Personalized Sleep Parameters Estimation from Actigraphy: A Machine Learning Approach

Performance of wearable sleep trackers during nocturnal sleep and periods of simulated real-world smartphone use

GOAL AND AIMS

To test sleep/wake transition detection of consumer sleep trackers and research-grade actigraphy during nocturnal sleep and simulated peri-sleep behavior involving minimal movement.

FOCUS TECHNOLOGY

Oura Ring Gen 3, Fitbit Sense, AXTRO Fit 3, Xiaomi Mi Band 7, and ActiGraph GT9X.

REFERENCE TECHNOLOGY

Polysomnography.

SAMPLE

Sixty-three participants (36 female) aged 20-68.

DESIGN

Participants engaged in common peri-sleep behavior (reading news articles, watching videos, and exchanging texts) on a smartphone before and after the sleep period. They were woken up during the night to complete a short questionnaire to simulate responding to an incoming message.

CORE ANALYTICS

Detection and timing accuracy for the sleep onset times and wake times.

ADDITIONAL ANALYTICS AND EXPLORATORY ANALYSES

Discrepancy analysis both including and excluding the peri-sleep activity periods. Epoch-by-epoch analysis of rate and extent of wake misclassification during peri-sleep activity periods.

CORE OUTCOMES

Oura and Fitbit were more accurate at detecting sleep/wake transitions than the actigraph and the lower-priced consumer sleep tracker devices. Detection accuracy was less reliable in participants with lower sleep efficiency.

IMPORTANT ADDITIONAL OUTCOMES

With inclusion of peri-sleep periods, specificity and Kappa improved significantly for Oura and Fitbit, but not ActiGraph. All devices misclassified motionless wake as sleep to some extent, but this was less prevalent for Oura and Fitbit.

CORE CONCLUSIONS

Performance of Oura and Fitbit is robust on nights with suboptimal bedtime routines or minor sleep disturbances. Reduced performance on nights with low sleep efficiency bolsters concerns that these devices are less accurate for fragmented or disturbed sleep.

A narrative review on insomnia and hypersomnolence within Major Depressive Disorder and bipolar disorder: A proposal for a novel psychometric protocol

Sleep disorders have become increasingly prevalent, with many adults worldwide reporting sleep dissatisfaction. Major Depressive Disorder (MDD) and Bipolar Disorder (BD) are common conditions associated with disrupted sleep patterns such as insomnia and hypersomnolence. These sleep disorders significantly affect the progression, severity, treatment, and outcome of unipolar and bipolar depression. While there is evidence of a connection between sleep disorders and depression, it remains unclear if sleep features differ between MDD and BD. In light of this, this narrative review aims to: (1) summarize findings on common sleep disorders like insomnia and hypersomnolence, strongly linked to MDD and BD; (2) propose a novel psychometric approach to assess sleep in individuals with depressive disorders. Despite insomnia seems to be more influent in unipolar depression, while hypersomnolence in bipolar one, there is no common agreement. So, it is essential adopting a comprehensive psychometric protocol for try to fill this gap. Understanding the relationship between sleep and MDD and BD disorders are crucial for effective management and better quality of life for those affected.

Overview of methods and available tools used in complex brain disorders

Complex brain disorders, including Alzheimer's dementia, sleep disorders, and epilepsy, are chronic conditions that have high prevalence individually and in combination, increasing mortality risk, and contributing to the socioeconomic burden of patients, their families and, their communities at large. Although some literature reviews have been conducted mentioning the available methods and tools used for supporting the diagnosis of complex brain disorders and processing different files, there are still limitations. Specifically, these research works have focused primarily on one single brain disorder, i.e., sleep disorders or dementia or epilepsy. Additionally, existing research initiatives mentioning some tools, focus mainly on one single type of data, i.e., electroencephalography (EEG) signals or actigraphies or Magnetic Resonance Imaging, and so on. To tackle the aforementioned limitations, this is the first study conducting a comprehensive literature review of the available methods used for supporting the diagnosis of multiple complex brain disorders, i.e., Alzheimer's dementia, sleep disorders, epilepsy. Also, to the best of our knowledge, we present the first study conducting a comprehensive literature review of all the available tools, which can be exploited for processing multiple types of data, including EEG, actigraphies, and MRIs, and receiving valuable forms of information which can be used for differentiating people in a healthy control group and patients suffering from complex brain disorders. Additionally, the present study highlights both the benefits and limitations of the existing available tools.

