Resting state immune response prediction

Abstract

A surface electrode array device, resting state immune response prediction systems, and a method for predicting immune responses are disclosed. The surface electrode array device is configured to detect multi-channel cervical neuronal activity of a subject via several wearable sensors applied to the subject. The system includes a computing device with a receiving unit to receive sensor signals from several wearable sensors worn by a subject, a memory in which to load a resting state immune response prediction program, and a processor that performs operations of the program to determine immune response of the subject before the subject is symptomatic. The method includes receiving sensor signals from wearable sensors of a sensor array worn by a subject, classifying an inflammation risk for the subject based on the sensor signals, classifying an inflammation biotype for the subject based on the sensor signals, and creating a notification based on the results.

Description

RESTING STATE IMMUNE RESPONSE PREDICTIONSTATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT

[0001] This invention was made with government support under grant number 75A50119C00038 awarded by Center for the Biomedical Advanced Research and Development Authority (BARDA) under the U.S. Department of Health and Human Services (DHHS). The government has certain rights in the invention.CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This patent document claims priority to and benefits of U.S. Provisional Application No. 63 / 598,453, titled “RESTING STATE IMMUNE RESPONSE PREDICTION,” and filed on November 13, 2023. The entire contents of the before-mentioned patent application are incorporated by reference as part of the disclosure of this patent document.BACKGROUND

[0003] The physiology of certain organisms, such as human beings, includes an immune system, which is a network of biological systems that protects the organism from diseases. The role of the immune system is to detect and respond to a wide variety of pathogens, which are foreign agents or organisms that can produce disease, such as viruses, bacteria, parasites, etc., or foreign objects, such as a splinter or dirt, or the organisms own cells or tissue, such as cancer. When the immune system detects a pathogen, injury, foreign objects, it undergoes an immune response.

[0004] The immune system’s immune response is a physiological reaction for defending against exogenous factors such as pathogens and that typically involves inflammation, which uses immune cells, blood vessels, and biomolecules to carry out various functions that eliminate the exogenous factors that caused the immune response, e.g., cell injury due to the pathogen or foreign object. While inflammation can clear out damaged cells / tissue and initiate tissue repair, it also can be associated with symptoms exhibited by certain organisms, such as swelling, heat, pain, color change in tissue, or even loss of function.

[0005] Inflammation caused by immune response can be acute or chronic. Acute inflammationis typically classified as an initial inflammatory response achieved by the increased movement of plasma and leukocytes (e.g., granulocytes) from the blood into the tissue affected by the pathogenic source. When the inflammatory response is prolonged, then the inflammation is considered as chronic, which involves different types of cells present at the site of inflammation (e.g., mononuclear cells) that can result in concurrent healing and destruction of the tissue.SUMMARY

[0006] Described herein are method and apparatuses (e.g., devices, systems, etc., including hardware, software and / or firmware) for determining a subject’s susceptibility to inflammation.

[0007] There is large variation in inflammatory severity between individuals, depending on how susceptible a particular individual is to inflammation. Specifically, there is a substantial intrasubject variability in response to inflammatory stimuli, such as infection, trauma, exposure to toxins, etc. The methods and apparatuses described herein are based on the surprising finding that there is a strong correlation between the inflammatory severity that a subject will display to an inflammatory stimuli, and the subject’s response to various autonomic stress challenges. Thus, the methods and apparatuses described herein may determine a subject’s susceptibility to inflammation.

[0008] In particular, in some example implementations, these methods and apparatuses may determine an inflammation risk and / or an inflammation biotype for the subject based on the subject’s response to one or more (e.g., two or more, etc.) autonomic stress challenges. For example, a subject’s inflammation biotype, which indicates how that subject will most likely respond to an inflammatory stimuli, may be safely and reliably determined even in the absence of any inflammatory stimulus.

[0009] For example, the subject’s inflammation biotype may be determined based on cardiac data and / or neural data collected from the patient as the patient is experiencing an autonomic stress challenge and / or at rest (e.g., without the autonomic stress challenge). Cardiac data may include any appropriate cardiac signal, such as ECG data (or data derived from ECG data, which may be 1-lead ECG data, 3-lead ECG data, 12-lead ECG data, etc.), heart rate variability, etc. Neural data may preferably be neural data from autonomic nervous system nerve(s), such as the neural activities in vagus and sympathetic nerve, and may include (but is not limited to) spike frequency and / or distribution. In some implementations, any appropriate autonomic stress challenge may beused, and may be coordinated (applied, started, stopped, etc.) by the methods and apparatuses described herein.

[0010] In examples where the technique includes the subject exhibiting an autonomic stress challenge, some cases two or more types of autonomic stress challenge may be used. Autonomic stress challenges are tests that activate the autonomic nervous system (ANS) to observe physiological responses, helping to assess how well the ANS regulates bodily functions, particularly in response to stress. These challenges can measure how the sympathetic and parasympathetic branches of the ANS respond under different conditions. Examples of autonomic stress challenges that may be used with the methods and apparatuses described herein may include temperature-based challenges, such as the cold pressor test, a respiratory challenge (such as a timed deep breathing test, Valsalva maneuver), exercise challenges, postural stress tests (e.g., orthostatic challenge, tilt table test, etc.).

[0011] In general, the methods and apparatuses in accordance with the disclosed technology may be used to assign a score or characteristic value to the patient indicating the patient’s susceptibility to inflammation, which may provide clinicians or caregivers (e.g., hospitals, pharmacies, etc.) an indication of the risk and / or severity of inflammation, should the patient become infected or otherwise be caused to have an inflammatory response. The inflammation risk score may be used to identify likelihood of patient response to an anti-inflammatory drug. Any appropriate score may be provided, such as (but not limited to) an inflammation biotype. The inflammation biotype may be qualitative and / or quantitative and may be based on the response of the subject’s cardiac and / or neuronal (e.g., sympathetic / parasympathetic nerves) while the subject is at rest (e.g., autonomic stress is unchallenged). The inflammation biotype may be qualitative and / or quantitative and may be based on the response of the subject’s cardiac and / or neuronal (e.g., sympathetic / parasympathetic nerves) to an intentionally applied autonomic stress challenge as compared to a baseline (at rest / unchallenged).

[0012] The methods and apparatuses described herein offer, for the first time, a technical solution to the technical problem of predicting how a subject, including a hospital patient, will respond to an inflammation-inducing event, such as an infection, injury (including surgery), or other stress, before the inflammation-inducing event occurs. The methods and apparatuses can thus be implemented to enable healthcare providers to more effectively and efficiently treat their subjects.

[0013] For example, in some cases subjects may be classified on a scale including hypo- and hyper- inflammatory biotypes. Biotypes may include: very low inflammation likely, low inflammation likely, modest inflammation likely, high inflammation likely or very high inflammation likely. The biotypes may also include an immunoparalytic type or types, which may be a special case of low (e.g., hypoinflammatory) responders. Hyperinflammatory subjects may display sympathetic dominance and hypoinflammatory subjects may display parasympathetic dominance.

[0014] The various biotypes may exhibit distinct cervical electroneurography (CEN) firing responses across different challenges, as well as distinct cardiac output. For example, in some cases there is a negative relationship between the rate of the subject’s heart rate (HR) reduction during an autonomic stress challenge (such as a ‘cold pressor,’ CPT, challenge) and inflammatory severity. The periodicity, predictability and stability of heartbeat dynamics may be negatively correlated with the peak TNF-a concentration produced, therefore showing a strong correlation with inflammation. Observations such as these can be utilized, as described herein, to estimate the inflammatory severity risk a subject might have during inflammation, even when the subject is not presently undergoing inflammation. The predictive value of these measurements may greatly enhance patient care and may help optimize recovery pathways.

[0015] The biotypes may correlate to different levels of inflammation severity (i.e., cytokine concentration levels) when challenged with an inflammation-inducing event (e.g., infection, toxicity, etc.).

[0016] In some implementations of the disclosed methods and apparatuses, for example, non- invasive, readily measurable physiological data (sensor data) may be recoded from a subject during rest or during or in response to an autonomic stress challenge, and the resulting sensor data may be used as described herein to determine the subject’s likely response to inflammation, should an inflammatory response be triggered in the subject thereafter. Knowing the subject’s ‘score’ or biotype may be used to proactively treat the patient, or prepare to treat a patient, for example in situations in which the patient is at increased risk for infection and / or inflammation.

[0017] For example, described herein are methods of determining a subject’s susceptibility to inflammation. In some embodiments in accordance with the present technology, these methods may include: receiving, in one or more processors, a plurality of sensor signals, wherein the sensor signals are recorded from the subject while the subject is at rest or undergoing an autonomic stresschallenge; automatically classifying an inflammation risk and / or an inflammation biotype for the subject based on the plurality of sensor signals; and outputting a notification of the subject’s susceptibility to inflammation based on at least one of the inflammation risk and / or the inflammation biotype.

[0018] Any appropriate sensor signal or collection of sensor signals that reflect the response of the sympathetic and parasympathetic branches of the subject’s autonomic nervous system may be used in implementations of the disclosed methods and apparatuses. For example, the plurality of sensor signals may comprise at least one of: an electrocardiogram (ECG) signal, an electroencephalographic (EEG) signal, an electrogastrography (EGG) signal, a cervical electroneurography (CEN) signal, a cervical magnetoneurography (c-MNG) signal, and a respiration signal.

[0019] Any appropriate autonomic stress challenge may be used in implementations of the disclosed methods and apparatuses. For example, the autonomic stress challenge may include one or more of: a deep breathing exercise, exposure to cold water (e.g., CPT), traumatic event viewing, and traumatic event script reading, or other conventional autonomic stress such as Valsalva maneuver or exercise challenges, postural stress tests (e.g., orthostatic challenge, tilt table test, etc.). In any of these methods and apparatuses, the method and / or apparatus may control the application of the autonomic stress challenge or may sense the start and / or finish of the autonomic stress challenge in order to further automate the method and / or apparatus. In some cases the apparatus may include one or more outputs to output the autonomic stress challenge. In some cases the apparatus or method may be configured to receive input from a user (e.g., doctor, nurse, therapist, etc. or any medical professional) and / or the subject, including input indicating the start and / or finish, as well as the type, of autonomic stress challenge.

[0020] In any of these methods and apparatuses, the plurality of sensor signals may comprise a cardiac signal and a cervical electroneurographic signal. The plurality of sensor signals may be received from a plurality of wearable sensors. At least one of the sensor signals may include a neural signal from the subject. In general, these sensor signals may be measured noninvasively, including transcutaneously.

[0021] In any of these methods and apparatuses, automatically classifying the inflammation risk and / or an inflammation biotype may include sorting spikes in neural activity using a spike sorting algorithm. Spike sorting may be performed as described herein, and may offer a quantifiedparameter. Thus, in some cases, automatically classifying the inflammation risk and / or an inflammation biotype may comprise identifying a spatial relationship of spikes of neural activity between two or more of the sensor signals.

[0022] In general, the methods and apparatuses described herein may automatically determine an inflammation risk and / or an inflammation biotype for the patient using may be any appropriate machine learning algorithm . In some cases the machine learning algorithm may be a trained neural network (e.g., to classify the subject). In some cases the machine learning algorithm may be a deep learning algorithm.

[0023] Automatically classifying the inflammation risk and / or an inflammation biotype may comprise correlating temporal signal characteristics of one or more of the sensor signals to temporal and / or spatial signal characteristics of previous sensor signals. In any of these methods and apparatuses a database of prior sensor signals may be accessed for comparison.

[0024] In some cases automatically classifying the inflammation risk and / or an inflammation biotype may comprise classifying the inflammation biotype based on one or more molecular biomarkers.

[0025] In general, these method may be performed prior to the subject experiencing inflammation. For example, the sensor signals may be recorded from the subject before the subject experiences an event that triggers an immune response (e.g., an infection, an injury, etc.).

[0026] The notification may be output in any appropriate manner, including displaying, storing and / or transmitting. In some cases, outputting may comprise outputting a graph of the sensor signals. In some cases outputting comprises transmitting the notification to a remote device. In some examples outputting comprises outputting the subject’s inflammation biotype.

[0027] Any of these methods and apparatuses may include automatically classifying the subject’s inflammation biotype by classifying on a scale of sub-groups including: a hyperinflammation sub-group, a hypo-inflammation subgroup, and an immunoparalysis sub-group.

[0028] For example, a method of determining a subject’s susceptibility to inflammation may include: receiving, in one or more processors, a first plurality of sensor signals, wherein the first plurality of sensor signals are recorded from the subject while the subject is undergoing a first autonomic stress challenge; receiving, in one or more processors, a second plurality of sensor signals, wherein the second plurality of sensor signals are recorded from the subject while the subject is undergoing a second autonomic stress challenge that is different from the fist autonomicstress challenge; automatically classifying an inflammation risk and / or an inflammation biotype for the subject based on the first plurality of sensor signals and the second plurality of sensor signals; and outputting a notification based on at least one of the inflammation risk and / or the inflammation biotype.

