A Minimalist Method Toward Severity Assessment and Progression Monitoring of Obstructive Sleep Apnea on the Edge

2022 ◽  
Vol 3 (2) ◽  
pp. 1-16
Author(s):  
Md Juber Rahman ◽  
Bashir I. Morshed
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Area Under The Curve ◽  
Recursive Feature Elimination ◽  
Rank Test ◽  
Apnea Hypopnea Index ◽  
Time Duration ◽  
Severity Estimation ◽  
Severity Classification ◽  
Obstructive Sleep

Artificial Intelligence-enabled applications on edge devices have the potential to revolutionize disease detection and monitoring in future smart health (sHealth) systems. In this study, we investigated a minimalist approach for the severity classification, severity estimation, and progression monitoring of obstructive sleep apnea (OSA) in a home environment using wearables. We used the recursive feature elimination technique to select the best feature set of 70 features from a total of 200 features extracted from polysomnogram. We used a multi-layer perceptron model to investigate the performance of OSA severity classification with all the ranked features to a subset of features available from either Electroencephalography or Heart Rate Variability (HRV) and time duration of SpO2 level. The results indicate that using only computationally inexpensive features from HRV and SpO2, an area under the curve of 0.91 and an accuracy of 83.97% can be achieved for the severity classification of OSA. For estimation of the apnea-hypopnea index, the accuracy of RMSE = 4.6 and R-squared value = 0.71 have been achieved in the test set using only ranked HRV and SpO2 features. The Wilcoxon-signed-rank test indicates a significant change (p < 0.05) in the selected feature values for a progression in the disease over 2.5 years. The method has the potential for integration with edge computing for deployment on everyday wearables. This may facilitate the preliminary severity estimation, monitoring, and management of OSA patients and reduce associated healthcare costs as well as the prevalence of untreated OSA.

scholarly journals Cardiorespiratory Polygraphy for Detection of Obstructive Sleep Apnea in Patients With Atrial Fibrillation

2021 ◽  
Vol 8 ◽  
Author(s):  
Michiel Delesie ◽  
Lieselotte Knaepen ◽  
Johan Verbraecken ◽  
Karolien Weytjens ◽  
Paul Dendale ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Screening Tool ◽  
Area Under The Curve ◽  
Screening Tools ◽  
Apnea Hypopnea Index ◽  
Automated Algorithm ◽  
Obstructive Sleep ◽  
At Home

Background: Obstructive sleep apnea (OSA) is a modifiable risk factor of atrial fibrillation (AF) but is underdiagnosed in these patients due to absence of good OSA screening pathways. Polysomnography (PSG) is the gold standard for diagnosing OSA but too resource-intensive as a screening tool. We explored whether cardiorespiratory polygraphy (PG) devices using an automated algorithm for Apnea-Hypopnea Index (AHI) determination can meet the requirements of a good screening tool in AF patients.Methods: This prospective study validated the performance of three PGs [ApneaLink Air (ALA), SOMNOtouch RESP (STR) and SpiderSAS (SpS)] in consecutive AF patients who were referred for PSG evaluation. Patients wore one of the three PGs simultaneously with PSG, and a different PG during each of three consecutive nights at home. Severity of OSA was classified according to the AHI during PSG (&lt;5 = no OSA, 5–14 = mild, 15–30 = moderate, &gt;30 = severe).Results: Of the 100 included AF patients, PSG diagnosed at least moderate in 69% and severe OSA in 33%. Successful PG execution at home was obtained in 79.1, 80.2 and 86.8% of patients with the ALA, STR and SpS, respectively. For the detection of clinically relevant OSA (AHI ≥ 15), an area under the curve of 0.802, 0.772 and 0.803 was calculated for the ALA, STR and SpS, respectively.Conclusions: This study indicates that home-worn PGs with an automated AHI algorithm can be used as OSA screening tools in AF patients. Based on an appropriate AHI cut-off value for each PG, the device can guide referral for definite PSG diagnosis.

scholarly journals Obstructive Sleep Apnea Is Associated With Altered Glycemic Patterns in Pregnant Women With Obesity

