Wearable cardioverter defibrillator with AI-based features
“Artificial Intelligence” or “AI” technology can be applied to Wearable Cardioverter Defibrillators (“WCDs”) and other wearable medical equipment in various ways, including: garment fitting and adjustment; analyzing electrocardiogam (“ECG”), other sensor data and/or other patient data (e.g., age, gender, previous medical conditions, etc.) in real time to detect/assess the patient's present condition and/or need for treatment for cardiac and other conditions (e.g., stroke, coughing, apnea, etc.); detecting imminent failure of the wearable medical device components; capturing and reporting data collected from the patient for presenting to clinicians; adjusting thresholds for alarms and notifications based on patient's responses; improving patient compliance based on the patient's past non-compliant behavior and actions that resulted in the patient becoming compliant; providing tests to the patient (e.g., grip test, dexterity tests, balance tests, etc.) and learning the patient's responses to detect/assess the patient's present condition and/or need for treatment; learning the patient's voice, activity, posture, time of day, etc. for implementing intelligent voice recognition/activation of the medical device.
1. A Wearable Cardioverter Defibrillator (WCD) system, comprising:
a support structure configured to be worn by an ambulatory patient, the support structure having a fitment that corresponds to how well the support structure fits the ambulatory patient;
an energy storage module configured to store an electrical charge;
a discharge circuit coupled to the energy storage module;
a plurality of sensors, a first sensor in the plurality being operative to detect physiological conditions of the ambulatory patient, a second sensor in the plurality being operative to detect environmental conditions, the physiological conditions including at least a heart rhythm of the ambulatory patient, the environmental conditions including at least one of motion or location;
a data input source in communication with a remote data provision service, the data input source being operative to receive data from the data provision service; and
one or more processor(s) configured to:
provide input from the plurality of sensors and from the data input source to an Artificial Intelligence (AI) processing module, the AI processing module being configured to analyze the input and make a determination regarding the fitment of the support structure while worn by the ambulatory patient, and, and wherein the input includes an activity level of the ambulatory patient, or breathing sounds of the ambulatory patient, or both the activity level and the breathings sounds of the ambulatory patient, and further wherein the determination indicates an improper fitment of the support structure;
make adjustments based on the analysis by the AI processing module, and
initiate a shock therapy to the ambulatory patient by causing the discharge circuit to discharge the electrical charge to the patient while being worn by the ambulatory patient.
2. The WCD system recited in claim 1 , wherein the AI processing module comprises one or more of a neural network, a convolutional neural network, a support vector machine, stochastic computing circuits, and a random forest.
3. The WCD system recited in claim 1 , wherein the fitment of the support structure comprises one or more of a style of the support structure, dimensions of the support structure, materials of the support structure, features of the support structure, or components included with the support structure.
4. The WCD system recited in claim 1 , wherein the improper fitment comprises an indication that the fitment is too tight.
5. The WCD system recited in claim 1 , wherein the processor is further configured to make adjustment by providing a notification that the fitment is incorrect.
6. The WCD system recited in claim 5 , wherein the notification further comprises instructions for adjusting the fitment of the support structure.
7. The WCD system recited in claim 1 , wherein the remote data provision service is collocated with the support structure, the energy storage module, the discharge circuit, and the plurality of sensors.
8. The WCD system recited in claim 1 , wherein the data input source is collocated with at least one of the one or more processor(s).
9. The WCD system recited in claim 8 , wherein the WCD system comprises two or more processor(s), and further wherein a first of the two or more processor(s) is configured to implement the AI processing module and to make the adjustments.
10. The WCD system recited in claim 9 , wherein a second of the two or more processor(s) is configured to initiate the shock therapy.
11. The WCD system recited in claim 10 , wherein the second of the two or more processor(s) is collocated with the support structure, the energy storage module, the discharge circuit, the plurality of sensors, and the remote data provision service.
12. The WCD system recited in claim 4 , wherein the improper fitment further comprises an indication that the ECG sensors are not in contact with skin of the patient.