1
|
Wulterkens BM, Den Teuling NGP, Hermans LWA, Asin J, Duis N, Overeem S, Fonseca P, van Gilst MM. Multi-night home assessment of sleep structure in OSA with and without insomnia. Sleep Med 2024; 117:152-161. [PMID: 38547592 DOI: 10.1016/j.sleep.2024.03.031] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/26/2024] [Revised: 03/07/2024] [Accepted: 03/17/2024] [Indexed: 04/16/2024]
Abstract
OBJECTIVE To explore sleep structure in participants with obstructive sleep apnea (OSA) and comorbid insomnia (COMISA) and participants with OSA without insomnia (OSA-only) using both single-night polysomnography and multi-night wrist-worn photoplethysmography/accelerometry. METHODS Multi-night 4-class sleep-staging was performed with a validated algorithm based on actigraphy and heart rate variability, in 67 COMISA (23 women, median age: 51 years) and 50 OSA-only (15 women, median age: 51) participants. Sleep statistics were compared using linear regression models and mixed-effects models. Multi-night variability was explored using a clustering approach and between- and within-participant analysis. RESULTS Polysomnographic parameters showed no significant group differences. Multi-night measurements, during 13.4 ± 5.2 nights per subject, demonstrated a longer sleep onset latency and lower sleep efficiency for the COMISA group. Detailed analysis of wake parameters revealed longer mean durations of awakenings in COMISA, as well as higher numbers of awakenings lasting 5 min and longer (WKN≥5min) and longer wake after sleep onset containing only awakenings of 5 min or longer. Within-participant variance was significantly larger in COMISA for sleep onset latency, sleep efficiency, mean duration of awakenings and WKN≥5min. Unsupervised clustering uncovered three clusters; participants with consistently high values for at least one of the wake parameters, participants with consistently low values, and participants displaying higher variability. CONCLUSION Patients with COMISA more often showed extended, and more variable periods of wakefulness. These observations were not discernible using single night polysomnography, highlighting the relevance of multi-night measurements to assess characteristics indicative for insomnia.
Collapse
Affiliation(s)
- Bernice M Wulterkens
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands; Philips Sleep and Respiratory Care, Eindhoven, the Netherlands.
| | | | - Lieke W A Hermans
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands
| | - Jerryll Asin
- Center for Sleep Medicine, Amphia Hospital, Breda, the Netherlands
| | - Nanny Duis
- Center for Sleep Medicine, Amphia Hospital, Breda, the Netherlands
| | - Sebastiaan Overeem
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands; Sleep Medicine Center Kempenhaeghe, Heeze, the Netherlands
| | - Pedro Fonseca
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands; Philips Sleep and Respiratory Care, Eindhoven, the Netherlands
| | - Merel M van Gilst
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands; Sleep Medicine Center Kempenhaeghe, Heeze, the Netherlands
| |
Collapse
|
2
|
Wulterkens BM, Hermans LWA, Fonseca P, Asin J, Duis N, Janssen HCJP, Overeem S, van Gilst MM. Sleep structure in patients with COMISA compared to OSA and insomnia. J Clin Sleep Med 2023; 19:1051-1059. [PMID: 36740913 PMCID: PMC10235713 DOI: 10.5664/jcsm.10500] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2022] [Revised: 01/24/2023] [Accepted: 01/24/2023] [Indexed: 02/07/2023]
Abstract
STUDY OBJECTIVES Obstructive sleep apnea (OSA) and insomnia frequently co-occur, making diagnosis and treatment challenging. We investigated differences in sleep structure between patients with OSA, insomnia, and comorbid insomnia and sleep apnea (COMISA) to identify characteristics that can be used to improve the diagnosis of COMISA. METHODS We obtained polysomnography data of 326 patients from the Sleep and OSA Monitoring with Non-Invasive Applications database. The group included patients with OSA (n = 199), insomnia (n = 47), and COMISA (n = 80). We compared statistics related to sleep structure between the 3 patient groups. RESULTS Wake after sleep onset was significantly shorter for the OSA group (median: 60.0 minutes) compared to the COMISA (median: 83.3 minutes, P < .01) and the insomnia (median: 83.5 minutes, P = .01) groups. No significant differences were found in the total number of awakenings and the number of short (up to and including 2 minutes) and medium-length awakenings (2.5 up to and including 4.5 minutes). However, the number of long awakenings (5 