408 Validation of claim based algorithms for sleep apnea using ICD codes

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A162-A162
Author(s):  
Rizwana Sultana ◽  
Elizabeth Lam ◽  
Enshuo Hsu ◽  
Erin Gurski ◽  
Gulshan Sharma
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Individual Performance ◽  
Care Utilization ◽  
Office Visits ◽  
Sleep Study ◽  
Diagnostic Codes ◽  
Obstructive Sleep ◽  
Icd 10 ◽  
Icd Codes

Abstract Introduction Obstructive sleep apnea (OSA) is a common condition characterized by repeated episodes of partial or complete obstruction of the respiratory passages during sleep. According to recent studies prevalence of obstructive sleep apnea ranges between 9–38%. OSA is associated with increased all-cause mortality particularly associated with cardiac diseases. In order to provide representation of larger population estimates, administrative data using ICD codes have been utilized. Accurate identification of sleep apnea is important for research related to health care utilization and health outcomes. Our aim is to validate an algorithm for identification of patients with obstructive sleep apnea using ICD 10 codes seen at UTMB. Methods Patient medical records were collected from University of Texas Medical Branch EHR system. We included patients who visited from 6/1/2015 to 5/31/2018 in pulmonary or primary care clinics who had any sleep disorder diagnostic codes (ICD-10: G47.30, G47.31, G47.33, G47.34, G47.36, G47.20, G47.10, G47.39, G47.8, G47.9, F51.13, F51.09, R06.89, J96.90, R40.0, F51.9, R06.83, R06.3, G47.63, G47.39, Z86.69). Two algorithms were created. First algorithm included patient with sleep diagnostic codes used at 2 separate office visits. Second algorithm included patients with sleep diagnostic codes and evidence of sleep study. The performance of most used codes was calculated individually. Results 1200 patients were identified with ICD codes used during two office visits. According to the first algorithm with only ICD codes 75% of patients had sleep apnea. Upon addition of evidence of sleep apnea with ICD codes the % of patients with sleep apnea increased to 95.44. Among most used ICD codes, G47.30 had 86.47% patients with sleep apnea according to first algorithm and 96.01% with second algorithm. The percentages for G47.33 was 80.86% and 96.4%, for G47.10, 78.05% and 87.67%, for R40.0 78.91% and 90.63% respectively. Conclusion In conclusion, claim based algorithms for sleep apnea diagnostic codes showed good test positive percentages overall, but algorithm with ICD 10 codes with sleep study performed better in identifying patients with sleep apnea than ICD-9-CM codes alone. Similarly, the individual performance of most used ICD codes was highly improved when evidence of sleep study was present. Support (if any):

419 STOP-Bang Score and History of Radiation Predicts Risk of Obstructive Sleep Apnea in Cancer Patients: A Machine Learning Study

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A166-A166
Author(s):  
Ankita Paul ◽  
Karen Wong ◽  
Anup Das ◽  
Diane Lim ◽  
Miranda Tan
Keyword(s):  
Machine Learning ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Cancer Patients ◽  
Prediction Accuracy ◽  
Screening Tools ◽  
Cancer Type ◽  
Sleep Study ◽  
Obstructive Sleep ◽  
History Of

Abstract Introduction Cancer patients are at an increased risk of moderate-to-severe obstructive sleep apnea (OSA). The STOP-Bang score is a commonly used screening questionnaire to assess risk of OSA in the general population. We hypothesize that cancer-relevant features, like radiation therapy (RT), may be used to determine the risk of OSA in cancer patients. Machine learning (ML) with non-parametric regression is applied to increase the prediction accuracy of OSA risk. Methods Ten features namely STOP-Bang score, history of RT to the head/neck/thorax, cancer type, cancer stage, metastasis, hypertension, diabetes, asthma, COPD, and chronic kidney disease were extracted from a database of cancer patients with a sleep study. The ML technique, K-Nearest-Neighbor (KNN), with a range of k values (5 to 20), was chosen because, unlike Logistic Regression (LR), KNN is not presumptive of data distribution and mapping function, and supports non-linear relationships among features. A correlation heatmap was computed to identify features having high correlation with OSA. Principal Component Analysis (PCA) was performed on the correlated features and then KNN was applied on the components to predict the risk of OSA. Receiver Operating Characteristic (ROC) - Area Under Curve (AUC) and Precision-Recall curves were computed to compare and validate performance for different test sets and majority class scenarios. Results In our cohort of 174 cancer patients, the accuracy in determining OSA among cancer patients using STOP-Bang score was 82.3% (LR) and 90.69% (KNN) but reduced to 89.9% in KNN using all 10 features mentioned above. PCA + KNN application using STOP-Bang score and RT as features, increased prediction accuracy to 94.1%. We validated our ML approach using a separate cohort of 20 cancer patients; the accuracies in OSA prediction were 85.57% (LR), 91.1% (KNN), and 92.8% (PCA + KNN). Conclusion STOP-Bang score and history of RT can be useful to predict risk of OSA in cancer patients with the PCA + KNN approach. This ML technique can refine screening tools to improve prediction accuracy of OSA in cancer patients. Larger studies investigating additional features using ML may improve OSA screening accuracy in various populations Support (if any):

