Cardiac condition detection
Systems and methods for determining a cardiac condition of the human based on acceleration measurements received from one or more accelerometers of a garment worn by a human, electrocardiogram measurements received from electrodes of a garment worn by the human, and a machine learning model previously determined based on training data. An alert message that indicates the determined cardiac condition may be transmitted or displayed to the human wearing the garment or another person who will assist the human. For example, a posture pattern may be determined based on the acceleration measurements. The cardiac condition may be determined based in part on the posture pattern.
1. A system, comprising:
a garment comprising a plurality of electrodes and one or more accelerometers; and
a processing apparatus that is configured to:
receive acceleration measurements from the one or more accelerometers;
receive electrocardiogram measurements from the plurality of electrodes;
determine a posture pattern of a human based on the acceleration measurements;
determine a cardiac condition of the human based on the posture pattern and the electrocardiogram measurements by inputting features extracted from the electrocardiogram measurements and the posture pattern to a machine learning model previously determined based on training data; and
transmit or display an alert message that indicates the determined cardiac condition.
2. The system of claim 1 , in which the one or more accelerometers comprise:
a first accelerometer that is positioned, as a component of the garment, such that the first accelerometer is capable of being fastened to a chest of the human.
3. The system of claim 2 , in which the one or more accelerometers comprise:
a second accelerometer that is positioned, as a component of the garment, such that the second accelerometer is capable of being fastened to a waist of the human.
4. The system of claim 1 , in which the processing apparatus is attached to the garment.
5. The system of claim 1 , in which the garment comprises:
one or more motion sensor modules that include the one or more accelerometers;
an electrocardiogram sensor module that is connected via conductors to the plurality of electrodes and detects the electrocardiogram measurements from the electrodes; and
conductors that connect the processing apparatus to the electrocardiogram sensor module and to the one or more motion sensor modules.
6. The system of claim 1 , in which the processing apparatus is configured to receive the acceleration measurements and the electrocardiogram measurements via wireless communications from one or more sensor modules connected to the one or more accelerometers and the plurality of electrodes.
7. The system of claim 1 , comprising a defibrillator, and in which the processing apparatus is configured to:
activate the defibrillator responsive to the determination of the cardiac condition.
8. The system of claim 1 , in which the cardiac condition is ventricular fibrillation or supraventricular tachycardia.
9. The system of claim 1 , in which the machine learning module is a first machine learning model, and in which the processing apparatus is configured to:
input features extracted from the acceleration measurements to a second machine learning module that has been determined based on training data; and
determine the posture pattern based on output of the second machine learning module.
10. The system of claim 9 , in which the posture pattern is selected from a set of posture patterns that comprises sitting, standing, walking, running, lying, and fallen.
11. The system of claim 9 , in which the processing apparatus is configured to:
determine a feature based on an estimate of an entropy of a normalized power spectral density of a sequence of the acceleration measurements; and
determine the posture pattern based in part on the feature.
12. The system of claim 9 , in which the processing apparatus is configured to:
determine a feature based on an estimate of a power spectral density within a frequency band for a sequence of the acceleration measurements; and
determine the posture pattern based in part on the feature.
13. The system of claim 1 , in which the processing apparatus is configured to:
determine a feature based on an estimate of an entropy of a normalized power spectral density of a sequence of the acceleration measurements; and
determine the cardiac condition based in part on the feature.
14. The system of claim 1 , in which the processing apparatus is configured to:
determine a feature based on an estimate of a power spectral density within a frequency band for a sequence of the acceleration measurements; and
determine the cardiac condition based in part on the feature.
15. The system of claim 1 , in which the processing apparatus is configured to:
determine a feature based on an estimate of an entropy of a normalized power spectral density of a sequence of the electrocardiogram measurements; and
determine the cardiac condition based in part on the feature.
16. The system of claim 1 , in which the processing apparatus is configured to:
determine a feature based on an estimate of a power spectral density within a frequency band for a sequence of the electrocardiogram measurements; and
determine the cardiac condition based in part on the feature.
17. The system of claim 1 , in which the processing apparatus is configured to collect training data with the garment, and in which some of the training data has been gathered from the human using the garment.
18. The system of claim 1 , in which the processing apparatus is configured to:
determine a profile of the human including a plurality of features based on the electrocardiogram measurements;
compare the profile to a registered template associated with an identity;
confirm the identity of the human based on comparison of the profile to the registered template; and
transmit or display information about the confirmed identity along with the alert message that indicates the determined cardiac condition.
19. A method comprising:
receiving acceleration measurements from one or more accelerometers of a garment worn by a human;
receiving electrocardiogram measurements from electrodes of a garment worn by the human;
determining a posture pattern of the human based on the acceleration measurements;
determining a cardiac condition of the human based on the posture pattern and the electrocardiogram measurements by inputting features extracted from the electrocardiogram measurements and the posture pattern to a machine learning model previously determined based on training data; and
transmitting or displaying an alert message that indicates the determined cardiac condition.
20. A system comprising:
a processor;
a network interface; and
a memory storing instructions executable by the processor that upon execution by the processor cause the processor to perform operations comprising:
receiving acceleration measurements from one or more accelerometers of a garment worn by a human;
receiving electrocardiogram measurements from electrodes of a garment worn by the human;
determining a posture pattern of the human based on the acceleration measurements;
determining a cardiac condition of the human based on the posture pattern and the electrocardiogram measurements by inputting features extracted from the electrocardiogram measurements and the posture pattern to a machine learning model previously determined based on training data; and
transmitting, via the network interface, an alert message that indicates the determined cardiac condition.