Design and Evaluation of a Non-ContactBed-Mounted Sensing Device for AutomatedIn-Home Detection of Obstructive Sleep Apnea:A Pilot Study.

We conducted a pilot study to evaluate the accuracy of a custom built non-contactpressure-sensitive device in diagnosing obstructive sleep apnea (OSA) severity as an alternative toin-laboratory polysomnography (PSG) and a Type 3 in-home sleep apnea test (HSAT). Fourteenpatients completed PSG sleep studies for one night with simultaneous recording from ourload-cell-based sensing device in the bed. Subjects subsequently installed pressure sensors in theirbed at home and recorded signals for up to four nights. Machine learning models were optimized toclassify sleep apnea severity using a standardized American Academy of Sleep Medicine (AASM)scoring of the gold standard studies as reference. On a per-night basis, our model reached a correctOSA detection rate of 82.9% (sensitivity = 88.9%, specificity = 76.5%), and OSA severity classificationaccuracy of 74.3% (61.5% and 81.8% correctly classified in-clinic and in-home tests, respectively).There was no difference in Apnea Hypopnea Index (AHI) estimation when subjects wore HSATsensors versus load cells (LCs) only (p-value = 0.62). Our in-home diagnostic system providesan unobtrusive method for detecting OSA with high sensitivity and may potentially be used forlong-term monitoring of breathing during sleep. Further research is needed to address the lowerspecificity resulting from using the highest AHI from repeated samples.

In-Home Sleep Apnea Severity Classification using Contact-free Load Cells and an AdaBoosted Decision Tree Algorithm.

We present a method for automated diagnosis and classification of severity of sleep apnea using an array of non-contact pressure-sensitive sensors placed underneath a mattress as an alternative to conventional obtrusive sensors. Our algorithm comprises two stages: i) A decision tree classifier that identifies patients with sleep apnea, and ii) a subsequent linear regression model that estimates the Apnea-Hypopnea Index (AHI), which is used to determine the severity of sleep disordered breathing. We tested our algorithm on a cohort of 14 patients who underwent overnight home sleep apnea test. The machine learning algorithm was trained and performance was evaluated using leave-one-patient-out cross-validation. The accuracy of the proposed approach in detecting sleep apnea is 86.96%, with sensitivity and specificity of 81.82% and 91.67%, respectively. Moreover, classification of severity of the sleep disorder was correctly assigned in 11 out of 14 cases, and the mean absolute error in the AHI estimation was calculated to be 3.83 events/hr.

A time-frequency respiration tracking system using non-contact bed sensors with harmonic artifact rejection.

Sleep apnea is a breathing disorder that affects many individuals and has been associated with serious health conditions such as cardiovascular disease. Clinical diagnosis of sleep apnea requires that a patient spend the night in a sleep clinic while being wired up to numerous obtrusive sensors. We are developing a system that utilizes respiration rate and breathing amplitude inferred from non-contact bed sensors (i.e. load cells placed under bed supports) to detect sleep apnea. Multi-harmonic artifacts generated either biologically or as a result of the impulse response of the bed have made it challenging to track respiration rate and amplitude with high resolution in time. In this paper, we present an algorithm that can accurately track respiration on a second-by-second basis while removing noise harmonics. The algorithm is tested using data collected from 5 patients during overnight sleep studies. Respiration rate is compared with polysomnography estimations of respiration rate estimated by a technician following clinical standards. Results indicate that certain subjects exhibit a large harmonic component of their breathing signal that can be removed by our algorithm. When compared with technician transcribed respiration rates using polysomnography signals, we demonstrate improved accuracy of respiration rate tracking using harmonic artifact rejection (mean error: 0.18 breaths/minute) over tracking not using harmonic artifact rejection (mean error: -2.74 breaths/minute).

Accurate scoring of the apnea-hypopnea index using a simple non-contact breathing sensor.