scholarly journals Subjective and Objective Appraisal of Activity in Adults with Obstructive Sleep Apnea

2011 ◽  
Vol 2011 ◽  
pp. 1-6 ◽  
Author(s):  
Eileen R. Chasens ◽  
Susan M. Sereika ◽  
Martin P. Houze ◽  
Patrick J. Strollo
Keyword(s):  
Physical Activity ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Epworth Sleepiness Scale ◽  
Functional Outcomes ◽  
Apnea Hypopnea Index ◽  
Sleep Study ◽  
Obstructive Sleep ◽  
Subjective Sleepiness ◽  
Aging Adults

Objective.This study examined the association between obstructive sleep apnea (OSA), daytime sleepiness, functional activity, and objective physical activity.Setting.Subjects (N=37) being evaluated for OSA were recruited from a sleep clinic.Participants. The sample was balanced by gender (53% male), middle-aged, primarily White, and overweight or obese with a mean BMI of 33.98 (SD=7.35;median BMI=32.30). Over 40% reported subjective sleepiness (Epworth Sleepiness Scale (ESS) ≥10) and had OSA (78% with apnea + hypopnea index (AHI) ≥5/hr).Measurements.Evaluation included questionnaires to evaluate subjective sleepiness (Epworth Sleepiness Scale (ESS)) and functional outcomes (Functional Outcomes of Sleep Questionnaire (FOSQ)), an activity monitor, and an overnight sleep study to determine OSA severity.Results.Increased subjective sleepiness was significantly associated with lower scores on the FOSQ but not with average number of steps walked per day. A multiple regression analysis showed that higher AHI values were significantly associated with lower average number of steps walked per day after controlling patient's age, sex, and ESS.Conclusion.Subjective sleepiness was associated with perceived difficulty in activity but not with objectively measured activity. However, OSA severity was associated with decreased objective physical activity in aging adults.

Abstract P195: Lack of Association between Sleep Duration and ECG Arrhythmia Risk Measures: Chicago Area Sleep Study

Circulation ◽  
2013 ◽  
Vol 127 (suppl_12) ◽  
Author(s):  
Jason Ng ◽  
Phyllis C Zee ◽  
Jeffrey J Goldberger ◽  
Kristen L Knutson ◽  
Kiang Liu ◽  
...  
Keyword(s):  
Risk Factors ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Sleep Duration ◽  
Low Risk ◽  
Qtc Interval ◽  
Sleep Study ◽  
Chicago Area ◽  
Obstructive Sleep ◽  
Pr Interval

Introduction Sleep duration is significantly associated with cardiovascular disease risk factors such as hypertension, diabetes, and obesity in adults at low risk for obstructive sleep apnea. Although it is known that apnea increases the risk for sudden cardiac death, it is not known whether adults with short sleep duration independent of apnea have a higher risk for cardiac arrhythmias Hypothesis We tested the hypothesis that sleep duration in adults at low risk for obstructive sleep apnea would be associated with ECG measures that are known risk factors for ventricular arrhythmias. Methods The Chicago Area Sleep Study recruited 610 participants via commercially available telephone listings. Participants were screened using in-home apnea detection equipment (ApneaLinkTM) for one night to exclude subjects with apnea/hypopnea index ≥ 15. Participants wore wrist actigraphs for 7 days to objectively determine sleep duration. A 10-minute 12-lead ECG was recorded for each subject. Standard measures of heart rate, PR interval, and QTc interval were obtained along with markers of ventricular repolarization, Tpeak to Tend interval (Tpe) and spatial QRS-T angle. Signal-averaged ECG analysis was performed to measure filtered QRS duration (fQRSd), RMS voltage of terminal 40 ms (RMS), and duration of terminal QRS signals <40μV (LAS). Participants with atrial fibrillation, >20% ectopic beats and those using antihypertensive and sleep medications were excluded from analysis. The effect of sleep duration on the ECG parameters was estimated using a multiple linear regression model adjusting for demographics (sex, age, and race) and cardiovascular risk factors (BMI, hypertension, coronary heart disease, and diabetes). Results ECGs from a total of 504 participants (200 male, 48±8 years old) were analyzed. Mean sleep duration was 7±1 hrs, heart rate was 64±9 bpm, PR interval was 165±18 ms, and QTc interval was 424±23 ms. Mean Tpe interval was 83±14 ms and spatial QRS-T angle was 29±26 deg. The signal-averaged ECG measures of fQRSd, RMS, and LAS had mean values of 78±12 ms, 58±34 μV, and 24±9 ms, respectively. In an unadjusted model, there was a borderline association between sleep duration and QTc (β=0.004 ms/hr, SE=0.0023, p=0.08). However, that association was no longer significant following adjustment with demographics and cardiovascular risk factors. No other ECG measures were associated with sleep duration. Conclusions In a population at low risk of obstructive sleep apnea, ECG-based measures of cardiovascular risks were not associated with sleep duration. Previously reported associations between short sleep and cardiovascular events may not be arrhythmic in origin.

