Search

Sleep is an important indicator of a person’s health, and its accurate and cost-effective quantification is of great value in healthcare. The gold standard for sleep assessment and the clinical diagnosis of sleep disorders is polysomnography (PSG). However, PSG requires an overnight clinic visit and trained technicians to score the obtained multimodality data. Wrist-worn consumer devices, such as smartwatches, are a promising alternative to PSG because of their small form factor, continuous monitoring capability, and popularity. Unlike PSG, however, wearables-derived data are noisier and far less information-rich because of the fewer number of modalities and less accurate measurements due to their small form factor. Given these challenges, most consumer devices perform two-stage (i.e., sleep-wake) classification, which is inadequate for deep insights into a person’s sleep health. The challenging multi-class (three, four, or five-class) staging of sleep using data from wrist-worn wearables remains unresolved. The difference in the data quality between consumer-grade wearables and lab-grade clinical equipment is the motivation behind this study. In this paper, we present an artificial intelligence (AI) technique termed sequence-to-sequence LSTM for automated mobile sleep staging (SLAMSS), which can perform three-class (wake, NREM, REM) and four-class (wake, light, deep, REM) sleep classification from activity (i.e., wrist-accelerometry-derived locomotion) and two coarse heart rate measures—both of which can be reliably obtained from a consumer-grade wrist-wearable device. Our method relies on raw time-series datasets and obviates the need for manual feature selection. We validated our model using actigraphy and coarse heart rate data from two independent study populations: the Multi-Ethnic Study of Atherosclerosis (MESA; N = 808) cohort and the Osteoporotic Fractures in Men (MrOS; N = 817) cohort. SLAMSS achieves an overall accuracy of 79%, weighted F1 score of 0.80, 77% sensitivity, and 89% specificity for three-class sleep staging and an overall accuracy of 70-72%, weighted F1 score of 0.72-0.73, 64-66% sensitivity, and 89-90% specificity for four-class sleep staging in the MESA cohort. It yielded an overall accuracy of 77%, weighted F1 score of 0.77, 74% sensitivity, and 88% specificity for three-class sleep staging and an overall accuracy of 68-69%, weighted F1 score of 0.68-0.69, 60-63% sensitivity, and 88-89% specificity for four-class sleep staging in the MrOS cohort. These results were achieved with feature-poor inputs with a low temporal resolution. In addition, we extended our three-class staging model to an unrelated Apple Watch dataset. Importantly, SLAMSS predicts the duration of each sleep stage with high accuracy. This is especially significant for four-class sleep staging, where deep sleep is severely underrepresented. We show that, by appropriately choosing the loss function to address the inherent class imbalance, our method can accurately estimate deep sleep time (SLAMSS/MESA: 0.61±0.69 hours, PSG/MESA ground truth: 0.60±0.60 hours; SLAMSS/MrOS: 0.53±0.66 hours, PSG/MrOS ground truth: 0.55±0.57 hours;). Deep sleep quality and quantity are vital metrics and early indicators for a number of diseases. Our method, which enables accurate deep sleep estimation from wearables-derived data, is therefore promising for a variety of clinical applications requiring long-term deep sleep monitoring.

Castleman disease (CD) describes a spectrum of heterogeneous disorders defined by characteristic lymph node histopathology. Enlarged lymph nodes demonstrating CD histopathology can occur in isolation (unicentric CD; UCD) sometimes accompanied by mild symptoms, or at multiple sites (multicentric CD, MCD) with systemic inflammation and cytokine-driven multi-organ dysfunction. The discovery that Kaposi sarcoma herpesvirus/human herpesvirus (HHV)-8 drives MCD in a subset of patients has led to the hypotheses that UCD and MCD patients with negative HHV-8 testing by conventional methods may represent false negatives, or that these cases are driven by another virus, known or unknown. To investigate these hypotheses, the virome capture sequencing for vertebrate viruses (VirCapSeq-VERT) platform was employed to detect RNA transcripts from known and novel viruses in fresh frozen lymph node tissue from CD patients (12 UCD, 11 HHV-8-negative MCD [idiopathic MCD; iMCD], and two HHV-8-positive MCD) and related diseases (three T cell lymphoma and three Hodgkin lymphoma). This assay detected HHV-8 in both HHV-8-positive cases; however, HHV-8 was not found in clinically HHV-8-negative iMCD or UCD cases. Additionally, no novel viruses were discovered, and no single known virus was detected with apparent association to HHV-8-negative CD cases. Herpesviridae family members, notably including Epstein-Barr virus (EBV), were detected in 7 out of 12 UCD and 5 of 11 iMCD cases with apparent correlations with markers of disease severity in iMCD. Analysis of a separate cohort of archival formalin-fixed, paraffin-embedded lymph node tissue by In situ hybridization revealed significantly fewer EBV-positive cells in UCD and iMCD compared to tissue from HHV-8-positive MCD and EBV-associated lymphoproliferative disorder. In an additional cohort, quantitative testing for EBV by PCR in peripheral blood during disease flare did not detect systemic EBV viremia, suggesting detection lymph node tissue is due to occult, local reactivation in UCD and iMCD. This study confirms that HHV-8 is not present in UCD and iMCD patients. Further, it fails to establish a clear association between any single virus, novel or known, and CD in HHV-8-negative cases. Given that distinct forms of CD exist with viral and non-viral etiological drivers, CD should be considered a group of distinct and separate diseases with heterogeneous causes worthy of further study.

