Comparative assessment of sleep quality estimates using home monitoring technology

Perez-Macias, Jose Maria; Jimison, Holly; Korhonen, Ilkka; Pavel, Misha

doi:10.1109/embc.2014.6944742

Cited by 18 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The FitBit may not be considered equivalent to the hi-fidelity actigraphy devices available in 2015. However, they are of sufficient and similar quality to the devices available only a decade ago and provide a low cost alternative to examine sleep and nursing behavior (Lyons et al, 2014;Perez-Macias et al, 2014;Vooijs et al, 2014).…”

Section: Limitationsmentioning

confidence: 99%

Sleep quality, but not quantity, is associated with self-perceived minor error rates among emergency department nurses

Weaver

Stutzman

Supnet

et al. 2016

International Emergency Nursing

View full text Add to dashboard Cite

Section: Limitationsmentioning

confidence: 99%

Sleep quality, but not quantity, is associated with self-perceived minor error rates among emergency department nurses

Weaver

Stutzman

Supnet

et al. 2016

International Emergency Nursing

View full text Add to dashboard Cite

“…Research is growing on the potentials and limitations of modern technology in evaluating sleep. 1,62,63 A recent study compared data from conventional PSG with snore recordings from a standard smartphone taped to a subject's chest, and found good agreement on snore data, high correlation between respiratory disturbance index ("smart-RDI") on the smartphone and apnea-hypopnea index (AHI) on the PSG, and high specificity of the smart-RDI for diagnosing moderate to severe OSA (AHI ≥ 15 identified on PSG). 64 The Sonomat, a contactless sleep monitoring system embedded into a foam mattress and designed to detect conventional events such as apneas and hypopneas, was recently compared to PSG and found to have good AHI, apnea index, and hypopnea index correlation, especially for AHI < 50.…”

Section: Discussionmentioning

confidence: 99%

Consumer Sleep Technologies: A Review of the Landscape

Kientz

Choe

et al. 2015

Journal of Clinical Sleep Medicine

189

148

View full text Add to dashboard Cite

Objective: To review sleep related consumer technologies, including mobile electronic device "apps," wearable devices, and other technologies. Validation and methodological transparency, the effect on clinical sleep medicine, and various social, legal, and ethical issues are discussed. C onsumer sleep technologies (CSTs) are increasingly popular computer-based systems available to the general public for the purpose of improving or self-monitoring sleep. Their primary goals include sleep induction, wake induction, selfguided sleep assessment, entertainment, social connection, information sharing, and sleep education. There is scant literature discussing these technologies.1,2 Despite a paucity of clinical validation with traditional sleep technologies (e.g., polysomnography (PSG), multiple sleep latency testing (MSLT), and clinical-grade actigraphy), CSTs are here to stay because of their innovative nature, convenience, and affordability.Although adoption rates are not available, sleep-tracking products such as Fitbit and Jawbone are top sellers in consumer health products.3,4 The highest-funded health device on Kickstarter was a sleep monitor, which garnered more than $2.4 million in fi nancial backing. 5 A recent search for "sleep" in the Apple iTunes app store returned over 500 different sleep related applications, or "apps," available for download 6 ; similar searches on Android and Microsoft's app stores return hundreds of results. 7,8 Certain apps boast more than fi ve million downloads; one of the top fi ve paid apps in 2014 on iTunes was a sleep tracker and alarm clock. 9 We use the metaphor "over-the-counter" to describe these CSTs, because they are mostly available without a prescription or clinical guidance. Clinical sleep specialists should be aware of these increasingly popular technologies, as patients may request interpretation of derived data. This paper aims to provide a general overview of CSTs and their potential social, ethical, legal, and clinical effect. Although rapid development of these technologies obviates an exhaustive review, we outline some of the more popular, illustrative, or innovative technologies to give sleep specialists an idea of the recent landscape. Consumer Sleep Technologies: A Review of the Landscape METHODSWe searched PubMed and the digital libraries of the Association for Computing Machinery and Institute of Electrical and Electronics Engineers (where technology developers publish peer-reviewed articles), with search terms including "sleep technology," "sleep app," and "sleep monitoring." We eliminated articles that were not relevant to sleep (e.g., applications for controlling a computer's hibernation mode). We ran similar searches on Google, specifi cally focusing on consumer technology-related websites such as MIT Technology Review, 10

show abstract

“…These methods are expensive and intrusive, and therefore not useful for daily use. In order to minimize the discomfort, researchers developed pressure-based bed sensors [42, 45] for long-term and continuous respiration monitoring while users are lying down.…”

Section: Background and Related Workmentioning

confidence: 99%

rConverse

Bari

Adams

Rahman

et al. 2018

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

View full text Add to dashboard Cite

Monitoring of in-person conversations has largely been done using acoustic sensors. In this paper, we propose a new method to detect moment-by-moment conversation episodes by analyzing breathing patterns captured by a mobile respiration sensor. Since breathing is affected by physical and cognitive activities, we develop a comprehensive method for cleaning, screening, and analyzing noisy respiration data captured in the field environment at individual breath cycle level. Using training data collected from a speech dynamics lab study with 12 participants, we show that our algorithm can identify each respiration cycle with 96.34% accuracy even in presence of walking. We present a Conditional Random Field, Context-Free Grammar (CRF-CFG) based conversation model, called rConverse, to classify respiration cycles into speech or non-speech, and subsequently infer conversation episodes. Our model achieves 82.7% accuracy for speech/non-speech classification and it identifies conversation episodes with 95.9% accuracy on lab data using a leave-one-subject-out cross-validation. Finally, the system is validated against audio ground-truth in a field study with 32 participants. rConverse identifies conversation episodes with 71.7% accuracy on 254 hours of field data. For comparison, the accuracy from a high-quality audio-recorder on the same data is 71.9%.

show abstract

Comparative assessment of sleep quality estimates using home monitoring technology

Cited by 18 publications

References 11 publications

Sleep quality, but not quantity, is associated with self-perceived minor error rates among emergency department nurses

Sleep quality, but not quantity, is associated with self-perceived minor error rates among emergency department nurses

Consumer Sleep Technologies: A Review of the Landscape

rConverse

Contact Info

Product

Resources

About