The research, recently published in the journal Digital Medicine, evaluated 12,000 studies that investigated characteristics of people during their sleep, such as chin and leg movement, breathing and heart rate. The scientists, including Emmanuel Mignot from Stanford University, developed a system that uses machine learning to predict a person’s “sleep age” and identify the variations in sleep most closely associated with mortality. Sleep age, they say, is an estimated age of a person based on sleep characteristics linked to their health. Previous research has documented that sleep is one of the first things to be disrupted in many disorders. The scientists cited the example of patients with Parkinson’s disease and said that in most cases, they have violent dreams about five to ten years before other symptoms appear. By assessing different characteristics of people’s sleep, the new study found that sleep fragmentation, when people wake up briefly several times a night without remembering it, was the “strongest predictor” of mortality. Researchers say this type of sleep disturbance is different from when a person realizes they are waking up, as is referred to in sleep disorders such as insomnia and sleep apnea. However, scientists say it is not clear how sleep fragmentation is linked to the risk of death. “Determining why sleep fragmentation is so detrimental to health is something we plan to study in the future,” Dr. Minio said in a statement. In the research, the scientists determined what the average sleep looks like at a certain age. They then used a machine learning system to assess patterns in the subjects’ data across the 12,000 studies and used that to predict their sleep ages. Using the difference between people’s chronological age and their sleep age, the researchers then predicted their mortality based on the hypothesis that older sleep age is an indicator of a health problem. Older sleep age was primarily reflected in “increased sleep fragmentation,” suggesting it is an indicator of future health, the scientists concluded in the study.
