-
Computers in Biology and Medicine Jun 2024Sleep apnea is a common sleep disorder. The availability of an easy-to-use sleep apnea predictor would provide a public health benefit by promoting early diagnosis and...
Sleep apnea is a common sleep disorder. The availability of an easy-to-use sleep apnea predictor would provide a public health benefit by promoting early diagnosis and treatment. Our goal was to develop a prediction tool that used commonly available variables and was accessible to the public through a web site. Using data from polysomnography (PSG) studies that measured the apnea-hypopnea index (AHI), we built a machine learning tool to predict the presence of moderate to severe obstructive sleep apnea (OSA) (defined as AHI ≥15). Our tool employs only seven widely available predictor variables: age, sex, weight, height, pulse oxygen saturation, heart rate and respiratory rate. As a preliminary step, we used 16,958 PSG studies to examine eight machine learning algorithms via five-fold cross validation and determined that XGBoost exhibited superior predictive performance. We then refined the XGBoost predictor by randomly partitioning the data into a training and a test set (13,566 and 3392 PSGs, respectively) and repeatedly subsampling from the training set to construct 1000 training subsets. We evaluated each of the resulting 1000 XGBoost models on the single set-aside test set. The resulting classification tool correctly identified 72.5 % of those with moderate to severe OSA as having the condition (sensitivity) and 62.8 % of those without moderate to-severe OSA as not having it (specificity); overall accuracy was 66 %. We developed a user-friendly publicly available website (https://manticore.niehs.nih.gov/OSApredictor). We hope that our easy-to-use tool will serve as a screening vehicle that enables more patients to be clinically diagnosed and treated for OSA.
PubMed: 38901189
DOI: 10.1016/j.compbiomed.2024.108777 -
Clinical and Experimental... Jun 2024Supine sleep position and rapid eye movement (REM) stage are widely known to aggravate the severity of obstructive sleep apnea (OSA). In general, position-dependent OSA...
OBJECTIVE
Supine sleep position and rapid eye movement (REM) stage are widely known to aggravate the severity of obstructive sleep apnea (OSA). In general, position-dependent OSA is defined as an apnea-hypopnea index (AHI) at least twice as high in the supine position as in other sleep positions, but it can be misdiagnosed if a certain sleep stage, REM or NREM, is dominant in a specific sleep position. In this study, we investigated the influences of the sleep stages on positional dependency.
METHODS
The polysomnographic data from 111 OSA patients aged ≥ 18 years (AHI > five events/hour) who slept in both supine and non-supine positions (each ≥ 5% of the total sleep time) were retrospectively analyzed. The overall ratio of non-supine AHI/supine AHI (NS/S AHI ratio) during the entire sleep was compared between specific sleep stages, i.e., REM or NREM sleep. Additionally, the weighted NS/S AHI ratio reflecting the proportion of each sleep time was created and compared with the original NS/S AHI ratio.
RESULTS
The mean value of the NS/S AHI ratio did not differ between the entire sleep and the specific sleep stages. However, those ratios in the individual patients showed poor agreement of the NS/S AHI ratios between the entire sleep and the specific sleep stages. The weighted NS/S AHI ratio also demonstrated poor agreement with the original NS/S AHI ratio, mainly due to the discrepancy in mild to moderate OSA patients.
CONCLUSION
The weighted NS/S AHI ratio might help assess precise positional dependency.
PubMed: 38898811
DOI: 10.21053/ceo.2023.00037 -
BMC Psychiatry Jun 2024Tinnitus affects approximately 740 million adults globally, involving hearing, emotion, and sleep systems. However, studies using polysomnography and pure-tone...
BACKGROUND
Tinnitus affects approximately 740 million adults globally, involving hearing, emotion, and sleep systems. However, studies using polysomnography and pure-tone audiometry (PTA) are limited. We aimed to assess the correlation between tinnitus and hearing, sleep quality, characteristics, and depression using polysomnography and PTA.