minutes or longer) and wake after sleep onset containing only long awakenings was significantly lower for patients with OSA (median: 2 awakenings and 25.5 minutes) compared to patients with COMISA (median: 3 awakenings, P < .01 and 43.3 minutes, P < .001) or with insomnia (median: 3 awakenings, P < .01 and 56.0 minutes, P < .001). Total sleep time was significantly longer and sleep efficiency was significantly higher for the OSA group (median: 418.5 minutes and 84.4%) compared to both the COMISA (median: 391.5 minutes, P < .001 and 77.3%, P < .001) and the insomnia (median: 381.5 minutes, P < .001 and 78.2%, P < .001) groups. The number of sleep-stage transitions during the night for patients with COMISA (median: 194.0) was lower compared to that for patients with OSA (median: 218.0, P < .01) and higher compared to that for patients with insomnia (median: 156.0, P < .001). Other sleep architectural parameters were not discriminative between the groups. CONCLUSIONS Patients with COMISA show specific characteristics of insomnia, including prolonged awakenings. This variable is distinctive in comparison to patients with OSA. The combination of prolonged awakenings and the presence of sleep-disordered breathing leads to increased sleep disturbance compared to patients having only 1 of the sleep disorders. CITATION Wulterkens BM, Hermans LWA, Fonseca P, et al. Sleep structure in patients with COMISA compared to OSA and insomnia. J Clin Sleep Med. 2023;19(6):1051-1059.
Collapse
Affiliation(s)
- Bernice M. Wulterkens
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
- Philips Research, Eindhoven, The Netherlands
| | | | - Pedro Fonseca
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
- Philips Research, Eindhoven, The Netherlands
| | - Jerryll Asin
- Center for Sleep Medicine, Amphia Hospital, Breda, The Netherlands
| | - Nanny Duis
- Center for Sleep Medicine, Amphia Hospital, Breda, The Netherlands
| | | | - Sebastiaan Overeem
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
- Sleep Medicine Center Kempenhaeghe, Heeze, The Netherlands
| | - Merel M. van Gilst
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
- Sleep Medicine Center Kempenhaeghe, Heeze, The Netherlands
| |
Collapse
|
3
|
Huijben IAM, Hermans LWA, Rossi AC, Overeem S, van Gilst MM, van Sloun RJG. Interpretation and further development of the hypnodensity representation of sleep structure. Physiol Meas 2023; 44. [PMID: 36595329 DOI: 10.1088/1361-6579/aca641] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/07/2022] [Accepted: 11/25/2022] [Indexed: 11/27/2022]
Abstract
Objective.The recently-introduced hypnodensity graph provides a probability distribution over sleep stages per data window (i.e. an epoch). This work explored whether this representation reveals continuities that can only be attributed to intra- and inter-rater disagreement of expert scorings, or also to co-occurrence of sleep stage-dependent features within one epoch.Approach.We proposed a simplified model for time series like the ones measured during sleep, and a second model to describe the annotation process by an expert. Generating data according to these models, enabled controlled experiments to investigate the interpretation of the hypnodensity graph. Moreover, the influence of both the supervised training strategy, and the used softmax non-linearity were investigated. Polysomnography recordings of 96 healthy sleepers (of which 11 were used as independent test set), were subsequently used to transfer conclusions to real data.Main results.A hypnodensity graph, predicted by a supervised neural classifier, represents the probability with which the sleep expert(s) assigned a label to an epoch. It thus reflects annotator behavior, and is thereby only indirectly linked to the ratio of sleep stage-dependent features in the epoch. Unsupervised training was shown to result in hypnodensity graph that were slightly less dependent on this annotation process, resulting in, on average, higher-entropy distributions over sleep stages (Hunsupervised= 0.41 versusHsupervised= 0.29). Moreover, pre-softmax predictions were, for both training strategies, found to better reflect the ratio of sleep stage-dependent characteristics in an epoch, as compared to the post-softmax counterparts (i.e. the hypnodensity graph). In real data, this was observed from the linear relation between pre-softmax N3 predictions and the amount of delta power.Significance.This study provides insights in, and proposes new, representations of sleep that may enhance our comprehension about sleep and sleep disorders.
