Automatic identification of sleep and wakefulness using single-channel EEG and respiratory polygraphy signals for the diagnosis of obstructive sleep apnea.

Polysomnography (PSG) is necessary for the accurate estimation of total sleep time (TST) and the calculation of the apnea-hypopnea index (AHI). In type III home sleep apnea testing (HSAT), TST is overestimated because of the lack of electrophysiological sleep recordings. The aim of this study was to evaluate the accuracy and reliability of a novel automated sleep/wake scoring algorithm combining a single electroencephalogram (EEG) channel with actimetry and HSAT signals. The study included 160 patients investigated by PSG for suspected obstructive sleep apnea (OSA). Each PSG was recorded and scored manually using American Academy of Sleep Medicine (AASM) rules. The automatic sleep/wake-scoring algorithm was based on a single-channel EEG (FP2-A1) and the variability analysis of HSAT signals (airflow, snoring, actimetry, light and respiratory inductive plethysmography). Optimal detection thresholds were derived for each signal using a training set. Automatic and manual scorings were then compared epoch by epoch considering two states (sleep and wake). Cohen's kappa coefficient between the manual scoring and the proposed automatic algorithm was substantial, 0.74 ± 0.18, in separating wakefulness and sleep. The sensitivity, specificity and the positive and negative predictive values for the detection of wakefulness were 76.51% ± 21.67%, 95.48% ± 5.27%, 81.84% ± 15.42% and 93.85% ± 6.23% respectively. Compared with HSAT signals alone, AHI increased by 22.12% and 27 patients changed categories of OSA severity with the automatic sleep/wake-scoring algorithm. Automatic sleep/wake detection using a single-channel EEG combined with HSAT signals was a reliable method for TST estimation and improved AHI calculation compared with HSAT.

Feasibility of Type 3 Polygraphy for Evaluating Leak Determinants in CPAP-Treated OSA Patients: A Step Toward Personalized Leak Management.

BACKGROUND: Unintentional leaks (ULs) are frequent adverse effects in CPAP-treated patients. We previously published a novel methodology for analyzing the determinants of UL using polysomnography. We now propose a simplified recording system using a type 3 polygraphic device (Somnolter; Nomics S.A.). RESEARCH QUESTION: (1) To describe individual UL determinants provided by the Somnolter software in automatic-CPAP-treated OSA patients; (2) To subsequently describe the clinical consensus of four physicians on how to manage each individual UL situation. STUDY DESIGN AND METHODS: Somnoler recordings performed under nasal automatic-CPAP were automatically analyzed with APIOS software. For each polygraphic recording, APIOS provided the OR and the CIs for potential determinants of UL: mouth opening, CPAP pressure, body position, and mandibular oscillation. Based on these results, each of four physicians was asked to choose one of four strategies: (1) increase or decrease therapeutic pressure; (2) change nasal mask for oro-nasal mask/chinstrap; (3) favor a nonsupine or supine position; (4) no action for individual leak management. Subsequently, a meeting was held to determine a consensus choice for each individual case. RESULTS: Seventy-eight consecutive patients underwent home-polygraphy with Somnolter. Fifty recordings were analyzed (16 females; 65 [57-75] years of age; BMI = 31.1 [27.4-35.3]). Individual diagnosis of UL was routinely feasible. The determinants of UL were heterogeneous in the population, and diagnosis of UL was not feasible in 10 patients. Based on the results from this analysis, we established consensus leak management strategies at the individual level. The average Cohen κ coefficient for the four raters was 0.58. Pressure modification was proposed in 36% of patients, no action in 24%, installation of a facial mask/chinstrap in 22%, and positional treatment in 18%. INTERPRETATION: The use of type 3 polygraphy for characterizing leak determinants in patients treated with nasal automatic-CPAP is feasible in routine practice. Leak determinants are patient specific. Interrater concordance for determining individual leak management strategies demonstrated a "fair" level of agreement. TRIAL REGISTRY: ClinicalTrials.gov; No.: NCT03381508; URL: www.clinicaltrials.gov).