US-12616415-B2 - Neural signal detection of immune responses

Abstract

Disclosed are devices, systems and methods for neural signal detection of immune responses. In some aspects, a system includes a processing unit: a receiving unit configured to receive at least one sensor signal from a wearable sensor, where the wearable sensor is configured to detect at least one neural signal of a patient; and a tangible non-transitory computer readable medium having instructions configured to cause the processing unit to automatically receive a data signal from the receiving unit, automatically detect an immune response based at least in part on the data signal, automatically create a notification based at least in part on the immune response, and automatically present the notification to a user of the system.

Inventors

• Imanuel Lerman
• Ramesh Rao
• Ming-Xiong Huang
• Todd P. Coleman
• Yifeng Bu

Assignees

• THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Dates

Publication Date

20260505

Application Date

20220725

Claims (20)

1. 1 . A system for immune response identification to detect a hyperinflammatory response, comprising: a wearable sensor device configured to be worn against a cervical region of a subject, wherein the wearable sensor device comprises a magnetic field sensor and/or an array of electrodes configured to transcutaneously collect sensor data from the subject; and a processing unit comprising at least one processor and at least one memory, wherein the at least one processor executes instructions stored on the at least one memory to cause the processing unit to: receive, via the wearable sensor device, a neural signal of the subject and a physiological signal of the subject detected by the wearable sensor device: compare a plurality of signal features across the at least one neural signal and the at least one physiological signal with historical signal labels associated with historical immune responses from a database of historical signal labels specific to the patient and/or a demographic of the patient; based on the comparing, identify an occurrence of an immune response of the subject indicating a hyperinflammatory response; and cause a notification of the occurrence of the immune response to be presented.
2. 2 . The system of claim 1 , wherein the magnetic field sensor includes an optically pumped magnetometer (OPM).
3. 3 . The system of claim 2 , wherein the at least one neural signal includes a vagus nerve signal that is detected via an array of electrodes of the wearable sensor device located at the cervical region of the subject.
4. 4 . The system of claim 2 , wherein the at least one neural signal includes a vagus nerve signal that is detected via an optically pumped magnetometer of the wearable sensor device located at the cervical region of the subject.
5. 5 . The system of claim 1 , wherein identifying the occurrence of the immune response of the subject comprises classifying the immune response as one of: an inflammation, an infection, a cytokine response, a specific pathogen, or a specific disease.
6. 6 . The system of claim 1 , wherein the historical signal labels are associated with a resting state of the subject.
7. 7 . The system of claim 1 , wherein the at least one processor executes instructions to further cause the processing unit to determine the historical signal labels associated with historical immune responses based on: obtaining a historical neural signal and a historical physiological signal over a duration of a historical immune response, and determining, via a data model, the historical signal labels to indicate a first correlation between features of the historical neural signal and the historical physiological signal and a second correlation between features of the historical neural signal and the historical immune response.
8. 8 . The system of claim 7 , wherein the historical neural signal is obtained using an optically pumped magnetometer (OPM) and/or an array of electrodes configured to transcutaneously collect sensor data from the subject.
9. 9 . The system of claim 1 , wherein the plurality of signal features includes a cytokine-to-neural-signal value that is compared against a threshold in the historical signal labels.
10. 10 . The system of claim 1 , wherein the plurality of signal features includes a frequency of neural spike firings in the at least one neural signal.
11. 11 . The system of claim 1 , wherein the plurality of signal features across the at least one neural signal and the at least one physiological signal are identified based on correlating the at least one neural signal and the at least one physiological signal with respect to time.
12. 12 . A non-transitory computer readable medium having executable computer code stored thereon, the executable computer code comprising instructions configured to cause a processor to perform operations comprising: receiving, via a wearable sensor attached to a surface of a subject, a neural signal of the subject and a physiological signal of the subject detected by the wearable sensor, wherein the neural signal comprises a vagus nerve signal that is detected by the wearable sensor from a cervical region of the subject; comparing a plurality of signal features across the at least one neural signal and the at least one physiological signal with historical signal labels associated with one or more past immune responses from a database of historical signal labels specific to the patient and/or a demographic of the patient; based on the comparing, identifying an occurrence of an immune response of the subject indicating sepsis; and causing a notification of the occurrence of the immune response to be presented.
13. 13 . The non-transitory computer readable medium of claim 12 , wherein the at least one neural signal is detected via an array of electrodes of the wearable sensor.
14. 14 . The non-transitory computer readable medium of claim 12 , wherein the at least one neural signal includes a vagus nerve signal that is detected via an optically pumped magnetometer of the wearable sensor located at a cervical region of the subject.
15. 15 . The non-transitory computer readable medium of claim 12 , wherein identifying whether the occurrence of the immune response of the subject comprises classifying the immune response as one of: an inflammation, an infection, a cytokine response, a specific pathogen, or a specific disease.
