0324 Improving our Understanding of Sleep By Generating and Sharing a Large Sleep Cohort and Data Analytic Tools

Leary, E; Seeger-Zybok, R K; Kushida, Clete A.; Mignot, Emmanuel

doi:10.1093/sleep/zsy061.323

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, we used a combined sample of 13,332 PSGs from seven cohorts: the Stanford Technology Analytics and Genomics of Sleep (STAGES) 31 , 32 , the Stanford Sleep Cohort (SSC) 33 , 34 , the Wisconsin Sleep Cohort (WSC) 4 , 34 , the SHHS 35 , 36 , the Osteoporotic Fractures in Men (MrOS) Sleep Study 36 – 38 , the Cleveland Family Study (CFS) 36 , 39 , and the Home Positive Airway Pressure (HomePAP) Study 36 , 40 .…”

Section: Resultsmentioning

confidence: 99%

“…In this study, we included participants with a wide age range from seven study cohorts: STAGES 31 , 32 , the SSC 33 , 34 , the WSC 4 , 34 , the SHHS 35 , 36 , the MrOS 36 – 38 , the CFS 36 , 39 , and HomePAP Study 36 , 40 . Access to the SHHS, MrOS, CFS, and HomePAP Study was granted through the National Sleep Research Resource 36 .…”

Section: Methodsmentioning

confidence: 99%

“…The STAGES 31 , 32 is a prospective cross-sectional multi-site cohort designed to investigate the relationship between different sleep-related data including in-lab polysomnography, questionnaire data, genomics, actigraphy data etc. A total of 1859 PSGs were recorded in 1627 participants of ages between 13 and 83 at the following 6 clinical sites: Stanford University, Bogan Sleep Consultants, Geisinger Health, Mayo Clinic, MedSleep, and St. Luke’s Hospital.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Age estimation from sleep studies using deep learning predicts life expectancy

et al. 2022

View full text Add to dashboard Cite

Sleep disturbances increase with age and are predictors of mortality. Here, we present deep neural networks that estimate age and mortality risk through polysomnograms (PSGs). Aging was modeled using 2500 PSGs and tested in 10,699 PSGs from men and women in seven different cohorts aged between 20 and 90. Ages were estimated with a mean absolute error of 5.8 ± 1.6 years, while basic sleep scoring measures had an error of 14.9 ± 6.29 years. After controlling for demographics, sleep, and health covariates, each 10-year increment in age estimate error (AEE) was associated with increased all-cause mortality rate of 29% (95% confidence interval: 20–39%). An increase from −10 to +10 years in AEE translates to an estimated decreased life expectancy of 8.7 years (95% confidence interval: 6.1–11.4 years). Greater AEE was mostly reflected in increased sleep fragmentation, suggesting this is an important biomarker of future health independent of sleep apnea.

show abstract