Sleep apnea is a serious condition that afflicts many individuals and is associated with serious health complications. Polysomnography, the gold standard for assessing and diagnosing sleep apnea, uses breathing sensors that are intrusive and can disrupt the patient's sleep during the overnight testing. We investigated the use of breathing signals derived from non-contact force sensors (i.e. load cells) placed under the supports of the bed as an alternative to traditional polysomnography breathing sensors (e.g. nasal pressure, oral-nasal thermistor, chest belt and abdominal belt). The apnea-hypopnea index estimated using the load cells was not different than that estimated using standard polysomnography leads (t44  = 0.37, P = 0.71). Overnight polysomnography sleep studies scored using load cell breathing signals had an intra-class correlation coefficient of 0.97 for the apnea-hypopnea index and an intra-class correlation coefficient of 0.85 for the respiratory disturbance index when compared with scoring using traditional polysomnography breathing sensors following American Academy of Sleep Medicine guidelines. These results demonstrate the feasibility of using unobtrusive load cells installed under the bed to measure the apnea-hypopnea index.

Unobtrusive classification of sleep and wakefulness using load cells under the bed.

Poor quality of sleep increases the risk of many adverse health outcomes. Some measures of sleep, such as sleep efficiency or sleep duration, are calculated from periods of time when a patient is asleep and awake. The current method for assessing sleep and wakefulness is based on polysomnography, an expensive and inconvenient method of measuring sleep in a clinical setting. In this paper, we suggest an alternative method of detecting periods of sleep and wake that can be obtained unobtrusively in a patient's own home by placing load cells under the supports of their bed. Specifically, we use a support vector machine to classify periods of sleep and wake in a cohort of patients admitted to a sleep lab. The inputs to the classifier are subject demographic information, a statistical characterization of the load cell derived signals, and several sleep parameters estimated from the load cell data that are related to movement and respiration. Our proposed classifier achieves an average sensitivity of 0.808 and specificity of 0.812 with 90% confidence intervals of (0.790, 0.821) and (0.798, 0.826), respectively, when compared to the "gold-standard" sleep/wake annotations during polysomnography. As this performance is over 27 sleep patients with a wide variety of diagnosis levels of sleep disordered breathing, age, body mass index, and other demographics, our method is robust and works well in clinical practice.

Classification of lying position using load cells under the bed.

Individuals who suffer from acid reflux at night, who snore chronically, or who have sleep apnea are frequently encouraged to sleep in a particular lying position. Side sleeping decreases the frequency and severity of obstructive respiratory events (e.g. apnea and hypopnea) in patients with positional sleep apnea. It has been suggested that individuals with Gastroesophageal Reflux Disease sleep on their left sides in order to help minimize symptoms. In this paper, we present a method of predicting the position of an individual lying on the bed using load cells placed under each of the bed supports. Our results suggest that load cells utilized in this manner could be successfully implemented into a system that tracks or helps train individuals to sleep in a particular lying position.

Classification of breathing events using load cells under the bed.

Sleep disturbances are prevalent, financially taxing, and have a negative effect on health and quality of life. One of the most common sleep disturbances is obstructive sleep apnea-hypopnea syndrome (OSAHS) which frequently goes undiagnosed. The gold standard for diagnosing OSAHS is polysomnography (PSG)-a procedure that is inconvenient, time-consuming, and interferes with normal sleep patterns. We are investigating an alternative to PSG in which unobtrusive load cells fitted under the bed are used to monitor movement, heart rate, and respiration. In this paper we describe how load cell data can be used to distinguish between clinically relevant disordered breathing (apneas and hypopneas) and normal respiration. The method correctly classified disordered breathing segments with a sensitivity of 0.77 and a specificity of 0.91.

Catathrenia: parasomnia or uncommon feature of sleep disordered breathing?