16. 16 . The non-transitory computer readable medium of claim 12 , wherein the historical signal labels are associated with a resting state of the subject.
17. 17 . The non-transitory computer readable medium of claim 12 , further comprising determining the historical signal labels associated with one or more past immune responses based on: obtaining a historical neural signal and a historical physiological signal over a duration of a past immune response, and determining, via a data model, the historical signal labels to indicate a first correlation between features of the historical neural signal and the historical physiological signal and a second correlation between features of the historical neural signal and the past immune response.
18. 18 . The non-transitory computer readable medium of claim 17 , wherein the historical neural signal is obtained using an optically pumped magnetometer (OPM).
19. 19 . The non-transitory computer readable medium of claim 12 , wherein the plurality of signal features includes a cytokine-to-neural-signal value that is compared against a threshold in the historical signal labels.
20. 20 . The non-transitory computer readable medium of claim 12 , wherein the plurality of signal features includes a frequency of neural spike firings in the at least one neural signal.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This patent document claims priorities and benefits of U.S. Provisional Application No. 63/226,087, titled “NEURAL SIGNAL DETECTION OF IMMUNE RESPONSES” and filed on Jul. 27, 2021. The entire content of the aforementioned patent application is incorporated by reference as part of the disclosure of this patent document. TECHNICAL FIELD This patent document relates to wearable sensor technology. BACKGROUND Many conventional methods for determining disease states employ blood cultures and/or laboratory tests. Yet, conventional methods are time typically time-consuming causing delays in disease state identification in patients, which may delay treatment. Some conventional systems and technological processes may generate neuromodulation signals to stimulate peripheral nerves in a patient. Some of these systems may detect a response to nerve stimulation. Some of these conventional systems and technological processes may determine a disease in a patient that is neurologic and/or psychiatric, based on the response to the nerve stimulation. Other conventional systems and technological processes may measure nerve activities in a patient through employment of invasively-implanted electrodes in patients with diabetes. Therefore, a need exists for more efficient and noninvasive early stage detection of disease states. SUMMARY Disclosed are devices, systems and methods for neural signal detection of immune responses. Immune and inflammatory responses are controlled by the vagus nerve in response to pathogen invasion, tissue injury, and other stimuli. Thus, certain vagus nerve signal features/signatures are correlated with immune responses to different stimuli. According to various embodiments described herein, a catalog of vagus nerve signal signatures is generated. Vagus nerve activity and other physiological signals of a given subject are monitored and compared against the features/signatures of the catalog. Based on this comparison, early detection of pathogen exposure of the given subject can be accomplished. Further, early detection of immune responses, such as cytokine release, can enable early detection of sepsis and septic shock caused by dysregulated or excessive cytokine concentrations. In one exemplary aspect, a system for pre-symptomatic detection of pathogen-stimulated immune responses via neural signals is disclosed. The system includes a processing unit including a processor configured to cause the system to, for a first subject stimulated with a known pathogen, obtaining a neural signal and a physiological signal from a cervical region of the first subject through which a vagus nerve of the first subject extends. The neural signal includes a vagus nerve signal that is autonomically communicated through the vagus nerve as an immune response to the known pathogen. The processor is configured to further cause the system to extract, from the neural signal and the physiological signal, a plurality of historical labels that correlate signal features across the neural signal and the physiological signal with the known pathogen. The processor is configured to further cause the system to for a second subject, monitor a second neural signal of the second subject via a wearable device adhered to a cervical region of the second subject through which a vagus nerve of the second subject extends. The processor is configured to further cause the system to, based on identifying a particular signal feature in the second neural signal that is correlated with the known pathogen according to the plurality of historical labels, determine an occurrence of the immune response to the known pathogen in the second subject. The processor is configured to further cause the system to cause a notification of the occurrence of the immune response to the known pathogen to be presented to the second subject via a personal device associated with the second subject. In another exemplary aspect, a method for early detection of immune response of a subject is disclosed. The method includes receiving, via a wearable sensor attached to a surface of the subject, at least one neural signal of the subject and at least one physiological signal of the subject detected by the wearable sensor. The method further includes comparing a plurality of signal features across the at least one neural signal and the at least one physiological signal with historical signal labels associated with one or more past immune responses. The method further includes identifying an occurrence of an immune response of the subject based on the comparing. The method further includes causing a notification of the occurrence of the immune response to be presented to the subject via a personal device for the subject. In another exemplary aspect, a non-transitory computer readable medium having executable computer code stored thereon is disclosed. The executable computer code includes instructions configured to cause a processor to perform