2019 ◽  
Vol 104 (7) ◽  
pp. 2569-2579 ◽  
Author(s):  
Sarah S Farabi ◽  
Linda A Barbour ◽  
Kristy Heiss ◽  
Nicole M Hirsch ◽  
Emily Dunn ◽  
...  
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Pregnant Women ◽  
Area Under The Curve ◽  
Perinatal Outcomes ◽  
Late Pregnancy ◽  
Apnea Hypopnea Index ◽  
Oral Glucose ◽  
Continuous Glucose Monitor ◽  
Obstructive Sleep

AbstractObjectiveOften unrecognized, obstructive sleep apnea (OSA) worsens over pregnancy and is associated with poorer perinatal outcomes. The association between OSA in late pregnancy and metabolic biomarkers remains poorly understood. We tested the hypothesis that OSA in pregnant women with obesity is positively correlated with 24-hour patterns of glycemia and IR despite controlling for diet.DesignPregnant women (32 to 34 weeks’ gestation; body mass index, 30 to 40 kg/m2) wore a continuous glucose monitor for 3 days. OSA was measured in-home by WatchPAT 200™ [apnea hypopnea index (AHI), oxygen desaturation index (ODI; number per hour)]. Fasting blood was collected followed by a 2-hour, 75-g, oral glucose tolerance test to measure IR. Association between AHI and 24-hour glucose area under the curve (AUC) was the powered outcome.ResultsOf 18 women (29.4 ± 1.4 years of age [mean ± SEM]), 12 (67%) had an AHI ≥5 (mild OSA). AHI and ODI were correlated with 24-hour glucose AUC (r = 0.50 to 0.54; P ≤ 0.03) and mean 24-hour glucose (r = 0.55 to 0.59; P ≤ 0.02). AHI and ODI were correlated with estimated hepatic IR (r = 0.59 to 0.74; P < 0.01), fasting free fatty acids (fFFAs; r = 0.53 to 0.56; P < 0.05), and waking cortisol (r = 0.49 to 0.64; P < 0.05).ConclusionsMild OSA is common in pregnant women with obesity and correlated with increased glycemic profiles, fFFAs, and estimates of hepatic IR. OSA is a potentially treatable target to optimize maternal glycemia and metabolism, fetal fuel supply, and pregnancy outcomes.

scholarly journals Usefulness of Cathepsin S to Predict Risk for Obstructive Sleep Apnea among Patients with Type 2 Diabetes

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Wanwan Wen ◽  
Haili Sun ◽  
Yunxiao Yang ◽  
Yifan Jia ◽  
Fang Fang ◽  
...  
Keyword(s):  
Type 2 Diabetes ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Fasting Blood Glucose ◽  
Area Under The Curve ◽  
Cathepsin S ◽  
Control Group ◽  
Apnea Hypopnea Index ◽  
Obstructive Sleep

Background. Obstructive sleep apnea (OSA) was highly prevalent in patients with type 2 diabetes (T2D). Cathepsin S (CTSS), a cysteine protease, is involved in the inflammatory activity in T2D and hypoxia conditions. The aim of the study was to evaluate whether CTSS could be involved in the inflammatory reaction of OSA in patients with T2D. Methods. We included 158 participants in this study matched for age, gender, and body mass index in 4 groups (control, non-OSA&T2D, OSA&non-T2D, and OSA&T2D). After overnight polysomnography, we collected the clinical data including anthropometrical characteristics, blood pressure, and fasting blood samples in the morning. Plasma CTSS concentration was evaluated using the human Magnetic Luminex Assay. Results. Compared with the control group, both the non-OSA&T2D group and the OSA&non-T2D group showed higher CTSS levels. Plasma CTSS expression was significantly increased in subjects with OSA&T2D compared to subjects with non-OSA&T2D. The OSA&T2D group had higher CTSS levels than the OSA&non-T2D group, but there were no statistically significant differences. Plasma CTSS levels showed significant correlation with the apnea-hypopnea index (AHI) (r=0.559, P<0.001) and plasma fasting blood glucose (r=0.427, P<0.001). After adjusting confounding factors, plasma CTSS levels were independently associated with the AHI (Beta: 0.386, 95% confidence intervals (CI): 21.988 to 57.781; P<0.001). Furthermore, we confirmed the higher pinpoint accuracy of plasma CTSS in the diagnosis of OSA (area under the curve: 0.868). Conclusions. Plasma CTSS expression was significantly elevated in the OSA&T2D group and was independently associated with the AHI; it could be a biomarker with a positive diagnostic value on diagnosing OSA among patients with T2D.

