Monitoring healthy and disturbed sleep through smartphone applications: a review of experimental evidence

Advances and Opportunities of Mobile Health in the Postpandemic Era: Smartphonization of Wearable Devices and Wearable Deviceization of Smartphones

Mobile health (mHealth) with continuous real-time monitoring is leading the era of digital medical convergence. Wearable devices and smartphones optimized as personalized health management platforms enable disease prediction, prevention, diagnosis, and even treatment. Ubiquitous and accessible medical services offered through mHealth strengthen universal health coverage to facilitate service use without discrimination. This viewpoint investigates the latest trends in mHealth technology, which are comprehensive in terms of form factors and detection targets according to body attachment location and type. Insights and breakthroughs from the perspective of mHealth sensing through a new form factor and sensor-integrated display overcome the problems of existing mHealth by proposing a solution of smartphonization of wearable devices and the wearable deviceization of smartphones. This approach maximizes the infinite potential of stagnant mHealth technology and will present a new milestone leading to the popularization of mHealth. In the postpandemic era, innovative mHealth solutions through the smartphonization of wearable devices and the wearable deviceization of smartphones could become the standard for a new paradigm in the field of digital medicine.

Accuracy of 11 Wearable, Nearable, and Airable Consumer Sleep Trackers: Prospective Multicenter Validation Study

BACKGROUND

Consumer sleep trackers (CSTs) have gained significant popularity because they enable individuals to conveniently monitor and analyze their sleep. However, limited studies have comprehensively validated the performance of widely used CSTs. Our study therefore investigated popular CSTs based on various biosignals and algorithms by assessing the agreement with polysomnography.

OBJECTIVE

This study aimed to validate the accuracy of various types of CSTs through a comparison with in-lab polysomnography. Additionally, by including widely used CSTs and conducting a multicenter study with a large sample size, this study seeks to provide comprehensive insights into the performance and applicability of these CSTs for sleep monitoring in a hospital environment.

METHODS

The study analyzed 11 commercially available CSTs, including 5 wearables (Google Pixel Watch, Galaxy Watch 5, Fitbit Sense 2, Apple Watch 8, and Oura Ring 3), 3 nearables (Withings Sleep Tracking Mat, Google Nest Hub 2, and Amazon Halo Rise), and 3 airables (SleepRoutine, SleepScore, and Pillow). The 11 CSTs were divided into 2 groups, ensuring maximum inclusion while avoiding interference between the CSTs within each group. Each group (comprising 8 CSTs) was also compared via polysomnography.

RESULTS

The study enrolled 75 participants from a tertiary hospital and a primary sleep-specialized clinic in Korea. Across the 2 centers, we collected a total of 3890 hours of sleep sessions based on 11 CSTs, along with 543 hours of polysomnography recordings. Each CST sleep recording covered an average of 353 hours. We analyzed a total of 349,114 epochs from the 11 CSTs compared with polysomnography, where epoch-by-epoch agreement in sleep stage classification showed substantial performance variation. More specifically, the highest macro F1 score was 0.69, while the lowest macro F1 score was 0.26. Various sleep trackers exhibited diverse performances across sleep stages, with SleepRoutine excelling in the wake and rapid eye movement stages, and wearables like Google Pixel Watch and Fitbit Sense 2 showing superiority in the deep stage. There was a distinct trend in sleep measure estimation according to the type of device. Wearables showed high proportional bias in sleep efficiency, while nearables exhibited high proportional bias in sleep latency. Subgroup analyses of sleep trackers revealed variations in macro F1 scores based on factors, such as BMI, sleep efficiency, and apnea-hypopnea index, while the differences between male and female subgroups were minimal.

CONCLUSIONS

Our study showed that among the 11 CSTs examined, specific CSTs showed substantial agreement with polysomnography, indicating their potential application in sleep monitoring, while other CSTs were partially consistent with polysomnography. This study offers insights into the strengths of CSTs within the 3 different classes for individuals interested in wellness who wish to understand and proactively manage their own sleep.

Investigating the relationship between sleep and migraine in a global sample: a Bayesian cross-sectional approach

BACKGROUND

There is a bidirectional link between sleep and migraine, however causality is difficult to determine. This study aimed to investigate this relationship using data collected from a smartphone application.

METHODS

Self-reported data from 11,166 global users (aged 18-81 years, mean: 41.21, standard deviation: 11.49) were collected from the Migraine Buddy application (Healint Pte. Ltd.). Measures included: start and end times of sleep and migraine attacks, and pain intensity. Bayesian regression models were used to predict occurrence of a migraine attack the next day based on users' deviations from average sleep, number of sleep interruptions, and hours slept the night before in those reporting ≥ 8 and < 25 migraine attacks on average per month. Conversely, we modelled whether attack occurrence and pain intensity predicted hours slept that night.

RESULTS

There were 724 users (129 males, 412 females, 183 unknown, mean age = 41.88 years, SD = 11.63), with a mean monthly attack frequency of 9.94. More sleep interruptions (95% Highest Density Interval (95%HDI [0.11 - 0.21]) and deviation from a user's mean sleep (95%HDI [0.04 - 0.08]) were significant predictors of a next day attack. Total hours slept was not a significant predictor (95%HDI [-0.04 - 0.04]). Pain intensity, but not attack occurrence was a positive predictor of hours slept.

