Identification of individual sleep apnea events from the ECG using neural networks and a dynamic markovian state model

Bystricky, W.; Safer, Alan M.

doi:10.1109/cic.2004.1442931

Cited by 8 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature there are similar proposals that generate the same information. 2,4,5,22,23,32,33 Our algorithms are capable of identifying apneas, hypopneas, desaturations, thoracic and abdominal movement limitations and snoring in the polysomnogram. 25 For the study presented in this paper, they were only used to identify apneas, hypopneas and desaturations.…”

Section: Indexes Generationmentioning

confidence: 99%

An Evaluation of Indexes as Support Tools in the Diagnosis of Sleep Apnea

et al. 2012

View full text Add to dashboard Cite

This article evaluates several indexes as support tools to diagnose patients with Sleep Apnea-Hypopnea Syndrome (SAHS). Some of these indexes, such as the Apnea-Hypopnea Index, have been standardized and studied in depth in the literature. Other indexes are used extensively in the reports that commercial polysomnographs generate. However, they have not been studied in detail and clinicians have no standardized guidelines for interpreting them. Examples are the mean and maximum duration of apneas and hypopneas. Finally, several novel indexes proposed by the authors are also evaluated. To evaluate the indexes, we have used a database of 274 patients who have undergone a polysomnographic test. Several feature selection techniques were used to assess the capability of each index to discriminate between healthy and SAHS patients. The capability of the indexes for diagnosing the patients was analyzed by using decision trees which were trained using each index individually, and all the indexes together. Our results suggest that some indexes which are often present in the reports of commercial polysomnographs provide little or no information. On the other hand, other indexes that are usually not considered have a great capability to discern between SAHS and control patients.

show abstract

Section: Indexes Generationmentioning

confidence: 99%

An Evaluation of Indexes as Support Tools in the Diagnosis of Sleep Apnea

et al. 2012

View full text Add to dashboard Cite

show abstract

“…In the literature there are several proposals to identify these events [1], [4], [5], [8], [9]. We have used algorithms that we previously developed for this purpose (see Figure 1).…”

Section: A Features Derived From the Pathological Eventsmentioning

confidence: 99%

Is the average duration of apneas, hypopneas and desaturations useful in the diagnosis of SAHS?

Otero

Félix

Presedo

et al. 2011

2011 IEEE 7th International Symposium on Intelligent Signal Processing

View full text Add to dashboard Cite

Sleep Apnea-Hypopnea Syndrome (SAHS) is usually diagnosed by polysomnography, a test that consists of the registration of a wide range of physiological parameters while the patient is asleep. The commercial monitoring devices used in the polysomnography generate a report summarizing the test. Some of the information presented to the clinicians in these reports, such as the Apnea-Hypopnea Index, has been the target of comprehensive clinical studies, and there are detailed clinical guidelines to interpret it. However, these reports also contain other data such as mean and maximum values of the descriptors of various pathological events recorded in the polysomnogram; e.g., the mean and maximum duration of the apneas, hypopneas and desaturations that the patient has experienced. These features have not been studied in the literature. Therefore, guidelines for their interpretation do not exist.This paper attempts to evaluate the usefulness of this information in the diagnosis of SAHS. It also tries to provide guidelines for clinicians on how to interpret it. To this end, we have calculated these features for 210 patients who underwent polysomnographic testing, and we have analyzed their capability to discriminate between healthy and SAHS patients, as well as to stratify the patients according to their severity. Our results suggest that most of them have little or no utility for diagnosing SAHS patients. Therefore, they could be omitted from the reports without significant loss of information.

show abstract

“…Tulga and Ozdamar 4 used wavelet coefficient corresponding to epilepsy signals as input and employed a neural network to distinguish epilepsy signals from background brain waves, and thereby achieved the goal of detecting and identifying epilepsy signals. 6 Some research has subjected many vital signs of SAS patients taken from the MIT/BIH sleep database to EEG analysis in order to detect and classify SAS. 5 Another study used the RR interval, QRS waves, and T waves from 35 ECGs as its research data, and employed a two-layer sensor framework in conjunction with the dynamic Markovian state model to classify SAS.…”

Section: Literature Reviewmentioning

confidence: 99%

Sleep Apnea Syndrome Recognition Using the Greyart Network

Lee

Chen

Hsiao

et al. 2011

Biomed. Eng. Appl. Basis Commun.

View full text Add to dashboard Cite

This study employs relational analysis and the GreyART network to identify and study the characteristics of electroencephalogram signals of sleep apnea syndrome (SAS). Seventeen raw electroencephalogram data records from the sleep database compiled by Massachusetts Institute of Technology (MIT) and Beth Israel Hospital (BIH) were used in conjunction with four wavelet decomposition steps to obtain the cD4 wavelet coefficient as input for the GreyART network. The GreyART network was then used for simulation training and testing in order to achieve the best recognition results. This study achieved an average recognition rate of 93.33% for electroencephalogram data record slp01b, and recognition rates during the training and testing stage for this record were 95.80% and 92.12%, respectively. This was the best recognition result for any of the 17 records. The overall average recognition rate for all 17 records was 78.10%. In comparison with past literature, this study's use of the GreyART network to recognize electroencephalogram signal characteristics of SAS possesses excellent reference value. To further reduce the costs and the physiological signal measurement items to make it easier for patients to use, this research also proposes to use a single type of physiological signals, electroencephalographic (EEG) signals, as the sole input as identification information to identify SAS diseases. EEG signal detection is utilized because it is nonintrusive, suitable for long-term monitoring and most importantly, it can be used to detect various types of abnormal physiological conditions in SAS, moods, sleep stages, heart rate abnormalities and mental states. In addition, constant monitoring of users in their familiar home environment can also be utilized as self-screening at home to reduce the burden of sleep medicine centers.

show abstract

Identification of individual sleep apnea events from the ECG using neural networks and a dynamic markovian state model

Abstract: Abstract

Cited by 8 publications

References 4 publications

An Evaluation of Indexes as Support Tools in the Diagnosis of Sleep Apnea

An Evaluation of Indexes as Support Tools in the Diagnosis of Sleep Apnea

Is the average duration of apneas, hypopneas and desaturations useful in the diagnosis of SAHS?

Sleep Apnea Syndrome Recognition Using the Greyart Network

Contact Info

Product

Resources

About