Sana Tmar-Ben Hamida

Computer based sleep staging: Challenges for the future

Studies have shown that patients suffering from sleep deprivation have a risk for hypertension, diabetes and depression that is higher than normal sleepers. Treatment for all these problems requires accurate analysis of the sleep stages and patterns in the polysomnographic signals collected in overnight recording over several months. However, manual sleep staging is a repetitive and time-consuming process as marking one typical eight hours overnight polysomnographic recording can take up to two hours to complete. Due to increased processing capabilities, it is now possible to automate this process and assist the sleep expert. A large number of algorithms have been proposed during the last few decades. This review article presents an overview of the existing automatic sleep staging methods, discusses the different challenges and proposes future prospects for new research opportunities.

Empirical analysis of UWB channel characteristics for secret key generation in indoor environments

Recent security methods propose to generate secret keys from Ultra Wide Band (UWB) channels. These solutions rely on the reciprocity and spatial channel correlation principles. This work aims at presenting empirical studies on the aforesaid properties. First, we verify the UWB reciprocity for different multipath scenarios. In these experiences, the reciprocity is always valid independently of distance between the receiver and emitter. However, we show that using an asymmetric hardware in up and down links, can affect the channel similarity. Secondly, we report measurements of spatial correlation in near and far field channel. Various experimental scenarios are tested to validate location channel variations. We observe that in very close and far receivers locations, there is no correlation. This variation is not depending on distance but mainly on the indoor environment. In addition, various channel parameters: channel impulse response, channel envelope, and power delay profile have been investigated. We show that channel properties rely on these parameters.

A new mHealth communication framework for use in wearable WBANs and mobile technologies.

Driven by the development of biomedical sensors and the availability of high mobile bandwidth, mobile health (mHealth) systems are now offering a wider range of new services. This revolution makes the idea of in-home health monitoring practical and provides the opportunity for assessment in “real-world” environments producing more ecologically valid data. In the field of insomnia diagnosis, for example, it is now possible to offer patients wearable sleep monitoring systems which can be used in the comfort of their homes over long periods of time. The recorded data collected from body sensors can be sent to a remote clinical back-end system for analysis and assessment. Most of the research on sleep reported in the literature mainly looks into how to automate the analysis of the sleep data and does not address the problem of the efficient encoding and secure transmissions of the collected health data. This article reviews the key enabling communication technologies and research challenges for the design of efficient mHealth systems. An end-to-end mHealth system architecture enabling the remote assessment and monitoring of patients sleep disorders is then proposed and described as a case study. Finally, various mHealth data serialization formats and machine-to-machine (M2M) communication protocols are evaluated and compared under realistic operating conditions.

EEG time and frequency domain analyses of primary insomnia.

In this work, we present a range of electroencephalographic (EEG) time and frequency domain features that can be used to characterize patients suffering with primary insomnia. When evaluated using 10 insomniacs and 10 healthy subjects, we found significant differences in the feature values between the two groups. Participants with primary insomnia were observed to have significantly elevated Hjorths parameters particularly complexity, high zero crossing rates specifically during wake and sleep stage 1 and high gamma power in all sleep stages. Given the significant differences between the two groups, these features can be used to better understand the sleep dynamics of insomniacs and accurately discriminate insomniac EEG data from that of healthy subjects.

A New Era in Sleep Monitoring: The Application of Mobile Technologies in Insomnia Diagnosis

Sleep disorders, such as insomnia can seriously impair a patient’s quality of life. Existing studies have shown that insomniacs have a risk of hypertension 350 percent higher than normal sleepers. Insomnia is also a risk factor for diabetes, as well as anxiety and depression. Sleep measurements based on polysomnographic (PSG) signals and questionnaires are necessary for an accurate evaluation of insomnia; however PSG systems are uncomfortable and inconvenient as they require patients to stay overnight at sleep centers. There is an increasing interest in portable devices, which provide the opportunity for the assessment of insomnia in a native environment (e.g. patients’ homes). Due to recent advances in technology, it is now possible to continuously monitor a patient’s sleep at home and send their sleep data to a remote clinical back-end system for analysis and reporting. This chapter provides a systematic analysis on the sleep monitoring technologies that can be used for insomnia assessment and treatment. This study highlights the key technical challenges of sleep monitoring, describes different types of technologies and discusses their applications in insomnia assessment. An overview of some model-based signal processing for sleep staging and insomnia detection is presented. Lastly, this chapter ends with a discussion, which provides future directions for the deployment of effective in-home patient monitoring systems for insomnia diagnosis.