CONCLUSIONS

Sleep fragmentation and deviation from typical sleep are the main drivers of the relationship between sleep and migraine. Having a migraine attack does not predict sleep duration, yet the pain associated with it does. This study highlights sleep as crucial in migraine management.

Associations of smartphone usage patterns with sleep and mental health symptoms in a clinical cohort receiving virtual behavioral medicine care: a retrospective study

Study Objectives

We sought to develop behavioral sleep measures from passively sensed human-smartphone interactions and retrospectively evaluate their associations with sleep disturbance, anxiety, and depressive symptoms in a large cohort of real-world patients receiving virtual behavioral medicine care.

Methods

Behavioral sleep measures from smartphone data were developed: daily longest period of smartphone inactivity (inferred sleep period [ISP]); 30-day expected period of inactivity (expected sleep period [ESP]); regularity of the daily ISP compared to the ESP (overlap percentage); and smartphone usage during inferred sleep (disruptions, wakefulness during sleep period). These measures were compared to symptoms of sleep disturbance, anxiety, and depression using linear mixed-effects modeling. More than 2300 patients receiving standard-of-care virtual mental healthcare across more than 111 000 days were retrospectively analyzed.

Results

Mean ESP duration was 8.4 h (SD = 2.3), overlap percentage 75% (SD = 18%) and disrupted time windows 4.85 (SD = 3). There were significant associations between overlap percentage (p < 0.001) and disruptions (p < 0.001) with sleep disturbance symptoms after accounting for demographics. Overlap percentage and disruptions were similarly associated with anxiety and depression symptoms (all p < 0.001).

Conclusions

Smartphone behavioral measures appear useful to longitudinally monitor sleep and benchmark depressive and anxiety symptoms in patients receiving virtual behavioral medicine care. Patterns consistent with better sleep practices (i.e. greater regularity of ISP, fewer disruptions) were associated with lower levels of reported sleep disturbances, anxiety, and depression.

A Trainable Open-Source Machine Learning Accelerometer Activity Recognition Toolbox: Deep Learning Approach

BACKGROUND

The accuracy of movement determination software in current activity trackers is insufficient for scientific applications, which are also not open-source.

OBJECTIVE

To address this issue, we developed an accurate, trainable, and open-source smartphone-based activity-tracking toolbox that consists of an Android app (HumanActivityRecorder) and 2 different deep learning algorithms that can be adapted to new behaviors.

METHODS

We employed a semisupervised deep learning approach to identify the different classes of activity based on accelerometry and gyroscope data, using both our own data and open competition data.

RESULTS

Our approach is robust against variation in sampling rate and sensor dimensional input and achieved an accuracy of around 87% in classifying 6 different behaviors on both our own recorded data and the MotionSense data. However, if the dimension-adaptive neural architecture model is tested on our own data, the accuracy drops to 26%, which demonstrates the superiority of our algorithm, which performs at 63% on the MotionSense data used to train the dimension-adaptive neural architecture model.

CONCLUSIONS

HumanActivityRecorder is a versatile, retrainable, open-source, and accurate toolbox that is continually tested on new data. This enables researchers to adapt to the behavior being measured and achieve repeatability in scientific studies.

Consumer sleep technology for the screening of obstructive sleep apnea and snoring: current status and a protocol for a systematic review and meta-analysis of diagnostic test accuracy

There are concerns about the validation and accuracy of currently available consumer sleep technology for sleep-disordered breathing. The present report provides a background review of existing consumer sleep technologies and discloses the methods and procedures for a systematic review and meta-analysis of diagnostic test accuracy of these devices and apps for the detection of obstructive sleep apnea and snoring in comparison with polysomnography. The search will be performed in four databases (PubMed, Scopus, Web of Science, and the Cochrane Library). Studies will be selected in two steps, first by an analysis of abstracts followed by full-text analysis, and two independent reviewers will perform both phases. Primary outcomes include apnea-hypopnea index, respiratory disturbance index, respiratory event index, oxygen desaturation index, and snoring duration for both index and reference tests, as well as the number of true positives, false positives, true negatives, and false negatives for each threshold, as well as for epoch-by-epoch and event-by-event results, which will be considered for the calculation of surrogate measures (including sensitivity, specificity, and accuracy). Diagnostic test accuracy meta-analyses will be performed using the Chu and Cole bivariate binomial model. Mean difference meta-analysis will be performed for continuous outcomes using the DerSimonian and Laird random-effects model. Analyses will be performed independently for each outcome. Subgroup and sensitivity analyses will evaluate the effects of the types (wearables, nearables, bed sensors, smartphone applications), technologies (e.g., oximeter, microphone, arterial tonometry, accelerometer), the role of manufacturers, and the representativeness of the samples.