METHODS
In this cross-sectional study, we divided participants into tinnitus and non-tinnitus groups. We included 100 outpatients (65 with tinnitus, 35 without) from a medical center in Taiwan, who underwent polysomnography and completed rating scales including the Patient Health Questionnaire-9 (PHQ-9), Chinese version of the Pittsburgh Sleep Quality Index (PSQI), and Chinese-Mandarin version of the Tinnitus Handicap Inventory (THI-CM). We analyzed correlations, conducted group comparisons, assessed factors related to THI-CM scores, constructed ROC curves to predict depression in the tinnitus group, and performed multinomial and logistic regression to explore associations.
RESULTS
Descriptive statistics identified a cohort with mean age 53.9 ± 12.80 years, 63% exhibited PHQ-9 scores ≥ 10, and 66% had Apnea-Hypopnea Index (AHI) > 5. The ratio of rapid eye movement and deep sleep to stage 1 + 2 sleep was relatively low and non-significant. Likewise, leg movements was higher in the tinnitus group but not statistically significant. In the tinnitus group, 63.08% had depression, and 81.54% had AHI > 5. Univariate logistic regression linked tinnitus to AHI > 5 (Odds ratio (OR) 2.67, p = 0.026) and male sex (OR 2.49, p = 0.034). A moderate positive correlation was found between the THI-CM score and PHQ-9 score (rs = 0.50, p < 0.001). Further adjustment for obstructive sleep apnea showed associations between PHQ-9 (total score) or depression and THI-CM Grade 3-5 (OR = 1.28; OR = 8.68). Single- and multifactor regression analyses highlighted significant associations of PSQI scores > 13 (OR 7.06, p = 0.018) and THI-CM scores > 47 (OR 7.43, p = 0.002) with depression.
CONCLUSIONS
Our study recruited tinnitus participants with slight or mild hearing loss and mild tinnitus handicap. Depression was identified as a predominant factor in tinnitus-related handicap. The mild tinnitus handicap in tinnitus participants may explain the lack of significant differences in depression, sleep quality, and polysomnographic sleep characteristics between tinnitus and non-tinnitus groups. Further extensive and prospective studies are needed to elucidate the complex links among depression, sleep, and tinnitus.
Topics: Humans; Male; Female; Tinnitus; Middle Aged; Polysomnography; Cross-Sectional Studies; Audiometry, Pure-Tone; Adult; Sleep Quality; Aged; Taiwan; Depression
PubMed: 38898451
DOI: 10.1186/s12888-024-05912-y -
BMJ Paediatrics Open Jun 2024Awareness of the need for early identification and treatment of sleep disordered breathing (SDB) in neonates is increasing but is challenging. Unrecognised SDB can have...
OBJECTIVE
Awareness of the need for early identification and treatment of sleep disordered breathing (SDB) in neonates is increasing but is challenging. Unrecognised SDB can have negative neurodevelopmental consequences. Our study aims to describe the clinical profile, risk factors, diagnostic modalities and interventions that can be used to manage neonates with SDB to facilitate early recognition and improved management.
METHODS
A single-centre retrospective study of neonates referred for assessment of suspected SDB to a tertiary newborn intensive care unit in New South Wales Australia over a 2-year period. Electronic records were reviewed. Outcome measures included demographic data, clinical characteristics, comorbidities, reason for referral, polysomnography (PSG) data, interventions targeted to treat SDB and hospital outcome. Descriptive analysis was performed and reported.
RESULTS
Eighty neonates were included. Increased work of breathing, or apnoea with oxygen desaturation being the most common reasons (46% and 31%, respectively) for referral. Most neonates had significant comorbidities requiring involvement of multiple specialists (mean 3.3) in management. The majority had moderate to severe SDB based on PSG parameters of very high mean apnoea-hypopnoea index (62.5/hour) with a mean obstructive apnoea index (38.7/hour). Ten per cent of patients required airway surgery. The majority of neonates (70%) were discharged home on non-invasive ventilation.
CONCLUSION
SDB is a serious problem in high-risk neonates and it is associated with significant multisystem comorbidities necessitating a multidisciplinary team approach to optimise management. This study shows that PSG is useful in neonates to diagnose and guide management of SDB.