Delirium detection using wearable sensors and machine learning in patients with intracerebral hemorrhage

Objective

Delirium is associated with worse outcomes in patients with stroke and neurocritical illness, but delirium detection in these patients can be challenging with existing screening tools. To address this gap, we aimed to develop and evaluate machine learning models that detect episodes of post-stroke delirium based on data from wearable activity monitors in conjunction with stroke-related clinical features.

Design

Prospective observational cohort study.

Setting

Neurocritical Care and Stroke Units at an academic medical center.

Patients

We recruited 39 patients with moderate-to-severe acute intracerebral hemorrhage (ICH) and hemiparesis over a 1-year period [mean (SD) age 71.3 (12.20), 54% male, median (IQR) initial NIH Stroke Scale 14.5 (6), median (IQR) ICH score 2 (1)].

Measurements and main results

Each patient received daily assessments for delirium by an attending neurologist, while activity data were recorded throughout each patient's hospitalization using wrist-worn actigraph devices (on both paretic and non-paretic arms). We compared the predictive accuracy of Random Forest, SVM and XGBoost machine learning methods in classifying daily delirium status using clinical information alone and combined with actigraph data. Among our study cohort, 85% of patients (n = 33) had at least one delirium episode, while 71% of monitoring days (n = 209) were rated as days with delirium. Clinical information alone had a low accuracy in detecting delirium on a day-to-day basis [accuracy mean (SD) 62% (18%), F1 score mean (SD) 50% (17%)]. Prediction performance improved significantly (p < 0.001) with the addition of actigraph data [accuracy mean (SD) 74% (10%), F1 score 65% (10%)]. Among actigraphy features, night-time actigraph data were especially relevant for classification accuracy.

Conclusions

We found that actigraphy in conjunction with machine learning models improves clinical detection of delirium in patients with stroke, thus paving the way to make actigraph-assisted predictions clinically actionable.

Circadian dysregulation and Alzheimer’s disease: A comprehensive review

Alzheimer’s disease (AD), the foremost variant of dementia, has been associated with a menagerie of risk factors, many of which are considered to be modifiable. Among these modifiable risk factors is circadian rhythm, the chronobiological system that regulates sleep‐wake cycles, food consumption timing, hydration timing, and immune responses amongst many other necessary physiological processes. Circadian rhythm at the level of the suprachiasmatic nucleus (SCN), is tightly regulated in the human body by a host of biomolecular substances, principally the hormones melatonin, cortisol, and serotonin. In addition, photic information projected along afferent pathways to the SCN and peripheral oscillators regulates the synthesis of these hormones and mediates the manner in which they act on the SCN and its substructures. Dysregulation of this cycle, whether induced by environmental changes involving irregular exposure to light, or through endogenous pathology, will have a negative impact on immune system optimization and will heighten the deposition of Aβ and the hyperphosphorylation of the tau protein. Given these correlations, it appears that there is a physiologic association between circadian rhythm dysregulation and AD. This review will explore the physiology of circadian dysregulation in the AD brain, and will propose a basic model for its role in AD‐typical pathology, derived from the literature compiled and referenced throughout.