Investigating the combined effect of ALAN and noise on sleep by simultaneous real-time monitoring using low-cost smartphone devices

The association between artificial light at night (ALAN) and noise, on the one hand, and sleep, on the other, is well established. Yet studies investigating these associations have been infrequent and mostly conducted in controlled laboratory conditions. As a result, little is known about the applicability of their results to real-world settings. In this paper, we attempt to bridge this knowledge gap by carrying out an individual-level real-world study, involving 72 volunteers from different urban localities in Israel. The survey participants were asked to use their personal smartphones and smartwatches to monitor sleep patterns for 30 consecutive days, while ALAN and noise exposures were monitored in parallel, with inputs reported each second. The volunteers were also asked to fill in a questionnaire about their individual attributes, daily habits, room settings, and personal health, to serve as individual-level controls. Upon cointegration, the assembled data were co-analyzed using bivariate and multivariate statistical tools. As the study reveals, the effect of ALAN and noise on sleep largely depends on when the exposure occurred, that is, before sleep or during sleep. In particular, the effect of ALAN exposure was found to be most pronounced if it occurred before sleep, while exposure to noise mattered most if it occurred during the sleep phase. As the study also reveals, the effects of ALAN and noise appear to amplify each other, with a 14-15.3% reduction in sleep duration and an 8-9% reduction in sleep efficiency observed at high levels of ALAN-noise exposures. The study helped to assemble a massive amount of real-time observations, enabling a robust individual-level analysis.

Isolated REM sleep behaviour disorder: current diagnostic procedures and emerging new technologies

Isolated REM sleep behaviour disorder (iRBD) is characterised by dream enactment behaviours, such as kicking and punching while asleep, and vivid/violent dreams. It is now acknowledged as a prodromal phase of neurodegenerative disease-approximately 80% of people with iRBD will develop dementia with Lewy Bodies, Parkinson's disease or another degenerative brain disease within 10 years. It is important that neurologists and other clinicians understand how to make an early accurate diagnosis of iRBD so that affected people can have the opportunity to take part in clinical trials. However, making a diagnosis can be clinically challenging due to a variety of reasons, including delayed referral, symptom overlap with other disorders, and uncertainty about how to confirm a diagnosis. Several methods of assessment are available, such as clinical interview, screening questionnaires and video polysomnography or 'sleep study'. This review aims to support clinical neurologists in assessing people who present with symptoms suggestive of iRBD. We describe the usefulness and limitations of each diagnostic method currently available in clinical practice, and present recent research on the utility of new wearable technologies to assist with iRBD diagnosis, which may offer a more practical assessment method for clinicians. This review highlights the importance of thorough clinical investigation when patients present with suspected iRBD and emphasises the need for easier access to diagnostic procedures for accurate and early diagnosis.

Diagnostic value of smartphone in obstructive sleep apnea syndrome: A systematic review and meta-analysis

Objectives

To assess the diagnostic utility of smartphone-based measurement in detecting moderate to severe obstructive sleep apnea syndrome (OSAS).

Methods

Six databases were thoroughly reviewed. Random-effect models were used to estimate the summary sensitivity, specificity, negative predictive value, positive predictive value, diagnostic odds ratio, summary receiver operating characteristic curve and measured the areas under the curve. To assess the accuracy and precision, pooled mean difference and standard deviation of apnea hypopnea index (AHI) between smartphone and polysomnography (95% limits of agreement) across studies were calculated using the random-effects model. Study methodological quality was evaluated using the QUADAS-2 tool.

Results

Eleven studies were analyzed. The smartphone diagnostic odds ratio for moderate-to-severe OSAS (apnea/hypopnea index > 15) was 57.3873 (95% confidence interval [CI]: [34.7462; 94.7815]). The area under the summary receiver operating characteristic curve was 0.917. The sensitivity, specificity, negative predictive value, and positive predictive value were 0.9064 [0.8789; 0.9282], 0.8801 [0.8227; 0.9207], 0.9049 [0.8556; 0.9386], and 0.8844 [0.8234; 0.9263], respectively. We performed subgroup analysis based on the various OSAS detection methods (motion, sound, oximetry, and combinations thereof). Although the diagnostic odds ratios, specificities, and negative predictive values varied significantly (all p < 0.05), all methods afforded good sensitivity (> 80%). The sensitivities and positive predictive values were similar for the various methods (both p > 0.05). The mean difference with standard deviation in the AHI between smartphone and polysomnography was -0.6845 ± 1.611 events/h [-3.8426; 2.4735].

Conclusions

Smartphone could be used to screen the moderate-to-severe OSAS. The mean difference between smartphones and polysomnography AHI measurements was small, though limits of agreement was wide. Therefore, clinicians should be cautious when making clinical decisions based on these devices.

A systematic review of smartphone applications and devices for obstructive sleep apnea

OBJECTIVE

Sleep is fundamental for both health and wellness. The advent of "on a chip" and "smartphone" technologies have created an explosion of inexpensive, at-home applications and devices specifically addressing sleep health and sleep disordered breathing. Sleep-related smartphone Applications and devices are offering diagnosis, management, and treatment of a variety of sleep disorders, mainly obstructive sleep apnea. New technology requires both a learning curve and a review of reliability. Our objective was to evaluate which app have scientific publications as well as their potential to help in the diagnosis, management, and follow-up of sleep disordered breathing.

METHODS

We search for relevant sleep apnea related apps on both the Google Play Store and the Apple App Store. In addition, an exhaustive literature search was carried out in MEDLINE, EMBase, web of science and Scopus for works of apps or devices that have published in the scientific literature and have been used in a clinical setting for diagnosis or treatment of sleep disordered breathing performing a systematic review.

RESULTS

We found 10 smartphone apps that met the inclusion criteria.

CONCLUSIONS

The development of these apps and devices has a great future, but today are not as accurate as other traditional options. This new technology offers accessible, inexpensive, and continuous at home data monitoring of obstructive sleep apnea, but still does not count with proper testing and their validation may be unreliable.

