FITBIT, INC.

Health information for a woman can be used to predict timing of events related to the woman's menstrual cycle. If available, historical cycle information for a woman can be used to predict upcoming cycle events, such as the start and stop of menstruation. To improve the accuracy of those predictions, one or more health metrics are monitored for the woman that can be correlated with the menstrual cycle. These can include, for example, the resting heart rate (RHR), blood oxygen concentration (SpO 2 ) level, and hemoglobin concentration, among other such options. The metrics are monitored over time to determine patterns that can be correlated with menstrual cycle. This information can then be used to update the predictive model, as well as to update individual event predictions. Information about the predictions, and updates to the predictions, can be surfaced accordingly.

Various embodiments provide a wellness tracking device with a base plate that may be utilized as a combination electrode by a variety of sensors. The base plate may be a multi-material electrode that includes a conductor and a transparent or semi-transparent material to enable optical sensing. In certain embodiments, the base plate supports a plurality of different sensors, which may selectively utilize the base plate as an electrode.

The disclosure provides BMDs that have multiple device modes depending on operational conditions of the devices, e.g., motion intensity, device placement, and/or activity type. The device modes are associated with various data processing algorithms. In some embodiments, the BMD is implemented as a wrist-worn or arm-worn device. In some embodiments, methods for tracking physiological metrics using the BMDs are provided. In some embodiments, the process or the BMD applies a time domain analysis on data provided by a sensor of the BMD for a first activity, and applies a frequency domain analysis on the data for a second activity, which contributes to improved accuracy and speed of biometric data.

A system, computer-readable storage medium, and a method capable of, directly or indirectly, estimating sleep states of a user based on sensor data from movement sensors and/or optical sensors.

Physiological variables, metrics, biomarkers, and other data points can be used, in connection with a non-invasive wearable device, to screen for, and predict, mental health issues and cognitive states. In addition to metrics such as heart rate, sleep data, activity level, gamification data, and the like, information such as text message and email data, as well as vocal data obtained through a phone and/or a microphone, may be analyzed, provided user authorization. Applying predictive modeling, one or more of the monitored metrics can be correlated with mental states and disorders. Identified patterns can be used to update the predictive models, such as via machine learning-trained models, as well as to update individual event predictions. Information about the mental state predictions, and updates thereto, can be surfaced to the user accordingly.

Assessing the sleep quality of a user in association with an electronic device with one or more physiological sensors includes detecting an attempt by the user to fall asleep, and collecting physiological information associated with the user. The disclosed method of assessing sleep quality may include determining respective values for one or more sleep quality metrics, including a first set of sleep quality metrics associated with sleep quality of a plurality of users, and a second set of sleep quality metrics associated with historical sleep quality of the user, based at least in part on the collected physiological information and at least one wakeful resting heart rate of the user, and determining a unified score for sleep quality of the user, based at least in part on the respective values of the one or more sleep quality metrics.

This invention provides devices, systems, and methods for performing point-of-care, analysis, including multiplexed analysis, of a biological fluid analyte, such as blood. The invention includes a cartridge for collecting the biological fluid analyte. The cartridge is configured to be inserted into an assay reader, in which one or more assay reactions may be performed. The assay reader is designed to read and report the results of the one or more assay reactions.

Techniques are disclosed for using contextual information to determine an appropriate response in a system that includes a device paired with an accessory device. The contextual information can be sourced from local sensors, received communications, and information stored on a device within the system. Stored parameters in the system allow flexibility and configurability in evaluating the contextual information. Using feedback obtained after actions taken based on the contextual information allows the system to adapt to better meet the needs of the user.

The accuracy of physiological data measured through contact with skin can be validated by characterizing the forces at the surfaces where data is measured. Conventional devices do not monitor the fit of skin-based sensors, making the accuracy and confidence in physiological data dependent on the user ensuring that the device is fitted properly. Over time, the seating of a device will vary due to changes in user activity and the need to periodically remove a device. Inevitably, instances will arise where the device is not fitted correctly, which may result in skewed physiological metrics. By monitoring the forces acting on the housing of a device, the interface of skin sensors can be characterized allowing for confidence metrics in the corresponding physiological data to be determined. In some cases, a user can be notified when a device is not seated properly, and in some cases, data may even be calibrated based on the fit of a device.