scholarly journals Are Sleep Questionnaires Valid in All Adult Age Groups as Screening Tools for Obstructive Sleep Apnea?

2020 ◽  
Vol 27 (2) ◽  
pp. 90-94
Author(s):  
Ho Min Lee ◽  
Jae Ki Kim ◽  
Jung Gwon Nam ◽  
Tae-Hoon Lee
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Sensitivity And Specificity ◽  
Age Groups ◽  
Area Under The Curve ◽  
Screening Tools ◽  
Apnea Hypopnea Index ◽  
Adult Age ◽  
Age Related ◽  
Obstructive Sleep

Background and Objectives: Evaluation of Epworth Sleepiness Scale (ESS), Berlin, STOP, and STOP-Bang questionnaire validities for obstructive sleep apnea (OSA) screening among various adult age groups.Materials and Method: Results for each of those questionnaires were compared with diagnostic overnight polysomnography (PSG) data obtained for 396 patients suffering either insomnia, sleep apnea, excessive daytime sleepiness, or chronic snoring who had been divided into three age groups (20-39, 40-59, or ≥60 years). For each questionnaire, the sensitivity, specificity, accuracy, and area under the curve (AUC) were calculated.Results: Among the OSA group [apnea hypopnea index (AHI) cutoff ＞5], Berlin and STOP questionnaire sensitivity and specificity were significantly different among the age groups. Among the moderate-to-severe OSA sub-group (AHI cutoff ＞15), the specificity of Berlin, STOP, and STOP-Bang questionnaire was significantly different among age groups.Conclusion: The Berlin and STOP questionnaires differed with patient age in OSA screening. The ESS questionnaire, by contrast, did not show any age-related differences of sensitivity and specificity in OSA screening or moderate-to-severe OSA screening.

scholarly journals Monocyte to HDL cholesterol ratio as a marker of the presence and severity of obstructive sleep apnea in hypertensive patients

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Min Sun ◽  
Chao Liang ◽  
Hui Lin ◽  
Yuezhi Meng ◽  
Qunzhong Tang ◽  
...  
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Area Under The Curve ◽  
Density Lipoprotein ◽  
Hdl Cholesterol ◽  
Control Group ◽  
Apnea Hypopnea Index ◽  
Hypertensive Patients ◽  
Cholesterol Ratio ◽  
Obstructive Sleep

AbstractThis study aimed to investigate the correlation between monocyte to high-density lipoprotein cholesterol ratio (MHR) and obstructive sleep apnea (OSA) in patients with hypertension. A total of 246 hypertensive patients (67 controls, 65 mild, 51 moderate, and 63 severe OSA) were included. The relationship between MHR and OSA was analyzed. MHR correlated positively with apnea–hypopnea index (AHI), while negatively with mean SpO2 (P < 0.01). MHR was higher in OSA group than the control group (9.2 ± 2.6 vs. 10.8 ± 3.6, P < 0.001). Moreover, MHR in severe OSA group was the highest among all groups (9.2 ± 2.6, 10.2 ± 3.2, 10.4 ± 4.0, and 11.8 ± 3.4 in control, mild, moderate, and severe OSA group, respectively, P < 0.001). Logistic regression analysis demonstrated that MHR was an independent predictor of the presence of OSA (OR = 1.152, P < 0.01) and severe OSA (OR = 1.142, P < 0.01). Area under the curve of MHR was 0.634 (P < 0.05) and 0.660 (P < 0.05) for predicting OSA and severe OSA respectively in the ROC analysis. In conclusion, MHR increased with the severity of OSA. As a practical and cost-effective test, MHR was expected to be an available marker in evaluating OSA risk and severity in hypertensive patients.