[0029] Also described herein are apparatuses that may perform any of these methods. For example, an apparatus for determining a subject’s susceptibility to inflammation may include: one or more sensors configured to sense a neural signal and / or a cardiac signal; one or more processors in communication with the one or more sensors; and a memory coupled to the one or more processors, the memory storing computer-program instructions, that, when executed by the one or more processors, perform a computer-implemented method comprising: receiving, in one or more processors, a plurality of sensor signals, wherein the plurality of sensor signals are recorded from the subject while the subject is undergoing an autonomic stress challenge; automatically classifying an inflammation risk and / or an inflammation biotype for the subject based on the plurality of sensor signals; and outputting a notification of the subject’s susceptibility to inflammation based on at least one of the inflammation risk and / or the inflammation biotype.

[0030] These apparatuses may include any appropriate sensor, including the electrical sensors descried herein. For example, the one or more sensors may include an array of electrodes configured to sense a cervical electroneurography (CEN) signal. The one or more sensors may include a first sensor configured to sense a neural signal and a second sensor is configured to sense a cardiac signal. The cardiac signal may be one of: an electrocardiogram (ECG) signal and / or a heart rate (HR). The computer-program instructions may be configured to coordinate receiving the plurality of sensor signals with the performance of the autonomic stress challenge by the subject. As discussed above, coordinating the sensor signals with the autonomic stress challenge. Coordinating the sensor signals with the autonomic stress challenge may include recording the sensor signals once the autonomic stress challenge has begun (immediately or after a delay period). Coordinating the sensor signals may include detecting that the autonomic stress challenge is occurring (and recording the sensor signals during this period). In some cases performance of the autonomic stress challenge may include starting and / or stopping recording of the sensor signals.

[0031] As discussed above, the first autonomic stress challenge may be selected from the group consisting of: a deep breathing exercise, exposure to cold water, traumatic event viewing, and traumatic event script reading.

[0032] Any of these apparatuses may include a receiving unit to which the one or more sensors is coupled, wherein the receiving unit is a wearable receiving unit. The receiving unit may include a housing, case, or outer surface. The receiving unit may enclose circuitry (e.g., one or more processors, a memory, etc.) and / or telecommunications. In some cases the apparatus may be configured as a wearable apparatus (e.g., wearable device), which may be worn on the subject, on the subject’s skin, clothes, etc. In any of these apparatuses the memory may be part of a wearable device, and / or the one or more processors may be part of a wearable one or more processors. In some cases the one or more sensors is configured to detect the neural signal in a vagus nerve of the subject. In any of these cases the one or more sensors may be configured to detect the neural signal in a cervical nerve of the subject. The plurality of sensor signals may comprise one or more of: an electrocardiogram (ECG) signal, an electroencephalographic (EEG) signal, an electrogastrography (EGG) signal, a cervical electroneurography (CEN) signal, a cervical magnetoneurography (c-MNG) signal, and a respiration signal. The one or more sensors may be configured to detect the neural and / or cardiac signal transcutaneously. The computer-program instructions may be further configured to automatically classify the inflammation risk and / or an inflammation biotype using a spike sorting algorithm that is configured to sort spikes in neural activity identified in the plurality of neural signals.

[0033] The computer-program instructions may be further configured to automatically classify the inflammation risk and / or an inflammation biotype by identifying a spatial relationship of spikes in neural activity between a first neural signal in the plurality of sensor signals and a second neural signal in the plurality of sensor signals. In some cases the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by using a trained neural network to identify autonomic features of the neural signals and the physiological signals. The computer-program instructions may be further configured to automatically classify the inflammation risk and / or an inflammation biotype by correlating present temporal and / or spatial signal characteristics of at least one present sensor signal in the plurality of sensor signals to previous temporal and / or spatial signal characteristics of at least one previous sensor signal in the plurality of sensor signals. The computer-program instructions may be configured to automatically classify the inflammation risk and / or an inflammation biotype by correlating clusters of present spikes in neural activity in a plurality of present sensor signals inthe plurality of sensor signals to spatial clusters of previous spikes in neural activity in a plurality of previous sensor signals in the plurality of sensor signals.

[0034] Any of these apparatuses may include a wireless transmitter configured to transmit a remote notification to a remote device over a network, wherein the remote notification comprises at least one of an inflammation risk notification and an information biotype notification.

[0035] Also described herein are systems comprising: a wearable sensor; a receiving unit configured to (i) receive a sensor signal communicated from the wearable sensor and (ii) detect a signal type of the received sensor signal, wherein the signal type comprises a neural signal when the receiving unit detects at least a portion of a neural signal of a subject; a memory storing a set of instructions for predicting immune responses; and a processor that is configured to execute the set of instructions for predicting immune responses based on the sensor signal. The signal type may comprise a neural signal when the receiving unit detects a neural signal for the signal type. The signal type may include a physiological signal of the subject when the receiving unit detects a physiological signal for the signal type. The set of instructions for predicting immune responses based on the sensor signal may comprise a set of instructions for automatically classifying an inflammation risk for the subject. In some cases the set of instructions for predicting immune responses based on the sensor signal further comprises a set of instructions for automatically creating a notification based on the inflammation risk.

[0036] In any of these cases the receiving unit may be a wearable receiving unit. The memory may be a wearable memory. The processor may be a wearable processor. The receiving unit may be configured to detect the neural signal in a vagus nerve of the subject. In some cases the receiving unit is configured to detect the neural signal in a cervical nerve of the subject.

[0037] The sensor signal may comprise one of an electrocardiogram (ECG) signal, an electroencephalographic (EEG) signal, an electrogastrography (EGG) signal, a cervical electroneurography (CEN) signal, a cervical magnetoneurography (c-MNG) signal, and a respiration signal. The wearable sensor may be configured to detect the neural signal transcutaneously. The sensor signal may be a first sensor signal, wherein the receiving unit is further configured to receive a plurality of sensor signals comprising the first sensor signal. The receiving unit may be further configured to differentiate between a plurality of neural signals identified from one or more sensor signals in the plurality of sensor signals. The set of instructionsfor predicting immune responses may be based on the sensor signal comprises a set of instructions for automatically classifying an inflammation biotype for the subject.

[0038] The set of instructions for predicting immune responses may be based on the sensor signal further comprises a set of instructions for automatically creating a notification based on the inflammation biotype. The set of instructions for automatically classifying the inflammation biotype for the subject may further comprise a set of instructions for performing a spike sorting algorithm that is configured to sort spikes in neural activity identified in the plurality of neural signals.

[0039] The set of instructions for automatically classifying the inflammation biotype for the subject may further comprise a set of instructions for identifying a spatial relationship of spikes in neural activity between a first neural signal in the plurality of neural signals and a second neural signal in the plurality of neural signals. The plurality of sensor signals may comprise neural signals and physiological signals, wherein the set of instructions for automatically classifying the inflammation biotype for the subject may further comprise a set of instructions for utilizing a Convolutional Neural Network (CNN) to identify autonomic features of the neural signals and the physiological signals. The set of instructions for automatically classifying the inflammation biotype for the subject may further comprise a set of instructions for correlating present temporal signal characteristics of at least one present sensor signal in the plurality of sensor signals to previous temporal signal characteristics of at least one previous sensor signal in the plurality of sensor signals. In some examples the set of instructions for automatically classifying the inflammation biotype for the subject further comprises a set of instructions for correlating present spatial signal characteristics of at least one present sensor signal in the plurality of sensor signals to previous spatial signal characteristics of at least one previous sensor signal in the plurality of sensor signals.

[0040] The set of instructions for automatically classifying the inflammation biotype for the subject may further comprise a set of instructions for correlating clusters of present spikes in neural activity in a plurality of present sensor signals in the plurality of sensor signals to spatial clusters of previous spikes in neural activity in a plurality of previous sensor signals in the plurality of sensor signals.

[0041] Any of these apparatuses (e.g., systems) may include a plurality of wearable sensors, wherein the wearable sensor is a first wearable sensor in the plurality of wearable sensors. In someexamples the system may include a flexible surface electrode array comprising the plurality of wearable sensors. The system may include a flexible surface magnetometer array comprising the plurality of wearable sensors. Any of these apparatuses may include a wireless transmitter configured to transmit a remote notification to a remote device over a network, wherein the remote notification comprises at least one of an inflammation risk notification and an information biotype notification.

[0042] Also described herein are methods for predicting immune responses comprising: automatically receiving, by a receiving unit communicably connected to a processor, a plurality of sensor signals; automatically classifying an inflammation risk for a subject based on the sensor signals; automatically classifying an inflammation biotype for the subject based on the sensor signals; and automatically creating a notification based on at least one of the inflammation risk and the inflammation biotype.

[0043] The plurality of sensor signals may comprise at least one of an electrocardiogram (ECG) signal, an electroencephalographic (EEG) signal, an electrogastrography (EGG) signal, a cervical electroneurography (CEN) signal, a cervical magnetoneurography (c-MNG) signal, and a respiration signal. The plurality of sensor signals may be received from a plurality of wearable sensors. At least one of the sensor signals may comprise a neural signal of the subject. In some cases at least one of the wearable sensors is configured to detect the neural signal transcutaneously.

[0044] Automatically classifying an inflammation biotype may comprise sorting spikes in neural activity by way of a spike sorting algorithm. In some examples, automatically classifying an inflammation biotype may comprise utilizing a Convolutional Neural Network (CNN) to identify autonomic features. Automatically classifying an inflammation biotype may comprise identifying a spatial relationship of spikes in neural activity between two or more of the sensor signals. Automatically classifying an inflammation biotype may comprise correlating temporal signal characteristics of one or more of the sensor signals to temporal signal characteristics of previous sensor signals.

[0045] Automatically classifying an inflammation biotype may comprise correlating spatial signal characteristics of one or more of the sensor signals to spatial signal characteristics of previous sensor signals. Automatically classifying an inflammation biotype may comprise classifying the inflammation biotype based on one or more molecular biomarkers. The inflammation risk and the inflammation biotype may be automatically classified for the subjectbefore the subject experiences an event that trigger an immune response. Any of these methods may include automatically plotting sensor signals as data points in a plot and visually outputting the plot of the sensor signals on a display.

[0046] The methods described herein may include automatically transmitting a notification to a remote device. The notification may comprise at least one of the inflammation risk classified for the subject and the inflammation biotype classified for the subject.

[0047] Also described herein are surface electrode arrays configured to detect multi-channel cervical neuronal activity. For example, a surface electrode array may comprise: a first polyimide layer; a second polyimide layer; a plurality of wearable sensors placed between the first polyimide layer and the second polyimide layer; electrical wiring to a power source; and data communication wiring to a processor that is configured to detect channel-specific neural signals of a subject. Each wearable sensor in the plurality of wearable sensors may comprise an electrode. Any of these electrodes may include an adhesive that is configured to apply the plurality of wearable sensors transcutaneously to a vagus nerve area of the subject (e.g., on the neck over the vagus nerve).

[0048] All of the methods and apparatuses described herein, in any combination, are herein contemplated and can be used to achieve the benefits as described herein.BRIEF DESCRIPTION OF THE DRAWINGS

[0049] A better understanding of the features and advantages of the methods and apparatuses described herein will be obtained by reference to the following detailed description that sets forth illustrative embodiments, and the accompanying drawings of which:

[0050] FIG. 1A shows a block diagram depicting an example embodiment of a system for predicting immune response, in accordance with the disclosed technology

[0051] FIG. IB is a block diagram of an example embodiment of the system of FIG. 1A for predicting immune responses, in accordance with the present technology.

[0052] FIG. 2 schematically illustrates an example embodiment of the system of FIG. 1A for predicting immune responses, in accordance with the present technology.

[0053] FIG. 3 illustrates an example dimensionality reduction algorithm, in accordance with the present technology.

[0054] FIG. 4 schematically illustrates an example embodiment of a method for predicting immune responses, in accordance with the present technology.

[0055] FIGS. 5A-5D illustrates an example embodiment of a surface electrode array, in accordance with the present technology. FIG. 5A shows an exploded view of the example surface electrode array and wearable sensor. FIGS. 5B and 5C show examples of the surface electrode array during fabrication, and FIG. 5D shows an example of a fully-fabricated surface electrode array.

[0056] FIG. 6 illustrates an example embodiment of a surface electrode array in use, as applied to a subject.

[0057] FIG. 7 is an example of a graph of one example feature (heart rate variability) of a physiological signal for several subjects, consistent with disclosed embodiments, showing Hypoinflammation and Hyper-inflammation biotypes. The graph shows a comparison between the LF / HF ratio logarithm from baseline resting measurements and peak TNF-a concentration produced (ordered from left to most).

[0058] FIG. 8 is an example of a graph showing neurological activity before and after an autonomic nervous system challenge for a plurality of subjects, consistent with disclosed embodiments. FIG. 8 shows a comparison of cervical neural firing rates at LNG pre-to-post deep breathing challenge. Wilcoxon signed ranked tests were compared to the firing rate change pre-to- post deep breathing and the change between two biotypes.

[0059] FIG. 9 shows an example of plots of an example feature of an example physiological signal, shown as an exemplary recurrence plot for RR-interval dynamics during resting state. The diagonal line parallel to the main diagonal line (marked in first box) informs predictability and determinism during those periods, while the vertical line (marked in a second box) implies stability for those periods.

[0060] FIGS. 10A-10D depict example plots illustrating correlation between an example physiological signal with an example immune response for each of twelve subjects during resting state.