Collapse
Affiliation(s)
- Iris A M Huijben
- Dept. of Electrical Engineering, Eindhoven University of Technology, 5612 AP Eindhoven, The Netherlands.,Onera Health, 5617 BD Eindhoven, The Netherlands
| | - Lieke W A Hermans
- Dept. of Electrical Engineering, Eindhoven University of Technology, 5612 AP Eindhoven, The Netherlands
| | | | - Sebastiaan Overeem
- Dept. of Electrical Engineering, Eindhoven University of Technology, 5612 AP Eindhoven, The Netherlands.,Sleep Medicine Center Kempenhaeghe, 5591 VE Heeze, The Netherlands
| | - Merel M van Gilst
- Dept. of Electrical Engineering, Eindhoven University of Technology, 5612 AP Eindhoven, The Netherlands.,Sleep Medicine Center Kempenhaeghe, 5591 VE Heeze, The Netherlands
| | - Ruud J G van Sloun
- Dept. of Electrical Engineering, Eindhoven University of Technology, 5612 AP Eindhoven, The Netherlands
| |
Collapse
|
4
|
Huijben IAM, Nijdam AA, Hermans LWA, Overeem S, Van Gilst MM, Van Sloun RJG. Self-Organizing Maps for Contrastive Embeddings of Sleep Recordings. Annu Int Conf IEEE Eng Med Biol Soc 2022; 2022:2945-2948. [PMID: 36086087 DOI: 10.1109/embc48229.2022.9871236] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Nowadays, high amounts of data can be acquired in various applications, spurring the need for interpretable data representations that provide actionable insights. Algorithms that yield such representations ideally require as little a priori knowledge about the data or corresponding annotations as possible. To this end, we here investigate the use of Kohonen's Self-Organizing Map (SOM) in combination with data-driven low-dimensional embeddings obtained through self-supervised Contrastive Predictive Coding. We compare our approach to embeddings found with an auto-encoder and, moreover, investigate three ways to deal with node selection during SOM optimization. As a challenging experiment we analyze nocturnal sleep recordings of healthy subjects, and conclude that - for this noisy real-life data - contrastive learning yields a better low-dimensional embedding for the purpose of SOM training, compared to an auto-encoder. In addition, we show that a stochastic temperature-annealed SOM-training outperforms both a deterministic and a non-temperature-annealed stochastic approach. Clinical relevance - The hypnogram has for decades been the clinical standard in sleep medicine despite the fact that it is a highly simplified representation of a polysomnography recording. We propose a sensor-agnostic algorithm that is able to reveal more intricate patterns in sleep recordings which might teach us about sleep structure and sleep disorders.
Collapse
|
5
|
Hermans LWA, van Gilst MM, Regis M, van den Heuvel LCE, Langen H, van Mierlo P, Krijn R, Hoondert B, Maass H, van Dijk JP, Leufkens TRM, Overeem S. Modeling sleep onset misperception in insomnia. Sleep 2021; 43:5721963. [PMID: 32016410 DOI: 10.1093/sleep/zsaa014] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2019] [Revised: 12/06/2019] [Indexed: 11/14/2022] Open
Abstract
OBJECTIVES To extend and validate a previously suggested model of the influence of uninterrupted sleep bouts on sleep onset misperception in a large independent data set. METHODS Polysomnograms and sleep diaries of 139 insomnia patients and 92 controls were included. We modeled subjective sleep onset as the start of the first uninterrupted sleep fragment longer than Ls minutes, where parameter Ls reflects the minimum length of a sleep fragment required to be perceived as sleep. We compared the so-defined sleep onset latency (SOL) for various values of Ls. Model parameters were compared between groups, and across insomnia subgroups with respect to sleep onset misperception, medication use, age, and sex. Next, we extended the model to incorporate the length of wake fragments. Model performance was assessed by calculating root mean square errors (RMSEs) of the difference between estimated and perceived SOL. RESULTS Participants with insomnia needed a median of 34 minutes of undisturbed sleep to perceive sleep onset, while healthy controls needed 22 minutes (Mann-Whitney U = 4426, p < 0.001). Similar statistically significant differences were found between sleep onset misperceivers and non-misperceivers (median 40 vs. 20 minutes, Mann-Whitney U = 984.5, p < 0.001). Model outcomes were similar across other subgroups. Extended models including wake bout lengths resulted in only marginal improvements of model outcome. CONCLUSIONS Patients with insomnia, particularly sleep misperceivers, need larger continuous sleep bouts to perceive sleep onset. The modeling approach yields a parameter for which we coin the term Sleep Fragment Perception Index, providing a useful measure to further characterize sleep state misperception.
