Systems and methods for monitoring fetal wellbeing

1. A system for monitoring fetal wellbeing over time during pregnancy, the system comprising:

a sensor coupled to a pregnant woman;

a processor communicatively coupled to the sensor; and

a computer-readable medium having non-transitory, processor-executable instructions stored thereon, wherein execution of the instructions causes the processor to perform a method comprising:

acquiring a signal from the sensor;

processing the signal to identify and extract a plurality of parameters of interest from the signal, wherein the plurality of parameters of interest include at least one physiological parameter and at least one behavioral parameter;

tracking the plurality of parameters of interest to generate a personalized fetal wellbeing trend;

identifying a deviation from the personalized fetal wellbeing trend, the deviation including a measured change in one or more of the plurality of parameters of interest that is aberrant from the personalized fetal wellbeing trend;

analyzing the deviation to determine whether the deviation is indicative of a change in fetal wellbeing, the analyzing including determining whether the deviation indicates that a value associated with the at least one behavioral parameter drops below an average value for the at least one behavioral parameter represented in the personalized fetal wellbeing trend; and

determining, based on the analyzed deviation, a probability that a fetus associated with the pregnancy is in distress.

2. The system of claim 1 , wherein the identifying comprises comparing the plurality of parameters of interest to a fetal wellbeing index.

3. The system of claim 1 , wherein the method performed by the processor further comprises:

identifying a second deviation, the second deviation being from a population-level fetal wellbeing trend; and

analyzing the second deviation to determine whether the second deviation is indicative of a change in fetal wellbeing.

4. The system of claim 3 , wherein analyzing the second deviation is performed by one of thresholding, a machine learning algorithm, and regression modeling.

5. The system of claim 4 , wherein the machine learning algorithm comprises one or more of: a generalized linear model, support vector machines, and random forests.

6. The system of claim 1 , wherein the system comprises a plurality of sensors and wherein acquiring a signal comprises acquiring a plurality of signals.

7. The system of claim 1 , wherein the sensor comprises one or more sensors configured to measure one or more of: fetal movement, fetal heart electrical activity, fetal heart sound, fetal heart rate, fetal heart rate variability, fetal oxygenation, an amount of amniotic fluid, placental oxygenation, placental temperature, placental pH, fetal breathing, fetal position, fetal orientation, and fetal distress.

8. The system of claim 1 , wherein the sensor senses one or more of: a biopotential signal, inertial signal, acoustic signal, ultrasound signal, bio-impedance signal, optical signal, near-infrared spectroscopy signal, electrochemical signal and temperature signal.

9. The system of claim 1 , wherein the plurality of parameters of interest comprises two or more of: an average fetal heart rate, an average fetal heart rate variability, an average fetal heart beat, a fetal kick count, a fetal movement count, a fetal oxygenation level, an average placental oxygenation level, an average placental temperature, an average placental pH, an average amount of amniotic fluid, a fetal heart rate profile, a fetal heart rate variability profile, and a fetal movement profile.

10. The system of claim 1 , wherein the generated probability indicates whether the fetus is distressed or healthy and wherein the method performed by the processor further comprises determining a degree of certainty around the probability.

11. The system of claim 1 , wherein analyzing the plurality of parameters of interest further comprises:

comparing the plurality of parameters of interest to a threshold, wherein when one or more of the plurality of parameters of interest are above the threshold, there is a higher probability that the fetus is healthy; and wherein when one or more of the plurality of parameters of interest are below the threshold, there is a higher probability that the fetus is distressed.

12. The system of claim 1 , further comprising:

analyzing the plurality of parameters of interest using regression models or machine learning algorithms to determine a probability that the fetus is healthy or distressed.

13. The system of claim 6 , wherein the signal comprises a fetal heart rate signal and a plurality of fetal movement signals such that the method performed by the processor comprises:

acquiring the fetal heart rate signal using one or more sensors of the plurality of sensors; and

acquiring a plurality of fetal movement signals from one or more sensors of the plurality of sensors.

14. The system of claim 13 , wherein the method performed by the processor further comprises:

classifying an absolute value of the fetal heart rate signal into one of four classes: absent fetal heart rate variability (fHRV), minimal fHRV, moderate fHRV, and marked fHRV;

classifying each of the plurality of fetal movement signals into one of three classes: low movement, medium movement, and high movement;

combining the classified fetal heart rate signal and the classified fetal movement signals; and

comparing the combined signals to a fetal wellbeing index to determine a degree of fetal wellbeing.

15. The system of claim 1 , wherein the plurality of parameters of interest comprises at least a fetal movement parameter, an amount of amniotic fluid parameter, and an average fetal heart rate variability (fHRV) parameter.

16. The system of claim 1 , further comprising:

generating, based on the probability, a recommendation for a course of action.

17. The system of claim 1 , wherein the personalized fetal wellbeing trend is based on a personalized fetal wellbeing index comprising rank ordered observations and measurements derived from historical fetal wellbeing measurements associated with the personalized fetal wellbeing trend.