Topics: Humans; Retrospective Studies; Infant, Newborn; Sleep Apnea Syndromes; Male; Female; Comorbidity; Polysomnography; New South Wales; Risk Factors; Intensive Care Units, Neonatal
PubMed: 38897623
DOI: 10.1136/bmjpo-2024-002639 -
Sensors (Basel, Switzerland) May 2024Vital sign monitoring is dominated by precise but costly contact-based sensors. Contactless devices such as radars provide a promising alternative. In this article, the...
Vital sign monitoring is dominated by precise but costly contact-based sensors. Contactless devices such as radars provide a promising alternative. In this article, the effects of lateral radar positions on breathing and heartbeat extraction are evaluated based on a sleep study. A lateral radar position is a radar placement from which multiple human body zones are mapped onto different radar range sections. These body zones can be used to extract breathing and heartbeat motions independently from one another via these different range sections. Radars were positioned above the bed as a conventional approach and on a bedside table as well as at the foot end of the bed as lateral positions. These positions were evaluated based on six nights of sleep collected from healthy volunteers with polysomnography (PSG) as a reference system. For breathing extraction, comparable results were observed for all three radar positions. For heartbeat extraction, a higher level of agreement between the radar foot end position and the PSG was found. An example of the distinction between thoracic and abdominal breathing using a lateral radar position is shown. Lateral radar positions could lead to a more detailed analysis of movements along the body, with the potential for diagnostic applications.
Topics: Humans; Radar; Vital Signs; Monitoring, Physiologic; Heart Rate; Respiration; Adult; Male; Polysomnography; Female
PubMed: 38894339
DOI: 10.3390/s24113548 -
Journal of Clinical Medicine May 2024Repetitive episodes of apnea and hypopnea during sleep in patients with obstructive sleep apnea (OSA) are known to increase the risk of atherosclerosis. Underlying...
Repetitive episodes of apnea and hypopnea during sleep in patients with obstructive sleep apnea (OSA) are known to increase the risk of atherosclerosis. Underlying obesity and related disorders, such as insulin resistance, are indirectly related to the development of atherosclerosis. In addition, OSA is independently associated with insulin resistance; however, data regarding this relationship are scarce in Japanese populations. This study aimed to examine the relationship between the severity of OSA and insulin resistance in a Japanese population. We analyzed the data of consecutive patients who were referred for polysomnography under clinical suspicion of developing OSA and who did not have diabetes mellitus or any cardiovascular disease. Multiple regression analyses were performed to determine the relationship between the severity of OSA and insulin resistance. The data from a total of 483 consecutive patients were analyzed. The median apnea-hypopnea index (AHI) was 40.9/h (interquartile range: 26.5, 59.1) and the median homeostasis model assessment for insulin resistance (HOMA-IR) was 2.00 (interquartile range: 1.25, 3.50). Multiple regression analyses revealed that the AHI, the lowest oxyhemoglobin saturation (SO), and the percentage of time spent on SO < 90% were independently correlated with HOMA-IR (an adjusted R-squared value of 0.01278821, = 0.014; an adjusted R-squared value of -0.01481952, = 0.009; and an adjusted R-squared value of 0.018456581, = 0.003, respectively). The severity of OSA is associated with insulin resistance assessed by HOMA-IR in a Japanese population.
PubMed: 38892846
DOI: 10.3390/jcm13113135 -
Respiratory Research Jun 2024Sleep-disordered breathing (SDB) is a major comorbidity in idiopathic pulmonary fibrosis (IPF) and is associated with a poor outcome. There is a lack of knowledge...
Treating sleep-disordered breathing of idiopathic pulmonary fibrosis patients with CPAP and nocturnal oxygen treatment. A pilot study : Sleep-disordered breathing treatment in IPF.
INTRODUCTION
Sleep-disordered breathing (SDB) is a major comorbidity in idiopathic pulmonary fibrosis (IPF) and is associated with a poor outcome. There is a lack of knowledge regarding the impact of SDB treatment on IPF. We assessed at one year: (1) the effect of CPAP and/or nocturnal oxygen therapy on IPF regarding lung function, blood mediators, and quality of life; (2) adherence to SDB treatment and SDB changes.
