Fotbit's Sleep Tracking: Understanding Your Sleep Stages

Fitbit uses movement and heart rate patterns to estimate sleep stages. When a person doesn't move for about an hour, the tracker assumes they are asleep. The device then tracks beat-to-beat changes in heart rate, which fluctuate as the user transitions between light sleep, deep sleep, and REM sleep stages. While Fitbit can't measure brainwaves, it can infer sleep stages using an accelerometer coupled with optical photoplethysmography (PPG), which measures blood flow based on reflected light.

Fitbit uses movement and heart-rate patterns to estimate sleep stages

When you don't move for about an hour, your Fitbit tracker or watch assumes you're asleep. Additional data, such as the length of time when your movements indicate sleep behaviour (like rolling over), help confirm your sleep status. While you sleep, your Fitbit device tracks the beat-to-beat changes in your heart rate, known as heart rate variability (HRV), which fluctuate as you transition between light sleep, deep sleep, and REM sleep stages.

Fitbit's sleep researchers and the National Sleep Foundation categorise sleep into light sleep, deep sleep, and REM sleep. Light sleep serves as your entry point into sleep each night as your body unwinds and slows down. Deep sleep is characterised by less brain activity than REM sleep, and REM sleep is associated with vivid dreams.

While Fitbit's sleep staging is only correct in 30-second blocks slightly more than two-thirds of the time, there is no systematic bias to how much light sleep, deep sleep, or sleeplessness the device estimates. Fitbit does not over or underestimate the duration of these stages. However, it is important to note that Fitbit does not measure brainwaves, and only an EEG is an accurate measure of deep sleep.

Heart rate variability (HRV) is tracked to determine sleep stage transitions

Heart rate variability (HRV) is a measure of the variation in time between each heartbeat. HRV is controlled by the autonomic nervous system (ANS), which is responsible for regulating key bodily functions such as heart rate, blood pressure, breathing, and digestion. The ANS consists of two main components: the sympathetic nervous system, often referred to as the "fight-or-flight" mechanism, and the parasympathetic nervous system, also known as the "relaxation response".

HRV can be measured by electrocardiogram (ECG) in a clinical setting or by wearable heart rate monitors and apps. While the accuracy of these wearable devices is still under scrutiny, they offer a non-invasive way to track HRV and gain insights into the body's autonomic nervous system.

During sleep, HRV typically increases, indicating that sleep is a period of dominant vagal activity. HRV is higher during non-rapid eye movement (non-REM) sleep, a state of consciousness with the highest vagal influence on the heart rate. As the body transitions into REM sleep, there is a decrease in vagal contribution to heart rate control, resulting in a shift towards sympathetic dominance.

By tracking HRV, Fitbit can infer the sleep stages an individual is in. Fitbit devices use an accelerometer to measure bodily accelerations of the wrist, coupled with optical photoplethysmography (PPG) to measure blood flow based on how green light from an LED on the back of the watch is reflected by the body. While the accuracy of Fitbit's sleep staging has been questioned, it provides valuable insights into sleep patterns and can help users adjust their sleep habits for more restful sleep.

Fitbit's accuracy in classifying sleep stages is 69% in a 30-second window

Fitbit uses an accelerometer (a device that measures bodily accelerations of the wrist) and optical photoplethysmography (PPG) to determine when you're sleeping and what stage of sleep you're in. PPG measures blood flow based on how green light from an LED on the back of the watch is reflected by the body. Fitbit devices rely on two sensing modalities—accelerometer and PPG—and use these limited signals as input for sleep staging. Fitbit looks at how much you're moving and how often your heart is beating to infer whether you're awake, in a deep sleep, a light slumber, or dreaming.

Fitbit introduced its sleep-staging feature in 2017, which is now incorporated into the Fitbit Charge 2, Fitbit Charge 3, Fitbit Alta HR, Fitbit Versa, Fitbit Versa 2, Fitbit Blaze, and Fitbit Ionic models. This feature relies on a combined body movement and HRV algorithm to identify and estimate the time spent in individual sleep stages. The feature was derived using machine learning methods (i.e., linear discriminant classifier) applied to three types of parameters—motion, HRV, and respiratory rate, with the last two calculated from heartbeat data sensed by photoplethysmography.