Abstract 14771: Obstructive Sleep Apnea is Associated With Cardiac Dysfunction in Children With Congenital Heart Disease

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Daniel Combs ◽  
Vanessa Fernandez ◽  
brent j barber ◽  
Wayne J Morgan ◽  
Chiu-Hsieh Hsu ◽  
...  
Keyword(s):  
Congenital Heart Disease ◽  
Obstructive Sleep Apnea ◽  
Heart Disease ◽  
Sleep Apnea ◽  
Right Ventricular ◽  
Cardiac Dysfunction ◽  
Congenital Heart ◽  
Left Ventricular ◽  
Sleep Study ◽  
Obstructive Sleep

Introduction: Obstructive sleep apnea (OSA) is associated with cardiac dysfunction in children without congenital heart disease (CHD). Children with CHD are at increased risk for OSA and may be susceptible to further cardiovascular consequences due to OSA but the extent and nature of such cardiovascular effects of OSA are unknown. Methods: Children (6-17 years old) with corrected CHD without current cyanosis or Down syndrome were recruited from pediatric cardiology clinic. Home sleep tests were done to determine the presence and severity of OSA. OSA was defined as an obstructive apnea hypopnea index (oAHI) ≥1. Mild OSA was defined as an oAHI of ≥1 to <5 and moderate OSA was defined as an oAHI of ≥5 to <10. Standard clinically indicated echocardiograms were performed in clinic. Echocardiographic findings were compared between children with CHD with and without comorbid OSA using t-tests, Wilcoxon-sign rank tests as well as linear or logistic regression as appropriate. Results: Thirty-two children had sleep study and echocardiographic data available. OSA was present in 18 children (56%). OSA was mild in 89% and moderate in 11% of cases. There were no significant differences in age, body mass index, CHD severity, gender or ethnicity between children with and without OSA. Children with OSA had larger height-indexed right ventricular end-diastolic diameter (RVDi) compared to those without OSA (median 1.35, 95% CI 1.09, 1.56 vs. 1.21, 95% CI 1.01, 1.57; p=0.04). Children with moderate OSA had a reduced left ventricular shortening fraction compared to both those with mild OSA and no OSA (30.0 ± 6.1% vs. 38.7 ± 4.4%; p=0.009 and 39.2 ± 3.6%; p=0.007, respectively). Children with moderate OSA had increased left ventricular end-systolic diameter compared to those with mild OSA and no OSA (3.4 ± 0.4 cm vs. 2.5 ± 0.4; p=0.007 and 2.4 ± 0.5; p=0.001, respectively). Children with an RVDi above the median were seven times more likely to have OSA than those with an RVDi below the median (odds ratio 6.9.; 95% CI 1.3, 35; p=0.02). Conclusions: OSA is associated with changes in cardiac morphology and reduced contractility in children with CHD. Additionally, the presence of right ventricular dilation may suggest the need for OSA evaluation in children with CHD.

scholarly journals Associations of Obstructive Sleep Apnea, Obestatin, Leptin, and Ghrelin with Gastroesophageal Reflux

2021 ◽  
Vol 10 (21) ◽  
pp. 5195
Author(s):  
Piotr Pardak ◽  
Rafał Filip ◽  
Jarosław Woliński ◽  
Maciej Krzaczek
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Gastroesophageal Reflux ◽  
Ph Monitoring ◽  
Sleep Study ◽  
Esophageal Ph ◽  
Obstructive Sleep ◽  
The Relationship ◽  
Gerd Symptoms ◽  
Severe Sleep Apnea