Home Sleep Testing of Sleep Apnea

Measurement methods with graded complexity for use in the lab as well as for home sleep testing (HST) are available for the diagnosis of sleep apnea, and there are different classification systems in existence. Simplified HST measurements, which record fewer parameters than traditional four- to six-channel devices, can indicate sleep apnea and can be used as screening tool in high-prevalence patient groups. Peripheral arterial tonometry (PAT) is a technique which can be suitable for the diagnosis of sleep apnea in certain cases. Different measurement methods are used, which has an influence on the significance of the results. New minimal-contact and non-contact technologies of recording and analysis of surrogate parameters are under development. If they are validated by clinical studies, it will be possible to detect sleep apnea in need of treatment more effectively. In addition, this could become a solution to monitor the effectiveness of such treatment.

A scoping review of mobile apps for sleep management: User needs and design considerations

Sleep disorders are prevalent nowadays, leading to anxiety, depression, high blood pressure, and other health problems. Due to the proliferation of mobile devices and the development of communication technologies, mobile apps have become a popular way to deliver sleep disorder therapy or manage sleep. This scoping review aims to conduct a systematic investigation of mobile apps and technologies supporting sleep, including the essential functions of sleep apps, how they are used to improve sleep and the facilitators of and barriers to using apps among patients and other stakeholders. We searched articles (2010 to 2022) from Scopus, Web of Science, Science Direct, PubMed, and IEEE Xplore using the keyword sleep apps. In total, 1,650 peer-reviewed articles were screened, and 51 were selected for inclusion. The most frequently provided functions by the apps are sleep monitoring, measuring sleep, providing alarms, and recording sleep using a sleep diary. Several wearable devices have been used with mobile apps to record sleep duration and sleep problems. Facilitators and barriers to using apps were identified, along with the evidence-based design guidelines. Existing studies have proved the initial validation and efficiency of delivering sleep treatment by mobile apps; however, more research is needed to improve the performance of sleep apps and devise a way to utilize them as a therapy tool.

Effects of sleep self-monitoring via app on subjective sleep markers in student athletes

As sleep problems are highly prevalent among university students and competitive athletes, and the application of commercial sleep technologies may be either useful or harmful, this study investigated the effects of a 2-week sleep self-monitoring on the sleep of physically active university students (n = 98, 21 ± 1.7 years). Two intervention groups used a free sleep app (Sleep Score; SleepScore Labs™, Carlsbad, CA, USA: n = 20 or Sleep Cycle; Sleep Cycle AB, Gothenburg, Sweden: n = 24) while answering online sleep diaries. They used the app analysis function in week 1 and the 'smart alarm' additionally in week 2. As controls, one group answered the online sleep diary without intervention (n = 21) and another the pre-post questionnaires only (n = 33). Facets of subjective sleep behaviour and the role of bedtime procrastination were analysed. Multilevel models did not show significant interactions, indicating intervention effects equal for both app groups. Sleep Cycle users showed trends toward negative changes in sleep behaviour, while the online sleep diary group showed more, tendentially positive, developments. Bedtime procrastination was a significant predictor of several variables of sleep behaviour and quality. The results indicate neither benefits nor negative effects of app-based sleep self-tracking. Thus, student athletes do not seem to be as susceptible to non-validated sleep technologies as expected. However, bedtime procrastination was correlated with poor sleep quality and should be addressed in sleep intervention programmes.

Nutritional Formulation for Patients with Angelman Syndrome: A Randomized, Double-Blind, Placebo-Controlled Study of Exogenous Ketones

BACKGROUND

Angelman syndrome (AS) patients often respond to low glycemic index therapy to manage refractory seizures. These diets significantly affect quality of life and are challenging to implement. These formulations may have benefits in AS even in the absence of biomarkers suggesting ketosis.

OBJECTIVES

We aimed to compare an exogenous medical food ketone formulation (KF) with placebo for the dietary management of AS.

METHODS

This randomized, double-blind, placebo-controlled, crossover clinical trial was conducted in an academic center from 15 November, 2018 to 6 January, 2020. Thirteen participants with molecularly confirmed AS aged 4-11 y met the criteria and completed the 16-wk study. The study consisted of four 4-wk phases: a baseline phase, a blinded KF or placebo phase, a washout phase, and the crossover phase with alternate blinded KF or placebo. Primary outcomes were safety and tolerability rated by retention in the study and adherence to the formulation. Additional secondary outcomes of safety in this nonverbal population included blood chemistry, gastrointestinal health, seizure burden, cortical irritability, cognition, mobility, sleep, and developmental staging.

RESULTS

Data were compared between the baseline, KF, and placebo epochs. One participant exited the trial owing to difficulty consuming the formulation. Adverse events included an increase in cholesterol in 1 subject when consuming KF and a decrease in albumin in 1 subject when consuming placebo. Stool consistency improved with KF consumption, from 6.04 ± 1.61 at baseline and 6.35 ± 1.55 during placebo to 4.54 ± 1.19 during KF (P = 0.0027). Electroencephalograph trends showed a decrease in Δ frequency power during the KF arm and event-related potentials suggested a change in the frontal memory response. Vineland-3 showed improved fine motor skills in the KF arm.