METHODOLOGY
This is a prospective study of consecutive newly diagnosed IPF patients initiating anti-fibrotic treatment. Lung function, polysomnography, blood tests and quality of life questionnaires were performed at inclusion and after one year. Patients were classified as obstructive sleep apnoea (OSA), central sleep apnoea (CSA), and sleep-sustained hypoxemia (SSH). SDB therapy (CPAP and/or nocturnal oxygen therapy) was initiated if needed.
RESULTS
Fifty patients were enrolled (36% had OSA, 22% CSA, and 12% SSH). CPAP was started in 54% of patients and nocturnal oxygen therapy in 16%. At one-year, polysomnography found improved parameters, though 17% of patients had to add nocturnal oxygen therapy or CPAP, while 33% presented SDB onset at this second polysomnography. CPAP compliance at one year was 6.74 h/night (SD 0.74). After one year, matrix metalloproteinase-1 decreased in OSA and CSA (p = 0.029; p = 0.027), C-reactive protein in OSA (p = 0.045), and surfactant protein D in CSA group (p = 0.074). There was no significant change in lung function.
CONCLUSIONS
Treatment of SBD with CPAP and NOT can be well tolerated with a high compliance. IPF patients may exhibit SDB progression and require periodic re-assessment. Further studies to evaluate the impact of SDB treatment on lung function and serological mediators are needed.
Topics: Humans; Continuous Positive Airway Pressure; Female; Male; Idiopathic Pulmonary Fibrosis; Pilot Projects; Aged; Prospective Studies; Sleep Apnea Syndromes; Oxygen Inhalation Therapy; Middle Aged; Treatment Outcome; Polysomnography; Quality of Life
PubMed: 38890648
DOI: 10.1186/s12931-024-02871-6 -
Scientific Reports Jun 2024Previous studies on sleep state misperception have objectively evaluated sleep status in special environments using polysomnography. There is a paucity of data from...
Previous studies on sleep state misperception have objectively evaluated sleep status in special environments using polysomnography. There is a paucity of data from studies that evaluated habitual sleep status in home environments. The present study aimed to investigate sleep state misperception in the home environment of patients with chronic insomnia using a lumbar-worn actigraphy to identify sleep habits associated with sleep state misperception severity. Thirty-one patients and 42 healthy volunteers were included in the insomnia and non-insomnia group, respectively. Participants recorded subjective assessments in sleep diaries, objective assessments with an actigraphy worn for 14 days, and self-assessments using questionnaires. Both groups had similar objective sleep ratings; however, insomnia group had significantly worse subjective ratings (total sleep time, wake after sleep onset, and sleep onset latency). A significant correlation was found between subjective and objective total sleep time scores in non-insomnia group but not in insomnia group. Insomnia group had earlier bedtimes, significantly longer bedtimes, and impaired daytime functioning (Sheehan Disability Scale score); additionally, they underestimated their total sleep time, particularly with earlier bedtimes and longer laying durations. Monitoring the sleep status and habits of individuals in home environments could be instrumental in identifying key points for targeted interventions on sleep hygiene and cognitive behavioral therapy for insomnia.
Topics: Humans; Sleep Initiation and Maintenance Disorders; Male; Female; Middle Aged; Adult; Sleep; Actigraphy; Surveys and Questionnaires; Polysomnography; Sleep Quality; Habits
PubMed: 38886489
DOI: 10.1038/s41598-024-64355-3 -
Sleep Medicine Jun 2024This research work was performed: (1) To assess the accessibility of in-laboratory polysomnography for individuals with spinal cord injury (SCI); (2) to evaluate the...
OBJECTIVES
This research work was performed: (1) To assess the accessibility of in-laboratory polysomnography for individuals with spinal cord injury (SCI); (2) to evaluate the validity of four screening questionnaires for sleep-related breathing disorders (SRBDs); and (3) to assess the association between anthropometric features and apnea-hypopnea index (AHI).