The accuracy of Fitbit's sleep-staging feature has been the subject of several studies. One study found that the feature showed no significant difference in measured values of WASO, TST, and SE compared to PSG (polysomnography, the gold standard for measurement of sleep stages). However, it underestimated SOL. Another study found that the sleep-staging feature had an overall per-epoch accuracy of 0.731 ± 0.119, which is higher than the 69% accuracy reported in the 2017 paper by Fitbit scientists. This discrepancy may be due to the small sample size of the study.

It's important to note that the 69% accuracy reported by Fitbit scientists is based on a 30-second time window. This means that Fitbit's sleep staging is correct in these 30-second blocks slightly more than two-thirds of the time. This accuracy may seem low, but it depends on the context. Additionally, there is no systematic bias in how much light sleep, deep sleep, or sleeplessness Fitbit estimates, so it does not over or underestimate the duration of these stages.

Fitbit's sleep stages are based on light sleep, deep sleep, and REM sleep

Sleep is an essential component of health, impacting everything from a person's daily mood to their appetite, physical activity, and more. Fitbit offers tools to help you understand your sleep patterns and quality. Fitbit's sleep stages are based on light sleep, deep sleep, and REM sleep.

Fitbit devices that track heart rate (excluding Charge HR and Surge) also track sleep stages. Fitbit looks at how much you're moving and how often your heart is beating to determine whether you're awake, in a deep sleep, a light slumber, or dreaming. The Fitbit Versa features an SpO2 sensor for measuring blood oxygenation, but this feature is not yet used to provide information about your sleep.

The Fitbit Sleep Score is a quick way to gauge your sleep and is based on heart rate, the time spent awake or restless, and sleep stages. The overall sleep score is the sum of individual scores in three components: sleep duration, sleep quality, and restoration. Sleep duration is the number of hours you slept each night, sleep quality is how much time you spent in light, deep, and REM sleep, and restoration is based on blood oxygen saturation levels.

Fitbit's sleep staging has been found to be 69% accurate in any given 30-second time window. While this may seem low, there is no systematic bias to how much light sleep, deep sleep, or sleeplessness Fitbit estimates. In other words, Fitbit does not over or underestimate the duration of these stages. However, it is important to note that the sleep sensitivity setting on your device does not affect sleep stages.

To get the best results when tracking your sleep with Fitbit, wear your device higher on your wrist (2-3 finger widths above your wrist bone) so that it can get a consistent heart rate reading. Additionally, you can set a sleep schedule in the Fitbit app to maintain a consistent sleep pattern and set bedtime reminders to help you wind down each night.

Fitbit does not measure brainwaves, so it cannot decipher deep sleep

Sleep is an essential component of health, and its timing, duration, and quality are critical determinants of a person's overall health. While you sleep, your Fitbit device tracks the beat-to-beat changes in your heart rate, known as heart rate variability (HRV). However, it is important to note that Fitbit does not measure brainwaves, so it cannot decipher deep sleep.

Fitbit uses movement and heart rate patterns to estimate sleep cycles from the previous night. It infers when you're sleeping and what stage of sleep you're in using an accelerometer (an instrument for measuring bodily accelerations of the wrist) coupled with a technique called optical photoplethysmography, or PPG. PPG measures blood flow based on how green light from an LED on the back of the watch is reflected by the body.

Fitbit's sleep feature estimates sleep stages using a combination of movement and heart rate patterns. When you haven't moved for about an hour, your tracker or smartwatch assumes you're asleep. Additional data, such as the length of time of movements that are indicative of sleep behaviour (such as rolling over), can also help confirm that you're asleep.

Fitbit's sleep researchers and the National Sleep Foundation describe the following sleep stages: Light Sleep, Deep Sleep, and REM Sleep. Light Sleep serves as your entry point into sleep each night as your body unwinds and slows down. During the early part of light sleep, you may drift between being awake and asleep, remaining somewhat alert and easily awoken. Your breathing and heart rate usually decrease slightly during this stage.

Deep Sleep is the second stage of sleep, typically longer in the first half of the night. It is characterised by less brain activity than REM sleep. REM sleep, or Rapid Eye Movement sleep, is the final stage of sleep when your brain becomes more active, and dreams mainly occur. Your heart rate increases, and your breathing becomes more irregular.

Frequently asked questions