A novel, simple, and accurate pulse oximetry indicator for screening adult obstructive sleep apnea

Predictive factors and screening strategy for obstructive sleep apnea in patients with advanced multiple sclerosis

BACKGROUND

Obstructive sleep apnea (OSA) screening questionnaires have been evaluated in Multiple Sclerosis (MS) but not yet validated in patients with advanced disease. The aim of this study is to identify OSA predictive factors in advanced MS and to discuss screening strategies.

METHODS

Oximetry data from 125 patients were retrospectively derived from polysomnographic reports. Univariate and multivariate analysis were used to determine predictive factors for OSA. A two-level screening model was assessed combining the oxygen desaturation index (ODI) and a method of visual analysis.

RESULTS

multivariate analysis showed that among the clinical factors only age and snoring were associated with OSA. Usual predictive factors such as sleepiness, Body mass index (BMI) or sex were not significantly associated with increased Apnea Hypopnea Index (AHI). The ODI was highly predictive (p < 0.0001) and correctly identified 84.1 % of patients with moderate OSA and 93.8 % with severe OSA. The visual analysis model combined with the ODI did not outperform the properties of ODI used alone.

CONCLUSION

As the usual clinical predictors are not associated with OSA in patients with advanced MS, questionnaires developed for the general population are not appropriate in these patients. Nocturnal oximetry seems a pertinent, ambulatory and accessible method for OSA screening in this population.

Proposal of a diagnostic algorithm based on the use of pulse oximetry in obstructive sleep apnea

PURPOSE

The aims of this study were to assess the cut-off values for oxygen desaturation index ≥ 3% (ODI3) to confirm obstructive sleep apnea (OSA) in subjects undergoing polysomnography (PSG) and home-based respiratory polygraphy (RP), and to propose an algorithm based on pulse oximetry (PO) for initial management of patients with suspected OSA.

METHODS

This was an observational, cross-sectional, retrospective study. ODI3 was used to classify subjects as healthy (no OSA = AHI < 5 or < 15 events/h) or unhealthy (OSA = AHI ≥ 5 or ≥ 15 events/h). On the PSG or experimental group (Exp-G), we determined ODI3 cut-off values with 100% specificity (Sp) for both OSA definitions. ODI3 values without false positives in the Exp-G were applied to a validation group (Val-G) to assess their performance. A strategy based on PO was proposed in patients with suspected OSA.

RESULTS

In Exp-G (PSG) 1141 patients and in Val-G (RP) 1141 patients were included. In Exp-G, ODI3 > 12 (OSA = AHI ≥ 5) had a sensitivity of 69.5% (CI95% 66.1-72.7) and Sp of 100% (CI95% 99-100), while an ODI3 ≥ 26 had a 53.8% sensitivity (CI95% 49.3-58.2) and Sp of 100% (CI95% 99.4-100) for AHI ≥ 15. A high pretest probability for OSA by Berlin questionaire (≥ 2 categories) had a lower diagnostic performance than by STOP-BANG questionnaire ≥ 5 points (AHI ≥ 5: 0.856 vs. 0.899, p < 0.001; AHI ≥ 15: 0.783 vs. 0.807, p 0.026).

CONCLUSION

We propose the initial use of PO at home in cases of moderate-to-high pretest probability of OSA. This algorithm considers PO as well as RP and PSG for more challenging cases or in case of doubt.

Screening the risk of obstructive sleep apnea by utilizing supervised learning techniques based on anthropometric features and snoring events

Objectives

Obstructive sleep apnea (OSA) is typically diagnosed by polysomnography (PSG). However, PSG is time-consuming and has some clinical limitations. This study thus aimed to establish machine learning models to screen for the risk of having moderate-to-severe and severe OSA based on easily acquired features.

Methods

We collected PSG data on 3529 patients from Taiwan and further derived the number of snoring events. Their baseline characteristics and anthropometric measures were obtained, and correlations among the collected variables were investigated. Next, six common supervised machine learning techniques were utilized, including random forest (RF), extreme gradient boosting (XGBoost), k-nearest neighbor (kNN), support vector machine (SVM), logistic regression (LR), and naïve Bayes (NB). First, data were independently separated into a training and validation dataset (80%) and a test dataset (20%). The approach with the highest accuracy in the training and validation phase was employed to classify the test dataset. Next, feature importance was investigated by calculating the Shapley value of every factor, which represented the impact on OSA risk screening.

Results

The RF produced the highest accuracy (of >70%) in the training and validation phase in screening for both OSA severities. Hence, we employed the RF to classify the test dataset, and results showed a 79.32% accuracy for moderate-to-severe OSA and 74.37% accuracy for severe OSA. Snoring events and the visceral fat level were the most and second most essential features of screening for OSA risk.

Conclusions

The established model can be considered for screening for the risk of having moderate-to-severe or severe OSA.

Quantitative Data Integration Analysis Method for Cross-Studies: Obstructive Sleep Apnea as an Example

Objective

In recent years, the prevalence of obstructive sleep apnea (OSA) has gradually increased. The diagnosis of this multiphenotypic disorder requires a combination of several indicators. The objective of this study was to find significant apnea monitor indicators of OSA by developing a strategy for cross-study screening and integration of quantitative data.

Methods

Articles related to sleep disorders were obtained from the PubMed database. A sleep disorder dataset and an OSA dataset were manually curated from these articles. Two evaluation indexes, the indicator coverage ratio (ICR) and the study integrity ratio (SIR), were used to filter out OSA indicators from the OSA dataset and create profiles including different numbers of indicators and studies for analysis. Data were analyzed by the meta 4.18-0 package of R, and the p value and standard mean difference (SMD) values were calculated to evaluate the change of each indicator.

Results

The sleep disorder dataset was constructed based on 178 studies from 119 publications, the OSA dataset was extracted from 89 studies, 284 sleep-related indicators were filtered out, and 22 profiles were constructed. Apnea hypopnea index was significantly decreased in all 22 profiles. Total sleep time (TST) (min) showed no significant differences in 21 profiles. There were significant increases in rapid eye movement (REM) (%TST) in 18 profiles, minimum arterial oxygen saturation (SaO₂) in 9 profiles, REM duration in 3 profiles, and slow wave sleep duration (%TST) and pulse oximetry lowest point in 2 profiles. There were significant decreases in apnea index (AI) in 14 profiles; arousal index and SaO₂ < 90 (%TST) in 8 profiles; N1 stage (%TST) in 7 profiles; and hypopnea index, N1 stage (% sleep period time (%SPT)), N2 stage (%SPT), respiratory arousal index, and respiratory disorder index in 2 profiles.

Conclusion

The proposed data integration strategy successfully identified multiple significant OSA indicators.