Gastroesophageal reflux disease (GERD) is commonly observed in patients with obstructive sleep apnea (OSA). Hormonal disorders observed in OSA may be relevant in the development of GERD. The aim of the study was to assess the correlations between ghrelin, obestatin, leptin, and the intensity of GERD in patients with OSA. The study included 58 patients hospitalized due to clinical suspicion of sleep disorders during sleep. All patients underwent a sleep study, and blood samples were collected overnight for hormonal tests. Survey data concerning symptoms of GERD, gastroscopy, and esophageal pH monitoring results were included in the study. In patients with OSA, GERD was twice as common when compared to the group without OSA. Among subjects with severe sleep apnea (AHI > 30; n = 31; 53%), we observed lower ghrelin levels, especially in the second half of the night and in the morning (p5.00 = 0.0207; p7.00 = 0.0344); the presence of OSA had no effect on obestatin and leptin levels. No significant differences in hormonal levels were observed between the groups depending on the diagnosis of GERD. However, correlations of ghrelin levels with the severity of esophagitis, leptin and ghrelin levels with the severity of GERD symptoms, and leptin levels with lower esophageal pH were found. GERD is more frequent among patients with OSA. In both GERD and OSA, deviations were observed in the levels of ghrelin and leptin. However, our analysis demonstrates that the relationship between OSA and GERD does not result from these disorders.

scholarly journals Detection of obstructive sleep apnea using Belun Sleep Platform wearable with neural network-based algorithm and its combined use with STOP-Bang questionnaire

PLoS ONE ◽  
2021 ◽  
Vol 16 (10) ◽  
pp. e0258040
Author(s):  
Eric Yeh ◽  
Eileen Wong ◽  
Chih-Wei Tsai ◽  
Wenbo Gu ◽  
Pai-Lien Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Physiological Data ◽  
Apnea Hypopnea Index ◽  
Clinical Practices ◽  
Sleep Study ◽  
Link Type ◽  
Obstructive Sleep ◽  
Sensitivity Specificity

Many wearables allow physiological data acquisition in sleep and enable clinicians to assess sleep outside of sleep labs. Belun Sleep Platform (BSP) is a novel neural network-based home sleep apnea testing system utilizing a wearable ring device to detect obstructive sleep apnea (OSA). The objective of the study is to assess the performance of BSP for the evaluation of OSA. Subjects who take heart rate-affecting medications and those with non-arrhythmic comorbidities were included in this cohort. Polysomnography (PSG) studies were performed simultaneously with the Belun Ring in individuals who were referred to the sleep lab for an overnight sleep study. The sleep studies were manually scored using the American Academy of Sleep Medicine Scoring Manual (version 2.4) with 4% desaturation hypopnea criteria. A total of 78 subjects were recruited. Of these, 45% had AHI < 5; 18% had AHI 5–15; 19% had AHI 15–30; 18% had AHI ≥ 30. The Belun apnea-hypopnea index (bAHI) correlated well with the PSG-AHI (r = 0.888, P < 0.001). The Belun total sleep time (bTST) and PSG-TST had a high correlation coefficient (r = 0.967, P < 0.001). The accuracy, sensitivity, specificity in categorizing AHI ≥ 15 were 0.808 [95% CI, 0.703–0.888], 0.931 [95% CI, 0.772–0.992], and 0.735 [95% CI, 0.589–0.850], respectively. The use of beta-blocker/calcium-receptor antagonist and the presence of comorbidities did not negatively affect the sensitivity and specificity of BSP in predicting OSA. A diagnostic algorithm combining STOP-Bang cutoff of 5 and bAHI cutoff of 15 events/h demonstrated an accuracy, sensitivity, specificity of 0.938 [95% CI, 0.828–0.987], 0.944 [95% CI, 0.727–0.999], and 0.933 [95% CI, 0.779–0.992], respectively, for the diagnosis of moderate to severe OSA. BSP is a promising testing tool for OSA assessment and can potentially be incorporated into clinical practices for the identification of OSA. Trial registration: ClinicalTrial.org NCT03997916 https://clinicaltrials.gov/ct2/show/NCT03997916?term=belun+ring&draw=2&rank=1

scholarly journals Sleep Study Interpretation in Obstructive Sleep Apnea

2019 ◽  
Vol 10 (2) ◽  
pp. 42-46
Author(s):  
Pralhad Prabhudesai ◽  
Milan Patankar ◽  
Anand Vardhan
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Sleep Study ◽  
Obstructive Sleep

scholarly journals TLRs and RAGE are elevated in carotid plaques from patients with moderate-to-severe obstructive sleep apnea syndrome