[0061] FIGS. 11A-11C illustrate an example ensemble learning method, in accordance with the present technology, based on three example machine learning models.

[0062] FIGS. 12A-12B illustrates an example deep learning model, in accordance with the present technology, which may include a Convolutional Neural Network (CNN) to identify higher- level autonomic features of neural and / or physiological signals.

[0063] FIGS. 13 A-l 3C illustrate change in heart rate (HR) during a cold pressor task / challenge (CPT). FIG. 13 A shows the HR change during CPT from an exemplary Hypo-inflammation subject, and an exemplary Hyper-inflammation subject (FIG. 13B). FIG. 13C show a Pearson correlation between inflammation severity and HR gradient change after reaching HR during CPT.

[0064] FIG. 14 shows a Pearson correlation between peak miRNA (hsa-miR-210-3p) and sympathetic activity index (SAI) / parasympathetic activity index (PAI) ratio measured during baseline resting state.DETAILED DESCRIPTION

[0065] Conventional methods for predicting immunity to vaccines rely on recognizing a gene signature in blood cells. These methods may require days of processing time. Conventional methods for predicting an inpatient inflammatory response to bacterial, parasitic, fungal or viral infection relies on signatures detected in bodily fluids such as blood, sputum, and or cerebrospinal fluid. These methods may require days of processing time. Conventional methods that identify response to treatment of infection (for example, cleared culture) may require days of processing time. Conventional methods for predicting treatment response in melanoma tumor samples rely on gene expression feature analysis. Conventional methods for employing machine learning to predict subject response to immune checkpoint inhibitors for melanoma, gastric cancer, and bladder cancer may require cancer tissue samples.

[0066] Some conventional systems and technological processes for measuring nerve activity may employ needle electrodes. Other conventional systems and technological processes may measure nerve activity through the employment of implanted electrodes in subjects.

[0067] Unconventional systems and technological processes are needed for more efficient and less invasive prediction of immune responses.

[0068] Described herein are systems and methods for predicting immune responses. Embodiments consistent with the present disclosure are rooted in computer and sensor technologies and may include collecting, storing, and / or processing various types of signals including neural signals and / or other physiological signals. Collecting and processing neural signals and / or other physiological signals according to the enclosed embodiments may lead to more effective and accurate predictions of future immune response(s) in subjects. Collecting and processing neural signals and / or other physiological signals according to the enclosedembodiments may also lead to more efficient predictions of future immune response(s) in subjects. For example, employing the enclosed embodiments may result in predictions of future immune response(s) in subjects within short time spans (e.g., several minutes to less than two hours) or in subjects with longer time spans (e.g., several hours to several days) from non-invasive signal detection. Additionally, collecting and processing neural signals and / or other physiological signals according to the enclosed embodiments may lead to improved efficiency in treating immune response(s) in subjects. Immune response(s) and / or root cause(s) of immune response(s) may be identified in each of at least some pre-symptomatic subjects through the employment of the disclosed embodiments.

[0069] The unconventional systems and methods in the disclosed embodiments may enable measurements of neural signals over a more prolonged period than conventional devices and technological processes. The unconventional systems and methods in the disclosed embodiments may enable measurements of neural signals with less noise over conventional devices and technological processes. Collecting and processing neural signals and / or other physiological signals prior to any infection (in other words, during pre-infectious regular activity) may predict host immune response severity, morbidity, and mortality in subjects through the employment of the disclosed embodiments. Some embodiments provide unconventional systems and methods for detecting pre-infection or pre-inflammation activity based on baseline recordings of neural signals and / or other physiological signals that may predict susceptibility to infection or inflammation due to infection.

[0070] Some embodiments provide an unconventional surface electrode array that may be configured to achieve a higher signal -to-noise ratio during neural recordings over conventional solutions. For example, the disclosed technology includes such an unconventional surface electrode array that can record neural signals with a high signal -to-noise ratio when placed in the ventral cervical area. The unconventional surface electrode array may be configured to reduce harmonics in sensor signals. In some embodiments, the unconventional surface electrode array includes a first polyimide layer, a second polyimide layer, and one or more wearable sensors (e.g., which can include at least one electrode) placed between the first polyimide layer and the second polyimide layer.

[0071] As used herein, a subject may be referred to equivalently as a patient and may include a person under the care of a medical practitioner and / or a user of any of the disclosed embodiments.A person may comprise an employee, a soldier, a government official, or a person in any other role. Subject’s may include non-human subjects (e.g., mammalian subjects) or human subjects.

[0072] As used herein, Autonomic Gradient Drive (AGD) refers to autonomic neuro- immune regulation. An AGD bias for a particular subject may be determined through the employment of some of the disclosed embodiments.

[0073] As used herein, Autonomic Immune Pathogen Bias (AIPB) refers to a pathogen response bias for a subject. AIPB may be based on a bias towards a disease response to infection. AIPB may be pathogen agnostic.

[0074] As used herein, R-R intervals refer to the time intervals between R wave peaks in an ECG signal.

[0075] As used herein, pNN50 is a percentage of adj acent pairs of successive R-R intervals in a heart rate signal that differ from each other by more than 50 ms.

[0076] As used herein, RMSSD is the root square of successive difference between normal heartbeats in a heart signal. RMSSD may reflect the beat-to-beat variance in heart rate. RMSSD may be employed to estimate vagally mediated changes reflected in heart rate variability (HRV).

[0077] As used herein, SDNN is the standard deviation of normal sinus beats. Lower SDNN may indicate a reduction in dynamic complexity.

[0078] As used herein, acceleration capacity (AC) is an autonomic nervous system indicator of cardiac neural regulation for an accelerating heartbeat.

[0079] As used herein, deceleration capacity (DC) is an autonomic nervous system indicator of cardiac neural regulation for a decelerating heartbeat.

[0080] As used herein, low frequency (LF) normalized is the proportion of sympathetic tone in an autonomic nervous system.

[0081] As used herein, high frequency (HF) normalized is the proportion of parasympathetic tone in an autonomic nervous system.

[0082] As used herein, LF / HF ratio may reflect a sympathovagal balance. As used herein, Respiratory Sinus Arrhythmia (RSA) refers to an autonomic relationship between respiration and heart rate. RSA may be identified as an increase in heart rate during inhalation. RSA may be identified as a decrease in heart rate during exhalation.

[0083] As used herein, a molecular biomarker is an indicator of a physiological state. Molecular biomarkers may be available after being obtained or discovered through employmentof point of care blood samples, tissue samples, saliva samples, and / or other samples from a subject. Molecular biomarkers may be indicated as part of an Electronic Medical Record (EMR) of the subject.

[0084] As used herein, a Receiver Operating Characteristic (ROC) curve is a plot showing the performance of a classification model. A ROC curve may comprise a plot of a True Positive Rate (TPR) against a False Positive Rate (FPR) at various threshold settings.

[0085] As used herein, Area Under the Curve (AUC) may be employed to measure performance of a classification model.

[0086] As used herein, Recurrence Quantification Analysis (RQA) may be employed to quantify a number and / or duration of recurrences of an aspect or feature of one or more neural signals and / or other physiological signals through a phase space trajectory.

[0087] The disclosed methods and systems provide techniques for predicting an immune response of a subject based on electrophysiological signal monitoring when the subject is at a resting state and in response to an autonomic stress challenge. The technique can be used to identify a quantitative degree of inflammation, which is linked to a disease state that can be characterized by the disclosed method and system.

[0088] The disclosed method and system can use various neural sources and the sensing modalities (e.g., magnetometer- or electrode-based action potential detection) to monitor the electrophysiological signals of the subject. In some implementations, the electrophysiological signal monitoring includes neural signal sensing recorded at the ventral cervical neck area, in which there are multiple different targets that transmit inflammatory signals being recorded by the sensor.

[0089] The disclosed method and system can process the monitored electrophysiological signals by interrogating the signal characteristics and comparing the determined characteristics to signatures indicative of inflammatory response based processing using machine learning model(s) and / or deep learning model(s). For example, the neural signals transmitted by each neuron and / or group of neurons detected by the sensor can have a signature shape indicative of inflammatory response by the subject. The shape is characterized by the signal spikes' magnitude (normalized) and frequency over a time interval, for multiple time intervals (i.e., time series data), where the spikes are representative of an ensemble of neurons emitting action potentials in response to particular cytokine concentrations. The data processing of these recorded neural signals analyzesthe change in activity (e g., spike frequency characteristics, such as spike slope rise and / or run, for normalized magnitude threshold), over time, to exhibit a pattern that correlates with neural signaling signatures determined to relate to particular inflammatory response patterns associated with disease states for certain pathogens and for certain organs of the subject.

[0090] As an example, for a subject with an early stage infection of his / her lungs being monitored by the example system in accordance with the disclosed technology, the system analyzes the monitored neural signals detected by the sensor to determine the neural signal characteristics, such as the change in spike frequency over time, and compares the determined characteristics with a plurality of signatures associated with certain cytokine concentrations linked to particular pathologies to best predict a potential pathology trajectory of the subject early on. For instance, the analysis of the detected neural signals by the system can indicate a first signal entrainment cycle that corresponds to a first cytokine concentrations that changes (e.g., increases) slowly over time and a second signal entrainment cycle that corresponds to a second cytokine concentration that initiates later in the monitoring period and may change (e.g., increase) fast over time, and so-on for any additional signal entrainment cycles exhibited in the neural signal data. As an illustrative example, if the subject was infected with Covid, the cytokine response signal entrainments in the detected neural signals would indicate a faster series of entrainments as compared to an influenza virus infection in the subject's lungs— for example, Covid- 19 has a 5-7 day ramp-up rate in the lungs compared to influenza with a 8-12 day ramp-up rate in the lungs. Also, as an illustrative example, if the early stage infection were in a different part of the subject's anatomy, the cytokine response signal entrainments would exhibit a different signature that the data model (e.g., machine learning model and / or deep learning model) of the system would be able to analyze and identify from the subject's neural signals detected by the sensor.

[0091] The data processing unit of the system is able to process a large amount of neural signal data of the subject in conjunction with the data model that has been trained on exponentially larger amounts of data (from large sample sizes of subjects) to compare intricate characteristic features in the data that would be unidentifiable to conventional correlation algorithms. The data processing unit of the system is able to decode the neural signal data to give a predictive assessment of the subject’s immune response, which can be indicative of a particular pathogen or group of pathogens, a particular disease state, and / or a particular anatomical structure or region (e.g., tissue or organ) associated with the subject’s health condition.

[0092] Example embodiments of the disclosed system and method are described in further details below.

[0093] FIG. 1 A shows a block diagram depicting an example embodiment of a system 100 for predicting immune response, in accordance with the disclosed technology. The system 100 includes a computer device 110A in communication (e.g., wired or wireless communication) with one or more wearable sensor(s) 130, described in further detail later in this disclosure. In various implementations, the computer device 110A includes a data processing unit 111. In some embodiments, the computer device 110A optionally includes a display unit 160A. The data processing unit 111 can include various hardware and / or software modules or units of the disclosed system for predicting immune response of a subject. For example, the computer device 110A can be implemented as any one or more of various data processing systems, such as a personal computer (PC), laptop, and / or mobile communication device, such as a smartphone, tablet, or wearable computing device such as a smartwatch or smartglasses.

[0094] In some embodiments, for example, the (optional) display unit 160A can include a visual, auditory, and / or tactile display device, which can include various types of screen-based displays, audio speakers, and / or printing interfaces, e.g., which can be used to implement an alarm or display based on processed data by the data processing unit 111. For example, the (optional) display unit 160A can include cathode ray tube (CRT), light emitting diode (LED), or liquid crystal display (LCD) monitor or screen, among other visual displays, as a visual display. In some examples, the (optional) display unit 160A can include various types of audio signal transducer apparatuses or other sensory inducing apparatuses to implement the alarms or display. In other examples, the (optional) display unit 160A can include a printing apparatus, such as a toner, liquid inkjet, solid ink, dye sublimation, inkless (e.g., such as thermal or UV) printing device to implement an output of the data processing unit 111. The (optional) display unit 160A can exhibit data and information, such as the system data in a completely processed or partially processed form. The (optional) display unit 160A can be used to input and / or store data and information used to implement the disclosed immune response prediction techniques.