Slow wave (or stage N3) sleep has been linked to a variety of cognitive processes. However, the role of stage N3 in the elderly is debated. The link between stage N3 and episodic memory may be weakened or changed in the older adult population, possibly due to several altered mechanisms impacting the cellular structure of the brain. The bases for the age-related dissociation between stage N3 and cognition are not understood. Since APOEε4 status is the strongest genetic risk factor for cognitive decline, we assessed whether the ε4 allele is associated with stage N3 sleep. Participants were from the population-based Osteoporotic Fractures in Men (MrOS) cohort with polysomnography and APOEε4 genotype data (n = 2,302, 100% male, mean age 76.6 years). Sleep stages were objectively measured using overnight in-home polysomnography and central electroencephalogram data were used to score stage N3 sleep. Cognitive function was assessed using the Modified Mini Mental State Exam (3MS). The APOE rs429358 single nucleotide polymorphism, which defines the APOEε4 allele, was genotyped using a custom genotyping array. Total time in stage N3 sleep was significantly higher (p

Context: Short sleep duration is associated with adverse health outcomes, but the mechanisms involved are unknown. It has been postulated that short sleep duration may elevate cortisol levels, but studies have had conflicting results. It is unclear whether these differing findings may be due to methodological issues, such as assessment of sleep duration. Specifically, objective versus subjective methods of measuring habitual sleep duration may account for the conflicting results found in epidemiological studies. Objective: Our goal was to determine whether habitual sleep duration, measured objectively (by actigraphy) and subjectively (by self-report), was associated with 24-hour urine free cortisol (UFC), a measure of integrated cortisol secretion. Our secondary goal was to determine whether slow wave sleep (SWS, determined by polysomnography) was associated with 24-hour UFC. Design/Setting: Cross sectional study of community dwelling older men. Patients/Participants: 325 men (mean age=76.6 years, SD=5.5) from the Portland site of the MrOS Sleep Study, who underwent 24-hour urine collection, polysomnography, actigraphy and sleep questionnaire. Primary Outcome: 24-hour UFC. Results: In this study of community dwelling older men, self-reported sleep duration was inversely related to 24-hour UFC levels. Participants reporting ,5 hours of habitual sleep had an adjusted mean 24-hour UFC of 29.8 ug, compared to 28.0 ug in participants reporting . 5t o,8 hours of sleep 25.5 ug in those reporting .8 hours of habitual sleep. However, sleep duration determined by actigraphy was not associated with 24-hour UFC in either univariable or multivariable regression models. SWS was not associated with 24-hour UFC. Conclusion: Objectively measured (i.e., actigraphic) sleep duration is not associated with 24-hour UFC in these community dwelling older men. This finding, together with prior studies, suggests that elevated levels of integrated cortisol secretion is not the mechanisms by which short sleep duration leads to adverse health outcomes.

Multicentric Castleman Disease is largely driven by increased signaling in the pathway for the plasma cell growth factor interleukin-6. We hypothesized that interleukin-6/interleukin-6 receptor/gp130 polymorphisms contribute to increased interleukin-6 and/or other components of the interleukin-6 signaling pathway in HIV-negative Castleman Disease patients. The study group was composed of 58 patients and 50 healthy donors of a similar racial/ethnic profile. Of seven polymorphisms chosen for analysis, we observed an increased frequency between patients and controls of the minor allele of interleukin-6 receptor polymorphism rs4537545, which is in linkage disequilibrium with interleukin-6 receptor polymorphism rs2228145. Further, individuals possessing at least one copy of the minor allele of either polymorphism expressed higher levels of soluble interleukin-6 receptor. These elevated interleukin-6 receptor levels may contribute to increased interleukin-6 activity through the trans-signaling pathway. These data suggest that interleukin-6 receptor polymorphism may be a contributing factor in Castleman Disease, and further research is warranted.