Sleep Quality
The Sleep Quality metric provides insights into the overall quality and restorative nature of users' sleep. It considers factors such as sleep duration and sleep-wake patterns to assess how well the user is recovering and preparing for the day ahead. By understanding sleep quality, users can make informed decisions to improve their rest and overall well-being. It allows users to quantify the quality of their sleep and corresponding ability to face greater challenges during the day.
Furthermore, Sleep Quality can be used to grow your active users by offering a daily powerful morning check-in within your platform.
The Sleep Quality metric is calculated using a combination of different data sources.
- Biometric data: heart rate (HR), heart rate variability (HRV), and stress levels.
- User-reported information: qualitative user input and contextual data about sleep habits.
- Facial keypoints: drooping/hanging eyelids, paler skin, redder eyes, more puffy/swollen eyes, dark circles under the eyes, more wrinkles/fine lines and more drooping corners of the mouth.
By integrating these data points, IntelliProve can provide a comprehensive assessment of sleep quality and deliver an accurate insight into the restorative effectiveness of the user’s sleep.
When is the first reading available? At least two Face Scans need to be performed before 10 am within one week. In general, a first reading is obtained after the first week.
To validate the accuracy of the Sleep Quality calculation through the IntelliProve algorithm, a benchmarking study was performed between 'The Groningen Sleep Quality Score' and the IntelliProve Sleep Quality metric. In 87% of the cases a poor night's sleep, with negative impact on energy level, is correctly identified.
This metric helps users understand their sleep quality and emotional well-being each morning, guiding them on whether they are ready for peak performance or if they should prioritize rest and recovery.
Sleep Quality can also support users in improving their sleep patterns and optimizing sleep therapy. By tracking progress and analyzing the effectiveness of sleep interventions, users can refine both the duration and quality of their sleep routines. A lower Sleep Quality score can serve as a starting point to guide users toward sleep-enhancing content, like articles, videos, exercises, or therapy options.
Sleep Quality is returned as an integer on a scale of 0 to 100 and can be requested as a Widget or via the Rest API.
Name | Unit | Range | programmatic name | Health Profile |
|---|---|---|---|---|
Sleep Quality | Percentage [%] | 0 - 100 | sleep_quality | Energy & Sleep |
Value | Meaning | Zone | Example User Text |
|---|---|---|---|
10 – 40 | Low | Red | Prioritize recovery-promoting activities today. Avoid pushing your physical or mental limits if possible. Focus on hydration, supportive nutrition and a solid night’s sleep. |
50 – 60 | Medium | Yellow | Consider reducing stressful activities today. If you decide to push harder, then stay extra aware of recovery needs for the next few days. |
70 – 80 | Medium | Yellow | Your readiness score is good and your HRV balance indicates that you have recovered quite well. Plan for some moderate physical exercises or mental activities, but don’t overdo it. |
90 – 100 | High | Green | Your HRV balance indicates that you have recovered well. You should be able to handle more stress and activity today! If there are any challenging tasks on your to-do list, today could be the day to tackle them! |
The table above shows
- Value: The possible values for the health insight
- Meaning: What does the value mean
- Zone: We distinguish three zones, useful – for example - when creating a widget to clarify the feel towars the user
- Green = Optimal to normal
- Yellow = Normal to average
- Red = Outside the typical range; may require attention
- Example user text: An example of what could be communicated to the user in case this value is measured.
- Sundelin T, Lekander M, Kecklund G, Van Someren EJ, Olsson A, Axelsson J. 2013. Cues of fatigue: effects of sleep deprivation on facial appearance. Sleep. 36(9):1355–1360.
- Van de Water AT, Holmes A, Hurley DA. 2011. Objective measurements of sleep for non-laboratory settings as alternatives to polysomnography—a systematic review. J Sleep Res. 20(1 Pt 2):183–200.
- Peng X, Luo J, Glenn C, Chi LK, Zhan J. 2018. Sleep-deprived fatigue pattern analysis using large-scale selfies from social media. arXiv preprint arXiv:1802.08310.