CONCLUSIONS

The exogenous KF appears safe. More data are needed to determine the utility of exogenous ketones as a nutritional approach in children with AS.This trial was registered at clinicaltrials.gov as NCT03644693.

Proposal for a Home Sleep Monitoring Platform Employing a Smart Glove

The present paper proposes the design of a sleep monitoring platform. It consists of an entire sleep monitoring system based on a smart glove sensor called UpNEA worn during the night for signals acquisition, a mobile application, and a remote server called AeneA for cloud computing. UpNEA acquires a 3-axis accelerometer signal, a photoplethysmography (PPG), and a peripheral oxygen saturation (SpO2) signal from the index finger. Overnight recordings are sent from the hardware to a mobile application and then transferred to AeneA. After cloud computing, the results are shown in a web application, accessible for the user and the clinician. The AeneA sleep monitoring activity performs different tasks: sleep stages classification and oxygen desaturation assessment; heart rate and respiration rate estimation; tachycardia, bradycardia, atrial fibrillation, and premature ventricular contraction detection; and apnea and hypopnea identification and classification. The PPG breathing rate estimation algorithm showed an absolute median error of 0.5 breaths per minute for the 32 s window and 0.2 for the 64 s window. The apnea and hypopnea detection algorithm showed an accuracy (Acc) of 75.1%, by windowing the PPG in one-minute segments. The classification task revealed 92.6% Acc in separating central from obstructive apnea, 83.7% in separating central apnea from central hypopnea and 82.7% in separating obstructive apnea from obstructive hypopnea. The novelty of the integrated algorithms and the top-notch cloud computing products deployed, encourage the production of the proposed solution for home sleep monitoring.

Consumer-grade sleep trackers are still not up to par compared to polysomnography

PURPOSE

Although polysomnography (PSG) is the gold standard for monitoring sleep, it has many limitations. We aimed to prospectively determine the validity of wearable sleep-tracking devices and smartphone applications by comparing the data to that of PSGs.

METHODS

Patients who underwent one night of attended PSG at a single institution from January, 2015 to July 2019 were recruited. Either a sleep application or wearable device was used simultaneously while undergoing PSG. Nine smartphone applications and three wearable devices were assessed.

RESULTS

We analyzed the results of 495 cases of smartphone applications and 170 cases of wearables by comparing each against PSG. None of the tested applications were able to show a statistically significant correlation between sleep efficiency, durations of wake time, light sleep or deep sleep with PSG. Snore time correlated well in both of the two applications which provided such information. Deep sleep duration and WASO measured by two of the three wearable devices correlated significantly with PSG. Even after controlling for transition count and moving count, the correlation indices of the wearables did not increase, suggesting that the algorithms used by the wearables were not largely affected by tossing and turning.

CONCLUSIONS

Most of the applications tested in this study showed poor validity, while wearable devices mildly correlated with PSG. An effective use for these devices may be as a tool to identify the change seen in an individual's sleep patterns on a day-to-day basis, instead of as a method of detecting absolute measurements.

Lung Auscultation Using the Smartphone-Feasibility Study in Real-World Clinical Practice

Conventional lung auscultation is essential in the management of respiratory diseases. However, detecting adventitious sounds outside medical facilities remains challenging. We assessed the feasibility of lung auscultation using the smartphone built-in microphone in real-world clinical practice. We recruited 134 patients (median[interquartile range] 16[11-22.25]y; 54% male; 31% cystic fibrosis, 29% other respiratory diseases, 28% asthma; 12% no respiratory diseases) at the Pediatrics and Pulmonology departments of a tertiary hospital. First, clinicians performed conventional auscultation with analog stethoscopes at 4 locations (trachea, right anterior chest, right and left lung bases), and documented any adventitious sounds. Then, smartphone auscultation was recorded twice in the same four locations. The recordings (n = 1060) were classified by two annotators. Seventy-three percent of recordings had quality (obtained in 92% of the participants), with the quality proportion being higher at the trachea (82%) and in the children's group (75%). Adventitious sounds were present in only 35% of the participants and 14% of the recordings, which may have contributed to the fair agreement between conventional and smartphone auscultation (85%; k = 0.35(95% CI 0.26-0.44)). Our results show that smartphone auscultation was feasible, but further investigation is required to improve its agreement with conventional auscultation.

Accuracy of a Smartphone Application Measuring Snoring in Adults-How Smart Is It Actually?

About 40% of the adult population is affected by snoring, which is closely related to obstructive sleep apnea (OSA) and can be associated with serious health implications. Commercial smartphone applications (apps) offer the possibility of monitoring snoring at home. However, the number of validation studies addressing snoring apps is limited. The purpose of the present study was to assess the accuracy of recorded snoring using the free version of the app SnoreLab (Reviva Softworks Ltd., London, UK) in comparison to a full-night polygraphic measurement (Miniscreen plus, Löwenstein Medical GmbH & Co., KG, Bad Ems, Germany). Nineteen healthy adult volunteers (4 female, 15 male, mean age: 38.9 ± 19.4 years) underwent simultaneous polygraphic and SnoreLab app measurement for one night at home. Parameters obtained by the SnoreLab app were: starting/ending time of monitoring, time in bed, duration and percent of quiet sleep, light, loud and epic snoring, total snoring time and Snore Score, a specific score obtained by the SnoreLab app. Data obtained from polygraphy were: starting/ending time of monitoring, time in bed, total snoring time, snore index (SI), snore index obstructive (SI obstructive) and apnea-hypopnea-index (AHI). For different thresholds of percentage snoring per night, accuracy, sensitivity, specificity, positive and negative predictive values were calculated. Comparison of methods was undertaken by Spearman-Rho correlations and Bland-Altman plots. The SnoreLab app provides acceptable accuracy values measuring snoring >50% per night: 94.7% accuracy, 100% sensitivity, 94.1% specificity, 66.6% positive prediction value and 100% negative prediction value. Best agreement between both methods was achieved in comparing the sum of loud and epic snoring ratios obtained by the SnoreLab app with the total snoring ratio measured by polygraphy. Obstructive events could not be detected by the SnoreLab app. Compared to polygraphy, the SnoreLab app provides acceptable accuracy values regarding the measurement of especially heavy snoring.

