Dataset Information

Enhancing Obstructive Sleep Apnea Diagnosis With Screening Through Disease Phenotypes: Algorithm Development and Validation.

ABSTRACT:

Background

The American Academy of Sleep Medicine guidelines suggest that clinical prediction algorithms can be used in patients with obstructive sleep apnea (OSA) without replacing polysomnography, which is the gold standard.

Objective

This study aims to develop a clinical decision support system for OSA diagnosis according to its standard definition (apnea-hypopnea index plus symptoms), identifying individuals with high pretest probability based on risk and diagnostic factors.

Methods

A total of 47 predictive variables were extracted from a cohort of patients who underwent polysomnography. A total of 14 variables that were univariately significant were then used to compute the distance between patients with OSA, defining a hierarchical clustering structure from which patient phenotypes were derived and described. Affinity from individuals at risk of OSA phenotypes was later computed, and cluster membership was used as an additional predictor in a Bayesian network classifier (model B).

Results

A total of 318 patients at risk were included, of whom 207 (65.1%) individuals were diagnosed with OSA (111, 53.6% with mild; 50, 24.2% with moderate; and 46, 22.2% with severe). On the basis of predictive variables, 3 phenotypes were defined (74/207, 35.7% low; 104/207, 50.2% medium; and 29/207, 14.1% high), with an increasing prevalence of symptoms and comorbidities, the latter describing older and obese patients, and a substantial increase in some comorbidities, suggesting their beneficial use as combined predictors (median apnea-hypopnea indices of 10, 14, and 31, respectively). Cross-validation results demonstrated that the inclusion of OSA phenotypes as an adjusting predictor in a Bayesian classifier improved screening specificity (26%, 95% CI 24-29, to 38%, 95% CI 35-40) while maintaining a high sensitivity (93%, 95% CI 91-95), with model B doubling the diagnostic model effectiveness (diagnostic odds ratio of 8.14).

Conclusions

Defined OSA phenotypes are a sensitive tool that enhances our understanding of the disease and allows the derivation of a predictive algorithm that can clearly outperform symptom-based guideline recommendations as a rule-out approach for screening.

SUBMITTER: Ferreira-Santos D

PROVIDER: S-EPMC8277326 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Rationale: Obstructive sleep apnea (OSA) is common in pregnancy and associated with maternal and fetal complications. Early detection of OSA may have important implications for maternal-fetal well-being. A screening tool combining several methods of assessment may better predict OSA among pregnant women compared with tools that rely solely on self-reported information.Objectives: To develop a screening tool combining subjective and objective measures to predict OSA in pregnant women.Methods: This study is a secondary analysis using data collected from a completed cohort of pregnant women (n = 121 during the first and n = 87 during the third trimester). Participants underwent full polysomnography and completed the Multivariable Apnea Prediction Questionnaire. The Obstructive Sleep Apnea/Hypopnea Syndrome Score and Facco apnea predictive model were obtained. Logistic regression analysis and area under the curve (AUC) were used to identify models predicting OSA risk.Results: Participants' mean age was 27.4 ± 7.0 years. The prevalence of OSA during the first and third trimester was 10.7% and 24.1%, respectively. The final model predicting OSA risk consisted of body mass index, age, and presence of tongue enlargement. During the first trimester, the AUC was 0.86 (95% confidence interval [CI], 0.76-0.96). During the third trimester, the AUC was 0.87 (95% CI, 0.77-0.96). When the first-trimester data were used to predict third-trimester OSA risk, the AUC was 0.87 (95% CI, 0.77-0.97). This model had high sensitivity and specificity when used during both trimesters. The negative posttest probabilities (probability of OSA given a negative test result) ranged from 0.03 to 0.07.Conclusions: A new model consisting of body mass index, age, and presence of tongue enlargement provided accurate screening of OSA in pregnant women, particularly African-Americans. This tool can be easily and rapidly administered in busy clinical practices without depending on patients' awareness of experiencing apnea symptoms.