Collapse
Affiliation(s)
- Lieke W A Hermans
- Department of Electrical Engineering, Eindhoven University of Technology, De Zaale, Eindhoven, The Netherlands
| | - Merel M van Gilst
- Department of Electrical Engineering, Eindhoven University of Technology, De Zaale, Eindhoven, The Netherlands.,Center for Sleep Medicine, Kempenhaeghe Foundation, Heeze, Noord Brabant, The Netherlands
| | - Marta Regis
- Department of Mathematics and Computer Science, Eindhoven University of Technology, De Zaale, Eindhoven, The Netherlands
| | | | - Hanneke Langen
- Center for Sleep Medicine, Kempenhaeghe Foundation, Heeze, Noord Brabant, The Netherlands
| | - Petra van Mierlo
- Center for Sleep Medicine, Kempenhaeghe Foundation, Heeze, Noord Brabant, The Netherlands
| | - Roy Krijn
- Center for Sleep Medicine, Kempenhaeghe Foundation, Heeze, Noord Brabant, The Netherlands
| | - Bertram Hoondert
- Center for Sleep Medicine, Kempenhaeghe Foundation, Heeze, Noord Brabant, The Netherlands
| | | | - Johannes P van Dijk
- Department of Electrical Engineering, Eindhoven University of Technology, De Zaale, Eindhoven, The Netherlands.,Center for Sleep Medicine, Kempenhaeghe Foundation, Heeze, Noord Brabant, The Netherlands.,Department of Orthodontics, University of Ulm, Ulm, Germany
| | - Tim R M Leufkens
- Philips Research, Eindhoven, The Netherlands.,Department of Industrial Design, Eindhoven University of Technology, De Zaale, Eindhoven, The Netherlands
| | - Sebastiaan Overeem
- Department of Electrical Engineering, Eindhoven University of Technology, De Zaale, Eindhoven, The Netherlands.,Center for Sleep Medicine, Kempenhaeghe Foundation, Heeze, Noord Brabant, The Netherlands.,Department of Industrial Design, Eindhoven University of Technology, De Zaale, Eindhoven, The Netherlands
| |
Collapse
|
6
|
Hermans LWA, Regis M, Fonseca P, Overeem S, Leufkens TRM, Vermeeren A, van Gilst MM. Assessing sleep-wake survival dynamics in relation to sleep quality in a placebo-controlled pharmacological intervention study with people with insomnia and healthy controls. Psychopharmacology (Berl) 2021; 238:83-94. [PMID: 32939597 PMCID: PMC7794103 DOI: 10.1007/s00213-020-05660-3] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/19/2020] [Accepted: 09/07/2020] [Indexed: 12/21/2022]
Abstract
RATIONALE The mechanisms underlying impaired sleep quality in insomnia are not fully known, but an important role for sleep fragmentation has been proposed. OBJECTIVES The aim of this study is to explore potential mechanisms of sleep fragmentation influencing alterations of perceived sleep quality. METHODS We analyzed polysomnography (PSG) recordings from a double-blind crossover study with zopiclone 7.5 mg and placebo, in elderly participants with insomnia complaints and age-matched healthy controls. We compared survival dynamics of sleep and wake across group and treatment. Subsequently, we used a previously proposed model to estimate the amount of sleep onset latency (SOL) misperception from PSG-defined sleep fragmentation. Self-reported and model-estimated amount of SOL misperception were compared across group and treatment, as well as model prediction errors. RESULTS In the zopiclone night, the average segment length of NREM sleep was increased (group F = 1.16, p = 0.32; treatment F = 8.89, p < 0.01; group x treatment F = 0.44, p = 0.65), while the segment length of wake was decreased (group F = 1.48, p = 0.23; treatment F = 11.49, p < 0.01; group x treatment F = 0.36, p = 0.70). The self-reported and model-estimated amount of SOL misperception were lower during the zopiclone night (self-reported group F = 6.08, p < 0.01, treatment F = 10.8, p < 0.01, group x treatment F = 2.49, p = 0.09; model-estimated F = 1.70, p = 0.19, treatment F = 16.1, p < 0.001, group x treatment F = 0.60, p = 0.55). The prediction error was not altered (group F = 1.62, p = 0.20; treatment F = 0.20, p = 0.65; group x treatment F = 1.01, p = 0.37). CONCLUSIONS Impaired subjective sleep quality is associated with decreased NREM stability, together with increased stability of wake. Furthermore, we conclude that zopiclone-induced changes in SOL misperception can be largely attributed to predictable changes of sleep architecture.