SleepPos App: An Automated Smartphone Application for Angle Based High Resolution Sleep Position Monitoring and Treatment

Poor sleep quality or disturbed sleep is associated with multiple health conditions. Sleep position affects the severity and occurrence of these complications, and positional therapy is one of the less invasive treatments to deal with them. Sleep positions can be self-reported, which is unreliable, or determined by using specific devices, such as polysomnography, polygraphy or cameras, that can be expensive and difficult to employ at home. The aim of this study is to determine how smartphones could be used to monitor and treat sleep position at home. We divided our research into three tasks: (1) develop an Android smartphone application ('SleepPos' app) which monitors angle-based high-resolution sleep position and allows to simultaneously apply positional treatment; (2) test the smartphone application at home coupled with a pulse oximeter; and (3) explore the potential of this tool to detect the positional occurrence of desaturation events. The results show how the 'SleepPos' app successfully determined the sleep position and revealed positional patterns of occurrence of desaturation events. The 'SleepPos' app also succeeded in applying positional therapy and preventing the subjects from sleeping in the supine sleep position. This study demonstrates how smartphones are capable of reliably monitoring high-resolution sleep position and provide useful clinical information about the positional occurrence of desaturation events.

Daily self-reported and automatically generated smartphone-based sleep measurements in patients with newly diagnosed bipolar disorder, unaffected first-degree relatives and healthy control individuals

OBJECTIVES

(1) To investigate daily smartphone-based self-reported and automatically generated sleep measurements, respectively, against validated rating scales; (2) to investigate if daily smartphone-based self-reported sleep measurements reflected automatically generated sleep measurements and (3) to investigate the differences in smartphone-based sleep measurements between patients with bipolar disorder (BD), unaffected first-degree relatives (UR) and healthy control individuals (HC).

METHODS

We included 203 patients with BD, 54 UR and 109 HC in this study. To investigate whether smartphone-based sleep calculated from self-reported bedtime, wake-up time and screen on/off time reflected validated rating scales, we used the Pittsburgh Sleep Quality Index (PSQI) and sleep items on the Hamilton Depression Rating Scale 17-item (HAMD-17) and the Young Mania Rating Scale (YMRS).

FINDINGS

(1) Self-reported smartphone-based sleep was associated with the PSQI and sleep items of the HAMD and the YMRS. (2) Automatically generated smartphone-based sleep measurements were associated with daily self-reports of hours slept between 12:00 midnight and 06:00. (3) According to smartphone-based sleep, patients with BD slept less between 12:00 midnight and 06:00, with more interruption and daily variability compared with HC. However, differences in automatically generated smartphone-based sleep were not statistically significant.

CONCLUSION

Smartphone-based data may represent measurements of sleep patterns that discriminate between patients with BD and HC and potentially between UR and HC.

CLINICAL IMPLICATION

Detecting sleep disturbances and daily variability in sleep duration using smartphones may be helpful for both patients and clinicians for monitoring illness activity.

TRIAL REGISTRATION NUMBER

clinicaltrials.gov (NCT02888262).

Alternative algorithms and devices in sleep apnoea diagnosis: what we know and what we expect

PURPOSE OF REVIEW

Diagnosis of sleep apnoea was performed in sleep laboratories with polysomnography. This requires a room with supervision and presence of technologists and trained sleep experts. Today, clinical guidelines in most countries recommend home sleep apnoea testing with simple systems using six signals only. If criteria for signal quality, recording conditions, and patient selection are considered, then this is a reliable test with high accuracy.

RECENT FINDINGS

Recently diagnostic tools for sleep apnoea diagnosis become even more simple: smartwatches and wearables with smart apps claim to diagnose sleep apnoea when these devices are tracking sleep and sleep quality as part of new consumer health checking. Alternative and new devices range from excellent diagnostic tools with high accuracy and full validation studies down to very low-quality tools which only result in random diagnostic reports. Due to the high prevalence of sleep apnoea, even a random diagnosis may match a real disorder sometimes.

SUMMARY

Until now, there are no metrics established how to evaluate these alternative algorithms and simple devices. Proposals for evaluating smartwatches, smartphones, single-use sensors, and new algorithms are presented. New assessments may help to overcome current limitations in sleep apnoea severity metrics. VIDEO ABSTRACT: http://links.lww.com/COPM/A28.

