Search

Introduction The impact of not treating OSA identified using AASM standards (hypopneas scored using a minimum 3% O2 desaturation or arousal), but misclassified by CMS standards (hypopneas scored only if minimum 4% O2 desaturation) remains unclear. This analysis determined the ~5 year incident hypertension rates using the new 2018 ACC/AHA blood pressure (BP) guidelines in these individuals. Methods Data were analyzed from all Sleep Heart Health Study exam 2 study participants (N=1219) who were normotensive (BP≤120/80) at exam 1. The apnea hypopnea index (AHI) at exam 1 was classified into 4 categories of OSA severity: 120/80), Stage 1 (>130/80) and Stage 2 (>140/90) to determine incidence rates at exam 2. Results Five year follow-up data were available for 476 participants classified as having OSA (AHI ≥5) by AASM criteria, but not by CMS standards at exam 1. Incident hypertension rates in these misclassified participants for ACC/AHA defined BP categories were 15% (Elevated BP), 15% (Stage 1) and 6% (Stage 2). 4% of normotensive participants used hypertensive medications. Overall incidence rate of at least an elevated BP was 40% (191/476) in those with OSA defined using AASM, but not by CMS criteria and 17% (191/1219) of the overall population at risk. In comparison to those with incident hypertension and OSA identified by CMS standards, BMI (27.7 vs 30.1 kg/m2, p Conclusion Use of the CMS hypopnea definition as a component of the AHI resulted in the failure to identify a significant number of individuals with OSA who eventually developed hypertension and could have benefited from earlier diagnosis and treatment. Support HL53938

Introduction Despite an appreciable rise in sleep wellness and sleep medicine A.I. research publications, public data corpuses, institutional support, and health A.I. research funding opportunities, the availability of controlled-retrospective, hybrid-retrospective-prospective, and prospective-RCT quality clinical validation study evidence is limited with respect to their potential clinical impact. Furthermore, only a few practical examples of A.I. technologies are validated, in use today clinically, and widely adopted, to assist in sleep diagnoses and treatment. In this study, we contribute to this growing body of clinical A.I. validation evidence and experimental design methodologies with an interoperable A.I. scoring engine in Adult and Pediatric populations. Methods Stratified random sampling with proportionate allocation was applied to a database of N>10,000 retrospective diagnostic clinical polysomnography (PSG), selected by evidence grading standards, with controls applied for OSA severity, diagnoses; sleep, psychiatric, neurologic, neurodevelopmental, cardiac, pulmonary, metabolic disorders, medications; benzodiazepines, antidepressants, stimulants, opiates, sleep aids, demographic groups of interest; sex, adult age, pediatric age, BMI, weight, height, and patient-reported sleepiness, to establish representative N=100 Adult and N=100 Pediatric samples. Double Blinded scoring was prospectively collected for each sample by 3 experienced RPSGT certified sleep technologists randomized from a pool of 9 scorers. Sensitivity (PA), Specificity (NA), Accuracy (OA), Kappa (K), and 95% Bootstrap CI’s are presented for sleep stages, OSA/CSA, hypopnea 3%/4%, arousals, limb movements, Cheyenne-Stokes respiration, periodic breathing, atrial fibrillation, and other events, and normative, mild, moderate, and severe OSA categories for global-AHI and REM-AHI. Results for Sleep Staging and OSA Severity Diagnostic Accuracy are summarized. Results A.I. scoring performance meet but in most cases exceeded initial clinical validation study (N=72 Adults, 2017) PA, NA, OA, K point-estimates and confidence-interval results for the 26 event types and 8 AHI-categories evaluated. The Adult sample showed 87%/94% Sensitivity/Specificity across all stages (Wake/N1/N2/N3/REM) and 94%/96% Sensitivity/Specificity for AHI>=15. The Pediatric sample showed 87%/93% Sensitivity/Specificity staging, 89%/98% Sensitivity/Specificity AHI>=15. Observed Accuracy was >90% for Adults and Pediatrics all 26 events and 7 AHI-categories analyzed, except REM-AHI>=5 (85%/82% Adults/Pediatrics). Conclusion We provide clinical validation evidence that demonstrates interoperable A.I. scoring performance in representative Adult and Pediatric patient clinical PSG samples when compared to prospective, double-blind scoring panel. Support (if any)

