A New Sleep Staging System for Type III Sleep Studies Equipped With a Tracheal Sound Sensor.

Type III sleep studies record cardio-respiratory channels only. Compared with polysomnography, which also records electrophysiological channels, they present many advantages: they are less expensive, less time-consuming, and more likely to be performed at home. However, their accuracy is limited by missing sleep information. That is why many studies present specific cardio-respiratory parameters to assess the causal effects of sleep stages upon cardiac or respiratory activities. For this paper, we gathered many parameters proposed in literature, leading to 1,111 features. The pulse oximeter, the PneaVoX sensor (recording tracheal sounds), respiratory inductance plethysmography belts, the nasal cannula and the actimeter provided the 112 worthiest ones for automatic sleep scoring. Then, a 3-step model was implemented: classification with a multi-layer perceptron, sleep transition rules corrections (from the AASM guidelines), and sequence corrections using a Viterbi hidden Markov model. The whole process was trained and tested using 300 and 100 independent recordings provided from patients suspected of having sleep breathing disorders. Results indicated that the system achieves substantial agreement with manual scoring for classifications into 2 stages (wake vs. sleep: mean Cohen's Kappa κ of 0.63 and accuracy rate Acc of 87.8%) and 3 stages (wake vs. R stage vs. NREM stage: mean κ of 0.60 and Acc of 78.5%). It indicates that the method could provide information to help specialists while diagnosing sleep. The presented model had promising results and may enhance clinical diagnosis.

Diagnosis of sleep apnea without sensors on the patient's face.

STUDY OBJECTIVES: Thermistors, nasal cannulas, and respiratory inductance plethysmography (RIP) are the recommended reference sensors of the American Academy of Sleep Medicine (AASM) for the detection and characterization of apneas and hypopneas; however, these sensors are not well tolerated by patients and have poor scorability. We evaluated the performance of an alternative method using a combination of tracheal sounds (TSs) and RIP signals. METHODS: Consecutive recordings of 70 adult patients from the Pays de la Loire Sleep Cohort were manually scored in random order using the AASM standard signals and the combination TS and RIP signals, without respiratory sensors placed on the patient's face. The TS-RIP scoring used the TS and RIP-flow signals for detection of apneas and hypopneas, respectively, and the suprasternal pressure and RIP belt signals for the characterization of apneas. RESULTS: Sensitivity and specificity of the TS-RIP combination were 96.21% and 91.34% for apnea detection and 89.94% and 93.25% for detecting hypopneas, respectively, with a kappa coefficient of 0.87. For the characterization of apneas, sensitivity and specificity were 98.67% and 96.17% for obstructive apneas, 92.66% and 99.36% for mixed apneas, and 96.14% and 98.89% for central apneas, respectively, with a kappa coefficient of 0.94. The TS-RIP scoring revealed a high agreement for classifying obstructive sleep apnea into severity classes (none, mild, moderate, and severe obstructive sleep apnea) with a Cohen's kappa coefficient of 0.96. CONCLUSIONS: Compared with the AASM reference sensors, the TS-RIP combination allows reliable noninvasive detection and characterization of respiratory events with a high degree of sensitivity and specificity. TS-RIP combination could be used for diagnosis of obstructive sleep apnea in adults, either as an alternative to the AASM sensors or in combination with the recommended AASM sensors.

Tracheal sounds for the scoring of sleep respiratory events in children.