[0095] An example embodiment of the data processing unit 111 of the computer device 110A is shown in the diagram of FIG. 1A. The data processing unit 111 can include a processor 11 IP that can be in communication with a memory 11 IM and an input / output (I / O) unit 11 ID. In some implementations, for example, the data processing unit 111 can be included in the device structurethat includes the wearable sensor(s) 130. To support various functions of the data processing unit 111, the processor 11 IP can be included to interface with and control operations of other components of the data processing unit 111, such as the I / O unit 11 ID and / or the memory 11 IM. The memory H IM can store information and data, e.g., such as instructions, software, values, images, and other data processed or referenced by the processor 11 IP. Various types of Random Access Memory (RAM) devices, Read Only Memory (ROM) devices, Flash Memory devices, and other suitable storage media can be used to implement storage functions of the memory 11 IM. The memory H IM can store data and information, which can include sensor data (e.g., subject electrophysiological signal response data), and information about other units of the system 100, e.g., including the sensor device(s) 130 and / or the (optional) display unit 160A, such as device system parameters and hardware constraints. The memory 11 IM can store data and information that can be used to implement the system 100 and various methods executed by the system 100. The VO unit 11 ID can be connected to an external interface, source of data storage, or display device. Various types of wired or wireless interfaces compatible with typical data communication standards can be used in communications of the data processing unit 111 with the sensor device(s) 130 and / or the (optional) display unit 160A and / or other units of the system, e.g., including, but not limited to, Universal Serial Bus (USB), IEEE 1394 (FireWire), Bluetooth, Bluetooth Low Energy (BLE), ZigBee, IEEE 802. I l l, Wireless Local Area Network (WLAN), Wireless Personal Area Network (WPAN), Wireless Wide Area Network (WWAN), WiMAX, IEEE 802.16 (Worldwide Interoperability for Microwave Access (WiMAX)), 3G / 4G / LTE / 5G / 6G cellular communication methods, and parallel interfaces, can be used to implement the I / O unit 11 ID. The I / O unit 11 ID can interface with an external interface, source of data storage, or display device to retrieve and transfer data and information that can be processed by the processor 11 IP, stored in the memory 11 IM, or exhibited on the (optional) display unit 160A. In some embodiments of the data processing unit 111, for example, the processor 11 IP can include a central processing unit (CPU) and / or a graphic processing unit (GPU), or both the CPU and the GPU.

[0096] FIG. IB is a block diagram of a first embodiment of the system 100, described as system 100B, for predicting immune responses, consistent with disclosed embodiments. System 100B may comprise processor 110, receiving unit 120, wearable sensor 130, and memory 150. Processor 110 may comprise one or more processors. Receiving unit 120 may comprise one or more receivers. Receiving unit 120 may be configured to receive sensor signal 135. Sensor signal135 may comprise one or more sensor signals. Wearable sensor 130 may comprise one or more wearable sensors. Each sensor signal 135 may be communicated from a wearable sensor 130. Wearable sensor 130 may be configured to detect at least a portion of one or more neural signals of a subject. Wearable sensor 130 may be configured to detect at least a portion of one or more neural signals transcutaneously. Sensor signal 135 may comprise at least a portion of a neural signal of the subject. Receiving unit 120 may be configured to communicate data signal 125 to processor 110. Data signal 125 may comprise one or more data signals. Memory 150 may comprise one or more memories. Memory 150 may comprise data 151 and instructions 152. Data 151 may comprise data corresponding to, for example, sensor signal 135, data signal 125, physiological signals, neural signals, inflammation risk, inflammation biotype, and / or any other data corresponding to one or more subjects. Processor 110 may be configured to execute instructions 152 to perform operations. The operations may be performed prior to any symptoms experienced by the subject. Instructions 152 may comprise inflammation risk classifier 154. Instructions 152 may comprise inflammation biotype classifier 155. The particular arrangement of components depicted in FIG. IB is not intended to be limiting. System 100B may include additional components, or fewer components. Multiple components of system 100B may be implemented using the same physical computing device or different physical computing devices.

[0097] In some embodiments, a wearable sensor may comprise an electrocardiogram (ECG) sensor. In some embodiments, a sensor signal may comprise an ECG signal. For example, the wearable sensor 130 may be an ECG sensor and the sensor signal 135 may be an ECG signal. In some embodiments, a wearable sensor may comprise an electroencephalographic (EEG) sensor. In some embodiments, a sensor signal may comprise an EEG signal. For example, the wearable sensor 130 may be an EEG sensor and the sensor signal 135 may be an EEG signal. In some embodiments, a wearable sensor may comprise an electrogastrography (EGG) sensor. In some embodiments, an EGG sensor may be configured to measure slow-wave myoelectric activity in a stomach of a subject that is modulated by vagus nerve signaling. In some embodiments, a sensor signal may comprise an EGG signal. For example, the sensor signal 135 may be an EGG signal while the wearable sensor 130 may be an EGG sensor that may be configured to measure slow- wave myoelectric activity in the subject’s stomach as modulated by vagus nerve signaling of the subject. In some embodiments, a wearable sensor may comprise a cervical electroneurography (CEN) sensor. In some embodiments, a sensor signal may comprise a CEN signal. For example,the wearable sensor 130 may be a CEN sensor and the sensor signal 135 may be a CEN signal. In some embodiments, a wearable sensor may comprise a cervical magnetoneurography (c-MNG) sensor. In some embodiments, a sensor signal may comprise a c-MNG signal. For example, the wearable sensor 130 may be a c-MNG sensor and the sensor signal 135 may be a c-MNG signal. In some embodiments, a wearable sensor may comprise a respiration sensor. In some embodiments, a sensor signal may comprise a respiration signal. For example, the wearable sensor 130 may be a respiration sensor and the sensor signal 135 may be a respiration signal.

[0098] In some embodiments, sensor 130 may comprise a cervical electroneurography (CEN) sensor comprising one or more surface electrodes. A CEN sensor may be configured to sense neural activity in a subject. A CEN sensor may be configured to transmit a CEN signal. A CEN sensor may be configured to sense neural activity from dermal sympathetic nerve firing, also referred to as skin sympathetic nerve activity. A CEN sensor may be configured to sense neural activity in deeper muscular sympathetic neurons, carotid bodies, sympathetic chain, ganglia spanning a carotid body, middle cervical ganglion, superior cervical ganglion, and / or action potentials emanating from a glossopharyngeal nerve, a vagus nerve, a rostral ganglia, a nodose ganglia, and / or a jugular ganglia. A CEN sensor may be configured to sense neural activity from a spinal cord and / or a dorsal root ganglia. A CEN sensor may be configured to sense neural activity from brain stem reflexes and / or trigeminal nerve ganglia.