METHODS
An Environmental scan (E-scan) was performed in the province of Ontario, where all sleep clinics were invited to complete the E-scan survey. Furthermore, a cross-sectional study was performed at a rehabilitation hospital (Canada), where consecutive adults with subacute/chronic (>1 month) SCI were recruited. Using a home-based screening sleep test (HBSST), the validity of the Berlin, STOP, Medical Outcomes Study Sleep Scale [MOS-SS], and STOP-Bang screening questionnaires was assessed. The association between AHI and three features (i.e., neck circumference, body mass index [BMI] and oropharynx opening as assessed using the Modified Mallampati classification [MMC]) was evaluated.
RESULTS
According to the E-scan, access to polysomnography is limited for the SCI population in Ontario. Of the 28 participants with SCI (11 females, 17 males; mean age: 54.9 years) included in the cross-sectional study, 32.1 % were diagnosed with moderate-to-severe SRBD. The performance of the questionnaires was considered insufficient for screening of individuals living with SCI. AHI was not associated with neck circumference, BMI, or MMC.
CONCLUSIONS
Those results suggest that the use of a HBSST could overcome the barriers for individuals with SCI to access diagnostic testing of SRBDs. The use of screening questionnaires and risk assessment for SRBDs in the SCI population is unreliable.
PubMed: 38885542
DOI: 10.1016/j.sleep.2024.06.011 -
MedRxiv : the Preprint Server For... Jun 2024Atrial fibrillation (AF) is often asymptomatic and thus under-observed. Given the high risks of stroke and heart failure among patients with AF, early prediction and...
BACKGROUND
Atrial fibrillation (AF) is often asymptomatic and thus under-observed. Given the high risks of stroke and heart failure among patients with AF, early prediction and effective management are crucial. Importantly, obstructive sleep apnea is highly prevalent among AF patients (60-90%); therefore, electrocardiogram (ECG) analysis from polysomnography (PSG), a standard diagnostic tool for subjects with suspected sleep apnea, presents a unique opportunity for the early prediction of AF. Our goal is to identify individuals at a high risk of developing AF in the future from a single-lead ECG recorded during standard PSGs.
METHODS
We analyzed 18,782 single-lead ECG recordings from 13,609 subjects at Massachusetts General Hospital, identifying AF presence using ICD-9/10 codes in medical records. Our dataset comprises 15,913 recordings without a medical record for AF and 2,056 recordings from patients who were first diagnosed with AF between 1 day to 15 years after the PSG recording. The PSG data were partitioned into training, validation, and test cohorts. In the first phase, a signal quality index (SQI) was calculated in 30-second windows and those with SQI 0.95 were removed. From each remaining window, 150 hand-crafted features were extracted from time, frequency, time-frequency domains, and phase-space reconstructions of the ECG. A compilation of 12 statistical features summarized these window-specific features per recording, resulting in 1,800 features. We then updated a pre-trained deep neural network and data from the PhysioNet Challenge 2021 using transfer-learning to discriminate between recordings with and without AF using the same Challenge data. The model was applied to the PSG ECGs in 16-second windows to generate the probability of AF for each window. From the resultant probability sequence, 13 statistical features were extracted. Subsequently, we trained a shallow neural network to predict future AF using the extracted ECG and probability features.
RESULTS
On the test set, our model demonstrated a sensitivity of 0.67, specificity of 0.81, and precision of 0.3 for predicting AF. Further, survival analysis for AF outcomes, using the log-rank test, revealed a hazard ratio of 8.36 (p-value of 1.93 × 10 ).
CONCLUSIONS
Our proposed ECG analysis method, utilizing overnight PSG data, shows promise in AF prediction despite a modest precision indicating the presence of false positive cases. This approach could potentially enable low-cost screening and proactive treatment for high-risk patients. Ongoing refinement, such as integrating additional physiological parameters could significantly reduce false positives, enhancing its clinical utility and accuracy.
PubMed: 38883765
DOI: 10.1101/2024.06.04.24308444