scholarly journals Monocyte to HDL cholesterol ratio as a marker of the presence and severity of obstructive sleep apnea in hypertensive patients

2021 ◽  
Author(s):  
Min Sun ◽  
Chao Liang ◽  
Hui Lin ◽  
Yuezhi Meng ◽  
Qunzhong Tang ◽  
...  
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Area Under The Curve ◽  
Density Lipoprotein ◽  
Hdl Cholesterol ◽  
Control Group ◽  
Apnea Hypopnea Index ◽  
Hypertensive Patients ◽  
Cholesterol Ratio ◽  
Obstructive Sleep

Abstract This study aimed to investigate the correlation between monocyte to high-density lipoprotein cholesterol ratio (MHR) and obstructive sleep apnea (OSA) in patients with hypertension. A total of 246 hypertensive patients (67 controls, 65 mild, 51 moderate, and 63 severe OSA) were included. The relationship between MHR and OSA was analyzed. MHR correlated positively with apnea-hypopnea index (AHI), while negatively with mean SpO2 (P < 0.01). MHR was higher in OSA group than the control group (9.2 ± 2.6 vs. 10.8 ± 3.6, P < 0.001). Moreover, MHR in severe OSA group was the highest among all groups (9.2 ± 2.6, 10.2 ± 3.2, 10.4 ± 4.0, and 11.8 ± 3.4 in control, mild, moderate, and severe OSA group, respectively, P < 0.001). Logistic regression analysis demonstrated that MHR was an independent predictor of the presence of OSA (OR = 1.152, P < 0.01) and severe OSA (OR = 1.144, P < 0.01). Area under the curve of MHR was 0.634 (P < 0.05) and 0.660 (P < 0.05) for predicting OSA and severe OSA respectively in the ROC analysis. In conclusion, MHR increased with the severity of OSA. As a practical and cost-effective test, MHR was expected to be an available marker in evaluating OSA risk and severity in hypertensive patients.

scholarly journals Analyzing Neck Circumference as an Indicator of CPAP Treatment Response in Obstructive Sleep Apnea with Network Medicine

Diagnostics ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. 86
Author(s):  
Stefan Mihaicuta ◽  
Lucreţia Udrescu ◽  
Mihai Udrescu ◽  
Izabella-Anita Toth ◽  
Alexandru Topîrceanu ◽  
...  
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Treatment Response ◽  
Area Under The Curve ◽  
Positive Likelihood Ratio ◽  
Neck Circumference ◽  
Apnea Hypopnea Index ◽  
Anthropometric Measures ◽  
Cpap Treatment ◽  
Obstructive Sleep

We explored the relationship between obstructive sleep apnea (OSA) patients’ anthropometric measures and the CPAP treatment response. To that end, we processed three non-overlapping cohorts (D1, D2, D3) with 1046 patients from four sleep laboratories in Western Romania, including 145 subjects (D1) with one-night CPAP therapy. Using D1 data, we created a CPAP-response network of patients, and found neck circumference (NC) as the most significant qualitative indicator for apnea–hypopnea index (AHI) improvement. We also investigated a quantitative NC cutoff value for OSA screening on cohorts D2 (OSA-diagnosed) and D3 (control), using the area under the curve. As such, we confirmed the correlation between NC and AHI (ρ=0.35, p<0.001) and showed that 71% of diagnosed male subjects had bigger NC values than subjects with no OSA (area under the curve is 0.71, with 95% CI 0.63–0.79, p<0.001); the optimal NC cutoff is 41 cm, with a sensitivity of 0.8099, a specificity of 0.5185, positive predicted value (PPV) = 0.9588, negative predicted value (NPV) = 0.1647, and positive likelihood ratio (LR+) = 1.68. Our NC =41 cm threshold classified the D1 patients’ CPAP responses—measured as the difference in AHI prior to and after the one-night use of CPAP—with a sensitivity of 0.913 and a specificity of 0.859.

