Portable Sleep Study Device Versus Polysomnography: A Meta-analysis

Annual review of selected scientific literature: A report of the Committee on Scientific Investigation of the American Academy of Restorative Dentistry

The Scientific Investigation Committee of the American Academy of Restorative Dentistry offers this review of select 2023 dental literature to briefly touch on several topics of interest to modern restorative dentistry. Each committee member brings discipline-specific expertize in their subject areas that include (in order of appearance here): prosthodontics; periodontics, alveolar bone, and peri-implant tissues; dental materials and therapeutics; occlusion and temporomandibular disorders; sleep-related breathing disorders; oral medicine, oral and maxillofacial surgery, and oral radiology; and dental caries and cariology. The authors have focused their efforts on presenting information likely to influence the daily dental treatment decisions of the reader with an emphasis on current innovations, new materials and processes, emerging technology, and future trends in dentistry. With the overwhelming volume of literature published daily in dentistry and related disciplines, this review cannot be comprehensive. Instead, its purpose is to inform and update interested readers and provide valuable resource material for those willing to subsequently pursue greater detail on their own. Our intent remains to assist colleagues in navigating the tremendous volume of newly minted information produced annually. Finally, we hope readers find this work helpful in providing evidence-based care to patients seeking healthier and happier lives.

Long-term night-to-night variability of sleep-disordered breathing using a radar-based home sleep apnea test: a prospective cohort study

STUDY OBJECTIVES

Night-to-night variability of sleep-disordered breathing limits the diagnostic accuracy of a single measurement. Multiple recordings using a reliable, affordable method could reduce the uncertainty and avoid misdiagnosis, which could be possible with radar-based home sleep apnea testing (HSAT).

METHODS

We recruited consecutive patients with suspected sleep-disordered breathing and performed contactless radar-based HSAT with automated scoring (Sleepiz One; Sleepiz AG, Zurich, Switzerland) over 10 nights. During the first night, patients were simultaneously measured with peripheral arterial tonometry.

RESULTS

Twenty-four of the 28 included patients could achieve a minimum of 4 measurements. The failure rate was 16% (37 of 238 measurements). The apnea-hypopnea index (AHI) and oxygen desaturation index were consistently lower with radar-based HSAT compared with peripheral arterial tonometry. The variability of the AHI was considerable, with a standard error of measurement of 5.2 events/h (95% confidence interval [CI]: 4.6-5.7 events/h) and a minimal detectable difference of 14.4 events/h (95% CI: 12.7-15.9 events/h). Alcohol consumption partially accounted for the variability, with an AHI increase of 1.7 events/h (95% CI: 0.6-2.8 events/h) for each standard drink. Based on a single measurement, 17% of patients were misdiagnosed and 32% were misclassified for sleep-disordered breathing severity. After 5 measurements, the mean AHI of the measured nights stabilized with no evidence of substantial changes with additional measurements.

CONCLUSIONS

Night-to-night variability is considerable and stable over 10 nights. HSAT using radar-based methods over multiple nights is feasible and well tolerated by patients. It could offer lower costs and allow for multiple-night testing to increase accuracy. However, validation and reducing the failure rate are necessary for implementation in the clinical routine.

CLINICAL TRIAL REGISTRATION

Registry: ClinicalTrials.gov; Name: Recording of Multiple Nights Using a New Contactless Device (Sleepiz One Connect) in Obstructive Sleep Apnea; URL: https://clinicaltrials.gov/study/NCT05134402; Identifier: NCT05134402.

CITATION

Tschopp S, Borner U, Caversaccio M, Tschopp K. Long-term night-to-night variability of sleep-disordered breathing using a radar-based home sleep apnea test: a prospective cohort study. J Clin Sleep Med. 2024;20(7):1079-1086.

Development and application of a machine learning-based predictive model for obstructive sleep apnea screening

Objective

To develop a robust machine learning prediction model for the automatic screening and diagnosis of obstructive sleep apnea (OSA) using five advanced algorithms, namely Extreme Gradient Boosting (XGBoost), Logistic Regression (LR), Support Vector Machine (SVM), Light Gradient Boosting Machine (LightGBM), and Random Forest (RF) to provide substantial support for early clinical diagnosis and intervention.