Current Status and Future Challenges of Sleep Monitoring Systems: Systematic Review

Background

Sleep is essential for human health. Considerable effort has been put into academic and industrial research and in the development of wireless body area networks for sleep monitoring in terms of nonintrusiveness, portability, and autonomy. With the help of rapid advances in smart sensing and communication technologies, various sleep monitoring systems (hereafter, sleep monitoring systems) have been developed with advantages such as being low cost, accessible, discreet, contactless, unmanned, and suitable for long-term monitoring.

Objective

This paper aims to review current research in sleep monitoring to serve as a reference for researchers and to provide insights for future work. Specific selection criteria were chosen to include articles in which sleep monitoring systems or devices are covered.

Methods

This review investigates the use of various common sensors in the hardware implementation of current sleep monitoring systems as well as the types of parameters collected, their position in the body, the possible description of sleep phases, and the advantages and drawbacks. In addition, the data processing algorithms and software used in different studies on sleep monitoring systems and their results are presented. This review was not only limited to the study of laboratory research but also investigated the various popular commercial products available for sleep monitoring, presenting their characteristics, advantages, and disadvantages. In particular, we categorized existing research on sleep monitoring systems based on how the sensor is used, including the number and type of sensors, and the preferred position in the body. In addition to focusing on a specific system, issues concerning sleep monitoring systems such as privacy, economic, and social impact are also included. Finally, we presented an original sleep monitoring system solution developed in our laboratory.

Results

By retrieving a large number of articles and abstracts, we found that hotspot techniques such as big data, machine learning, artificial intelligence, and data mining have not been widely applied to the sleep monitoring research area. Accelerometers are the most commonly used sensor in sleep monitoring systems. Most commercial sleep monitoring products cannot provide performance evaluation based on gold standard polysomnography.

Conclusions

Combining hotspot techniques such as big data, machine learning, artificial intelligence, and data mining with sleep monitoring may be a promising research approach and will attract more researchers in the future. Balancing user acceptance and monitoring performance is the biggest challenge in sleep monitoring system research.

Sleep Monitoring in Athletes: Motivation, Methods, Miscalculations and Why it Matters

It is increasingly recognised that many athletes have poor sleep quantity and/or quality despite the advances in knowledge regarding the importance of sleep for an athletic population. The majority of research in sleep assessment and treatment (within the general population) focuses on the medical disorder insomnia, and therefore may not be specifically relevant for athletes. Further, there are currently no guidelines for the standardisation of assessment, intervention, feedback and behaviour change strategies in athletes. This review outlines potential reasons for sleep disturbances in athletes, advantages and disadvantages of a range of methods to assess sleep (polysomnography, activity monitoring, consumer sleep technology, sleep diaries and questionnaires), considerations for the provision of feedback, a description of potential interventions and behaviour change challenges and strategies. The objective of this review is to provide practitioners with the latest scientific evidence in an area rapidly progressing in awareness, consumerism and athlete engagement.

The future of sleep health: a data-driven revolution in sleep science and medicine

In recent years, there has been a significant expansion in the development and use of multi-modal sensors and technologies to monitor physical activity, sleep and circadian rhythms. These developments make accurate sleep monitoring at scale a possibility for the first time. Vast amounts of multi-sensor data are being generated with potential applications ranging from large-scale epidemiological research linking sleep patterns to disease, to wellness applications, including the sleep coaching of individuals with chronic conditions. However, in order to realise the full potential of these technologies for individuals, medicine and research, several significant challenges must be overcome. There are important outstanding questions regarding performance evaluation, as well as data storage, curation, processing, integration, modelling and interpretation. Here, we leverage expertise across neuroscience, clinical medicine, bioengineering, electrical engineering, epidemiology, computer science, mHealth and human-computer interaction to discuss the digitisation of sleep from a inter-disciplinary perspective. We introduce the state-of-the-art in sleep-monitoring technologies, and discuss the opportunities and challenges from data acquisition to the eventual application of insights in clinical and consumer settings. Further, we explore the strengths and limitations of current and emerging sensing methods with a particular focus on novel data-driven technologies, such as Artificial Intelligence.

Nightly sleep apnea severity in patients with atrial fibrillation: Potential applications of long-term sleep apnea monitoring

In patients with atrial fibrillation (AF), the prevalence of moderate-to-severe sleep-disordered breathing (SDB) ranges between 21% and 72% and observational studies have demonstrated that SDB reduces the efficacy of rhythm control strategies, while treatment with continuous positive airway pressure lowers the rate of AF recurrence. Currently, the number of apneas and hypopneas per hour (apnea-hypopnea-index, AHI) determined during a single overnight sleep study is clinically used to assess the severity of SDB. However, recent studies suggest that SDB-severity in an individual patient is not stable over time but exhibits a considerable night-to-night variability which cannot be detected by only one overnight sleep assessment. Nightly SDB-severity assessment rather than the single-night diagnosis by one overnight sleep study may better reflect the exposure to SDB-related factors and yield a superior metric to determine SDB-severity in the management of AF. In this review we discuss mechanisms of night-to-night SDB variability, arrhythmogenic consequences of night-to-night SDB variability, strategies for longitudinal assessment of nightly SDB-severity and clinical implications for screening and management of SDB in AF patients.

