MyMedR

Displaying all 8 publications

Abstract:

Sort:

Fulltext A Deep Learning Model for Automated Sleep Stages Classification Using PSG Signals

Yildirim O, Baloglu UB, Acharya UR

Int J Environ Res Public Health, 2019 02 19;16(4).
PMID: 30791379 DOI: 10.3390/ijerph16040599

Sleep disorder is a symptom of many neurological diseases that may significantly affect the quality of daily life. Traditional methods are time-consuming and involve the manual scoring of polysomnogram (PSG) signals obtained in a laboratory environment. However, the automated monitoring of sleep stages can help detect neurological disorders accurately as well. In this study, a flexible deep learning model is proposed using raw PSG signals. A one-dimensional convolutional neural network (1D-CNN) is developed using electroencephalogram (EEG) and electrooculogram (EOG) signals for the classification of sleep stages. The performance of the system is evaluated using two public databases (sleep-edf and sleep-edfx). The developed model yielded the highest accuracies of 98.06%, 94.64%, 92.36%, 91.22%, and 91.00% for two to six sleep classes, respectively, using the sleep-edf database. Further, the proposed model obtained the highest accuracies of 97.62%, 94.34%, 92.33%, 90.98%, and 89.54%, respectively for the same two to six sleep classes using the sleep-edfx dataset. The developed deep learning model is ready for clinical usage, and can be tested with big PSG data.

Matched MeSH terms: Polysomnography/methods*
Prevalence and factors associated with probable obstructive sleep apnea among patients with hypertension in two primary care clinics in Miri, Sarawak, Malaysia

Ching SM, Singh R, Azmi FSB, Chong KL, Ong CRS, Ayob NAB, et al.

Ir J Med Sci, 2024 Feb;193(1):375-382.
PMID: 37204559 DOI: 10.1007/s11845-023-03397-4

PURPOSE: Obstructive sleep apnea (OSA) has been increasingly recognized as an important factor contributing to medical morbidity and mortality. It was reported that more than half of the population with hypertension had OSA. Limited studies have been done on assessing OSA in hypertensive patients. This study aimed to determine the prevalence, socio-demographic characteristics, and factors associated with probable OSA in hypertensive patients in primary care clinics in Sarawak.
METHODS: A cross-sectional study was carried out using a systematic random sampling method in hypertensive patients who attended two government primary care clinics in Sarawak. The STOP-Bang questionnaire was used to screen for OSA, and social-demographic data was captured with a questionnaire. Multiple logistic regressions were used to examine the determinants of the OSA.
RESULTS: A total of 410 patients were enrolled in this study. The mean age of study population patients was 56.4 years, with more than half being female. The mean blood pressure was 136/82. The prevalence of probable OSA among patients with hypertension was 54.4%. According to multiple logistic regression analyses, smoking (odds ratio [OR] 14.37, 95% confidence interval [CI] 3.335-61.947), retirees (OR 3.20, 95% CI 1.675-6.113), and being Chinese (OR 2.21, 95% CI 1.262-3.863) had a significant positive association with probable OSA.
CONCLUSIONS: Because of the high prevalence of probable OSA among patients with hypertension, primary care physicians should be more vigilant in identifying hypertensive patients with OSA risk. Early detection and intervention would reduce disease complications and healthcare costs.

Matched MeSH terms: Polysomnography/methods
Improving detection of obstructive sleep apnoea by overnight oximetry in children using pulse rate parameters

Sahadan DZ, Davey MJ, Horne RS, Nixon GM

Sleep Breath, 2015 Dec;19(4):1409-14.
PMID: 25739713 DOI: 10.1007/s11325-014-1108-4