Methods

We conducted a retrospective analysis of clinical data from 439 patients who underwent polysomnography at the Affiliated Hospital of Xuzhou Medical University between October 2019 and October 2022. Predictor variables such as demographic information [age, sex, height, weight, body mass index (BMI)], medical history, and Epworth Sleepiness Scale (ESS) were used. Univariate analysis was used to identify variables with significant differences, and the dataset was then divided into training and validation sets in a 4:1 ratio. The training set was established to predict OSA severity grading. The validation set was used to assess model performance using the area under the curve (AUC). Additionally, a separate analysis was conducted, categorizing the normal population as one group and patients with moderate-to-severe OSA as another. The same univariate analysis was applied, and the dataset was divided into training and validation sets in a 4:1 ratio. The training set was used to build a prediction model for screening moderate-to-severe OSA, while the validation set was used to verify the model's performance.

Results

Among the four groups, the LightGBM model outperformed others, with the top five feature importance rankings of ESS total score, BMI, sex, hypertension, and gastroesophageal reflux (GERD), where Age, ESS total score and BMI played the most significant roles. In the dichotomous model, RF is the best performer of the five models respectively. The top five ranked feature importance of the best-performing RF models were ESS total score, BMI, GERD, age and Dry mouth, with ESS total score and BMI being particularly pivotal.

Conclusion

Machine learning-based prediction models for OSA disease grading and screening prove instrumental in the early identification of patients with moderate-to-severe OSA, revealing pertinent risk factors and facilitating timely interventions to counter pathological changes induced by OSA. Notably, ESS total score and BMI emerge as the most critical features for predicting OSA, emphasizing their significance in clinical assessments. The dataset will be publicly available on my Github.

Validation of sleep-staging accuracy for an in-home sleep electroencephalography device compared with simultaneous polysomnography in patients with obstructive sleep apnea

Efforts to simplify standard polysomnography (PSG) in laboratories, especially for obstructive sleep apnea (OSA), and assess its agreement with portable electroencephalogram (EEG) devices are limited. We aimed to evaluate the agreement between a portable EEG device and type I PSG in patients with OSA and examine the EEG-based arousal index's ability to estimate apnea severity. We enrolled 77 Japanese patients with OSA who underwent simultaneous type I PSG and portable EEG monitoring. Combining pulse rate, oxygen saturation (SpO2), and EEG improved sleep staging accuracy. Bland-Altman plots, paired t-tests, and receiver operating characteristics curves were used to assess agreement and screening accuracy. Significant small biases were observed for total sleep time, sleep latency, awakening after falling asleep, sleep efficiency, N1, N2, and N3 rates, arousal index, and apnea indexes. All variables showed > 95% agreement in the Bland-Altman analysis, with interclass correlation coefficients of 0.761-0.982, indicating high inter-instrument validity. The EEG-based arousal index demonstrated sufficient power for screening AHI ≥ 15 and ≥ 30 and yielded promising results in predicting apnea severity. Portable EEG device showed strong agreement with type I PSG in patients with OSA. These suggest that patients with OSA may assess their condition at home.

The Prevalence of Obstructive Sleep Apnea and Associated Symptoms among Patients with Sickle Cell Disease: A Systematic Review and Meta-analysis

Previous studies have shown that patients with sickle cell disease (SCD) are at high risk for obstructive sleep apnea (OSA). In the current study, we aimed to systematically review the literature to address the prevalence of OSA and associated symptoms among patients with SCD. Electronic databases, including Web of Science, Scopus, PubMed, Google Scholar, and Embase were systematically searched to identify the relevant original articles on patients with SCD. Newcastle Ottawa scale was used for quality assessment. Data were pooled by using random effects models. Subgroup analyses were performed by age groups. Thirty-nine studies containing details of 299,358 patients with SCD were included. The pooled results showed that more than half of these patients had OSA with different severities. The prevalence rates of OSA among children with apnea hypopnea index (AHI) cutoffs of above 1, 1.5, and 5 were 51% (95% confidence interval (CI) 36-67%), 29% (95% CI 19-40%), and 18% (95% CI 14-23%), respectively. The prevalence of OSA among adults with AHI cutoff of 5 was 43% (95% CI 21-64%). The pooled rates of snoring, nocturnal enuresis, nocturnal desaturation, and daytime sleepiness were 55% (95% CI 42-69%), 37% (95% CI 33-41%), 49% (95% CI 26-72%), and 21% (95% CI 12-30%), respectively. Given the high prevalence of OSA in patients with SCD, probable greater burden of SCD complications, and irreversible consequences of OSA, screening for OSA symptoms and signs seems useful in these patients. By screening and identifying this heterogeneous disorder earlier, available treatment modalities can be individualized for each patient.