A novel insomnia identification method based on Hjorth parameters

In this work, we present a &-means classifier using Hjorth parameters extracted from the central electroencephalogram (EEG) signals to accurately detect insomnia. To develop and test our classifier we used data from thirty six subjects: 18 patients diagnosed with primary insomnia (10 females, 8 males) and 18 controls (10 females, 8 males). The main findings of our work can be summarized as follows: 1) the Hjorth parameters, particularly the mobility and the complexity, accurately quantify the differences between the EEG sleep from insomnia patients and controls; 2) these differences can be observed across both C3 and C4 central channels; and 3) a k-means classifier based on Hjorth parameters extracted from the C3 channel is able to accurately detect epochs from insomnia patients with a Cohens Kappa of 0.83, sensitivity of 91.9% and specificity of 91%.

How many sleep stages do we need for an efficient automatic insomnia diagnosis

Tools used by clinicians to diagnose and treat insomnia typically include sleep diaries and questionnaires. Overnight polysomnography (PSG) recordings are used when the initial diagnosis is uncertain due to the presence of other sleep disorders or when the treatment, either behavioral or pharmacologic, is unsuccessful. However, the analysis and the scoring of PSG data are time-consuming. To simplify the diagnosis process, in this paper we have proposed an efficient insomnia detection algorithm based on a central single electroencephalographic (EEG) channel (C3) using only deep sleep. We also analyzed several spectral and statistical EEG features of good sleeper controls and subjects suffering from insomnia in different sleep stages to identify the features that offered the best discrimination between the two groups. Our proposed algorithm was evaluated using EEG recordings from 19 patients diagnosed with primary insomnia (11 females, 8 males) and 16 matched control subjects (11 females, 5 males). The sensitivity of our algorithm is 92%, the specificity is 89.9%, the Cohens kappa is 0.81 and the agreement is 91%, indicating the effectiveness of our proposed method.Tools used by clinicians to diagnose and treat insomnia typically include sleep diaries and questionnaires. Overnight polysomnography (PSG) recordings are used when the initial diagnosis is uncertain due to the presence of other sleep disorders or when the treatment, either behavioral or pharmacologic, is unsuccessful. However, the analysis and the scoring of PSG data are time-consuming. To simplify the diagnosis process, in this paper we have proposed an efficient insomnia detection algorithm based on a central single electroencephalographic (EEG) channel (C3) using only deep sleep. We also analyzed several spectral and statistical EEG features of good sleeper controls and subjects suffering from insomnia in different sleep stages to identify the features that offered the best discrimination between the two groups. Our proposed algorithm was evaluated using EEG recordings from 19 patients diagnosed with primary insomnia (11 females, 8 males) and 16 matched control subjects (11 females, 5 males). The sensitivity of our algorithm is 92%, the specificity is 89.9%, the Cohens kappa is 0.81 and the agreement is 91%, indicating the effectiveness of our proposed method.

A remote deep sleep monitoring system based on a single channel for in-home insomnia diagnosis

An efficient insomnia diagnosis and treatment requires the analysis of sleep stages and patterns in the vital signals and clinical face-to-face consultations. The measured signals are collected from different locations on the head and the body and used to evaluate the sleep quality and quantity. Generally, these measurements require spending several days of monitoring at sleep centers. However, the first night effect may cause perturbations to the control subjects and contrary to insomnia subjects who may sleep better because of the change of the sleep environment. Therefore, there is a great interest in developing non-invasive ambulatory physiological insomnia monitoring devices for in-home use. It has been shown in previous studies that the sleep quality can be evaluated based on the quantity of length of deep sleep particularly the slow wave sleep (SWS) periods. The aim of this paper is to present a new method to evaluate the deep sleep epochs using a single electrooculogram channel and to collect remotely the subjective data through sleep diaries.

Accurate automatic identification of slow wave sleep using a single electro-oculogram channel

Diagnosis and treatment of sleep disorders require analysis of the sleep stages and patterns in the polysomnographic (PSG) signals recorded over several hours. Traditionally, sleep is monitored based on PSG signals that require several measurements collected from different locations on the head and the body. These signals are used to evaluate the sleep quantity and quality. However, the need for unobtrusive monitoring and convenience motivates a variety of alternative approaches focused on the minimization of a number of monitored physiological signals. Previous studies have shown that the quantity and length of slow wave sleep (SWS) periods during sleep are the major indicators of the sleep quality. The aim of this paper is to present a new automatic method to detect SWS epochs using a single-channel electro-oculography (EOG). This method is based on a simple rule based algorithm with an adaptive method to adjust thresholds. The new method is evaluated through 9 healthy subjects and the results are compared to the clinical visual scoring. The agreement of our detection method for the validation data was 90.0%, the sensitivity was 90.5% and the specificity was 89.9% and the kappa value was 0.74.