China
Africa
Explore chapters and articles related to this topic
Major Depressive Disorder Detection and Monitoring Using Smart Wearable Devices with Multi-Feature Sensing
Published in Govind Singh Patel, Seema Nayak, Sunil Kumar Chaudhary, Machine Learning, Deep Learning, Big Data, and Internet of Things for Healthcare, 2023
Shamla Mantri, Seema Nayak, Ritom Gupta, Pranav Bakre, Pratik Gorade, Vignesh Iyer
Such a mechanism system requires patients to own and use a smart band with heart rate and sleep tracking capabilities for monitoring and a computer or mobile device to fill out the questionnaire. All this data is processed by models to classify the subject. To reduce the inherent complexity due to the nature of the solution, we chose to stick to what can be captured by even the most basic smart wearable devices. Many previous works have espoused heart rate variability (HRV) [2] and sleep patterns [3,4] for their noticeable correlation with depressive disorders. Both can be easily measured using any consumer-level smartwatch or fitness tracker available on the market; however, they function with varying levels of accuracy.
Motorsports
Published in R. C. Richard Davison, Paul M. Smith, James Hopker, Michael J. Price, Florentina Hettinga, Garry Tew, Lindsay Bottoms, Sport and Exercise Physiology Testing Guidelines: Volume I – Sport Testing, 2022
Elite racing drivers and performance staff look to reduce the impact of regular international travel on cognitive and biological systems through optimising sleep patterns via regular sleep tracking. Sleep tracking wearables, such as the OURA ring and the Whoop band, offer a non-invasive approach to evaluate the sleep activity and the effectiveness of driver sleep routines. Said technologies offer objective data to support and inform coach-driver conversations around optimising pre-bed sleep routines, considering the following: food and caffeine use, minimising light exposure, use of mental practices, optimal sleep environment (comfort, timing and temperature) and physical activity. It’s also useful to evaluate the effectiveness of sleep routines/behaviours by assessing the relationship with other markers such as resting heart rate, heart rate variability (HRV) and reporting subjective wellness and recovery. In combination these methods are useful to understand how sleep interacts and supports the wider wellness and performance needs of the driver athlete.
Emerging Methods for Patient Ergonomics
Published in Richard J. Holden, Rupa S. Valdez, The Patient Factor, 2021
Mustafa Ozkaynak, Laurie Lovett Novak, Yong K. Choi, Rohit Ashok Khot
Sleep self-management strategies that incorporate sensors have the potential to empower patients to track and improve their sleep quality. With the uptake of smartphone ownership, Depose have been developed that utilize embedded sensors in a smartphone to self-monitor activity levels and visualize sleep patterns. Such apps often instruct a user to connect the phone to the charger and place it on the sleeping surface or under the pillow to passively collect data. Using the data, the sleep tracking apps can provide information on sleep patterns (e.g., bedtime, wakeup time, and average time in bed). Additionally, consumer-grade wearable devices such as wrist-worn activity trackers and smart watches also provide users with estimates of sleep-related parameters using proprietary algorithms, including the amount of time in light, deep, and rapid eye movement stage of sleep (Choi et al., 2018). The wearables can collect biometric parameters such as heart rate and blood pressure and potentially provide more detailed estimates than smartphone sensor-based apps. However, sleep estimates generated by wearable devices are under scrutiny for inaccuracy and cannot be used as a substitute for data collected by polysomnography in a sleep lab (Haghayegh et al., 2019). The limitations of wrist-worn sensors also include limited battery life and discomfort of wearing the device during sleep. Despite the shortcomings, consumer-grade IoT sensors provide simple and economical means to longer-term sleep monitoring.
How are Consumer Sleep Technology Data Being Used to Deliver Behavioral Sleep Medicine Interventions? A Systematic Review
Published in Behavioral Sleep Medicine, 2022
K. Glazer Baron, E. Culnan, J. Duffecy, M. Berendson, I. Cheung Mason, E. Lattie, N. Manalo
It is important to point out that there was no evidence in our review that the use of consumer sleep technology led to poorer outcomes in participants. Using technology may also have negative effects in some circumstances or for some patients. For example, the use of a wearable device in a group weight management treatment led to lower long-term weight loss outcomes compared to participants that did not receive a device (Polzien et al., 2007). We also previously reported a case series of patients who were overly focused on their devices (Baron et al., 2017), which we called “orthosomnia” and this fixation interefered with treatment. Using technology also has the potential to expose patients to blue light, if they are using their smartphone applications at night (Chang et al., 2015). These studies suggest there may be some unintended effects of tracking in some situations but overall none of the studies in our review negative impacts on sleep as a result of sleep tracking.
Current and future strategies for diagnostic and management of obstructive sleep apnea
Published in Expert Review of Molecular Diagnostics, 2021
Sartaj Khurana, Narshone Soda, Muhammad J. A. Shiddiky, Ranu Nayak, Sudeep Bose
The above-mentioned modern detection methods have immense applications and advantages (specificity, less time consuming, cost-effectiveness, etc.) in the detection of OSA and associated biomarkers. However, they possess a few limitations as well. Home sleep apnea testing (HSAT) is unable to diagnose other sleep disorders, provides discomfort to the patient due to prolonged use, and improper evaluation using HSAT may result in inconclusive readings requiring repeat studies.Sleep tracking through smart wearables is challenging due to battery limitations as well as the limited number of sensors available to procure information about sleep disorders [63].Biomotion sensors have showcased their relevance in OSA detection, but there are a few limitations to their application such as periodic limb movements in OSA patients might lead to inconclusive results in sleep/wake patterns [64].Microarrays are rendered less useful due to requirement of large sample volumes and prolonged incubation times as well as limited detection sensitivity.
Sleep assessment by means of a wrist actigraphy-based algorithm: agreement with polysomnography in an ambulatory study on older adults
Published in Chronobiology International, 2021
Giulia Regalia, Giulia Gerboni, Matteo Migliorini, Matteo Lai, Jonathan Pham, Nirajan Puri, Milena K. Pavlova, Rosalind W. Picard, Rani A. Sarkis, Francesco Onorati
Since most validation studies of wrist-worn wearable devices have been conducted on healthy young populations that typically show non-disrupted and long-lasting sleep periods, clinically satisfactory ranges for actigraphy-based devices in relation to PSG-EEG outcomes are reported for young adults with no diagnosed sleep conditions (de Zambotti et al. 2019; Meltzer et al. 2012). On the other hand, aging has been associated with physiological and behavioral alterations of sleep, especially an increased number of arousals, more frequent awakenings and lower sleep durations and efficiencies (Bonnet and Arand 2007), albeit not only in response to pathological conditions (Morin and Gramling 1989). Few studies have reported sleep scoring (Palotti et al. 2019; Sivertsen et al. 2006) and sleep quality assessment (Blackwell et al. 2008; Taibi et al. 2013) in older adults, often in association with diagnosed sleep conditions (Sivertsen et al. 2006). Such studies are pivotal to assess the utility and effectiveness of ACT for automatic sleep tracking in a sensitive group that may significantly differ from young adults: older adults have the greatest need for sleep evaluation due to increasing risks of sleep problems with aging (Miner and Kryger 2017), and they might benefit the most from unobtrusive long-term ambulatory sleep monitoring technologies.