2020 ◽  
Vol 24 (4) ◽  
pp. 1573-1580 ◽  
Author(s):  
Wioletta Olejarz ◽  
Alicja Głuszko ◽  
Agata Cyran ◽  
Katarzyna Bednarek-Rajewska ◽  
Robert Proczka ◽  
...  
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Significant Role ◽  
Sleep Apnea Syndrome ◽  
Vascular Endothelial ◽  
Sleep Study ◽  
Carotid Plaques ◽  
Obstructive Sleep ◽  
Glycation End Products ◽  
Rage Expression

Abstract Background There is growing evidence that obstructive sleep apnea (OSA) promotes vascular endothelial dysfunction and atherogenesis. Pathways that mediate this pathology may include Toll-like receptors (TLRs) and receptor for advanced glycation end products (RAGE) which play a significant role in proinflammatory processes. The aim of this study was to measure the expression of the above-mentioned receptors in relation to OSA severity in carotid plaques obtained during open endarterectomy. Methods This prospective study included patients with a sleep study prior to surgery and a plaque specimen obtained during standard open endarterectomy. Immunohistochemistry of TLR2, TLR4, TLR7, TLR9, RAGE, HMGB1, and NF-κB was performed on atherosclerotic plaques from carotid arteries of patients with and without OSA. Results There were 46 patients (22 women, mean age 73.2 ± 1.3 years): 14 control patients, 13 with mild, 11 with moderate, and 8 with severe OSA. The expression of all TLRs and RAGE increased proportionately with increasing OSA severity. The largest differences between patients with severe OSA and no OSA were found for TLR2 (2.88 ± 0.35 vs. 1.27 ± 0.47, p < 0.001), TLR4 (2.88 ± 0.35 vs. 1.64 ± 0.5, p < 0.001), TLR9 (2.38 ± 0.52 vs. 1.45 ± 0.52, p < 0.01), and RAGE (2.5 ± 0.53 vs. 1.82 ± 0.6, p < 0.05). Conclusion TLR2, TLR4, TLR9, and RAGE expression was significantly increased in carotid plaques of patients with moderate-to-severe OSA when compared with control patients with no OSA and those with mild OSA. TLR and RAGE-mediated pathways may play a significant role in OSA-dependent atherogenesis.

scholarly journals 0577 Cluster Analysis for the Association Between Obstructive Sleep Apnea Phenotypes: A Population-Based Longitudinal Study

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A221-A221
Author(s):  
P F Tempaku ◽  
L O Silva ◽  
T M Guimaraes ◽  
T A Vidigal ◽  
V D’Almeida ◽  
...  
Keyword(s):  
Cluster Analysis ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Latent Class ◽  
Cluster Solution ◽  
Optimal Care ◽  
Sleep Study ◽  
Disturbed Sleep ◽  
Obstructive Sleep

Abstract Introduction The identification of subgroups of obstructive sleep apnea (OSA) is critical to understand disease causality and ultimately develop optimal care strategies customized for each subgroup. In this sense, we aimed to perform a cluster analysis to identify subgroups of individuals with OSA based on clinical parameters. Furthermore, we aimed to analyze whether subgroups remain after 8 years. Methods We used data derived from the Sao Paulo Epidemiologic Sleep Study (EPISONO) cohort, which was followed over 8 years. All individuals underwent polysomnography, answered questionnaires and had their blood collected for biochemical exams. OSA was defined according to an AHI equal or greater than 15 events per hour. Cluster analysis was performed using latent class analysis (LCA). Results Of the 1,042 individuals in the EPISONO baseline cohort, 68.3% accepted to participate in the follow-up study (n=712). We were able to replicate the OSA 3-cluster solution observed in previous studies: disturbed sleep, minimally symptomatic and excessively sleepy in both baseline (35.5%, 45.4% and 19.1%, respectively) and follow-up studies (41.9%, 43.4% and 14.8%, respectively). 44.8% of the participants migrated clusters between the two evaluations and the factor associated with this was a greater delta-AHI (B=-0.033, df=1, p=0.003). The optimal cluster solution for our sample based on Bayesian information criterion (BIC) was 2 clusters for baseline (disturbed sleep and excessively sleepy) and 3 clusters for follow-up (disturbed sleep, minimally symptomatic and excessively sleepy). Conclusion The results found replicate and confirm previously identified clinical clusters in OSA even in a longitudinal analysis. Support This work was supported by grants from AFIP, FAPESP and CAPES.

Sign in / Sign up

Export Citation Format

Share Document