[0099] Neural activity may comprise at least one Action Potential (AP). Neural activity may comprise a Compound Action Potential (CAP).[000100] In some embodiments, sensor 130 may comprise a cervical magnetoneurography (c- MNG) sensor. A c-MNG sensor may comprise a magnetometer. A c-MNG sensor may be configured to sense neural activity in a subject. A c-MNG sensor may be configured to transmit a c-MNG signal. A c-MNG sensor may be configured to sense neural activity from dermal sympathetic nerve firing, also referred to as skin sympathetic nerve activity. A c-MNG sensor may be configured to sense neural activity in deeper muscular sympathetic neurons, carotid bodies, sympathetic chain, ganglia spanning a carotid body, middle cervical ganglion, superior cervical ganglion, and / or action potentials emanating from a glossopharyngeal nerve, a vagus nerve, a rostral ganglia, a nodose ganglia, and / or a jugular ganglia. A c-MNG sensor may be configured to sense neural activity from a spinal cord and / or a dorsal root ganglia. A c-MNG sensor may be configured to sense neural activity from brain stem reflexes and / or trigeminal nerve ganglia.[000101] In some embodiments, data 151 may comprise molecular biomarker data. Molecular biomarker data may comprise salivary biomarkers. Examples of salivary biomarkers include, but are not limited to, metabolites, proteins, hormones, cytokines, and micro Ribonucleic Acids (miRNAs).[000102] In some embodiments, memory 150 may store instructions 152 which, when executed by processor 110, cause processor 110 to automatically receive data signal 125 from receiving unit 120. Data signal 125 may comprise one or more sensor signals 135. Receiving unit 120 may comprise an amplifier. Receiving unit 120 may be configured to apply one or more filters to one or more sensor signals 135. Receiving unit 120 may be configured to convert analog sensor signals into digital sensor signals. Analog sensor signals may be converted into digital sensor signals through the employment of one or more analog-to-digital converters (ADC). The ADC may be configured to sample analog signals up to a rate on the order of 16 kHz. The ADC may be configured to sample analog signals at a rate of 8 kHz. The ADC may be configured for 24-bit resolution. Instructions 152 may comprise data signal processor 153. Data signal processor 153 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically process data signal 125. Processing data signal 125 may comprise one or more of filtering, modulating, encoding, converting analog signals to digital signals, converting digital signals to analog signals, performing error correction, and multiplexing a plurality of signals. For example, data signal 125 may be filtered by a 50-500 Hz zero-phase bandpass filter. For example, one or more notch filters may be employed to remove powerline noise and / or harmonics from data signal 125.[000103] In some embodiments, inflammation risk classifier 154 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically classify an inflammation risk for a patient based on sensor signal 135. Inflammation risk classifier 154 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically classify an inflammation risk for a patient based on a correlation between sensor signal 135 and one or more previous sensor signals. Inflammation risk classifier 154 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically classify an inflammation risk for a patient based on an increase in neural activity and a corresponding increase in one or more other physiological activities. Inflammation risk classifier 154 may comprise instructions which, when executed by processor 110, cause processor 110 toautomatically classify an inflammation risk for a subject based on an increase in neural activity and a corresponding decrease in one or more other physiological activities. Inflammation risk classifier 154 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically classify an inflammation risk for a subject based on one or more molecular biomarkers. Inflammation risk classifier 154 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically classify an inflammation risk for a subject based on entrainment between neural activity and changes in one or more molecular biomarkers. Inflammation risk classifier 154 may comprise instructions which, when executed by processor 110, cause processor 110 to employ one or more machine learning models to automatically classify an inflammation risk for a subject based on sensor signal 135, one or more previous sensor signals, and / or one or more molecular biomarkers.[000104] In some embodiments, a previous sensor signal may comprise a sensor signal from the same subject from a previous time frame. In some embodiments, a previous sensor signal may comprise a sensor signal from another subject from a previous time frame. In some embodiments, a plurality of previous sensor signals may comprise one or more sensor signals from each of a plurality of other subjects from one or more previous time frames.[000105] In some embodiments, an inflammation biotype may be classified based on a healthy state. In some embodiments, an inflammation biotype may be classified based on a disease state. In some embodiments, an inflammation biotype may be classified based on an antecedent healthy state and a subsequent disease state of a subject. In some embodiments, an inflammation biotype may be classified based on an antecedent healthy state and a subsequent inflammation state of a subject. In some embodiments, an inflammation biotype may be classified based on an antecedent healthy state of a subject and a subsequent inflammation response to pain in the subject. In some embodiments, an inflammation biotype may be classified based on sterile inflammation. In some embodiments, an inflammation biotype may be classified based on non-sterile inflammation. In some embodiments, an inflammation biotype may be classified based on a response to one or more pharmacologic therapies. In some embodiments, an inflammation biotype may be classified based on a response to one or more neuromodulation therapies. In some embodiments, an inflammation biotype may be classified based on a response to one or more non-invasive stress events. Examples of non- invasive stress events include, without limitation, deep breathing exercise, exposure to cold water, traumatic event viewing, and traumatic event script reading. In some embodiments, aninflammation biotype may be classified based on a response to painful neurostimulation. As used herein, cold water may be water that is below a threshold value (e.g., between 0-20 degrees C, between 0-15 degrees C, between 0-10 degrees C, between 3-15 degrees C, between 3-10 degrees C, between 4-7 degrees C, etc.).[000106] Neuromodulation therapies may include, but are not limited to, the alteration of nervous tissue activity through targeted delivery of a stimulus, such as, for example, electrical stimulation, focused ultrasound, and / or chemical agents, to specific neurological sites in the body. Some embodiments may include methods of neuromodulation to stimulate specific neurological sites in the body. Neuromodulation therapies may include transcutaneous direct current stimulation. Neuromodulation therapies may include transcutaneous alternating current stimulation. Neuromodulation therapies may include transcutaneous magnetic stimulation. Neuromodulation therapies may include focused ultrasound stimulation. Neuromodulation therapies may include interferential targeted nerve stimulation. Some embodiments may comprise a neuromodulation device. A neuromodulation device may be structurally configured to deploy one or more neuromodulation therapies.[000107] In some embodiments, inflammation biotype classifier 155 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically classify an inflammation biotype for a subject based on sensor signal 135. Inflammation biotype classifier 155 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically classify an inflammation biotype for a subject based on a correlation between sensor signal 135 and one or more previous sensor signals. Inflammation biotype classifier 155 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically classify an inflammation biotype for a subject based on one or more clusters of spikes in neural activity in one or more sensor signals 135. In some embodiments, instructions 152 comprise a spike sorter 156. Spikes in neural activity may be sorted through the employment of the spike sorter 156 prior to cluster identification. Inflammation biotype classifier 155 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically classify an inflammation biotype for a subject based on a correlation between one or more clusters of spikes in neural activity in one or more sensor signals 135 and one or more clusters of spikes in neural activity in one or more previous sensor signals. Correlation between clusters of spikes may be based on one or more temporal relationships and / or one or more spatialrelationships. Inflammation biotype classifier 155 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically classify an inflammation biotype for a subject based on an increase in neural activity and a corresponding increase in one or more other physiological activities. Inflammation biotype classifier 155 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically classify an inflammation biotype for a subject based on an increase in neural activity and a corresponding decrease in one or more other physiological activities. Inflammation biotype classifier 155 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically classify an inflammation biotype for a subject based on one or more molecular biomarkers. Inflammation biotype classifier 155 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically classify an inflammation biotype for a subject based on entrainment between neural activity and changes in one or more molecular biomarkers. Inflammation biotype classifier 155 may comprise instructions which, when executed by processor 110, cause processor 110 to employ one or more data models (e.g., one or more machine learning model(s) and / or one or more deep learning model(s)) to automatically classify an inflammation biotype for a subject based on sensor signal 135, one or more previous sensor signals, and / or one or more molecular biomarkers.[000108] In some embodiments, a correlation between a sensor signal and one or more previous sensor signals may be based on a change in firing frequency. The change in firing frequency may be determined through the employment of one or more Generalized Estimating Equations (GEE). The change in firing frequency may be determined by one or more sensor signals. The change in firing frequency may be determined across two or more sensor signals. A correlation between a sensor signal and one or more previous sensor signals may be based on a rate change in firing frequency. The rate change in firing frequency may be determined through the employment of one or more GEEs. The rate change in firing frequency may be determined by one or more sensor signals. The rate change in firing frequency may be determined across two or more sensor signals. For example, the inflammation biotype classifier 155 may comprise instructions which, when executed by the processor 110, cause the processor to automatically classify an inflammation biotype for a subject based on rostral to caudal sensor position-specific (rostral to caudal) firing patterns.[000109] In some embodiments, a correlation between a sensor signal and one or more previous sensor signals may be based on a change in spike amplitude. The change in spike amplitude may be determined through the employment of one or more Generalized Estimating Equations (GEE). The change in spike amplitude may be determined by one or more sensor signals. The change in spike amplitude may be determined across two or more sensor signals. A correlation between a sensor signal and one or more previous sensor signals may be based on a rate change in spike amplitude. The rate change in spike amplitude may be determined through the employment of one or more GEEs. The rate change in spike amplitude may be determined by one or more sensor signals. The rate change in spike amplitude may be determined across two or more sensor signals. For example, inflammation biotype classifier 155 may comprise instructions which, when executed by processor 110, cause the processor to automatically classify an inflammation biotype for a subject based on rostral to caudal sensor position-specific (cephalad to caudal) spike amplitude patterns.[000110] In some embodiments, a correlation between a sensor signal and one or more previous sensor signals may be based on a change in spike frequency. The change in spike frequency may be determined through the employment of one or more Generalized Estimating Equations (GEE). The change in spike frequency may be determined by one or more sensor signals. The change in spike frequency may be determined across two or more sensor signals. A correlation between a sensor signal and one or more previous sensor signals may be based on a rate change in spike frequency. The rate change in spike frequency may be determined through the employment of one or more GEEs. The rate change in spike frequency may be determined by one or more sensor signals. The rate change in spike frequency may be determined across two or more sensor signals. For example, inflammation biotype classifier 155 may comprise instructions which, when executed by processor 110, cause the processor to automatically classify an inflammation biotype for a subject based on rostral to caudal sensor position-specific (cephalad to caudal) spike frequency patterns.[000111] In some embodiments, memory 150 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically create a notification based on at least an inflammation risk and / or an inflammation biotype. A notification may be created within a time frame of receiving data signals 125. For example, the time frame may be on the order of thirty minutes. A notification may comprise notification 115 and / or remote notification 175.[000112] In some embodiments, memory 150 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically present notification 115 to a user of system 100B. By way of example and not limitation, notification 115 may comprise one or more of an alert, a message, streaming data, and / or any other communicable form of notification. Notification 115 may be communicated to display device 160. Display device 160 may comprise one or more display devices. Display device 160 may be associated with a graphics processing unit (GPU) configured to render visual graphics output of notification 115 for presentation on display device 160. Display device 160 may be associated with graphical user interface (GUI) 165. Notification 115 may be communicated to one or more remote devices 190 through employment of network 180. A remote device 190 may comprise a remote display device. The remote display device may be associated with a graphics processing unit (GPU) configured to render visual graphics output of notification 115 for presentation on the remote display device.[000113] In some embodiments, memory 150 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically present a plot of at least one sensor signal 135 on display device 160. A plot may comprise a plurality of spikes in one or more neural signals. A plot may comprise one or more clusters of spikes in one or more neural signals. A plot may comprise one or more layers produced by a Neural Network (NN). A plot may comprise one or more aspects and / or features of other physiological signals. Display device 160 may be associated with a graphics processing unit (GPU) configured to render the plot graphically for visual output on display device 160.[000114] In some embodiments, system 100B may comprise wireless transmitter 170. Wireless transmitter 170 may comprise one or more wireless transmitters. Wireless transmitter 170 may be configured to communicate with remote device 190. Remote device 190 may comprise one or more remote devices. Wireless transmitter 170 may be configured for broadcast transmissions. Wireless transmitter 170 may be configured to communicate with remote device 190 through the employment of network 180. Wireless transmitter 170 may be configured to communicate with remote device 190 via a communication protocol. Examples of communication protocols wireless transmitter 170 may employ to communicate with remote device 190 include, without limitation Wi-Fi, Bluetooth, Bluetooth Low Energy, and / or any other communication protocol. Wireless transmitter 170 may comprise one or more antennas. Memory 150 may comprise instructions configured to cause processor 110 to automatically communicate remote notification 175 to remotedevice 190 employing wireless transmitter 170. Remote notification 175 may comprise one or more notifications. By way of example and not limitation, remote notification 175 may comprise one or more of an alert, a message, streaming data, and / or any other communicable form of notification. Streaming data may comprise one or more sensor signals 135. Streaming data may comprise one or more data signals 125. Remote notification 175 may be communicated from wireless transmitter 170 to remote device 190. By way of example and not limitation, remote device 190 may be employed by a user, a technician, a remote operator, a physician, a medical professional, and / or any other user. System 100B may be configured to accept operational instructions from remote device 190.[000115] In some embodiments, memory 150 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically communicate data signal 125 to remote device 190 through the employment of wireless transmitter 170. Data signal 125 may comprise one or more data signals. Data signal 125 may be processed by processor 110 prior to communication to remote device 190 via wireless transmitter 170.[000116] In some embodiments, instructions 152 may comprise spike sorter 156. Spike sorter 156 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically perform a spike sorting algorithm.[000117] In some embodiments, a spike sorting algorithm may be employed to identify action potentials for one or more neural signals. The one or more neural signals may be detected simultaneously. For example, a multi-channel surface electrode array may be configured to detect neural activity from a plurality of neural structures. Each channel of the multi-channel surface electrode array may be configured to communicate one or more neural signals once detected. In some embodiments, a spike sorting algorithm may be employed to identify nerve firing patterns for one or more neural signals. In some embodiments, a spike sorting algorithm may be employed to sort spikes in neural activity. In some embodiments, a spike sorting algorithm may be employed to identify action potentials for one or more sensor signals. The one or more sensor signals may be detected simultaneously. In some embodiments, a spike sorting algorithm may be employed to sort spikes that are specific to distinct sensor sites localized over various nerve targets. For example, nerve targets may be located in the cervical neck area. Nerve targets may include, for example, vagus nerve, vagus nerve branches, trigeminal nerve branches, sympathetic chain, sympathetic chain branches, hypoglossal nerves, glossopharyngeal nerves, muscular sympatheticnerves, dermal sympathetic nerves, and / or any other cervical neural structures including spinal cord, spinal nerve roots, dorsal root ganglia, and brachial plexus. For example, a plurality of wearable sensors may be configured to detect a plurality of neural signals and / or other physiological signals. In some embodiments, a spike sorting algorithm may be performed on each data signal. In some embodiments, classifying an inflammation biotype for a subject may be based on sorting spikes in neural signals and / or other physiological signals through the employment of a spike sorting algorithm.