Introduction New sensor technologies are entering sleep testing at a rapid pace; Neteera™ developed a novel sensor and algorithm for sleep apnea detection utilizing a contact-free, radar-based sensor system. The system utilizes a high-frequency, low-power, directional micro-radar which operates at ~120GHz and a sampling rate of 2500Hz as well as algorithms which are able to detect both pulse and respiratory activity of subjects during sleep. Methods Adult subjects undergoing diagnostic PSG for clinical purposes were simultaneously assessed with the novel micro-radar system with sensors under the mattress. Disordered breathing events (DBEs) were scored from the PSG using AASM scoring guidelines and were compared with those detected by the micro-radar sensor. Test data were grouped into three sets: 1. Single under mattress sensor; 2. Two under mattress sensors on each side of the bed (to improve signal capture); 3. After software optimization. The micro-radar sensor detected DBEs but software to describe the type of DBEs (obstructive apnea/central apnea/hypopnea) is still under development. Detection rate of DBEs was compared between the two methodologies and the development sets. Results n=22 (12 F, 10 M), Age=50.8±12.4 years, BMI=35.32±7.37 kg/m2. Diagnostic PSG AHI: 19.7±29.4/hr, T90=15.8±25.7%. Percent DBEs missed by the micro-radar sensor: 1st set=14.6±10.6%; 2nd set=9.4±8.3%; 3rd set=1.2±2.6%. Number of DBEs assessed for each set was 646, 1144, 125 events, respectively. With each successive set, the detection rate improved. Conclusion A novel micro-radar, non-contact sensor technology can be used to detect DBEs during sleep. Detection rate improved with utilization of two sensors per bed and software optimization. Future software development is expected to improve detection rate and facilitate breathing event classification into obstructive apneas/central apneas/hypopneas. Support None.

Introduction Sleep Apnea Syndrome (SAS) is largely underdiagnosed due to the cost and availability of Polysomnography (PSG). We aimed at evaluating the diagnosis of SAS with the WITHINGS Sleep Apnea Detector (SAD), a non-intrusive pressure and sound sensor placed under the mattress. Methods 118 patients (67 F, 49 years, BMI 33kg/m²) suspected of SAS had an in-laboratory PSG together with Sleep Apnea Detector. From the pressure signal, Sleep Apnea Detector derives respiratory and cardiac signals and movements. From the microphone, snoring and snorting are detected. These features are used to detect sleep periods with a Random Forest classifier and apnea and hypopnea events with a Convolutional Neural Network. The Total Sleep Time (TST) and Apnea Hypopnea Index (AHI) deduced (TSTsad, AHIsad) are compared with the PSG results scored according to AASM rules (TSTpsg, AHIpsg). AHI and TST were compared using bias and Mean Absolute Error (MAE). Sensitivity, specificity, likelihood ratios (LR) and AUROC were calculated for AHI thresholds of 15 and 30/hr. Results The average (SD) TSTpsg was 367 (61) minutes. Sleep Apnea Detector overestimated TST by 25 minutes, 7.0% of the average duration in the sample. The precision is acceptable, with a MAE=53 minutes. Average AHIpsg was 32.5 (30.1) and AHIsad 32.8 (29.9). The bias was 0.3 (95% CI [-2.7, 3.3]), MAE=10.3. The sensitivity (Se15) and specificity (Sp15) and their 95% confidence intervals were Se15=88.0% [79.0, 94.1] and Sp15=88.6% [73.3, 96.8]. Positive and negative LR were respectively LR+15=7.70 and LR-15=0.136. AUROC15=0.926. At the 30 threshold, Se30=86.0% [73.3, 94.2] and Sp30=91.2% [81.8, 96.7]. Positive and negative LR were LR+30=9.75 and LR-30=0.153. AUROC30=0.954. Conclusion Sleep Apnea Detector has excellent sensitivity and specificity, low bias and good precision. Thus it can be used as an unattended SAS screening device in patients likely to suffer from SAS. Support WITHINGS