scholarly journals MON-034 Impact of Race and Obstructive Sleep Apnea on Glucose and Insulin Regulation in Women with PCOS

2020 ◽  
Vol 4 (Supplement_1) ◽  
Author(s):  
Karla A Temple ◽  
Babak Mokhlesi ◽  
Jason R Carter ◽  
Harry Whitmore ◽  
Eve Van Cauter ◽  
...  
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Area Under The Curve ◽  
Apnea Hypopnea Index ◽  
Oral Glucose ◽  
Insulin Metabolism ◽  
C Peptide ◽  
Obstructive Sleep ◽  
Glucose Challenge ◽  
The Impact

Abstract The prevalence of prediabetes and diabetes is substantially higher in PCOS women with obstructive sleep apnea (OSA) compared to PCOS women without OSA1,2,3. Prior studies, however, did not examine the complex interaction between race and OSA on metabolic function in PCOS. We sought to determine if the impact of OSA on glucose and insulin metabolism is affected by race. We studied non-Hispanic white (NHW) (n=53) and African-American (AA) (n=48) women with PCOS. Following an overnight polysomnogram (PSG), PCOS women (NHW without OSA n=40; NHW with OSA n=13; AA without OSA n=36; AA with OSA n=12) had a 2-h 75-g oral glucose tolerance test (OGTT) with blood sampling every 30 minutes for measurement of glucose, insulin, and C-peptide concentrations. OSA severity was measured by the Apnea-Hypopnea Index (AHI). Only women without OSA (AHI &lt; 5) or with moderate-to-severe OSA (AHI &gt; 15) were included in these analyses; women with mild OSA were excluded. Insulin secretion rates (ISR) during the OGTT were derived by deconvolution of C-peptide levels 4. Area under the curve (AUC) response to the glucose challenge was calculated using the trapezoidal method. BMI and age did not differ between races in PCOS women without OSA (BMI [kg/m2]: 36.3±1.2 vs. 37.2±1.1, p=0.58; Age [yr]: 27.7±0.8 vs. 27.2±0.8, p=0.65; for NHW and AA respectively), or in PCOS women with OSA (BMI [kg/m2]: 42.8±1.7 vs. 44.7±2.0, p=0.50; Age [yr]: 31.4±1.6 vs. 28.6±1.6, p=0.18; for NHW and AA respectively). OSA severity was similar in NHW and AA PCOS women without OSA (AHI: 1.5±0.2 vs 2.1±0.2, p=0.076), and PCOS women with OSA (AHI: 32.0±4.9 vs. 28.3±4.4, p=0.26). Higher glucose responses during the OGTT were observed in NHW PCOS women with OSA compared to both NHW (AUC: 18,965±648 vs. 15,797±371, p=0.0004) and AA (AUC: 18,965±648 vs. 15,801±497, p=0.0005) PCOS women without OSA. Glucose responses did not differ significantly between AA PCOS women with OSA and AA PCOS women without OSA (AUC: 17,104±965 vs. 15,801±497, p=0.15). Similarly, ISR was higher in NHW PCOS women with OSA compared to both NHW (AUC: 5,648±488 vs. 3,907±231, p=0.0006) and AA (AUC: 5,648±488 vs. 3,981±235, p=0.0011) PCOS women without OSA. ISR did not differ significantly between AA PCOS women with OSA and AA PCOS women without OSA (AUC: 4,827±461 vs. 3,981±235, p=0.09). CONCLUSIONS: OSA has a greater impact on glucose and ISR during an oral glucose challenge in NHW compared to AA women with PCOS. Future studies would benefit from including race when evaluating metabolic outcomes in women with PCOS. References: 1Fogel et al., J Clin Endocrinol Metab. 2001: 86:1175–1180. 2Kapsimalis et al., Sleep. 2002; 25:499–506. 3Kapsimalis et al., Sleep. 2002; 25:412–419. 4Polonsky et al., J Clin Invest. 1986 Jan; 77(1):98–105.