Modeling Sleep Quality Depending on Objective Actigraphic Indicators Based on Machine Learning Methods

According to data from the World Health Organization and medical research centers, the frequency and severity of various sleep disorders, including insomnia, are increasing steadily. This dynamic is associated with increased daily stress, anxiety, and depressive disorders. Poor sleep quality affects people's productivity and activity and their perception of quality of life in general. Therefore, predicting and classifying sleep quality is vital to improving the quality and duration of human life. This study offers a model for assessing sleep quality based on the indications of an actigraph, which was used by 22 participants in the experiment for 24 h. Objective indicators of the actigraph include the amount of time spent in bed, sleep duration, number of awakenings, and duration of awakenings. The resulting classification model was evaluated using several machine learning methods and showed a satisfactory accuracy of approximately 80-86%. The results of this study can be used to treat sleep disorders, develop and design new systems to assess and track sleep quality, and improve existing electronic devices and sensors.

Rigorous performance evaluation (previously, "validation") for informed use of new technologies for sleep health measurement

New sleep technologies have become pervasive in the consumer space, and are becoming highly common in research and clinical sleep settings. The rapid, widespread use of largely unregulated and unstandardized technology has enabled the quantification of many different facets of sleep health, driving scientific discovery. As sleep scientists, it is our responsibility to inform principles and practices for proper evaluation of any new technology used in the clinical and research settings, and by consumers. A current lack of standardized methods for evaluating technology performance challenges the rigor of our scientific methods for accurate representation of the sleep health facets of interest. This special article describes the rationale and priorities of an interdisciplinary effort for rigorous, standardized, and rapid performance evaluation (previously, "validation") of new sleep and sleep disorders related technologies of all kinds (eg, devices or algorithms), including an associated article template for a new initiative for publication in Sleep Health of empirical studies systematically evaluating the performance of new sleep technologies. A structured article type should streamline manuscript development and enable more rapid writing, review, and publication. The goal is to promote rapid and rigorous evaluation and dissemination of new sleep technology, to enhance sleep research integrity, and to standardize terminology used in Rigorous Performance Evaluation papers to prevent misinterpretation while facilitating comparisons across technologies.

Open-source Longitudinal Sleep Analysis From Accelerometer Data (DPSleep): Algorithm Development and Validation

BACKGROUND

Wearable devices are now widely available to collect continuous objective behavioral data from individuals and to measure sleep.

OBJECTIVE

This study aims to introduce a pipeline to infer sleep onset, duration, and quality from raw accelerometer data and then quantify the relationships between derived sleep metrics and other variables of interest.

METHODS

The pipeline released here for the deep phenotyping of sleep, as the DPSleep software package, uses a stepwise algorithm to detect missing data; within-individual, minute-based, spectral power percentiles of activity; and iterative, forward-and-backward-sliding windows to estimate the major Sleep Episode onset and offset. Software modules allow for manual quality control adjustment of the derived sleep features and correction for time zone changes. In this paper, we have illustrated the pipeline with data from participants studied for more than 200 days each.

RESULTS

Actigraphy-based measures of sleep duration were associated with self-reported sleep quality ratings. Simultaneous measures of smartphone use and GPS location data support the validity of the sleep timing inferences and reveal how phone measures of sleep timing can differ from actigraphy data.

CONCLUSIONS

We discuss the use of DPSleep in relation to other available sleep estimation approaches and provide example use cases that include multi-dimensional, deep longitudinal phenotyping, extended measurement of dynamics associated with mental illness, and the possibility of combining wearable actigraphy and personal electronic device data (eg, smartphones and tablets) to measure individual differences across a wide range of behavioral variations in health and disease. A new open-source pipeline for deep phenotyping of sleep, DPSleep, analyzes raw accelerometer data from wearable devices and estimates sleep onset and offset while allowing for manual quality control adjustments.

On the Unification of Common Actigraphic Data Scoring Algorithms

Actigraphy is a well-known, inexpensive method to investigate human movement patterns. Sleep and circadian rhythm studies are among the most popular applications of actigraphy. In this study, we investigate seven common sleep-wake scoring algorithms designed for actigraphic data, namely Cole-Kripke algorithm, two versions of Sadeh algorithm, Sazonov algorithm, Webster algorithm, UCSD algorithm and Scripps Clinic algorithm. We propose a unified mathematical framework describing five of them. One of the observed novelties is that five of these algorithms are in fact equivalent to low-pass FIR filters with very similar characteristics. We also provide explanations about the role of some factors defining these algorithms, as none were given by their Authors who followed empirical procedures. Proposed framework provides a robust mathematical description of discussed algorithms, which for the first time allows one to fully understand their operation and basics.

