Premium
Physiological sleep measures predict time to 15‐year mortality in community adults: Application of a novel machine learning framework
Author(s) -
Wallace Meredith L.,
Coleman Timothy S.,
Mentch Lucas K.,
Buysse Daniel J.,
Graves Jessica L.,
Hagen Erika W.,
Hall Martica H.,
Stone Katie L.,
Redline Susan,
Peppard Paul E.
Publication year - 2021
Publication title -
journal of sleep research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.297
H-Index - 117
eISSN - 1365-2869
pISSN - 0962-1105
DOI - 10.1111/jsr.13386
Subject(s) - polysomnography , sleep (system call) , predictive validity , medicine , internal validity , random forest , machine learning , physical therapy , gerontology , clinical psychology , computer science , electroencephalography , psychiatry , pathology , operating system
Summary Clarifying whether physiological sleep measures predict mortality could inform risk screening; however, such investigations should account for complex and potentially non‐linear relationships among health risk factors. We aimed to establish the predictive utility of polysomnography (PSG)‐assessed sleep measures for mortality using a novel permutation random forest (PRF) machine learning framework. Data collected from the years 1995 to present are from the Sleep Heart Health Study (SHHS; n = 5,734) and the Wisconsin Sleep Cohort Study (WSCS; n = 1,015), and include initial assessments of sleep and health, and up to 15 years of follow‐up for all‐cause mortality. We applied PRF models to quantify the predictive abilities of 24 measures grouped into five domains: PSG‐assessed sleep (four measures), self‐reported sleep (three), health (eight), health behaviours (four), and sociodemographic factors (five). A 10‐fold repeated internal validation (WSCS and SHHS combined) and external validation (training in SHHS; testing in WSCS) were used to compute unbiased variable importance metrics and associated p values. We observed that health, sociodemographic factors, and PSG‐assessed sleep domains predicted mortality using both external validation and repeated internal validation. The PSG‐assessed sleep efficiency and the percentage of sleep time with oxygen saturation <90% were among the most predictive individual measures. Multivariable Cox regression also revealed the PSG‐assessed sleep domain to be predictive, with very low sleep efficiency and high hypoxaemia conferring the highest risk. These findings, coupled with the emergence of new low‐burden technologies for objectively assessing sleep and overnight oxygen saturation, suggest that consideration of physiological sleep measures may improve risk screening.