Smart technologies toward sleep monitoring at home

With progress in sensors and communication technologies, the range of sleep monitoring is extending from professional clinics into our usual home environments. Information from conventional overnight polysomnographic recordings can be derived from much simpler devices and methods. The gold standard of sleep monitoring is laboratory polysomnography, which classifies brain states based mainly on EEGs. Single-channel EEGs have been used for sleep stage scoring with accuracies of 84.9%. Actigraphy can estimate sleep efficiency with an accuracy of 86.0%. Sleep scoring based on respiratory dynamics provides accuracies of 89.2% and 70.9% for identifying sleep stages and sleep efficiency, respectively, and a correlation coefficient of 0.94 for apnea-hypopnea detection. Modulation of autonomic balance during the sleep stages are well recognized and widely used for simpler sleep scoring and sleep parameter estimation. This modulation can be recorded by several types of cardiovascular measurements, including ECG, PPG, BCG, and PAT, and the results showed accuracies up to 96.5% and 92.5% for sleep efficiency and OSA severity detection, respectively. Instead of using recordings for the entire night, less than 5 min ECG recordings have used for sleep efficiency and AHI estimation and resulted in high correlations of 0.94 and 0.99, respectively. These methods are based on their own models that relate sleep dynamics with a limited number of biological signals. Parameters representing sleep quality and disturbed breathing are estimated with high accuracies that are close to the results obtained by polysomnography. These unconstrained technologies, making sleep monitoring easier and simpler, will enhance qualities of life by expanding the range of ubiquitous healthcare.

Pragmatic Validation of Home Portable Sleep Monitor for diagnosing Obstructive Sleep Apnea in a non-referred population: The ELSA-Brasil study

Objective

Polygraphy (PG) is an attractive alternative for diagnosing obstructive sleep apnea (OSA) in patients with high pre-test probability. However, several patients may not present typical symptoms. In this scenario, it is unclear the performance of PG for diagnosing OSA in non-referred populations to sleep laboratories.

Methods

Data from participants of the ELSA-Brasil cohort were used for this analysis. We performed an overnight home PG (Embletta Gold^TM) synchronized with a wrist actigraphy (Actiwatch model 2^TM). The validation strategy comprised three scorings from each participant: 1) Original scoring (PG): Routine scoring using data from the exclamation button mark to define “analysis start” and “analysis stop”; 2) Scoring using actigraphy data (PG+actigraphy): total sleep time defined by the actigraphy data; 3) Scoring using diaries (PG+diary): “analysis start” and “analysis stop” based on the diaries. Bland-Altman plots were generated to assess the agreements (Kappa) between each scoring strategy.

Results

A total of 300 participants were included in the final analysis (45% males, mean age: 48±8 years). The frequency of OSA using the PG score was 27.3%. Despite small differences in the OSA severity index, we obtained a high concordance of AHI comparing the PG vs. PG+actigraphy (Kappa: 0.95) as well as PG+diary vs. PG+actigraphy (Kappa: 0.96). No significant changes in the OSA classification (mild, moderate and severe) were observed in the 3 protocols.

Conclusion

Using a pragmatic approach to address OSA at home, our results suggest that PG is a useful tool for OSA diagnosis even in subjects not referred to sleep studies.

Sleep Disorders Among People With Migraine: Results From the Chronic Migraine Epidemiology and Outcomes (CaMEO) Study

OBJECTIVES

We examined the cross-sectional association of sleep apnea and indices of sleep quality with both episodic migraine (EM) and chronic migraine (CM).

BACKGROUND

Sleep apnea and abnormal patterns of sleep, such as insomnia, were associated with migraine onset, severity, and progression in previous research.

METHODS

The Chronic Migraine Epidemiology & Outcomes Study, a longitudinal study, used a series of web-based surveys to assess migraine symptoms, burden, and patterns of health care utilization. Quota sampling was used from September 2012 to November 2013 to generate a representative sample of the US population. Persons who screened positive for sleep apnea on the Berlin Questionnaire are said to be at "high risk" for sleep apnea. Respondents indicated if they believed that they had sleep apnea, if a physician had diagnosed it, and if and how they were treated. Other aspects of sleep quality were assessed using the Medical Outcomes Study (MOS) Sleep Measures.

RESULTS

Of 12,810 eligible respondents with migraine and data on sleep, 11,699 with EM (91.3%) and 1111 with CM (8.7%) provided valid data for this analyses. According to the Berlin Questionnaire, 4739/12,810 (37.0%) were at "high risk" for sleep apnea, particularly persons with CM vs EM (575/1111 [51.8%] vs 4164/11,699 [35.6%]), men vs women (1431/3220 [44.4%] vs 3308/9590 [34.5%]), people with higher body mass index, and older people (all P < .001). Among respondents to the MOS Sleep Measures, persons with CM were more likely to report poor sleep quality than those with EM, including sleep disturbance (mean [SD] values: 53.2 [26.9] vs 37.9 [24.3]), snoring (38.0 [33.9] vs 31.0 [32.1]), shortness of breath (34.9 [29.8] vs 15.3 [20.6]), somnolence (44.1 [23.4] vs 32.2 [21.2]), and less likely to report sleep adequacy (34.0 [24.2] vs 39.2 [22.1]).

CONCLUSIONS

Compared with respondents with EM, a larger proportion of those with CM were at "high risk" for sleep apnea and reported poor sleep quality. This reflects an association between CM vs EM and sleep apnea and poor sleep quality; the potential relationships are discussed.