Miscarriage identification and prediction from wearable-based physiological data
Inventors
Thigpen, Nina Nicole • Gotlieb, Neta A. • Pho, Gerald • Aschbacher, Kirstin Elizabeth
Assignees
Publication Number
US-12171569-B2
Publication Date
2024-12-24
Expiration Date
2042-03-31
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Abstract
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.
Core Innovation
The invention provides methods, systems, and devices for miscarriage identification and prediction utilizing physiological data collected from wearable devices. The system receives physiological data associated with a pregnant user, including temperature data collected over multiple days, and determines a time series of temperature values. It identifies when these temperature values fall below a pregnancy baseline temperature for the user and detects an indication of an early pregnancy loss. Subsequently, the system generates a message for display on a graphical user interface indicating the early pregnancy loss indication.
The problem solved addresses deficiencies in conventional cycle detection and pregnancy monitoring techniques typically employed by wearable devices. Standard cycle prediction methods often rely on single daily manual temperature readings, which lack sufficient contextual information to accurately predict pregnancy patterns or early pregnancy loss. Even devices that continuously measure temperature do not typically integrate other physiological, behavioral, or contextual inputs to comprehensively assess pregnancy health. This invention enables continuous collection and analysis of physiological data, including temperature, heart rate, respiratory rate, heart rate variability, and sleep data, to identify morphological deviations from pregnancy baselines that indicate early pregnancy loss, before symptomatic manifestations.
Claims Coverage
The patent contains one main independent claim focused on a method for identifying and predicting early pregnancy loss using physiological data from a wearable ring device. The inventive features capture detection of temperature deviations relative to pregnancy baselines, and integration of other physiological parameters.
Detection of early pregnancy loss based on temperature deviations from pregnancy baseline
The system determines a time series of temperature values taken over multiple days from temperature data received from a wearable ring device. It identifies that these temperature values are lower than a pregnancy baseline for the user and detects an indication of early pregnancy loss based on these lower temperature values.
Analysis of positive slopes of temperature time series relative to pregnancy baseline slopes
The system identifies that one or more positive slopes of the user's temperature time series are lower than the positive slopes of the pregnancy baseline temperature values and uses this information to detect early pregnancy loss.
Incorporation of heart rate, heart rate variability, respiratory rate, and sleep disturbances data
The method acquires heart rate, heart rate variability, respiratory rate, and sleep data via the wearable ring device and determines whether these parameters deviate from pregnancy baselines to further detect indications of early pregnancy loss.
Generation of user interface messages and notifications
Upon detection of early pregnancy loss indications, the system generates messages for display on a graphical user interface of a user device to notify the user and possibly clinicians or caregivers.
Use of machine learning classifier for detection
The physiological data can be input into a machine learning classifier to improve detection and prediction of early pregnancy loss based at least in part on the collected data.
The claims focus on a comprehensive system using continuous physiological data collected via a wearable ring device to identify early pregnancy loss through temperature deviations and associated physiological parameters, with interactive user feedback via graphical interfaces, including predictive capabilities leveraging machine learning.
Stated Advantages
Early detection and prediction of miscarriage before the user experiences symptoms.
Improved accuracy and precision over conventional single-point temperature measurement methods.
Utilization of continuous temperature measurement at the finger to capture minute fluctuations not observable with core temperature readings.
Ability to combine multiple physiological data streams (heart rate, respiratory rate, heart rate variability, sleep disturbances) to enhance miscarriage identification.
Provision of personalized messages, alerts, symptom tags, and recommendations to users and caregivers.
Potential integration with machine learning models to improve prediction capabilities and personalized insights.
Documented Applications
Continuous monitoring of pregnancy health via wearable ring devices for early identification and prediction of miscarriage.
Generation of user notifications and messages to alert users and clinicians of potential early pregnancy loss.
Providing personalized fertility support including tracking menstrual cycles, ovulation, pregnancy, and miscarriage.
Use in clinical and fertility support contexts for monitoring pregnancy progression and risks.
Utilization of sleep, activity, and physiological data to guide fertility treatment and inform user lifestyle adjustments.
Interested in licensing this patent?