Deep learning applied to polysomnography to predict blood pressure in obstructive sleep apnea and obesity hypoventilation: a proof-of-concept study

STUDY OBJECTIVES

Nocturnal blood pressure (BP) profile shows characteristic abnormalities in OSA, namely acute postapnea BP surges and nondipping BP. These abnormal BP profiles provide prognostic clues indicating increased cardiovascular disease risk. We developed a deep neural network model to perform computerized analysis of polysomnography data and predict nocturnal BP profile.

METHODS

We analyzed concurrently performed polysomnography and noninvasive beat-to-beat BP measurement with a deep neural network model to predict nocturnal BP profiles from polysomnography data in 13 patients with severe OSA.

RESULTS

A good correlation was noted between measured and predicted postapnea systolic and diastolic BP (Pearson r ≥ .75). Moreover, Bland-Altman analyses showed good agreement between the 2 values. Continuous systolic and diastolic BP prediction by the deep neural network model was also well correlated with measured BP values (Pearson r ≥ .83).

CONCLUSIONS

We developed a deep neural network model to predict nocturnal BP profile from clinical polysomnography signals and provide a potential prognostic tool in OSA. Validation of the model in larger samples and examination of its utility in predicting CVD risk in future studies is warranted.

Artificial intelligence and sleep: Advancing sleep medicine

Artificial intelligence (AI) allows analysis of "big data" combining clinical, environmental and laboratory based objective measures to allow a deeper understanding of sleep and sleep disorders. This development has the potential to transform sleep medicine in coming years to the betterment of patient care and our collective understanding of human sleep. This review addresses the current state of the field starting with a broad definition of the various components and analytic methods deployed in AI. We review examples of AI use in screening, endotyping, diagnosing, and treating sleep disorders and place this in the context of precision/personalized sleep medicine. We explore the opportunities for AI to both facilitate and extend providers' clinical impact and present ethical considerations regarding AI derived prognostic information. We cover early adopting specialties of AI in the clinical realm, such as radiology and pathology, to provide a road map for the challenges sleep medicine is likely to face when deploying this technology. Finally, we discuss pitfalls to ensure clinical AI implementation proceeds in the safest and most effective manner possible.

Data-Driven Modeling of Pregnancy-Related Complications

A healthy pregnancy depends on complex interrelated biological adaptations involving placentation, maternal immune responses, and hormonal homeostasis. Recent advances in high-throughput technologies have provided access to multiomics biological data that, combined with clinical and social data, can provide a deeper understanding of normal and abnormal pregnancies. Integration of these heterogeneous datasets using state-of-the-art machine-learning methods can enable the prediction of short- and long-term health trajectories for a mother and offspring and the development of treatments to prevent or minimize complications. We review advanced machine-learning methods that could: provide deeper biological insights into a pregnancy not yet unveiled by current methodologies; clarify the etiologies and heterogeneity of pathologies that affect a pregnancy; and suggest the best approaches to address disparities in outcomes affecting vulnerable populations.

Efficient embedded sleep wake classification for open-source actigraphy

This study presents a thorough analysis of sleep/wake detection algorithms for efficient on-device sleep tracking using wearable accelerometric devices. It develops a novel end-to-end algorithm using convolutional neural network applied to raw accelerometric signals recorded by an open-source wrist-worn actigraph. The aim of the study is to develop an automatic classifier that: (1) is highly generalizable to heterogenous subjects, (2) would not require manual features' extraction, (3) is computationally lightweight, embeddable on a sleep tracking device, and (4) is suitable for a wide assortment of actigraphs. Hereby, authors analyze sleep parameters, such as total sleep time, waking after sleep onset and sleep efficiency, by comparing the outcomes of the proposed algorithm to the gold standard polysomnographic concurrent recordings. The relatively substantial agreement (Cohen's kappa coefficient, median, equal to 0.78 ± 0.07) and the low-computational cost (2727 floating-point operations) make this solution suitable for an on-board sleep-detection approach.

