early signs of health problems in community-dwelling older adults. OBJECTIVE In this work we aim to evaluate which contactlessly measurable sleep parameter is best suited to monitor perceived and actual health status changes in older adults. METHODS We analyzed real-world longitudinal (up to 1 year) data from 37 community-dwelling older adults including more than 6000 nights of measured sleep. Sleep parameters were recorded by a pressure sensor placed beneath the mattress, and corresponding health status information was acquired through weekly questionnaires and reports by health care personnel. A total of 20 sleep parameters were analyzed, including common sleep metrics such as sleep efficiency, sleep onset delay, and sleep stages but also vital signs in the form of heart and breathing rate as well as movements in bed. Association with self-reported health, evaluated by EuroQol visual analog scale (EQ-VAS) ratings, were quantitatively evaluated using individual linear mixed-effects models. Translation to objective, real-world health incidents was investigated through manual retrospective case-by-case analysis. RESULTS Using EQ-VAS rating based self-reported perceived health, we identified body movements in bed—measured by the number toss-and-turn events—as the most predictive sleep parameter (t score=–0.435, P value [adj]= CONCLUSIONS Our results suggest that nightly body movements in bed could potentially be a highly relevant as well as easy to interpret and derive digital biomarker to monitor a wide range of health deteriorations in older adults. As such, it could help in detecting health deteriorations early on and provide timelier, more personalized, and precise treatment options.

In older adults, physical activity is crucial for healthy aging and associated with numerous health indicators and outcomes. Regular assessments of physical activity can help detect early health-related changes and manage physical activity targeted interventions. The quantification of physical activity, however, is difficult as commonly used self-reported measures are biased and rather unprecise point in time measurements. Modern alternatives are commonly based on wearable technologies which are accurate but suffer from usability and compliance issues. In this study, we assessed the potential of an unobtrusive ambient-sensor based system for continuous, long-term physical activity quantification. Towards this goal, we analysed one year of longitudinal sensor- and medical-records stemming from thirteen community-dwelling old and oldest old subjects. Based on the sensor data the daily number of room-transitions as well as the raw sensor activity were calculated. We did find the number of room-transitions, and to some degree also the raw sensor activity, to capture numerous known associations of physical activity with cognitive, well-being and motor health indicators and outcomes. The results of this study indicate that such low-cost unobtrusive ambient-sensor systems can provide an adequate approximation of older adults’ overall physical activity, sufficient to capture relevant associations with health indicators and outcomes., Scientific Reports, 9, ISSN:2045-2322

In this work, we investigate the application of trainable and spectrally initializable matrix transformations on the feature maps produced by convolution operations. While previous literature has already demonstrated the possibility of adding static spectral transformations as feature processors, our focus is on more general trainable transforms. We study the transforms in various architectural configurations on four datasets of different nature: from medical (ColorectalHist, HAM10000) and natural (Flowers, ImageNet) images to historical documents (CB55) and handwriting recognition (GPDS). With rigorous experiments that control for the number of parameters and randomness, we show that networks utilizing the introduced matrix transformations outperform vanilla neural networks. The observed accuracy increases by an average of 2.2 across all datasets. In addition, we show that the benefit of spectral initialization leads to significantly faster convergence, as opposed to randomly initialized matrix transformations. The transformations are implemented as auto-differentiable PyTorch modules that can be incorporated into any neural network architecture. The entire code base is open-source., Comment: 8 pages