FERTILITY PREDICTION FROM WEARABLE-BASED PHYSIOLOGICAL DATA

1 . A method comprising:

receiving physiological data associated with a user from a wearable device, the physiological data comprising at least temperature data;

determining a time series of a plurality of temperature values taken over a plurality of days based at least in part on the received temperature data, wherein the time series comprises a plurality of menstrual cycles for the user;

determining a plurality of menstrual cycle length parameters associated with the plurality of menstrual cycles based at least in part on the received temperature data;

determining a user fertility prediction based at least in part on determining the plurality of menstrual cycle length parameters; and

generating a message for display on a graphical user interface on a user device that indicates the determined user fertility prediction.

2 . The method of claim 1 , further comprising:

identifying one or more local maximum of the time series of the plurality of temperature values based at least in part on determining the time series; and

calculating a duration between a first local maximum of the one or more local maximum and a second local maximum of the one or more local maximum based at least in part on the identifying, wherein determining the plurality of menstrual cycle length parameters is based at least in part on calculating the duration.

3 . The method of claim 1 , further comprising:

identifying one or more positive slopes of the time series of the plurality of temperature values based at least in part on determining the time series, wherein determining the plurality of menstrual cycle length parameters is based at least in part on identifying the one or more positive slopes.

4 . The method of claim 1 , wherein the physiological data further comprises heart rate data, the method further comprising:

determining that the received heart rate data satisfies a threshold heart rate for the user for at least a portion of the plurality of days, wherein determining the user fertility prediction is based at least in part on determining that the received heart rate data satisfies the threshold heart rate for the user.

5 . The method of claim 1 , wherein the physiological data further comprises heart rate variability data, the method further comprising:

determining that the received heart rate variability data satisfies a threshold heart rate variability for the user for at least a portion of the plurality of days, wherein determining the user fertility prediction is based at least in part on determining that the received heart rate variability data satisfies the threshold heart rate variability for the user.

6 . The method of claim 1 , wherein the physiological data further comprises respiratory rate data, the method further comprising:

determining that the respiratory rate data satisfies a threshold respiratory rate for the user for at least a portion of the plurality of days, wherein determining the user fertility prediction is based at least in part on determining that the received respiratory rate data satisfies the threshold respiratory rate for the user.

7 . The method of claim 1 , wherein the physiological data further comprises sleep data, the method further comprising:

determining that a quantity of detected sleep disturbances from the received sleep data satisfies a baseline sleep disturbance threshold for the user for at least a portion of the plurality of days, wherein determining the user fertility prediction is based at least in part on determining that the quantity of detected sleep disturbances satisfies the baseline sleep disturbance threshold for the user.

8 . The method of claim 1 , wherein the plurality of menstrual cycle length parameters comprise at least one of an average menstrual cycle length, a standard deviation menstrual cycle length, an average follicular phase length, an average luteal phase length, a range of menstrual cycle lengths, a quantity of anovulatory cycles, or a combination thereof.

9 . The method of claim 1 , further comprising:

determining each temperature value of the plurality of temperature values based at least in part on receiving the temperature data, wherein the temperature data comprises continuous daytime temperature data.

10 . The method of claim 1 , further comprising:

receiving, via the user device, an indication comprising an age of the user, a weight of the user, a lifestyle summary of the user, a type of fertility treatment experienced by the user, a quantity of miscarriages experienced by the user, or a combination thereof, wherein determining the user fertility prediction is based at least in part on receiving the indication.

11 . The method of claim 1 , further comprising:

transmitting the message that indicates the determined user fertility prediction to the user device, wherein the user device is associated with a clinician, the user, a fertility specialist, or a combination thereof.

12 . The method of claim 1 , further comprising:

causing a graphical user interface of a user device associated with the user to display a message associated with the determined user fertility prediction.

13 . The method of claim 12 , wherein the message further comprises a score associated with the determined user fertility prediction, a time interval during which the determined user fertility prediction is valid for, a probability of becoming pregnant within the time interval based on the determined user fertility prediction, an indication of physiological and behavioral indicators that contribute to the determined user fertility prediction, educational content associated with the determined user fertility prediction, recommendations to improve the determined user fertility prediction, or a combination thereof.

14 . The method of claim 1 , further comprising:

inputting the physiological data into a machine learning classifier, wherein determining the user fertility prediction is based at least in part on inputting the physiological data into the machine learning classifier.

15 . The method of claim 1 , wherein the wearable device comprises a wearable ring device.

16 . The method of claim 1 , wherein the wearable device collects the physiological data from the user based on arterial blood flow.

17 . An apparatus, comprising:

a processor;

memory coupled with the processor; and

instructions stored in the memory and executable by the processor to cause the apparatus to:

receive physiological data associated with a user from a wearable device, the physiological data comprising at least temperature data;

determine a time series of a plurality of temperature values taken over a plurality of days based at least in part on the received temperature data, wherein the time series comprises a plurality of menstrual cycles for the user;

determine a plurality of menstrual cycle length parameters associated with the plurality of menstrual cycles based at least in part on the received temperature data;

determine a user fertility prediction based at least in part on determining the plurality of menstrual cycle length parameters; and

generate a message for display on a graphical user interface on a user device that indicates the determined user fertility prediction.

18 . The apparatus of claim 17 , wherein the instructions are further executable by the processor to cause the apparatus to:

identify one or more local maximum of the time series of the plurality of temperature values based at least in part on determining the time series; and

calculate a duration between a first local maximum of the one or more local maximum and a second local maximum of the one or more local maximum based at least in part on the identifying, wherein determining the plurality of menstrual cycle length parameters is based at least in part on calculating the duration.

19 . A non-transitory computer-readable medium storing code, the code comprising instructions executable by a processor to:

receive physiological data associated with a user from a wearable device, the physiological data comprising at least temperature data;

determine a time series of a plurality of temperature values taken over a plurality of days based at least in part on the received temperature data, wherein the time series comprises a plurality of menstrual cycles for the user;

determine a plurality of menstrual cycle length parameters associated with the plurality of menstrual cycles based at least in part on the received temperature data;

determine a user fertility prediction based at least in part on determining the plurality of menstrual cycle length parameters; and

generate a message for display on a graphical user interface on a user device that indicates the determined user fertility prediction.

20 . The non-transitory computer-readable medium of claim 19 , wherein the instructions are further executable by the processor to:

identify one or more local maximum of the time series of the plurality of temperature values based at least in part on determining the time series; and

calculate a duration between a first local maximum of the one or more local maximum and a second local maximum of the one or more local maximum based at least in part on the identifying, wherein determining the plurality of menstrual cycle length parameters is based at least in part on calculating the duration.