DELIVERY DATE PREDICTION

1 - 23 . (canceled)

24 . A computer program product comprising non-transitory computer readable code that, when executing on one or more computing devices, causes the computing devices to perform the steps of:

acquiring data from a wearable monitor worn by a user during a pregnancy of the user, the data including heart rate data;

calculating a history of heart rate variability for the user during the pregnancy by:

identifying a number of periods of sleep for the user during the pregnancy based on the data from the wearable monitor, each of the number of periods of sleep associated with a calendar day;

during each of the number of periods of sleep for the user, calculating a plurality of heart rate variability measurements over a plurality of intervals;

for each of the number of periods of sleep for the user, aggregating the plurality of heart rate variability measurements into a heart rate variability;

aggregating the heart rate variability into a plurality of weekly multi-day medians for heart rate variability for each of a plurality of consecutive weeks;

identifying an inflection point in the history of heart rate variability at a day of a week where the weekly multi-day medians for heart rate variability change from a timewise decreasing value to a timewise increasing value;

determining a predicted delivery date for an infant of the user at a predetermined number of days after the inflection point; and

transmitting a notification to a user device of the user identifying the predicted delivery date.

25 . The computer program product of claim 24 , wherein each of the plurality of intervals is between four and six minutes.

26 . The computer program product of claim 24 , wherein the plurality of intervals include overlapping intervals with starting times separated by at least fifteen seconds.

27 . The computer program product of claim 24 , wherein aggregating the plurality of heart rate variability measurements into the heart rate variability includes calculating a weighted sum of the plurality of heart rate variability measurements.

28 . The computer program product of claim 27 , wherein the weighted sum weights the plurality of heart rate variability measurements more heavily toward an end of each sleep period.

29 . The computer program product of claim 27 , wherein the weighted sum weights the plurality of heart rate variability measurements according to a likelihood of occurring during a period of slow wave sleep.

30 . The computer program product of claim 24 , wherein the wearable monitor is a wearable photoplethysmography device.

31 . A method comprising:

acquiring heart rate data from a wearable monitor worn by a user during a pregnancy of the user;

calculating a history of a heart rate metric for the user during the pregnancy based on the heart rate data; and

determining a predicted delivery date for the pregnancy based on a trend in the history of the heart rate metric for the user.

32 . The method of claim 31 , wherein determining the predicted delivery date includes identifying an inflection point in the history of the heart rate metric and calculating the predicted delivery date to occur a predetermined number of days after the inflection point.

33 . The method of claim 31 , wherein the history of the heart rate metric includes a history of heart rate variability for the user during the pregnancy.

34 . The method of claim 33 , wherein each of a number of heart rate variability values in the history of heart rate variability is calculated based on an aggregation of individual heart rate variability measurements acquired during a period of sleep by the user.

35 . The method of claim 34 , wherein each of a number of heart rate variability values in the history of heart rate variability is calculated as a weighted sum of the individual heart rate variability measurements.

36 . The method of claim 35 , wherein the weighted sum weights heart rate variability measurements more heavily toward an end of the period of sleep.

37 . The method of claim 35 , wherein the weighted sum weights heart rate variability measurements more heavily according to a likelihood of occurring during a period of slow wave sleep.

38 . The method of claim 31 , wherein the history of the heart rate metric includes a history of resting heart rate measurements for the user during the pregnancy.

39 . The method of claim 31 , wherein calculating the history of the heart rate metric includes calculating a weekly sequence of seven day moving medians for the heart rate metric based on the heart rate data.

40 . The method of claim 31 , wherein the heart rate metric includes at least one of a heart rate variability for the user and a resting heart rate for the user.

41 . The method of claim 31 , wherein determining the predicted delivery date includes locating an inflection point in the heart rate metric from a first timewise decreasing value to a second timewise increasing value.

42 . The method of claim 41 , wherein determining the predicted delivery date includes calculating the predicted delivery date at a predetermined number of days after the inflection point.

43 . A system comprising:

a wearable monitor, the wearable monitor configured to acquire physiological data from a user; and

a server coupled in a communicating relationship with the wearable monitor, the server configured to calculate a predicted delivery date for the user by performing the steps of:

acquiring heart rate data from the wearable monitor while worn by the user during a pregnancy,

calculating a history of a heart rate metric for the user during the pregnancy based on the heart rate data, and

calculating the predicted delivery date for the pregnancy at a predetermined number of days after an inflection point in the history of the heart rate metric from a timewise decreasing value in the heart rate metric to a timewise increasing value in the heart rate metric.