Objective: Driver drowsiness detection is a key technology that can prevent fatal car accidents caused by drowsy driving. The present work proposes a driver drowsiness detection algorithm based on heart rate variability (HRV) analysis and validates the proposed method by comparing with electroencephalography (EEG)-based sleep scoring. Methods: Changes in sleep condition affect the autonomic nervous system (ANS) and then HRV, which is defined as an RR interval (RRI) fluctuation on an electrocardiogram (ECG) trace. Eight HRV features are monitored for detecting changes in HRV by using multivariate statistical process control (MSPC) which is a well-known anomaly detection method. Result: The performance of the proposed algorithm was evaluated through an experiment using a driving simulator. In this experiment, RRI data were measured from 34 participants during driving, and their sleep onsets were determined based on the EEG data by a sleep specialist. The validation result of the experimental data with the EEG data showed that drowsiness was detected in 12 out of 13 drowsy episodes prior to the sleep onsets, and the false positive rate was 1.7 times per hour. Conclusion: The present work also demonstrates the usefulness of the framework of HRV-based anomaly detection that was originally proposed for epileptic seizure prediction. Significance: The proposed method can contribute to prevent accidents caused by drowsy driving.
The Athens Insomnia Scale (AIS) can be regarded as a highly useful instrument in both clinical and research settings, except for when assessing the severity level. This study aims to determine the severity criteria for AIS by using the Insomnia Severity Index (ISI). A total of 1666 government employees aged 20 years or older were evaluated using the AIS and ISI, the Patient Health Questionnaire for depressive symptoms, the Epworth Sleepiness Scale for daytime sleepiness, and the Short Form Health Survey of the Medical Outcomes Study for health-related quality of life (QoL). A significant positive correlation (r) was found between the AIS and the ISI (r = 0.80, p < 0.001). As a result of describing receiver–operator curves, the severity criteria of the AIS are capable of categorizing insomnia severity as follows: absence of insomnia (0–5), mild insomnia (6–9), moderate insomnia (10–15), and severe insomnia (16–24). In addition, compared to all scales across groups categorized by AIS or ISI, it was revealed that similar results could be obtained (all p < 0.05). Therefore, the identification of the severity of AIS in this study is important in linking the findings of epidemiological studies with those of clinical studies.
Background: Humans spend more than a fourth of their life sleeping, and sleep quality has been significantly linked to health. However, the objective examination of ambulatory sleep quality remains a challenge, since sleep is a state of unconsciousness, which limits the reliability of self-reports. Therefore, a non-invasive, continuous, and objective method for the recording and analysis of naturalistic sleep is required. Objective: Portable sleep recording devices provide a suitable solution for the ambulatory analysis of sleep quality. In this study, the performance of two activity-based sleep monitors (Actiwatch and MTN-210) and a single-channel EEG-based sleep monitor (SleepScope) were compared in order to examine their reliability for the assessment of sleep quality. Methods: Twenty healthy adults were recruited for this study. First, data from daily activity recorded by Actiwatch and MTN-210 were compared to determine whether MTN-210, a more affordable device, could yield data similar to Actiwatch, the de-facto standard. In addition, sleep detection ability was examined using data obtained by polysomnography as reference. One simple analysis included comparing the sleep/wake detection ability of Actiwatch, MTN-210, and SleepScope. Furthermore, the fidelity of sleep stage determination was examined using SleepScope in finer time resolution. Results: The results indicate that MTN-210 demonstrates an activity pattern comparable to that of Actiwatch, although their sensitivity preferences were not identical. Moreover, MTN-210 provides assessment of sleep duration comparable to that of the wrist-worn Actiwatch when MTN-210 was attached to the body. SleepScope featured superior overall sleep detection performance among the three methods tested. Furthermore, SleepScope was able to provide information regarding sleep architecture, although systemic bias was found. Conclusion: The present results suggest that single-channel EEG-based sleep monitors are the superior option for the examination of naturalistic sleep. The current results pave a possible future use for reliable portable sleep assessment methods in an ambulatory rather than a laboratory setting.
7 January 2020 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Sleep spindles are important electroencephalographic (EEG) waveforms in sleep medicine; however, it is burdensome even for experts to detect spindles, so automatic spindle detection methodologies have been investigated. Conventional methods utilize waveforms template matching or machine learning for detecting spindles. In the former approach, it is necessary to tune thresholds for individual adaptation, while the latter approach has the problem of imbalanced data because the amount of sleep spindles is small compared with the entire EEG data. The present work proposes a sleep spindle detection method that combines wavelet synchrosqueezed transform (SST) and random under-sampling boosting (RUSBoost). SST is a time-frequency analysis method suitable for extracting features of spindle waveforms. RUSBoost is a framework for coping with the imbalanced data problem. The proposed SST-RUS can deal with the imbalanced data in spindle detection and does not require threshold tuning because RUSBoost uses majority voting of weak classifiers for discrimination. The performance of SST-RUS was validated using an open-access database called the Montreal archives of sleep studies cohort 1 (MASS-C1), which showed an F-measure of 0.70 with a sensitivity of 76.9% and a positive predictive value of 61.2%. The proposed method can reduce the burden of PSG scoring.
Purpose: Sleep apnea syndrome (SAS) is a prevalent sleep disorder in which apnea and hypopnea occur frequently during sleep and result in increase of the risk of lifestyle-related disease development as well as daytime sleepiness. Although SAS is a common sleep disorder, most patients remain undiagnosed because the gold standard test polysomnography (PSG), is high-cost and unavailable in many hospitals. Thus, an SAS screening system that can be used easily at home is needed. Methods: Apnea during sleep affects changes in the autonomic nervous function, which causes fluctuation of the heart rate. In this study, we propose a new SAS screening method that combines heart rate measurement and long short-term memory (LSTM) which is a type of recurrent neural network (RNN). We analyzed the data of intervals between adjacent R waves (R-R interval; RRI) on the electrocardiogram (ECG) records, and used an LSTM model whose inputs are the RRI data is trained to discriminate the respiratory condition during sleep. Results: The application of the proposed method to clinical data showed that it distinguished between patients with moderate-to-severe SAS with a sensitivity of 100% and specificity of 100%, results which are superior to any other existing SAS screening methods. Conclusion: Since the RRI data can be easily measured by means of wearable heart rate sensors, our method may prove to be useful as an SAS screening system at home.
Objective: Obstructive sleep apnea (OSA) is a common sleep disorder; however, most patients are undiagnosed and untreated because it is difficult for patients themselves to notice OSA in daily living. Polysomnography (PSG), which is the gold standard test for sleep disorder diagnosis, cannot be performed in many hospitals. This fact motivates us to develop a simple system for screening OSA at home. Approach: The autonomic nervous system changes during apnea, and such changes affect heart rate variability (HRV). This work develops a new apnea screening method based on HRV analysis and machine learning technologies. An apnea/normal respiration (A/N) discriminant model is built for respiration condition estimation for every heart rate measurement, and an apnea/sleep ratio is introduced for final diagnosis. A random forest is adopted for the A/N discriminant model construction, which is trained with the PhysioNet apnea-ECG database. Main results: The screening performance of the proposed method was evaluated by applying it to clinical PSG data. Sensitivity and specificity achieved 76% and 92%, respectively, which are comparable to existing portable sleep monitoring devices used in sleep laboratories. Significance: Since the proposed OSA screening method can be used more easily than existing devices, it will contribute to OSA treatment.