PURPOSE: Overnight oximetry is a simple tool for investigation of obstructive sleep apnoea (OSA) in children, but only severe cases will be detected, and children with obstructive events resulting in arousal, but not desaturation, will have a normal (inconclusive) result. We hypothesised that pulse rate rises using pulse rate indices per hour (PRI) and pulse rate standard deviation (PR-SD) automatically calculated from commercially available software would improve oximetry as a diagnostic tool.
METHODS: Children having home overnight oximetry for suspected OSA were identified over 12 months, and those with a normal result who went on to have polysomnography (PSG) were included. Oximetry, including PR-SD and PRI (rises of 8, 10 and 15 beats/min per hour), was analyzed using commercially available software. PR parameters were compared between those with OSA (obstructive apnoea-hypopnoea index (OAHI) >1 event/h) and those without OSA.
RESULTS: One hundred sixteen children had normal oximetry, of whom 93 (median age 4.5 years; 55 % M) had PSG. Fifty-seven of 93 (61 %) children had OSA (median OAHI 4.5 events/h, range 1.1-24). PR-SD was not different between the OSA and non-OSA groups (p = 0.87). PRI tended to be higher in those with OSA, but there was considerable overlap between the groups: PRI-8 (mean ± SD 58.5 ± 29.0/h in OSA group vs 48.6 ± 20.2/h in non-OSA group, p = 0.07), PRI-10 (45.1 ± 25.0 vs 36.2 ± 16.7, p = 0.06) and PRI-15 (24.4 ± 14.5 vs 18.9 ± 9.0, p = 0.04). A PRI-15 threshold of >35/h had specificity of 97 % for OSA.
CONCLUSION: The PRI-15 shows promise as an indicator of OSA in children with normal oximetry.

Matched MeSH terms: Polysomnography/methods*
Fulltext A portal recording system for the assessment of patients with sleep apnoea syndrome

Liam CK

Med J Malaysia, 1996 Mar;51(1):82-8.
PMID: 10967984

The gold standard for the diagnosis and evaluation of sleep apnoea is overnight polysomnography. However, full polysomnography is an expensive and labour intensive procedure which requires the patient to sleep overnight in a hospital sleep laboratory. This paper describes the use of a commercial ambulatory microprocessor based system (Edentrace II) for the evaluation of fifteen patients aged 24 to 68 years with clinical features suggestive of sleep apnoea syndrome. With this portable recording system, sleep studies can be carried out unattended in a hospital ward and computer-assisted scoring of respiratory events can be performed.
Study site: Chest clinic, wards, University Malaya Medical Centre (UMMC), Kuala Lumpur, Malaysia

Matched MeSH terms: Polysomnography/methods*
The effectiveness of combined tonsillectomy and anterior palatoplasty in the treatment of snoring and obstructive sleep apnoea (OSA)

Adzreil B, Wong EHC, Saraiza AB, Raman R, Amin J

Eur Arch Otorhinolaryngol, 2017 Apr;274(4):2005-2011.
PMID: 27838741 DOI: 10.1007/s00405-016-4382-x

The prevalence of obstructive sleep apnoea (OSA) is increasing due to a rising rate of obesity. Multiple surgical techniques used to address obstruction at the palatal level have been associated with significant morbidities. Few studies have reported good outcomes of anterior palatoplasty (AP) in mild-to-moderate OSA. The aim of this study is to investigate the effectiveness of combining tonsillectomy and anterior palatoplasty in the treatment of snoring and OSA. All patients with snoring and OSA treated with tonsillectomy and anterior palatoplasty were analyzed. The primary outcome was reduction of the apnoea hypopnoea index (AHI) with surgical success criteria; reduction of AHI by ≥50% and AHI ≤10. The secondary outcomes measured were patients' Epworth Sleepiness Scale (ESS) and snoring visual analogue scale (VAS) scores. Thirty one patients completed the study, where 19% had mild, 42% moderate, and 39% had severe OSA. The mean surgical success rate was 45% at 3 months and 32% at 1-year post-operatively. There was a significant reduction of ESS and VAS at 3 months and 1-year post-operatively (p

Matched MeSH terms: Polysomnography/methods
Fulltext Integrating the Divided Nasal Cannula Into Routine Polysomnography to Assess Nasal Cycle: Feasibility and Effect on Outcomes

Scapuccin M, Schneider L, Rashid N, Zaghi S, Rosa T, Tsou YA, et al.