STUDY OBJECTIVES: Oronasal thermistor and nasal cannula are recommended for the scoring of respiratory events (RE) but these sensors are poorly tolerated in children. The aim of the study was to evaluate tracheal sounds (TS) and suprasternal pressure (SSP) for the scoring of RE during sleep in children. METHODS: We compared the detection and characterization of RE by AASM-recommended sensors ("AASM" scoring), with the detection and characterization of RE by the combination of TS and SSP with respiratory inductance plethysmography-sum (TS-RIP scoring), and TS and SSP only (TS scoring). RESULTS: The recordings of 17 patients were analyzed. The TS, SSP, and RIP flow signals were present during 95%, 95%, and 99% of the validated recording time, respectively, as compared to 79% and 86% for nasal cannula and oronasal thermistor. A total of 1,456 RE were scored with the "AASM" scoring, 1,335 with the TS-RIP scoring, and 1,311 with the TS scoring. Sensitivity for apnea and hypopnea detection was 88% and 84% for the TS-RIP scoring, and 86% and 77% for the TS scoring. For apnea characterization, the TS-RIP scoring sensitivities and specificities were 97% and 100%, 76% and 98%, and 95% and 97%, for obstructive, mixed, and central apnea, respectively. For the TS scoring, they were 95% and 100%, 95% and 97%, and 91% and 97%, respectively. CONCLUSIONS: TS and SSP + RIP-sum has a good sensitivity and specificity for the detection and characterization of apnea and hypopnea in children. TS and SSP alone have good sensitivity and specificity for apnea detection and characterization but lower sensitivity for hypopnea detection.

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.

Pulse wave amplitude reduction as a surrogate for cortical arousal during sleep hypopnea in children.

OBJECTIVES: The accuracy of respiratory polygraphy (RP) is limited because of the absence of electroencephalography (EEG). Pulse wave amplitude (PWA) reduction has been shown to be a marker of autonomic activation during arousal, and may represent a substitute for obstructive respiratory-related cortical arousal (RRCA). This study tested the hypothesis that PWA could be a surrogate for RRCA in detecting obstructive hypopnea (OH) in a pediatric population. MATERIALS AND METHODS: Two experienced readers scored 30 consecutive polysomnographies (PSG) using standard scoring rules. Automatic software detected every 20-90% reduction in PWA. A second scoring of respiratory events using PWA reduction as a surrogate for RRCA was performed (RP with PWA) for each percentage of PWA reduction. The final analysis consisted of determining the concordance between the two methods of detecting OH. RESULTS: A total of 987 episodes of ≥30% flow reduction were analyzed: 330 with RRCA only, 205 with desaturation (DS) only, 134 with both, and 318 without RRCA or DS. As the percentage of reduction in PWA increased, the sensitivity of PWA as a substitute for RRCA decreased, but the specificity increased. For a decrease in PWA of 60% or 70%, the sensitivities of PWA as a substitute for RRCA were 79% and 57%, and the specificities 51% and 76%, respectively. CONCLUSION: Pulse wave amplitude reduction lacks sensitivity and specificity to be used as a surrogate for RRCA to detect OH in children. Polysomnography remains the gold standard for the diagnosis of sleep disordered breathing in children.

Validation of a Suprasternal Pressure Sensor for Sleep Apnea Classification in Children.

STUDY OBJECTIVES: The recognition and characterization of respiratory events is crucial when interpreting sleep studies. The aim of the study was to validate the PneaVoX sensor, which integrates the recording of respiratory effort by means of suprasternal pressure (SSP), respiratory flow, and snoring for the classification of sleep apneas in children. METHODS: Sleep recordings of 20 children with a median age of 7.5 (0.5-16.5) years were analyzed. Scoring of apneas according to the American Academy of Sleep Medicine (AASM) guidelines using nasal pressure, oronasal thermal sensor and respiratory efforts by means of respiratory inductance plethysmography (RIP), was compared to a scoring using the PneaVoX sensor and nasal pressure, without the oronasal thermal sensor nor RIP, during a dual blind study. RESULTS: The percentage of sleep time recording without artifacts was 97%, 97%, 87%, 65%, and 98% for the respiratory flow and SSP from the PneaVoX sensor, oronasal thermal sensor, nasal pressure, and RIP, respectively. As compared to the AASM scoring with RIP, sensitivity and specificity of the SSP for the scoring of central apneas were 75% and 99% for the first reader, and 70% and 100% for the second reader, respectively. Sensitivity and specificity for the scoring of obstructive apneas were 98% and 75%, and 100% and 70%, respectively. A significant number of apneas scored as central by RIP were scored as obstructive by the SSP. CONCLUSIONS: The PneaVoX sensor has a high degree of scorability in children. The PneaVoX sensor is a useful adjunct for characterizing apneas.