System for acquisition and analysis of maternal and/or fetal physiological signals
A system includes a wearable device configured to be worn by a pregnant patient and including a plurality of electrodes, the wearable device configured to sense a first patient data associated with the patient and her fetus, a second device configured to sense a second patient data associated with the patient and her fetus, and a computing device configured to obtain the first and second patient data. The computing device is also configured to identify first features of a maternal or a fetal heart rate signal determined from the first patient data and to identify second features of a maternal or a fetal biometric signal determined from the second patient data, and to determine, based on applying the first and second features as inputs to a machine learning model, predicted outcomes associated with the patient, and to generate reports including an indication of the predicted outcomes for display.
1 . A system comprising:
a first wearable device configured to be worn by a pregnant patient, the first wearable device further comprising: a plurality of electrodes configured to sense a first patient data associated with the patient and her fetus;
a second device configured to sense a second patient data associated with the patient and her fetus; and
a computing device configured to:
obtain the first patient data of a mother from the first wearable device;
obtain the second patient data of a fetus of the mother from the second device;
identify one or more first features of a maternal or a fetal heart rate signal determined from the first patient data;
identify one or more second features of a maternal biometric signal or a fetal biometric signal determined from the second patient data;
determine, based on applying the one or more first features and the one or more second features as inputs to a machine learning model trained with historical first patient data and historical second patient data, one or more predicted outcomes associated with the mother or the fetus of the mother; and
configure, by the computing device, algorithms to control an acquisition of the maternal biometric signal or the fetal biometric signal, implemented by the first wearable device and the second device, using the historical first patient data and the historical second patient data;
generate one or more reports including an indication of the one or more predicted outcomes for display on one or more of a patient computing device or a provider computing device, wherein the one or more predicted outcomes is a high risk pregnancy to enable a physician to make a decision to treat the mother and the fetus of the mother in fetal distress by Cesarean section.
2 . The system of claim 1 , wherein the first patient data comprises a maternal electrocardiography (ECG) or heart rate data or a fetal electrocardiography (ECG) or heart rate data, wherein the second patient data comprises other maternal biometric data or other fetal biometric data.
3 . The system of claim 2 , wherein the other maternal biometric data or other fetal biometric data comprises at least one of a blood pressure, a weight, a glucose level, a pH blood level, a blood oxygen level, a breathing rate, a temperature, a uterine contraction data, a patient posture, a patient movement, a skin impedance, a stress level, a bioimpedance spectrum, or an acoustic signal.
4 . The system of claim 3 , wherein the computing device is configured to obtain the other maternal biometric data or other fetal biometric data continuously.
5 . The system of claim 1 , wherein the computing device is configured to obtain the first patient data or the second patient data nocturnally.
6 . The system of claim 1 , wherein the first wearable device further comprises a wearable band configured to be worn about a torso of the patient, wherein the plurality of electrodes are affixed to or embedded in the wearable band, wherein the second device comprises at least one of a mobile device configured to sense the second patient data, a smart watch configured to sense the second patient data, a limb sensor configured to sense the second patient data, or a body sensor configured to sense the second patient data.
7 . The system of claim 1 , wherein the second device is a wearable device.
8 . The system of claim 1 , wherein the second device comprises at least one of a temperature sensor, an accelerometer, a pulse oximeter, a biopotential sensor, or an impedance sensor.
9 . The system of claim 1 , wherein the one or more first features comprise at least one of a baseline heart rate, a baseline variability, a number of accelerations per second, a number of early, late, and variable decelerations per second, a number of prolonged decelerations per second, a sinusoidal pattern, an ejection fraction, a P wave, a QRS complex, a T wave, a PQ interval, a QRS duration, a QT interval, or an RR interval.
10 . The system of claim 1 , wherein the one or more predicted outcomes include at least one of an Apgar score 1, 5 and 10 minutes after birth, a cord blood gas pH level, a neonatal destination immediately after birth, an admission to Neonatal Intensive Care Unit (NICU) within 48 hours of birth, a NICU length of stay, a resuscitation intervention, a neonatal death up to 28 days after birth, a maternal pulmonary embolism, a peripartum cardiomyopathy, a fetal academia, or an arrhythmia.
11 . The system of claim 1 , wherein the machine learning model comprises at least one of a convolutional neural network, a deep convolutional neural network, a random forest, a radial basis function (RBF) kernel support vector machine (SVM), a linear SVM, a linear regression, a logistic regression, a deep multilayer perceptron, a recurrent neural network, a long short-term memory neural network, an artificial neural network, a deep belief network, a Bayesian network, an autoregressive model, a fuzzy-logic system, a hidden Markov model, a Gaussian process model, or a transformer learning models.