Project description:ObjectivesObstructive sleep apnea (OSA) is a common but largely underdiagnosed condition. This study aimed to test the hypothesis that the oxygen desaturation index (ODI) obtained using a wireless high-resolution oximeter with a built-in accelerometer linked to a smartphone with automated cloud analysis, Overnight Digital Monitoring (ODM), is a reliable method for the diagnosis of OSA.MethodsConsecutive patients referred to the sleep laboratory with suspected OSA underwent in-laboratory polysomnography (PSG) and simultaneous ODM. The PSG apnea-hypopnea index (AHI) was analyzed using the criteria recommended and accepted by the American Academy of Sleep Medicine (AASM) for the definition of hypopnea: arousal or ≥3% O2 desaturation (PSG-AHI3%) and ≥4% O2 desaturation (PSG-AHI4%), respectively. The results of PSG and ODM were compared by drawing parallels between the PSG-AHI3% and PSG-AHI4% with ODM-ODI3% and ODM-ODI4%, respectively. Bland-Altman plots, intraclass correlation, receiver operating characteristics (ROC) and area under the curve (AUC) analyses were conducted for statistical evaluation. ClinicalTrial.gov: NCT03526133.ResultsThis study included 304 participants (men: 55%; age: 55±14 years; body mass index: 30.9±5.7 kg/m2; PSG-AHI3%: 35.3±30.1/h, ODM-ODI3%: 30.3±25.9/h). The variability in the AASM scoring bias (PSG-AHI3% vs PSG-AHI4%) was significantly higher than that for PSG-AHI3% vs ODM-ODI3% (3%) and PSG-AHI4% vs ODM-ODI4% (4%) (9.7, 5.0, and 2.9/h, respectively; p<0.001). The limits of agreement (2±SD, derived from the Bland-Altman plot) of AASM scoring variability were also within the same range for (PSG vs ODM) 3% and 4% variability: 18.9, 21.6, and 16.5/h, respectively. The intraclass correlation/AUC for AASM scoring variability and PSG vs ODM 3% or 4% variability were also within the same range (0.944/0.977 and 0.953/0.955 or 0.971/0.964, respectively).ConclusionOur results showed that ODM is a simple and accurate method for the diagnosis of OSA.

Project description:IntroductionDiagnosis and treatment of obstructive sleep apnea (OSA) in children is often delayed due to the high prevalence and limited physician and sleep testing resources. As a result, children may be referred to multiple specialties, such as pediatric sleep medicine and pediatric otolaryngology, resulting in long waitlists.MethodWe used data from our pediatric OSA clinic to identify predictors of tonsillectomy and/or adenoidectomy (AT). Before being seen in the clinic, parents completed the Pediatric Sleep Questionnaire (PSQ) and screening questionnaires for restless leg syndrome (RLS), nasal rhinitis, and gastroesophageal reflux disease (GERD). Tonsil size data were obtained from patient charts and graded using the Brodsky-five grade scale. Children completed an overnight oximetry study before being seen in the clinic, and a McGill oximetry score (MOS) was assigned based on the number and depth of oxygen desaturations. Logistic regression, controlling for otolaryngology physician, was used to identify significant predictors of AT. Three triage algorithms were subsequently generated based on the univariate and multivariate results to predict AT.ResultsFrom the OSA cohort, there were 469 eligible children (47% female, mean age = 8.19 years, SD = 3.59), with 89% of children reported snoring. Significant predictors of AT in univariate analysis included tonsil size and four PSQ questions, (1) struggles to breathe at night, (2) apneas, (3) daytime mouth breathing, and (4) AM dry mouth. The first triage algorithm, only using the four PSQ questions, had an odds ratio (OR) of 4.02 for predicting AT (sensitivity = 0.28, specificity = 0.91). Using only tonsil size, the second algorithm had an OR to predict AT of 9.11 (sensitivity = 0.72, specificity = 0.78). The third algorithm, where MOS was used to stratify risk for AT among those children with 2+ tonsils, had the same OR, sensitivity, and specificity as the tonsil-only algorithm.ConclusionTonsil size was the strongest predictor of AT, while oximetry helped stratify individual risk for AT. We recommend that referral letters for snoring children include graded tonsil size to aid in the triage based on our findings. Children with 2+ tonsil sizes should be triaged to otolaryngology, while the remainder should be referred to a pediatric sleep specialist.