Collapse
Affiliation(s)
- Lieke W. A. Hermans
- Department of Electrical Engineering, Eindhoven University of Technology, De Zaale, Eindhoven, The Netherlands
| | - Marta Regis
- Department of Mathematics and Computer Science, Eindhoven University of Technology, De Zaale, Eindhoven, The Netherlands
| | - Pedro Fonseca
- Department of Electrical Engineering, Eindhoven University of Technology, De Zaale, Eindhoven, The Netherlands ,Philips Research, High Tech Campus 34, Eindhoven, The Netherlands
| | - Sebastiaan Overeem
- Department of Electrical Engineering, Eindhoven University of Technology, De Zaale, Eindhoven, The Netherlands ,Sleep Medicine Center Kempenhaeghe, Sterkselseweg 65, Heeze, The Netherlands
| | | | - Annemiek Vermeeren
- Department of Neuropsychology and Psychopharmacology, Faculty of Psychology and Neuroscience, Maastricht University, Universiteitssingel 40, Maastricht, The Netherlands
| | - Merel M. van Gilst
- Department of Electrical Engineering, Eindhoven University of Technology, De Zaale, Eindhoven, The Netherlands ,Sleep Medicine Center Kempenhaeghe, Sterkselseweg 65, Heeze, The Netherlands
| |
Collapse
|
7
|
Hermans LWA, Regis M, Fonseca P, Hoondert B, Leufkens TRM, Overeem S, van Gilst MM. Sleep-Wake Survival Dynamics in People with Insomnia. Nat Sci Sleep 2021; 13:349-360. [PMID: 33737849 PMCID: PMC7966352 DOI: 10.2147/nss.s295699] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/04/2020] [Accepted: 02/04/2021] [Indexed: 01/28/2023] Open
Abstract
INTRODUCTION Assessing objective measures of sleep fragmentation could yield important features reflecting impaired sleep quality in people with insomnia. Survival analysis allows the specific examination of the stability of NREM sleep, REM sleep and wake. The objective of this study was to assess the differences between survival dynamics of NREM sleep, REM sleep and wake between people with insomnia and healthy controls. METHODS We analyzed retrospective polysomnography recordings from 86 people with insomnia and 94 healthy controls. For each participant, survival dynamics of REM sleep, NREM sleep and wake were represented using Weibull distributions. We used lasso penalized parameter selection in combination with linear regression to analyze the difference between participant groups with respect to the Weibull scale and shape parameters, while correcting for age, sex, total sleep time and relevant interaction effects. RESULTS Significant effects of group were found for the NREM scale parameter, and for the wake scale and shape parameters. Results indicated that people with insomnia had less stable NREM sleep and more stable wake after sleep onset compared to healthy controls. Additionally, the altered distribution of wake segment lengths indicated an increased difficulty to fall asleep after longer awakenings in the insomnia group. However, these differences were mainly observed in younger participants. Significant effects of group for the survival parameters of REM sleep were not found. CONCLUSION As illustrated by our results, survival analysis can be very useful for disentangling different types of sleep fragmentation in people with insomnia. For instance, the current findings suggest that people with insomnia have an increased fragmentation of NREM sleep, but not necessarily of REM sleep. Additional research into the underlying mechanisms of NREM sleep fragmentation could possibly lead to a better understanding of impaired sleep quality in people with insomnia, and consequently to improved treatment.