The relationship between machine-learning-derived sleep parameters and behavior problems in 3- and 5-year-old children: results from the CHILD Cohort study

STUDY OBJECTIVES

Machine learning (ML) may provide insights into the underlying sleep stages of accelerometer-assessed sleep duration. We examined associations between ML-sleep patterns and behavior problems among preschool children.

METHODS

Children from the CHILD Cohort Edmonton site with actigraphy and behavior data at 3-years (n = 330) and 5-years (n = 304) were included. Parent-reported behavior problems were assessed by the Child Behavior Checklist. The Hidden Markov Model (HMM) classification method was used for ML analysis of the accelerometer sleep period. The average time each participant spent in each HMM-derived sleep state was expressed in hours per day. We analyzed associations between sleep and behavior problems stratified by children with and without sleep-disordered breathing (SDB).

RESULTS

Four hidden sleep states were identified at 3 years and six hidden sleep states at 5 years using HMM. The first sleep state identified for both ages (HMM-0) had zero counts (no movement). The remaining hidden states were merged together (HMM-mov). Children spent an average of 8.2 ± 1.2 h/day in HMM-0 and 2.6 ± 0.8 h/day in HMM-mov at 3 years. At age 5, children spent an average of 8.2 ± 0.9 h/day in HMM-0 and 1.9 ± 0.7 h/day in HMM-mov. Among SDB children, each hour in HMM-0 was associated with 0.79-point reduced externalizing behavior problems (95% CI -1.4, -0.12; p < 0.05), and a 1.27-point lower internalizing behavior problems (95% CI -2.02, -0.53; p < 0.01).

CONCLUSIONS

ML-sleep states were not associated with behavior problems in the general population of children. Children with SDB who had greater sleep duration without movement had lower behavioral problems. The ML-sleep states require validation with polysomnography.

Wearable Device Heart Rate and Activity Data in an Unsupervised Approach to Personalized Sleep Monitoring: Algorithm Validation

Background

The proliferation of wearable devices that collect activity and heart rate data has facilitated new ways to measure sleeping and waking durations unobtrusively and longitudinally. Most existing sleep/wake identification algorithms are based on activity only and are trained on expensive and laboriously annotated polysomnography (PSG). Heart rate can also be reflective of sleep/wake transitions, which has motivated its investigation herein in an unsupervised algorithm. Moreover, it is necessary to develop a personalized approach to deal with interindividual variance in sleep/wake patterns.

Objective

We aimed to develop an unsupervised personalized sleep/wake identification algorithm using multifaceted data to explore the benefits of incorporating both heart rate and activity level in these types of algorithms and to compare this approach’s output with that of an existing commercial wearable device’s algorithms.

Methods

In this study, a total of 14 community-dwelling older adults wore wearable devices (Fitbit Alta; Fitbit Inc) 24 hours a day and 7 days a week over period of 3 months during which their heart rate and activity data were collected. After preprocessing the data, a model was developed to distinguish sleep/wake states based on each individual’s data. We proposed the use of hidden Markov models and compared different modeling schemes. With the best model selected, sleep/wake patterns were characterized by estimated parameters in hidden Markov models, and sleep/wake states were identified.

Results

When applying our proposed algorithm on a daily basis, we found there were significant differences in estimated parameters between weekday models and weekend models for some participants.

Conclusions

Our unsupervised approach can be effectively implemented based on an individual’s multifaceted sleep-related data from a commercial wearable device. A personalized model is shown to be necessary given the interindividual variability in estimated parameters.