The present invention relates to a system for unobtrusive fertility tracking, comprising a sensor for obtaining a heart signal, a processing unit configured to determine a subject's heart rate from the heart signal, and an evaluation unit configured to analyze the subject's heart rate to predict likelihood of ovulation. The processing unit is further configured to extract heart rate variability features from the heart signal, and the evaluation unit is further configured to predict likelihood of ovulation based on the heart rate variability features.

A lighting control system includes: a biological information obtainer which obtains biological information related to a biological body of a user; an environmental information obtainer which obtains environmental information related to a surrounding environment of the user; a severity determiner which determines a severity of premenstrual syndrome (PMS) based on the biological information obtained by the biological information obtainer and the environmental information obtained by the environmental information obtainer; and a lighting controller which controls a lighting device based on the severity determined by the severity determiner.

The present disclosure relates to methods and electronic devices for predicting a fertile period. In one example method, an electronic device obtains physiological parameters of a user and menstruation data entered by the user, and obtains a time length for which the user has worn a wearable device. If the time length for which the user has worn the wearable device is greater than or equal to a predetermined time length, the electronic device determines whether a current time is within a fertile period, and if the current time is not within the fertile period, the electronic device determines whether the current time has entered an initial window. If the current time is within the initial window, the electronic device reduces a length of the initial window, and outputs a reduced window.

The present invention relates to a system for unobtrusive fertility tracking, comprising a sensor for obtaining a heart signal, a processing unit configured to determine a subject's heart rate from the heart signal, and an evaluation unit configured to analyze the subject's heart rate to predict likelihood of ovulation. The processing unit is further configured to extract heart rate variability features from the heart signal, and the evaluation unit is further configured to predict likelihood of ovulation based on the heart rate variability features.

Methods, systems, and devices for miscarriage identification are described. A system may be configured to receive physiological data associated with a user that is pregnant and collected over a plurality of days, where the physiological data includes at least temperature data. Additionally, the system may be configured to determine a time series of temperature values. The system may then identify that the temperature values are lower than a pregnancy baseline of temperature values for the user and detect an indication of an early pregnancy loss of the user. The system may generate a message for display on a graphical user interface on a user device that indicates the indication of the early pregnancy loss.

A model for a cardiovascular amplitude metric characterizes timewise changes in a cardiac metric for a user based on a follicular mean of the cardiac metric and a luteal mean of the cardiac metric. The cardiovascular amplitude metric can be calculated for the user, e.g., based on data from a wearable physiological monitor, and used to provide coaching for fertility, hormonal health, fitness, and so forth.

An electronic system for detecting events related to a pregnancy of a female human, such as ovulation, conception, and miscarriage, comprises a wearable device (1) with a sensor system (100) worn in contact with the skin for measuring one or more physiological parameters. A processor (13, 30, 40) is configured to receive a user entry indicating a time of actual menses, and to determine time windows, for analyzing physiological parameters of the female human, using the time of actual menses. The processor is further configured to detect the pregnancy related events by comparing the physiological parameters, determined and recorded for a first time window, with those determined and recorded for a second time window, to indicate the pregnancy related events when defined detection criteria are met, and to use the user input for pregnancy related events to optimize the detection of these events with machine learning trained algorithms.

A device may include an artificial intelligence (AI) model for pregnancy classification. The AI model may be trained by inputting labeled training data. During training, the AI model may determine, using a loss function, an error margin for the binary classification AI model based on inputting the labeled training data. The loss function may impose, for false positive pregnancy classifications, a first penalty factor that is weighted relative to a menstruation start date and that is greater than a reward factor for true positive pregnancy classifications. The loss function may impose a second penalty factor for classification confidences that change by a threshold amount between two consecutive days. The AI model may adjust one or more parameters of the binary classification AI model based on the error margin determined using the loss function.