12 . A method of treating a mother or a fetus of the mother in fetal distress by Cesarean section comprising:
generating a maternal or fetal outcome prediction, comprising the steps of:
obtaining, by processing circuitry, first patient data of a mother from a first wearable device;
obtaining, by processing circuitry, second patient data of a fetus of the mother from a second device;
identifying, by processing circuitry, one or more first features of a maternal or a fetal heart rate signal determined from the first patient data;
identifying, by processing circuitry, one or more second features of a maternal biometric signal or a fetal biometric signal determined from the second patient data;
configuring, by the processing circuitry, algorithms to control an acquisition of the maternal biometric signal or the fetal biometric signal, implemented by the first wearable device and the second device, using a historical first patient data and a historical second patient data; and
determining, by processing circuitry and based on applying the one or more first features and the one or more second features as inputs to a machine learning model trained with historical first patient data and historical second patient data, one or more predicted outcomes associated with the mother or the fetus of the mother; and
generating, by processing circuitry, one or more reports including an indication of the one or more predicted outcomes for display on one or more of a patient computing device or a provider computing device;
determining, based upon the generated one or more reports, that the mother or the fetus of the mother is in fetal distress; and
treating the mother and fetus of the mother by Cesarean section.
13 . The method of claim 12 , wherein the first patient data comprises a maternal ECG or heart rate data or a fetal ECG or heart rate data, wherein the second patient data comprises other maternal biometric data or other fetal biometric data.
14 . The method of claim 13 , wherein the other maternal biometric data or other fetal biometric data comprises at least one of a blood pressure, a weight, a glucose level, a pH blood level, a blood oxygen level, a breathing rate, a temperature, a uterine contraction data, a patient posture, a patient movement, a skin impedance, a stress level, a bioimpedance spectrum, or an acoustic signal.
15 . The method of claim 14 , wherein the processing circuitry obtains the other maternal biometric data or other fetal biometric data continuously.
16 . The method of claim 12 , wherein the processing circuitry obtains the first patient data or the second patient data nocturnally.
17 . The method of claim 12 , wherein the one or more first features comprises at least one of a baseline heart rate, a baseline variability, a number of accelerations per second, a number of early, late, and variable decelerations per second, a number of prolonged decelerations per second, a sinusoidal pattern, an ejection fraction, a P wave, a QRS complex, a T wave, a PQ interval, a QRS duration, a QT interval, or an RR interval.
18 . The method of claim 12 , wherein the one or more predicted outcomes include at least one of an Apgar score 1, 5 and 10 minutes after birth, a cord blood gas pH level, a neonatal destination immediately after birth, an admission to Neonatal Intensive Care Unit (NICU) within 48 hours of birth, a NICU length of stay, a resuscitation intervention, a neonatal death up to 28 days after birth, a maternal pulmonary embolism, a peripartum cardiomyopathy, a fetal academia, or an arrhythmia.
19 . The method of claim 12 , wherein the machine learning model comprises at least one of a convolutional neural network, a deep convolutional neural network, a random forest, an radial basis function (RBF) kernel support vector machine (SVM), a linear SVM, a linear regression, a logistic regression, a deep multilayer perceptron, a recurrent neural network, a long short-term memory neural network, an artificial neural network, a deep belief network, a Bayesian network, an autoregressive model, a fuzzy-logic system, a hidden Markov model, a Gaussian process model, or a transformer learning model.
20 . A system comprising:
a first wearable device configured to be worn by a pregnant patient, the first wearable device further comprising: a plurality of electrodes configured to sense a first patient data associated with the patient and her fetus;
a second device configured to sense a second patient data associated with the patient and her fetus; and
a computing device configured to:
obtain the first patient data of a mother from the first wearable device;
obtain the second patient data of a fetus of the mother from the second device;
identify one or more first features of a maternal or a fetal heart rate signal determined from the first patient data;
identify one or more second features of a maternal biometric signal or a fetal biometric signal determined from the second patient data;
determine, based on applying the one or more first features and the one or more second features as inputs to a machine learning model trained with historical first patient data and historical second patient data, one or more predicted outcomes associated with the mother or the fetus of the mother;
configure, by the computing device, algorithms to control an acquisition of the maternal biometric signal or the fetal biometric signal, implemented by the first wearable device and the second device, using the historical first patient data and the historical second patient data;
generate one or more reports including an indication of the one or more predicted outcomes for display on one or more of a patient computing device or a provider computing device, wherein the one or more predicted outcomes is a high risk pregnancy to enable a physician to make a decision to treat the mother and the fetus of the mother in fetal distress by an appropriate intervention.