[000118] In some embodiments, instructions 152 may comprise Neural Network (NN) 157 (also referred to as Convolutional Neural Network or CNN 157). NN 157 may comprise instructions which, when executed by processor 110, cause processor 110 to automatically perform non-linear processing to identify autonomic features of one or more data signals 125 through the employment of one or more feature-specific saliency maps. NN 157 may employ one or more deep learning models to identify higher-level autonomic features of one or more data signals 125.[000119] FIG. 2 is a block diagram of a second embodiment of the system 100, described as system 200, for predicting immune responses, consistent with disclosed embodiments. System 200 may comprise processor 210, receiving unit 220, wearable sensors 237, and memory 250. Processor 210 may comprise one or more processors. Receiving unit 220 may comprise one or more receivers. Receiving unit 220 may be configured to receive a sensor signal from a wearable sensor 237. Receiving unit 220 may be configured to receive a plurality of sensor signals from wearable sensors 237. Wearable sensors 237 may comprise a plurality of electric circuits 240-249. Each electric circuit may be coupled to two or more sensors. As shown in this figure, for example, electric circuit 240 is coupled to sensor 230a and sensor 230b, electric circuit 241 is coupled to sensor 231a and sensor 231b, and electric circuit 249 is coupled to sensor 239a and sensor 239b. The sensors coupled to each electric circuit may be configured to detect at least a portion of a neural signal of a subject. Sensors may be configured to detect at least a portion of a neural signal transcutaneously. At least one sensor signal may include at least a portion of a neural signal. Receiving unit 220 may be configured to communicate sensor signals to processor 210. Memory 250 may comprise data 251. Data 251 may comprise data corresponding to, for example, sensor signals, physiological signals, neural signals, inflammation risk, inflammation biotype, and / or any other data corresponding to one or more subjects. Memory 250 may comprise instructions 252. Processor 210 may be configured to execute instructions 252 to perform operations. Instructions252 may comprise inflammation risk classifier 254. Instructions 252 may comprise inflammation biotype classifier 255. The particular arrangement of components depicted in FIG. 2 is not intended to be limiting. System 200 may include additional components, or fewer components. Multiple components of system 200 may be implemented using the same physical computing device or different physical computing devices.[000120] In some embodiments, information risk classifier 254 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically classify an inflammation risk for a subject based on one or more sensor signals. Inflammation risk classifier 254 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically classify an inflammation risk for a subject based on a correlation between one or more sensor signals and one or more previous sensor signals. Inflammation risk classifier 254 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically classify an inflammation risk for a subject based on an increase in neural activity and a corresponding increase in one or more other physiological activities. Inflammation risk classifier 254 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically classify an inflammation risk for a subject based on an increase in neural activity and a corresponding decrease in one or more other physiological activities. Inflammation risk classifier 254 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically classify an inflammation risk for a subject based on one or more molecular biomarkers. Inflammation risk classifier 254 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically classify an inflammation risk for a subject based on entrainment between neural activity and changes in one or more molecular biomarkers. Inflammation risk classifier 254 may comprise instructions which, when executed by processor 210, cause processor 210 to employ one or more machine learning models to automatically classify an inflammation risk for a subject based on one or more sensor signals, one or more previous sensor signals, and / or one or more molecular biomarkers.[000121] In some embodiments, inflammation biotype classifier 255 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically classify an inflammation biotype for a subject based on one or more sensor signals. Inflammation biotype classifier 255 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically classify an inflammation biotype for a subject based on a correlation betweenone or more sensor signals and one or more previous sensor signals. Inflammation biotype classifier 255 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically classify an inflammation biotype for a subject based on one or more clusters of spikes in neural activity in one or more sensor signals. Spikes in neural activity may be sorted through the employment of a spike sorter 256 prior to cluster identification. Inflammation biotype classifier 255 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically classify an inflammation biotype for a subject based on a correlation between one or more clusters of spikes in neural activity in one or more sensor signals and one or more clusters of spikes in neural activity in one or more previous sensor signals. Correlation between clusters of spikes may be based on one or more temporal relationships and / or one or more spatial relationships. Inflammation biotype classifier 255 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically classify an inflammation biotype for a subject based on an increase in neural activity and a corresponding increase in one or more other physiological activities. Inflammation biotype classifier 255 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically classify an inflammation biotype for a subject based on an increase in neural activity and a corresponding decrease in one or more other physiological activities. Inflammation biotype classifier 255 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically classify an inflammation biotype for a subject based on one or more molecular biomarkers. Inflammation biotype classifier 255 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically classify an inflammation biotype for a subject based on entrainment between neural activity and changes in one or more molecular biomarkers. Inflammation biotype classifier 255 may comprise instructions which, when executed by processor 210, cause processor 210 to employ one or more machine learning models to automatically classify an inflammation biotype for a subject based on one or more sensor signals, one or more previous sensor signals, and / or one or more molecular biomarkers.[000122] In some embodiments, electric circuits of wearable sensors 237 may be configured to reduce impedance artifacts. For example, at least a portion of electric circuits 240-249 may be coiled. Each electric circuit 240-249 may comprise an amplifier.[000123] In some embodiments, a surface electrode array may comprise wearable sensors 237. The surface electrode array may comprise at least one wearable material. A wearable material maybe flexible and / or stretchable. The surface electrode array may be configured to be worn by a subject. The surface electrode array may be part of a system that is configured to be worn by a subject. The surface electrode array may be configured to enable a subject to move freely. The surface electrode array may be configured to conform to a position over the left superior anterior cervical area of a subject. The surface electrode array may be configured to conform to a position over multiple neural structures including, for example, vagus nerve, vagus nerve branches, trigeminal nerve branches, sympathetic chain, sympathetic chain branches, hypoglossal nerves, glossopharyngeal nerves, muscular sympathetic nerves, dermal sympathetic nerves, and / or any other cervical neural structures including spinal cord, spinal nerve roots, dorsal root ganglia, and brachial plexus. The surface electrode array may be configured to detect electrodermal activity (EDA). The surface electrode array may be configured to maintain an impedance between the surface electrode array and the skin of a subject at or below 1.6 kQ. The surface electrode array may comprise a plurality of electric circuits. The surface electrode array may comprise a plurality of electrode circuits.[000124] In some embodiments, a surface electrode array may be placed lateral to the trachea and medial to the sternocleidomastoid of a subject. In some embodiments, a surface electrode array may be placed to overlay the left superior anterior cervical area of a subject spanning rostral to caudal diagonally. For example, a four-channel surface electrode array may be placed such that a wearable sensor is over each of the following anatomical targets: (1) the upper nodose ganglion, (2) the lower nodose ganglion, (3) the upper carotid artery, and (4) the lower carotid artery.[000125] In some embodiments, a surface magnetometer array may comprise wearable sensors 237. The surface magnetometer array may comprise at least one wearable material. A wearable material may be flexible and / or stretchable. The surface magnetometer array may be configured to enable a subject to move freely. The surface magnetometer array may be configured to conform to a position over the left superior anterior cervical area of a subject. The surface magnetometer array may be configured to conform to a position over multiple neural structures including, for example, vagus nerve, vagus nerve branches, trigeminal nerve branches, sympathetic chain, sympathetic chain branches, hypoglossal nerves, glossopharyngeal nerves, muscle sympathetic nerves, dermal sympathetic nerves, and / or any other cervical neural structures.[000126] In some embodiments, each of the wearable sensors 237 may comprise a contact surface with a small contact footprint. For example, a contact footprint may comprise 15mm x90mm. Wearable sensors 237 may comprise a surface having a low profile. For example, a profile may comprise a height in the range of 2-9 mm. Wearable sensors 237 may comprise material that is measured to be a light weight. For example, a weight of sensor material may measure 1g or less per wearable sensor. Wearable sensors 237 may comprise one or more integrated circuits. Wearable sensors 237 may comprise one or more physiological sensors. A physiological sensor may be configured to communicate a sensor signal comprising one or more neural signals and / or other physiological signals. Wearable sensors 237 may be configured to detect neural signals and / or other physiological signals over a minimum and / or maximum spatial resolution. For example, a maximum spatial resolution may comprise 2mm. Wearable sensors 237 may be configured to detect neural signals and / or other physiological signals for a minimum temporal resolution. For example, a minimum temporal resolution may comprise a range of 1000-14,000 samples per second.[000127] In some embodiments, system 200 may comprise wireless transmitter 270. Wireless transmitter 270 may comprise one or more wireless transmitters. Wireless transmitter 270 may be configured to communicate with remote device 290. Remote device 290 may comprise one or more remote devices. Memory 250 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically communicate a notification to remote device 290 through employment of wireless transmitter 270. A notification may comprise one or more of an alert, a message, streaming data, and / or any other communicable form notification. By way of example and not limitation, remote device 290 may be employed by a user, a technician, a remote operator, a physician, a medical professional, and / or any other user. System 200 may be configured to accept operational instructions from remote device 290.[000128] In some embodiments, memory 250 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically communicate a data signal to remote device 290 through employment of wireless transmitter 270.[000129] In some embodiments, memory 250 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically receive a data signal from receiving unit 220. A data signal may comprise one or more sensor signals. Receiving unit 220 may comprise an amplifier. Receiving unit 220 may be configured to apply one or more filters to one or more sensor signals. A filter may be configured to remove artifacts, pass high frequencies, pass low frequencies, and / or pass a band of frequencies. Receiving unit 220 may be configured to convertanalog sensor signals into digital sensor signals. Analog sensor signals may be converted into digital sensor signals through employment of one or more analog-to-digital converters (ADC). The ADC may be configured to sample analog signals up to a rate on the order of 16 kHz. The ADC may be configured to sample analog signals at a rate of 8 kHz. The ADC may be configured for 24-bit resolution.[000130] In some embodiments, instructions 252 may comprise data signal processor 253. Data signal processor 253 may comprise instructions configured to cause processor 210 to automatically process a data signal. Processing a data signal may comprise one or more of filtering, modulating, encoding, converting analog signals to digital, converting digital signals to analog, performing error correction, and / or multiplexing a plurality of signals. A data signal may be processed by processor 210 prior to communication to remote device 290. In some embodiments, instructions 252 may comprise spike sorter 256. Spike sorter 256 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically perform a spike sorting algorithm.[000131] In some embodiments, instructions 252 may comprise Neural Network (NN) 257 (also referred to as Convolutional Neural Network CNN 257). NN 257 may comprise instructions which, when executed by processor 210, cause processor 210 to automatically perform convolutions to identify autonomic features of one or more data signals through the employment of one or more feature-specific saliency maps. NN 257 may employ one or more deep learning models to identify higher-level autonomic features of one or more data signals.[000132] In some embodiments, a system for immune response prediction may be wearable. For example, the system 100, system 100B, and / or system 200 may be wearable by a subject / user. The system may comprise wearable components. For example, a processor, such as processor 110 or processor 210, may be wearable. The processor may be physically connected to an array of wearable sensors. For example, the processor may be connected to wearable sensors 237. By way of another example of a wearable component, a receiving unit, such as receiving unit 120 or receiving unit 220, may be wearable. The receiving unit may be physically connected to an array of wearable sensors, such as wearable sensors 237. Referring to another example of a component that may be wearable, a memory, such as memory 150 or memory 250, may be wearable. The memory may be physically connected to an array of wearable sensors, such as wearable sensors 237. For another example of a component that may be wearable, a wireless transmitter, such aswireless transmitter 170 or wireless transmitter 270, may be wearable. The wireless transmitter may be physically connected to an array of wearable sensors, such as wearable sensors 237.[0001331 In some embodiments, a receiving unit may comprise a transmitter. For example, receiving unit 120 or receiving unit 220 may comprise a transmitter. The transmitter may be configured to transmit one or more data signals to a processor, such as processor 110 or processor 210. For example, a processor, such as processor 110 or processor 210, may be part of a computing system such as a personal computer, smartphone, tablet computing device, single board computer, wearable computing system, and / or any other computing system. The computing system may comprise a memory, such as memory 150 or memory 250. The computing system may comprise a wireless transmitter, such as wireless transmitter 170 or wireless transmitter 270.[000134] In some embodiments, a receiving unit may be configured to detect at least a portion of one or more neural signals in neural structures of a subject. Examples of neural structures of the subject include, without limitation, a vagus nerve of the subject, a cervical nerve of the subject, a spinal nerve of the subject, and / or any other neural structure of the subject. In some embodiments, a receiving unit may be configured to detect a change in at least a portion of one or more neural signals in neural structures of a subject. For example, a change in neural signals may be detected by receiving unit 120 or receiving unit 220 in a vagus nerve of a subject, a cervical nerve of the subject, a spinal nerve of the subject, and / or any other neural structure of the subject. In some embodiments, a receiving unit may be configured to differentiate between a plurality of neural signals. For example, each of a plurality of neural signals may comprise a distinct frequency. By way of another example, each neural signal in a plurality of neural signals may comprise a distinct firing pattern or nested firing frequency. In another example, each neural signal in a plurality of neural signals may comprise a distinct amplitude. A plurality of neural signals may originate from a plurality of neurons. A plurality of neurons may comprise one or more groups of neurons.[000135] In some embodiments, a receiving unit may be configured to detect at least one neural signal and / or other physiological signal of the subject. In some embodiments, a receiving unit may be configured to detect a change in at least one neural signal and / or other physiological signal. In some embodiments, a receiving unit may be configured to differentiate between a plurality of neural signals and / or other physiological signals. For example, each neural signal in a plurality of neural signals and / or other physiological signals may comprise a distinct frequency. In another example, each neural signal in a plurality of neural signals and / or other physiological signals maycomprise a distinct firing pattern. Turning to another example, each neural signal in a plurality of neural signals and / or other physiological signals may comprise a distinct amplitude.[0001361 Insome embodiments, a system for predicting immune responses may be configured to differentiate between a plurality of neural signals from a subject. For example, the system 100, system 100B, or system 200 may be configured to differentiate a first vagus or sympathetic nerve waveform from a second vagus or sympathetic nerve waveform. In some embodiments, a system may be configured to compare one or more neural signals to one or more previous neural signals. A previous neural signal may be classified as having a specific inflammation biotype. The system may be configured to differentiate a waveform of one neural structure from waveforms of other neural structures. For example, the system 100, system 100B, or system 200 may be configured to differentiate a vagus or sympathetic nerve waveform from a neural waveform of another neural structure.