OBJECTIVE: We report a series of seven consecutive cases of catathrenia (sleep related groaning) that differ from limited previous reports in the literature with regard to sleep stage and response to treatment. BACKGROUND: Catathrenia was recently defined as a parasomnia in the International Classification of Sleep Disorders Diagnostic and Coding Manual (ICSD-2), but there is debate about its classification, and its response to CPAP is unknown. METHODS: We present 7 consecutive patients presenting with catathrenia over a 5-year period. They were all young women, ranging in age from 20 to 34 years with a body mass index (BMI) <25. They underwent standard clinical evaluation, questionnaires, physical exam, craniofacial evaluations, and nocturnal polysomnography. All seven were titrated on continuous passive airway pressure (CPAP) treatment for sleep disordered breathing then offered surgical treatment if unable to tolerate or adhere to CPAP recommendations. RESULTS: Groaning was present throughout all stages of sleep. The mean (SD) AHI and RDI were 3.2 (0.56) and 13.1 (2.4) respectively. CPAP resolved groaning in all cases. 5 patients (71%) elected subsequent surgical intervention. Three of the 4 that followed up after surgery required adjuvant oral appliance treatment, but all four ultimately had resolution of groaning. CONCLUSIONS: Catathrenia may have subtypes related to sleep stage specificity or presence of sleep disordered breathing. In our heterogeneous group of non-obese women with a normal AHI and elevated RDI, CPAP and select soft tissue surgeries of the upper airway (often augmented with an oral appliance) successfully treated nocturnal groaning.

Cyanotic breath-holding spells in children respond to adenotonsillectomy for sleep-disordered breathing.

Children with breath-holding (BH) spells may demonstrate sleep-disordered breathing (SDB) during polysomnography. We studied five young children with cyanotic spells retrospectively and found both SDB and a response to adenotonsillectomy. We therefore proceeded with a prospective investigation of treatment for SDB in children with comorbid cyanotic spells. Nineteen children with cyanotic BH spells were identified and enrolled in the prospective study. Parents chose either treatment or observation. Fourteen children underwent complete SDB evaluation and treatment trials while five selected observation only (control group). Sleep and sleep-surgery specialist evaluation and polysomnography revealed the presence of a narrow upper-airway and an abnormal respiratory disturbance index in all 14 children. Nasal CPAP was not successful, but adenotonsillectomy performed near 14 months of age eliminated SDB. BH spells were eliminated 1 month after surgery, while they persisted to the end of the study (24 months of age) in the control group. In conclusion, the presence of cyanotic BH should prompt investigation and polysomnography for possible SDB. Independent treatment of SDB may hasten resolution of BH spells in these cases.

The cyclic alternating pattern demonstrates increased sleep instability and correlates with fatigue and sleepiness in adults with upper airway resistance syndrome.

OBJECTIVE: To clarify the relationship between sleep instability and subjective complaints in patients with upper airway resistance syndrome (UARS). METHODS: Thirty subjects (15 women) with UARS and 30 age- and sex-matched controls in a prospective, single-blind, case-control study. Blinded cyclic alternating pattern (CAP) electroencephalogram analysis and scales of fatigue and sleepiness were completed. ANALYSIS: Mann-Whitney U tests for independent, nonparametric variables between groups and chi2 tests for nonparametric variables with defined standard values. RESULTS: Patients with UARS had significantly more complaints of fatigue and sleepiness, compared with controls, demonstrated on their Fatigue Severity Scale (P < 0.001) and Epworth Sleepiness Scale (P < 0.001). By design, the mean apnea-hypopnea index was normal in both groups, whereas the respiratory disturbance index was greater in patients with UARS than in those without (14.5 +/- 3.0 vs 9 +/- 5.2, respectively [P < 0.001]). CAP analysis demonstrated abnormal non-rapid eye movement sleep with abnormally increased CAP rate, electroencephalogram arousals, A2 index, and A3 index. Decreased A1 index in controls was consistent with their more normal progression of sleep. CAP rate correlated with both the Epworth Sleepiness Scale (r = 0.38, P < 0.01) and the Fatigue Severity Scale (r = 0.51, P < 0.0001), and there was a positive trend between the Fatigue Severity Scale and phase A2 index (r = 0.29, P < 0.05). CONCLUSION: Compared with age- and sex-matched controls, patients with UARS have higher electroencephalogram arousal indexes and important non-rapid eye movement sleep disturbances that correlate with subjective symptoms of sleepiness and fatigue. These disturbances are identifiable with sensitive measures such as CAP analysis but not with traditional diagnostic scoring systems.