Age estimation from sleep studies using deep learning predicts life expectancy
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Age estimation from sleep studies using deep learning predicts life expectancy. / Brink-Kjaer, Andreas; Leary, Eileen B.; Sun, Haoqi; Westover, M. Brandon; Stone, Katie L.; Peppard, Paul E.; Lane, Nancy E.; Cawthon, Peggy M.; Redline, Susan; Jennum, Poul; Sorensen, Helge B.D.; Mignot, Emmanuel.
I: npj Digital Medicine, Bind 5, Nr. 1, 103, 2022.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Age estimation from sleep studies using deep learning predicts life expectancy
AU - Brink-Kjaer, Andreas
AU - Leary, Eileen B.
AU - Sun, Haoqi
AU - Westover, M. Brandon
AU - Stone, Katie L.
AU - Peppard, Paul E.
AU - Lane, Nancy E.
AU - Cawthon, Peggy M.
AU - Redline, Susan
AU - Jennum, Poul
AU - Sorensen, Helge B.D.
AU - Mignot, Emmanuel
N1 - Publisher Copyright: © 2022, The Author(s).
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
U2 - 10.1038/s41746-022-00630-9
DO - 10.1038/s41746-022-00630-9
M3 - Journal article
C2 - 35869169
AN - SCOPUS:85134627620
VL - 5
JO - npj Digital Medicine
JF - npj Digital Medicine
SN - 2398-6352
IS - 1
M1 - 103
ER -
ID: 323983223