[000137] In some embodiments, a system for predicting immune responses may be configured to differentiate between a plurality of neural signals and / or other physiological signals from a subject. For example, the system 100, system 100B, or system 200 may be configured to differentiate a first neural waveform from a second neural waveform. For example, the system 100, system 100B, or system 200 may be configured to differentiate a first physiological waveform from a second physiological waveform. In some embodiments, a system may be configured to compare one or more neural signals and / or other physiological signals to one or more previous neural signals and / or other physiological signals. A previous neural signal and / or other physiological signal may be employed to determine a specific inflammation risk for a corresponding subject. A previous neural signal and / or other physiological signal may be employed to determine a specific inflammation biotype for a corresponding subject.[000138] Some embodiments may include one or more previous neural signals and / or other physiological signals. A previous neural signal and / or other physiological signal may comprise a neural signal and / or other physiological signal from the same subject from a previous time frame. A previous neural signal and / or other physiological signal may comprise a neural signal and / or other physiological signal from another subject from a previous time frame. A plurality of previous neural signals and / or other physiological signals may comprise one or more neural signals and / or other physiological signals from each of a plurality of other subjects from one or more previous time frames.[000139] In some embodiments, a system for predicting immune responses may be configured to detect a change in at least one neural signal of a subject. The change may be based on a change in frequency from a previous neural signal from the subject. For example, a firing frequency of a presently detected neural signal may be distinct from a firing frequency of a previous neural signal from the subject. The change may be based on a change in amplitude from a previous neural signal from the subject. For example, an amplitude of a presently detected neural signal may be distinct from an amplitude of a previous neural signal from the subject. The change may be based on a change in firing frequencies from a plurality of previous neural signals from the subject. For example, the firing frequencies of a plurality of presently detected neural signals may be distinct from the firing frequencies of a plurality of previous neural signals from the subject. A previous neural signal from a subject may comprise one or more neural signals captured during a resting state of the subject.[000140] Detection of a change in a neural signal of a subject may be based on a heart rate, a respiratory rate, a respiratory phase, an electrodermal activity, and / or any other physiological signal from the subject. In some embodiments, a system for predicting immune responses may be configured to determine when one or more neural signals crosses a threshold. For example, the system 100, system 100B, or system 200 may be configured to determine when a firing frequency of one or more neural signals crosses a firing frequency threshold. For example, the system 100, system 100B, or system 200 may be configured to determine when a spike frequency of one or more neural signals crosses a spike frequency threshold. For example, the system 100, system 100B, or system 200 may be configured to determine when a spike amplitude of one or more neural signals crosses a neural signal spike amplitude threshold.[000141] In some embodiments, a system for predicting immune responses may be configured to determine when one or more physiological signals crosses a threshold. For example, the system 100, system 100B, or system 200 may be configured to determine when one or more respiratory signals crosses a respiratory signal spike amplitude threshold. For example, the system 100, system 100B, or system 200 may be configured to determine when high and / or low respiratory spikes in one or more respiratory signals crosses a respiratory phase threshold. For example, the system 100, system 100B, or system 200 may be configured to detect a duration of time that high and / or low spikes in one or more respiratory signals remain over a respiratory phase threshold and determine when the detected duration of time exceeds a pre- determined amount of time.[000142] Some embodiments may include one or more data models. A data model may be configured to organize data for any combination of the following: one or more neural signals, aspects of one or more neural signals, features of one or more neural signals, one or more other physiological signals, aspects of one or more other physiological signals, features of one or more other physiological signals, one or more molecular biomarkers, an inflammation risk, and / or an inflammation biotype. A data model may comprise one or more labels. A label may be employed to correlate aspects and / or features of neural signals and / or other physiological signals with molecular biomarkers, inflammation risks, inflammation biotypes, inflammation, an infection, sepsis, a cytokine response, a cytokine response to a vaccine, a disease response to any pathogen, a disease response to an unknown pathogen, and / or a disease response to a specific pathogen. A label may be employed to correlate aspects and / or features of neural signals with aspects and / or features of other physiological signals. A data model may be expanded. Expansion of a data model may be based on newly labeled samples. Newly labeled samples may be labeled based on neural signals and / or other physiological signals from one or more subjects. Labeled samples may comprise an additional class of data.[000143] Some embodiments may include one or more machine learning models. One or more machine learning models may be employed to automatically classify an inflammation risk. One or more machine learning models may be employed to automatically classify an inflammation biotype. A machine learning model may comprise a Support Vector Machine (SVM). A machine learning model may comprise a random forest. A machine learning model may comprise Linear Discriminant Analysis (LDA). A machine learning model may comprise one or more Linear Mixed-Effects (LME) models. A machine learning model may be trained through employment of one or more training data sets. A training data set may comprise candidate spikes. Candidate spikes may be identified through employment of constant thresholding. A training data set may comprise aspects and / or features of one or more sensor signals. For example, a training data set may comprise one or more HRV features automatically determined from an ECG signal. For example, a training data set may comprise one or more respiration features automatically determined from a respiration signal. Physiological data may be automatically processed with a specific time window interval and step size. For example, the time window interval may comprise five minutes. For example, the step size may comprise 2.5 minutes. A training data set may comprise molecular biomarker data. For example, the molecular biomarker data may comprise a concentration of oneor more cytokines. For example, the molecular biomarker data may comprise features of one or more molecular biomarkers. Results of a plurality of machine learning models may be combined through employment of ensemble learning. The combination of machine learning models may result in generation of a single ensemble model. An output of ensemble learning may comprise labels with majority votes. A counting technique may be employed to improve AUC. For example, a final output of a current time window interval may be set to the label that counts more than half of the past k time window intervals. For example, a value of k may be set to seven.[000144] Some embodiments may include one or more deep learning models. One or more deep learning models may be employed to improve classification performance of one or more machine learning models. One or more deep learning models may be employed to automatically identify higher- level autonomic features of one or more sensor signals. One or more deep learning models may be employed to automatically identify one or more molecular biomarkers. A two-dimensional input may be constructed through employment of past time window interval data. For example, the past twelve time window intervals may be stacked. A Convolutional Neural Network (CNN) may be employed on a two-dimensional input. The CNN may comprise a multilayer CNN. A multilayer CNN may comprise three or more layers. Randomized Input Sampling for Explanation (RISE) of black-box models may be employed for transparency. A Gradient-weighted Class Activation Mapping (Grad-CAM) framework may be employed for interpretability of one or more classification decisions. For example, a Grad-CAM framework may be based on a time window interval of thirty minutes.[000145] In some embodiments, classified data may be employed to correlate one or more neural signals with one or more previous neural signals. One or more previous neural signals may be associated with an eventual outcome. An eventual outcome may be a determination of one or more of inflammation, an infection, sepsis, a cytokine response, a cytokine response to a vaccine, a disease response to any pathogen, and / or a disease response to a specific pathogen. Classified data may be shared with one or more systems. Classified data may be available to one or more systems. Classified data may be accessible to one or more systems. Classified data may be based on data signals from one or more systems. Classified data may be stored in databases accessible over a network (such as cloud- based databases or other cloud data storage systems or services) and / or communicably and locally connected databases (such as in-memory data 151 or data 251, which may be retrieved from a local database communicably connected to the associated system, such asthe system 100, system 100B, or system 200, respectively). Classified data may be compared to previously acquired data index libraries.[0001461 In some embodiments, an inflammation risk classifier may comprise instructions which, when executed by a processor, cause the processor to automatically employ classified data to determine an inflammation risk. For example, inflammation risk classifier 154 or inflammation risk classifier 254 provides sets of instructions for the processor (that is, processor 110 or processor 210, respectively) to automatically employ classified data to determine inflammation risk. In some embodiments, an inflammation risk classifier may comprise instructions which, when executed by a processor, cause the processor to automatically employ classified data to detect a change in an inflammation risk. For example, inflammation risk classifier 154 or inflammation risk classifier 254 provides sets of instructions for processor 110 or processor 210, respectively, to automatically employ classified data to detect a change in inflammation risk.[000147] In some embodiments, an inflammation biotype classifier may comprise instructions which, when executed by a processor, cause the processor to automatically employ classified data to determine an inflammation biotype. For example, inflammation biotype classifier 155 or inflammation biotype classifier 255 may provide sets of instructions for processor 110 or processor 210, respectively, to automatically employ classified data to determine an inflammation biotype. In some embodiments, an inflammation risk classifier may comprise instructions which, when executed by a processor, cause the processor to automatically employ classified data to detect a change in an inflammation biotype. For example, inflammation biotype classifier 155 or inflammation biotype classifier 255 may provide sets of instructions for processor 110 or processor 210, respectively, to automatically employ classified data to detect a change in an inflammation biotype.[000148] The system of some embodiments comprises a spike sorter. For example, spike sorter 156 of system 100B or spike sorter 256 of system 200. A spike sorter may comprise a spike sorter algorithm. A spike sorter may be employed by a processor to automatically detect and sort spikes in one or more data signals. For example, spike sorter 156 or spike sorter 256 may be employed by processor 110 or processor 210, respectively, to automatically detect and sort spokes in one or more data signals, such as data signal 125.[000149] In some embodiments, a physiological signal may comprise a heart rate signal, an electrocardiogram (ECG) signal, an electroencephalographic (EEG) signal, an electrogastrography(EGG) signal, a cervical electroneurography (CEN) signal, a cervical magnetoneurography (c- MNG) signal, a respiration signal, and / or any other physiological signal. In some embodiments, a physiological signal may comprise at least one data stream comprising measurements of respiratory rate, respiratory phase, heart rate, cortical potential, skin conductance response, laser Doppler shift, impedance pneumography potential, skin temperature, respiratory bio-acoustic signal, and / or any other physiological measurement or position. Heart rate may be determined through the employment of R-R intervals from an ECG signal. An electrocardiogram-derived heart rate may be estimated through the employment of one or more neural signals. By way of example and not limitation, the position may comprise chest position, chest displacement, chest movement, and / or any other measured position. A physiological signal may be synchronized with one or more other physiological signals and / or one or more neural signals.[000150] Some embodiments of the system include a physiological sensor. For example, a wearable sensor 237 may comprise a physiological sensor. In some embodiments, a physiological sensor may comprise a heart rate sensor, a scalp electrode, a skin conductance electrode, a photodetector, an avalanche photodiode, a respiration rate sensor, a thermistor, a thermometer, a thermocouple, an optically pumped magnetometer (0PM) or other magnetometer device, and / or any other physiological sensor. A heart rate sensor may be configured to measure heart rate electrically and / or optically. A heart rate sensor may be configured to measure HRV. HRV may be determined by a receiving unit, such as receiving unit 120 or receiving unit 220 and / or a processor, such as processor 110 or processor 210, based on a heart rate signal communicated from a heart rate sensor. Physiological sensors configured to measure HRV may be coupled to a wearable sensor array (for example, 237), a chest strap, and / or a wristband. A chest strap and / or wristband may be coupled to at least one additional physiological sensor configured to measure, for example, breathing rate, galvanic skin response, skin temperature, and / or any other physiological measurement. A photodetector may be configured to measure laser Doppler shift. Similarly, an avalanche photodiode may be configured to measure laser Doppler shift. A respiration rate sensor may comprise an impedance pneumography electrode, a capacitive sensor, a piezoelectric sensor, a servo, an acoustic transducer, an inclinometer, an accelerometer, and / or any other respiration rate sensor. Respiration rate may be estimated from HRV and / or a photoplethysmography (PPG). An 0PM may be configured to sense biological magnetic fields. A biological magnetic field may comprise one or more neural signals. A physiological sensor maybe configured to measure sympathetic tone. Sympathetic tone may be measured relative to previous measurements. A physiological sensor may be configured to measure parasympathetic tone. Parasympathetic tone may be measured relative to previous measurements. A physiological sensor may be wearable. A physiological sensor may be configured to communicate data in more than one time scale. Data communicated from a physiological sensor may be recorded in a fixed time scale, in more than one time scale, in one adjustable time scale, and / or in a plurality of adjustable time scales. A physiological sensor may comprise a tattoo-based sensor or a skin- applied electrochemical sensor.[000151] In some embodiments, a system for predicting immune responses may be configured to automatically determine HRV features. HRV features may be determined in a time domain. For example, the system 100, system 100B, or system 200 may be configured to automatically determine pNN50, RMSSD, SDNN, AC, DC, and / or other HRV features. HRV features may be determined in a frequency domain. For example, the system 100, system 100B, or system 200 may be configured to automatically determine LF normalized, HF normalized, a LF / HF ratio, and / or other HRV features.[000152] In some embodiments, a system for predicting immune responses may be configured to automatically determine respiration features. Examples of respiration features include, without limitation, respiration rate, root mean square of successive differences between respirations, and R-R coefficient of variation.[000153] In some embodiments, a system for predicting immune responses may be configured to determine RSA amplification. For example, the system 100, system 100B, or system 200 may be configured to determine instantaneous heart rate from an ECG signal. Instantaneous heart rate may be based on a determination of one or more R-R intervals. Instantaneous heart rate may be determined for a plurality of time window intervals in the ECG signal. For example, a time window interval may comprise sixty seconds. Instantaneous heart rate may be plotted against a phase of respiration from a respiratory signal for each time window interval. Iterative pairs of breathing cycles from the respiratory signal may be aggregated to generate a scatterplot representing each time window interval. A sinewave may be fitted to the scatterplot data to minimize a sum of squares. An amplitude of the sinewave may be described as the modulation of heart rate in response to inhalation and exhalation over the time window interval. An Iterated Amplitude Adjusted Fourier Transform (IAAFT) of the R- R intervals may be employed to generate a surrogate dataset.The surrogate dataset may be employed to verify one or more relationships between respiration phase and instantaneous heart rate.[0001541 Insome embodiments, a system for predicting immune responses may be configured to calculate a confidence score. The confidence score may be based on a prediction of an inflammation risk. The confidence score may be based on a prediction of an inflammation biotype. In some embodiments, a system for predicting immune responses may comprise at least one biofuel cell. A biofuel cell may be configured to power at least a portion of a system. A biofuel cell may be wearable. In some embodiments, a system for predicting immune responses may comprise at least one neuromodulation device. The system may be configured to employ a neuromodulation device in response to determination of an inflammation risk. The system may be configured to employ a neuromodulation device in response to determination of a specific inflammation biotype.[000155] In some embodiments, a system for predicting immune responses may comprise a System on a Chip (SoC). In some embodiments, at least a portion the system for predicting immune responses embeds the SoC. In some embodiments, a system for predicting immune responses may comprise signal conditioning circuitry. In some embodiments, a system for predicting immune responses may comprise integrated power management circuitry.