Project description:Study objectivesWe investigated the diagnostic accuracy for the identification of obstructive sleep apnea (OSA) and its severity of a noninvasive technology based on image processing (SleepWise).MethodsThis is an observational, prospective study to evaluate the degree of agreement between polysomnography (PSG) and SleepWise. We recruited 56 consecutive subjects with suspected OSA who were referred as outpatients to the Sleep Unit of the Hospital Universitari Germans Trias i Pujol (HUGTiP) from January 2013 to January 2014. All patients underwent laboratory PSG and image processing with SleepWise simultaneously the same night. Both PSG and SleepWise analyses were carried independently and blindly.ResultsWe analyzed 50 of the 56 patients recruited. OSA was diagnosed through PSG in a total of 44 patients (88%) with a median apnea-hypopnea index (AHI) of 25.35 (24.9). According to SleepWise, 45 patients (90%) met the criteria for a diagnosis of OSA, with a median AHI of 22.8 (22.03). An analysis of the ability of PSG and SleepWise to classify patients by severity on the basis of their AHI shows that the two diagnostic systems distribute the different groups similarly. According to PSG, 23 patients (46%) had a diagnosis of severe OSA, 11 patients (22%) moderate OSA, and 10 patients (20%) mild OSA. According to SleepWise, 20, 13, and 12 patients (40%, 26%, and 24%, respectively) had a diagnosis of severe, moderate, and mild OSA respectively. For OSA diagnosis, SleepWise was found to have sensitivity of 100% and specificity of 83% in relation to PSG. The positive predictive value was 97% and the negative predictive value was 100%. The Bland-Altman plot comparing the mean AHI values obtained through PSG and SleepWise shows very good agreement between the two diagnostic techniques, with a bias of -3.85, a standard error of 12.18, and a confidence interval of -0.39 to -7.31.ConclusionsSleepWise was reasonably accurate for noninvasive and automatic diagnosis of OSA in outpatients. SleepWise determined the severity of OSA with high reliability. The current study including simultaneous laboratory PSG and SleepWise processing image is proposed as a reasonable validation standard.

Project description:BACKGROUND:Obstructive sleep apnea syndrome (OSAS) is common in adults. People with OSAS have a higher risk of experiencing traffic accidents and occupational injuries (OIs). We aimed to clarify the diagnostic performance of a three-channel screening device (ApneaLinkTM) compared with the gold standard of full-night attended polysomnography (PSG) among hospital outpatients not referred for sleep-related symptoms. Furthermore, we aimed to determine whether manual revision of the ApneaLinkTM autoscore enhanced diagnostic performance. METHODS:We investigated 68 patients with OI and 44 without OI recruited from the University Hospital Basel emergency room, using a cross-sectional study design. Participating patients spent one night at home with ApneaLinkTM and within 2 weeks slept for one night at the sleep laboratory. We reanalyzed all ApneaLinkTM data after manual revision. RESULTS:We identified significant correlations between the ApneaLinkTM apnea-hypopnea index (AHI) autoscore and the AHI derived by PSG (r = 0.525; p <0.001) and between the ApneaLinkTM oxygen desaturation index (ODI) autoscore and that derived by PSG (r = 0.722; p <0.001). The ApneaLinkTM autoscore showed a sensitivity and specificity of 82% when comparing AHI ≥5 with the cutoff for AHI and/or ODI ≥15 from PSG. In Bland Altman plots the mean difference between ApneaLinkTM AHI autoscore and PSG was 2.75 with SD ± 8.80 (β = 0.034), and between ApneaLinkTM AHI revised score and PSG -1.50 with SD ± 9.28 (β = 0.060). CONCLUSIONS:The ApneaLinkTM autoscore demonstrated good sensitivity and specificity compared with the gold standard (full-night attended PSG). However, Bland Altman plots revealed substantial fluctuations between PSG and ApneaLinkTM AHI autoscore respectively manually revised score. This spread for the AHI from a clinical perspective is large, and therefore the results have to be interpreted with caution. Furthermore, our findings suggest that there is no clinical benefit in manually revising the ApneaLinkTM autoscore.