Collapse
Affiliation(s)
- Lieke W A Hermans
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands
| | - Marta Regis
- Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, the Netherlands
| | - Pedro Fonseca
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.,Philips Research, Eindhoven, the Netherlands
| | | | | | - Sebastiaan Overeem
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.,Sleep Medicine Center Kempenhaeghe, Heeze, the Netherlands
| | - Merel M van Gilst
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.,Sleep Medicine Center Kempenhaeghe, Heeze, the Netherlands
| |
Collapse
|
8
|
Wulterkens BM, Fonseca P, Hermans LWA, Ross M, Cerny A, Anderer P, Long X, van Dijk JP, Vandenbussche N, Pillen S, van Gilst MM, Overeem S. It is All in the Wrist: Wearable Sleep Staging in a Clinical Population versus Reference Polysomnography. Nat Sci Sleep 2021; 13:885-897. [PMID: 34234595 PMCID: PMC8253894 DOI: 10.2147/nss.s306808] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/18/2021] [Accepted: 05/04/2021] [Indexed: 12/31/2022] Open
Abstract
PURPOSE There is great interest in unobtrusive long-term sleep measurements using wearable devices based on reflective photoplethysmography (PPG). Unfortunately, consumer devices are not validated in patient populations and therefore not suitable for clinical use. Several sleep staging algorithms have been developed and validated based on ECG-signals. However, translation from these techniques to data derived by wearable PPG is not trivial, and requires the differences between sensing modalities to be integrated in the algorithm, or having the model trained directly with data obtained with the target sensor. Either way, validation of PPG-based sleep staging algorithms requires a large dataset containing both gold standard measurements and PPG-sensor in the applicable clinical population. Here, we take these important steps towards unobtrusive, long-term sleep monitoring. METHODS We developed and trained an algorithm based on wrist-worn PPG and accelerometry. The method was validated against reference polysomnography in an independent clinical population comprising 244 adults and 48 children (age: 3 to 82 years) with a wide variety of sleep disorders. RESULTS The classifier achieved substantial agreement on four-class sleep staging with an average Cohen's kappa of 0.62 and accuracy of 76.4%. For children/adolescents, it achieved even higher agreement with an average kappa of 0.66 and accuracy of 77.9%. Performance was significantly higher in non-REM parasomnias (kappa = 0.69, accuracy = 80.1%) and significantly lower in REM parasomnias (kappa = 0.55, accuracy = 72.3%). A weak correlation was found between age and kappa (ρ = -0.30, p<0.001) and age and accuracy (ρ = -0.22, p<0.001). CONCLUSION This study shows the feasibility of automatic wearable sleep staging in patients with a broad variety of sleep disorders and a wide age range. Results demonstrate the potential for ambulatory long-term monitoring of clinical populations, which may improve diagnosis, estimation of severity and follow up in both sleep medicine and research.
Collapse
Affiliation(s)
- Bernice M Wulterkens
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.,Philips Research, Eindhoven, the Netherlands
| | - Pedro Fonseca
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.,Philips Research, Eindhoven, the Netherlands
| | - Lieke W A Hermans
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands
| | - Marco Ross
- Sleep and Respiratory Care, Home Healthcare Solutions, Philips Austria GmbH, Vienna, Austria
| | - Andreas Cerny
- Sleep and Respiratory Care, Home Healthcare Solutions, Philips Austria GmbH, Vienna, Austria
| | - Peter Anderer
- Sleep and Respiratory Care, Home Healthcare Solutions, Philips Austria GmbH, Vienna, Austria
| | - Xi Long
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.,Philips Research, Eindhoven, the Netherlands
| | - Johannes P van Dijk
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.,Sleep Medicine Center Kempenhaeghe, Heeze, the Netherlands
| | | | - Sigrid Pillen
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.,Sleep Medicine Center Kempenhaeghe, Heeze, the Netherlands
| | - Merel M van Gilst
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.,Sleep Medicine Center Kempenhaeghe, Heeze, the Netherlands
| | - Sebastiaan Overeem
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.,Sleep Medicine Center Kempenhaeghe, Heeze, the Netherlands
| |
Collapse
|