Evaluation of Obstructive Sleep Apnea in Prone Versus Nonprone Body Positioning With Polysomnography in Infants With Robin Sequence

2019 ◽  
Vol 57 (2) ◽  
pp. 141-147
Author(s):  
Hanna Hong ◽  
Choo Phei Wee ◽  
Karla Haynes ◽  
Mark Urata ◽  
Jeffrey Hammoudeh ◽  
...  
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Los Angeles ◽  
Body Position ◽  
Rank Test ◽  
Sleep Position ◽  
Apnea Hypopnea Index ◽  
Prone Positioning ◽  
Robin Sequence ◽  
Obstructive Sleep

Objective: Management of obstructive sleep apnea in infants with Robin sequence (RS) includes prone positioning during sleep, which conflicts with safe infant sleep data. We examined changes in polysomnography (PSG) parameters for prone versus nonprone body positions in these infants. Design: Pre–post interventional, nonblinded study. Participants: Infants with RS referred for PSG were recruited from craniofacial clinic and inpatient units at Children’s Hospital Los Angeles, a tertiary pediatric center. Fourteen infants were recruited, and 12 studies were completed on both body positions; 11 studies were used in the analysis. Interventions: The PSG was divided into nonprone and prone sleep, moving from their usual sleep position to the other position midway in the study. Main Outcome Measures: Data was collected in each position for obstructive apnea–hypopnea index (oAHI), central apnea index (CAI), sleep efficiency (SE), and arousal index (AI). Signed rank test was used to evaluate the change in body position. Results: All infants were term except 1, age 7 to 218 days (mean: 55 days; standard deviation: 58 days), and 8 (57%) of 14 were female. From nonprone to prone sleep position, the median oAHI (16.0-14.0), CAI (2.9-1.0), and AI (28.0-19.9) decreased ( P = .065); SE increased (67.4-85.2; P = .227). Conclusions: Prone positioning may benefit some infants with RS. However, even those with significant improvement in obstructive sleep apnea did not completely resolve their obstruction. The decision to use prone positioning as a therapy should be objectively evaluated in individual infants.

Improvement in Obstructive Sleep Apnea (OSA) in Super Morbidly Obese Patients After Bariatric Surgery

2020 ◽  
Vol 103 (8) ◽  
pp. 725-728
Keyword(s):  
Bariatric Surgery ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Lifestyle Modification ◽  
Apnea Hypopnea Index ◽  
Morbidly Obese ◽  
Obese Patients ◽  
Obstructive Sleep ◽  
Objective Evidence

Background: Lifestyle modification is the mainstay therapy for obese patients with obstructive sleep apnea (OSA). However, most of these patients are unable to lose the necessary weight, and bariatric surgery (BS) has been proven to be an effective modality in selected cases. Objective: To provide objective evidence that BS can improve OSA severity. Materials and Methods: A prospective study was conducted in super morbidly obese patients (body mass index [BMI] greater than 40 kg/m² or BMI greater than 35 kg/m² with uncontrolled comorbidities) scheduled for BS. Polysomnography (PSG) was performed for preoperative assessment and OSA was treated accordingly. After successful surgery, patients were invited to perform follow-up PSG at 3, 6, and 12 months. Results: Twenty-four patients with a mean age of 35.0±14.0 years were enrolled. After a mean follow-up period of 7.8±3.4 months, the mean BMI, Epworth sleepiness scale (ESS), and apnea-hypopnea index (AHI) significantly decreased from 51.6±8.7 to 38.2±6.8 kg/m² (p<0.001), from 8.7±5.9 to 4.7±3.5 (p=0.003), and from 87.6±38.9 to 28.5±21.5 events/hour (p<0.001), respectively. Conclusion: BS was shown to dramatically improve clinical and sleep parameters in super morbidly obese patients. Keywords: Morbid obesity, Bariatric surgery, Obstructive sleep apnea (OSA)

Sign in / Sign up

Export Citation Format

Share Document