J Clin Sleep Med, 2018 04 15;14(4):641-650.
PMID: 29609709 DOI: 10.5664/jcsm.7062

STUDY OBJECTIVES: Patients suspected to have sleep-disordered breathing underwent an overnight polysomnography using a divided nasal cannula to gain additional information about the nasal cycle during sleep.
METHODS: This was a prospective, observational cohort study replacing the undivided nasal cannula with a divided nasal cannula during routine polysomnography (n = 28).
RESULTS: Integration of the divided nasal cannula pressure transducer system into routine polysomnography was easy and affordable. Most patients (89%) demonstrated nasal cycle changes during the test. Nasal cycle changes tended to occur during body position changes (62%) and transitions from non-rapid eye movement sleep to rapid eye movement sleep (41%). The mean nasal cycle duration was 2.5 ± 2.1 hours. Other sleep study metrics did not reveal statistically significant findings in relation to the nasal cycle.
CONCLUSIONS: Replacing an undivided nasal cannula with a divided nasal cannula is easy to implement, adding another physiologic measure to polysomnography. Although the divided nasal cannula did not significantly affect traditional polysomnographic metrics such as the apnea-hypopnea index or periodic limb movement index based on this small pilot study, we were able to replicate past nasal cycle findings that may be of interest to sleep clinicians and researchers. Given the ease with which the divided nasal cannula can be integrated, we encourage other sleep researchers to investigate the utility of using a divided nasal cannula during polysomnography.

Matched MeSH terms: Polysomnography/methods*
Drowsiness detection during different times of day using multiple features

Sahayadhas A, Sundaraj K, Murugappan M

Australas Phys Eng Sci Med, 2013 Jun;36(2):243-50.
PMID: 23719977 DOI: 10.1007/s13246-013-0200-6

Driver drowsiness has been one of the major causes of road accidents that lead to severe trauma, such as physical injury, death, and economic loss, which highlights the need to develop a system that can alert drivers of their drowsy state prior to accidents. Researchers have therefore attempted to develop systems that can determine driver drowsiness using the following four measures: (1) subjective ratings from drivers, (2) vehicle-based measures, (3) behavioral measures and (4) physiological measures. In this study, we analyzed the various factors that contribute towards drowsiness. A total of 15 male subjects were asked to drive for 2 h at three different times of the day (00:00-02:00, 03:00-05:00 and 15:00-17:00 h) when the circadian rhythm is low. The less intrusive physiological signal measurements, ECG and EMG, are analyzed during this driving task. Statistically significant differences in the features of ECG and sEMG signals were observed between the alert and drowsy states of the drivers during different times of day. In the future, these physiological measures can be fused with vision-based measures for the development of an efficient drowsiness detection system.

Matched MeSH terms: Polysomnography/methods*
Dental arch morphology in south-east Asian adults with obstructive sleep apnoea: geometric morphometrics

Banabilh SM, Suzina AH, Dinsuhaimi S, Samsudin AR, Singh GD

J Oral Rehabil, 2009 Mar;36(3):184-92.
PMID: 19207445 DOI: 10.1111/j.1365-2842.2008.01915.x

The association between dental arch morphology and the aetiology of obstructive sleep apnoea (OSA) is not clear. To compare dental arch morphology in 108 Asian adults with and without ''OSA, overnight'' hospital polysomnography was performed, and sleep reports were obtained for all subjects. Standardized digital photographs were also taken of the subjects' upper and lower study models. Using 25 homologous landmarks, mean OSA and control dental arch configurations were computed, and subjected to finite-element morphometry (FEM), t-tests and principal components analysis (PCA). Mean upper and lower OSA dental arch morphologies were statistically different from respective Control upper and lower arch morphologies (P < 0.05). FEM of the upper arch indicated that the mean OSA configuration was 7-11% narrower in the transverse plane in the incisor and canine regions when compared with the control configuration, and inter-landmark analysis (ILA) confirmed this finding. FEM for the lower arch indicated that the mean OSA configuration was 10-11% narrower in the antero-posterior plane in the pre-molar and molar regions, and confirmed by ILA. Using PCA, significant differences were also found between the two groups in the lower arch using the first two eigenvalues, which accounted for 90% of the total shape change (P < 0.001). Supporting their role as aetiological factors, size and shape differences in dental arch morphology are found in patients with OSA.

Matched MeSH terms: Polysomnography/methods