[000156] FIG. 3 illustrates an example dimensionality reduction algorithm, consistent with disclosed embodiments. The dimensionality reduction algorithm may be part of a spike sorting algorithm, consistent with disclosed embodiments. A spike sorting algorithm may comprise spike detection. In spike detection, a threshold value, Thr, may be set to 3c, where o = median (|%| / 0.6745) where is a bandpass filtered data signal. For each detected spike, a waveform of a specific number of samples may be saved as a candidate waveform template. For example, eighty samples (over 10 ms) may be saved. Each candidate waveform template (of the eighty samples) may be aligned to a maximum at a specific data point. For example, the data point may comprise data point thirty (3.75 ms). Due to the potential for a large number of candidate spikes, a kernel T-distributed stochastic neighbor embedding (t-SNE) algorithm may be employed to reduce dimensions. The kernel t-SNE algorithm may be employed to reduce time and / or space complexity which may reduce processing resources and / or processing time. A low-dimensional projection may be performed through density- based spatial clustering of application with noise (DBSCAN) to cluster candidate spikes into groups and / or identify outliers. The clustered groups may be characterizedby different firing rate and / or amplitude behaviors. A firing rate may be counted as the number of activities per second. An amplitude may be derived by calculating a peak-to-peak difference of each detected waveform. A spike sorting algorithm may comprise separating data points into a training set and a testing set. The spike sorting algorithm may comprise employing t-SNE on the training set to create a training map. The spike sorting algorithm may comprise mapping the testing set on a reduced dimension. The spike sorting algorithm may comprise investigating distances between the training map and a testing map. The spike sorting algorithm may comprise employing DBSCAN on the testing map. The spike sorting algorithm may comprise employing a K-Nearest Neighbor (K-NN) algorithm to perform a semi-supervised classification of spikes mapped through employment of a kernel t-SNE algorithm.[000157] FIG. 4 conceptually illustrates a method for predicting immune responses, consistent with example embodiments of the disclosed methods. The method includes a process 410 to receive a plurality of sensor signals associated with a subject (e.g., patient). The process 410 can include continuous or intermittent monitoring (e.g., in real time) of the sensor signals; and the process 410 can include acquisition of sensor data comprising the sensor signals post- or partially - post monitoring of the subject. A plurality of sensor signals may be automatically received (at 410). The plurality of sensor signals may be received from at least one or a plurality of wearable sensors, e.g., various embodiments of the wearable sensor(s) 130. Each of the sensor signals may be communicated from one of the wearable sensors. In some implementations, for example, at least one of the sensor signals may include at least a portion of a neural signal of a subject. At least one wearable sensor may be configured to detect the neural signal transcutaneously. The method includes a process 415 to analyze the sensor signals and determine an immune response parameter and / or immune response data or data set associated with the subject. In some embodiments of the process 415, the sensor signal is processed with respect to an immune response data model, including example embodiments of the data models described in this disclosure. In some embodiments of the process 415, the determined immune response parameter, data, or data set can include a classification of the subject’s immune response with respect to a biotype of the subject or a risk factor of the subject. For example, an inflammation risk for the subject may be automatically classified (at optional process 420 of the process 415). The inflammation risk may be classified based on at least one of the sensor signals. For example, in some embodiments of the process 415, an inflammation biotype for the subject may be classified automatically (at optionalprocess 430 of the process 415). The inflammation biotype may be classified based on at least one of the sensor signals.[0001581 Insome embodiments of the method, the method can optionally include a process 440 to generate a display output indicative of the determined immune response parameter, data, or data set. In various embodiments, the display output can include, but is not limited to, an alert (e.g., visual, auditory, and / or haptic alert), and / or a graphical user interface (GUI) illustrative of the display output (e.g., a graph, table, chart, and / or readable or hearable text that describes the immune response parameter, data, and / or data set). In some implementations, the alert and / or GUI can be outputted in the form of a notification. In some embodiments of the optional process 440, the notification may be automatically created (at 440). The creation of the notification may be based at least in part on the inflammation risk and / or the inflammation biotype. The notification may be automatically presented (at 450). A plot of one or more of the sensor signals may be automatically presented on a display (at 460). One or more of the sensor signals may be automatically transmitted to a remote device (at 470). The notification may be automatically transmitted (at 480) to a remote device.[000159] In some embodiments, automatically classifying an inflammation risk (at 420) for a subject may be performed prior to any symptoms experienced by the subject. Automatically classifying an inflammation biotype (at 430) for a subject may be performed prior to any symptoms experienced by the subject. In these embodiments, “symptoms experienced by the subject” refer to indications of inflammation and / or immune response known by the subject prior to inflammation risk and / or inflammation biotype classification being performed.[000160] In some embodiments, automatically classifying an inflammation risk (at 420) for a subject may be based on a determination of RS A amplification. A surrogate dataset may be generated. Modulation of heart rate in response to inhalation and exhalation may be compared to the surrogate dataset. One or more distinctions between actual RS A amplification data and surrogate data may be employed to determine the inflammation risk.[000161] In some embodiments, automatically classifying an inflammation biotype (at 430) for a subject may be based on identifying autonomic features through the employment of a Neural Network (NN). Automatically classifying an inflammation biotype (at 430) for a subject may be based on a spatial relationship of spikes in neural activity between two or more of the sensor signals. Automatically classifying an inflammation biotype (at 430) for a subject may be based oncorrelating temporal signal characteristics of one or more of the sensor signals to temporal signal characteristics of previous sensor signals. Automatically classifying an inflammation biotype (at 430) for a subject may be based on correlating spatial signal characteristics of one or more of the sensor signals to spatial signal characteristics of previous sensor signals. Automatically classifying an inflammation biotype (at 430) for a subject may be based on correlating one or more clusters of spikes in neural activity in one or more of the sensor signals to one or more clusters of spikes in neural activity in previous sensor signals.[000162] FIGS. 5A-5D illustrate an example of a surface electrode array, consistent with disclosed embodiments. Specifically, FIG. 5A shows an exploded view of one example of a surface electrode array and wearable sensor(s). FIGS. 5B and 5C show examples of the surface electrode array during fabrication, and FIG. 5D shows an example of a fully-fabricated surface electrode array. The exploded view of the example surface electrode array comprising wearable sensors is shown in FIG. 5A may form an electrode array configured for multi-channel cervical neuronal activity. For example, the surface electrode array may be configured for four channels of cervical neuronal activity. Each channel may detect a channel-specific neural signal and / or a channelspecific aspect of one or more neural signals. For example, the detected neural firing frequency and / or amplitude may be distinct on each neural signal from one or more channels. For example, one or more clusters of spikes in neural activity may be distinct on each of one or more channels. Each wearable sensor may comprise an electrode. Each electrode may be configured to have a size and a shape. In some embodiments, for example, the electrode of the wearable sensor may have a diameter of five mm. In some embodiments, for example, the wearable sensor(s) may have an interconnect width of five-hundred micrometers (500 pm). A sensor layer may be placed between two polyimide (PI) layers. In some embodiments, for example, the sensor layer (e.g., one or more electrode(s) and interconnect(s)) may be encompassed between the PI layers; whereas, in some embodiments, for example, the electrode(s) of the sensor layer may have one surface exposed through one of the PI layers while the remaining portion of the electrode(s) and the interconnect(s) are covered between the PI layers. In some embodiments, electrode size and associated impedance, electrode shape, and the arrangement of electrodes may be altered to improve spike sorting outcomes performed on one or more of the channels.[000163] In some embodiments, a surface electrode array may be fabricated through the employment of thin film microfabrication and through the employment of thick film screen printing.[000164] Aspects of surface electrode arrays during fabrication are shown in the second and third panels (panels ‘b’ and ‘c’, respectively). In particular, the second panel (panel ‘b;) illustrates a post-processed wafer ready for electrode ink printing and the third panel (panel ‘c’) illustrates the wafer with Ag / AgCl ink screen printed on the active electrode regions. The Ag / AgCl layer may be on the order of a micrometer in thickness.[000165] In an example fabrication process, a silicon wafer having a diameter on the order of four inches may be cleaned and dried. A dehydration bake may be performed on the wafer at a temperature on the order of one-hundred eighty degrees Celsius (180 °C). Polydimethylsiloxane (PDMS) may be deposited onto the wafer through the employment of spin coating at an RPM on the order of four-thousand (4000). Polyimide may be deposited onto the wafer through the employment of spin coating at an RPM on the order of four-thousand (4000). The wafer may be soft-baked at a temperature on the order of one-hundred ten degrees Celsius (110 °C) for a duration on the order of one minute. The wafer may be soft-baked at a temperature on the order of one- hundred fifty degrees Celsius (150 °C) for a duration on the order of five minutes. The wafer may be hard baked in a nitrogen-rich environment oven at a temperature on the order of three-hundred degrees Celsius (300 °C). Metallization may be performed through employment of an electron beam evaporator. The metallization may yield layers of the wafer including a chrome layer on the order of ten nanometers (10 nm) and a gold layer on the order of five-hundred nanometers (500 nm). Lithography of the metallization layer may be performed to define one or more electrode(s) and interconnect(s) of the sensor(s) on the wafer. In some embodiments, the one or more electrodes may have a diameter on the order of five mm (5 mm), and the one or more interconnect(s) may have a width on the order of five-hundred micrometers (500 pm). Another layer of polyimide may be deposited onto the wafer through the employment of spin coating at an RPM on the order of four- thousand (4000). Photolithography and reactive ion etching (RIE) with oxygen plasma may be employed to define a bottom and / or a top polyimide layer of the wafer. For example, in some embodiments of the surface electrode arrays, apertures in one of the polyimide layers can be formed by etching (e.g., via RIE with oxygen plasma) to expose a surface or portion of a surface of the metallization layer structure(s) (e.g., that become the electrode(s)). A silver / silver chlorideink may be screen printed onto the active sensor areas via a stainless-steel stencil. A zero insertion force (ZIF) connector may interface the surface electrode array through the employment of anisotropic tape and the application of heat and pressure to bonding sites. Water soluble tape may be employed to transfer-print the surface electrode array from the silicon wafer to a flexible silicone substrate. The flexible silicone substrate may be made on a petri dish having a diameter on the order of five inches. The flexible silicone substrate may be spin-coated with Ecoflex at an RPM on the order of three- thousand (3000). Silbione RT Gel may be employed as an adhesive silicone. The silicone substrate and the surface electrode array may be peeled off and transferred to a thin sheet of polyethylene terephthalate (PET). The silicone bilayer may be cut into a shape. The shape may comprise a rectangular shape.[000166] In some embodiments, EC3 conductive adhesive gel may be applied to a surface electrode array prior to the surface electrode array being applied to a subject. In some embodiments, a backing sheet of PET may be peeled off from a surface electrode array after the surface electrode array has been applied to a subject.[000167] FIG. 5D demonstrates an example of a fully- fabricated surface electrode array, consistent with disclosed embodiments. The surface electrode array may comprise a self-adhering flexible silicone substrate. Active electrodes may be transfer-printed onto the self-adhering flexible silicone substrate. The silicone substrate may comprise Ecoflex and Silbione.[000168] FIG. 6 illustrates an example surface electrode array 600 in use, as applied to a subject, consistent with disclosed embodiments. The surface electrode array 600 may be configured to be worn over a section of a vagus nerve or sympathetic nerve of a subject (as shown in this figure). The surface electrode array 600 may be adhesive integrated. The surface electrode array 600 may be configured to be worn by the subject through employment of one or more adhesives. The surface electrode array 600 may be configured to be worn over a section of a cervical nerve of the subject. The surface electrode array 600 may be configured to be worn over at least a section of a neural structure of the subject. The neural structure may be any neural structure of the subject. The surface electrode array 600 may be configured to detect at least one neural signal transcutaneously. The surface electrode array 600 may be communicably connected to a receiving unit. The receiving unit may comprise a biopotential data acquisition board configured to receive data from the surface electrode array 600. The receiving unit may be further connected to a ground and / or reference electrode. For example, a ground electrode may be configured to be placed on a forearm of asubject. For example, a reference cup electrode may be configured to be placed ipsilaterally above a surface electrode array on a mastoid of the subject.[0001691 Insome embodiments, neural signal data and / or other physiological signal data may be captured from subjects before and / or after stress events (invasive and / or non-invasive stress events) experienced by the subjects. Examples of such stress events include, without limitation, deep breathing exercise, exposure to cold water (for example, the cold pressor test), and / or an infectious challenge (for example, a Lipopolysaccharide (LPS) injection or injection of another live or attenuated pathogen and / or vaccine). In some embodiments, an inflammation risk may be classified for a subject based on a response to one or more stress events. The inflammation risk may be employed to qualify and / or classify subjects for one or more clinical trials. In some embodiments, an inflammation biotype may be classified for a subject based on a response to one or more stress events. The inflammation biotype may be employed to qualify and / or classify subjects as a candidate or non-candidate for one or more clinical trials. In some embodiments, development of one or more machine learning models may be based on responses by a plurality of subjects to one or more stress events. In some embodiments, development of one or more deep learning models may be based on responses by a plurality of subjects to one or more stress events. Classification of an inflammation risk for a subject may not require neural signal data and / or other physiological signal data from before and / or after a stress event. Classification of an inflammation biotype for a subject may not require neural signal data and / or other physiological signal data from before and / or after a stress event.[000170] In some embodiments, neural signal data and / or other physiological signal data captured from subjects may be correlated to cytokine concentrations or other inflammatory biomarkers. Correlations between one or more aspects or features of neural signals and / or other physiological signals and cytokine concentrations or other inflammatory biomarkers may be employed to develop one or more machine learning models. Correlations between one or more aspects or features of neural signals and / or other physiological signals and cytokine concentrations or other inflammatory biomarkers may be employed to develop one or more deep learning models. [000171] FIG. 7 depicts an example plot of an example feature of an example physiological signal for a plurality of subjects, consistent with disclosed embodiments. A first inflammation biotype may comprise a subject with a high Tumor Necrosis Factor (TNF) cytokine concentration after receiving an LPS injection. A second inflammation biotype may comprise a subject with alow TNF cytokine concentration after receiving an LPS injection. A physiological signal may comprise a heart rate signal. The physiological signal may be captured from a subject in a resting state. A feature of a heart rate signal may comprise HRV. A feature of a heart rate signal may comprise an LF / HF ratio. A subject may be classified as having a sympathetic-driven biotype based on the logarithm (log) of a LF / HF ratio and high production of TNF cytokine after receiving an LPS injection. A subject may be classified as having a parasympathetic-driven biotype based on the log of a LF / HF ratio and low generation of TNF cytokine after receiving an LPS injection. Subjects having experience with meditation may impact classification. For example, subjects having experience with meditation may experience peak cytokine concentrations that are low and, instead of being classified as having parasympathetic-driven biotypes, may be classified as having sympathetic-driven biotypes.[000172] In FIG. 7, twenty -three subjects were administered 3ng / kg dosage LPS and were grouped into hyper-inflammation and hypo-inflammation subgroups using the median of peak TNF at 850 pg / ml as the threshold. The log of the average LF / HF ratio of each individual using non-overlapping 5-minute windows from their baseline recordings (i.e., prior to LPS injection) was computed and plotted against their peak TNF-a concentration produced from low to high. The log of the LF / HF ratio above zero was considered to be sympathetic dominance (i.e., the LF numerator exceeds the HF denominator), while below zero is parasympathetic dominance (i.e., the HF denominator exceeds the LF numerator). Interestingly, all subjects grouped as hyperinflammation were sympathetic dominant while most subjects grouped as hypo-inflammation were parasympathetic driven (FIG. 7). The exception for sympathetic dominance subjects, which produced relatively less cytokine, included three subjects who practiced meditation weekly and one active water polo athlete.[000173] FIG. 8 depicts an example of neurological activity before and after an autonomic nervous system challenge for a plurality of subjects, consistent with disclosed embodiments. A first inflammation biotype may comprise a subject with a high TNF cytokine concentration after receiving an LPS injection (a “TNF high responder”). A second inflammation biotype may comprise a subject with a low TNF cytokine concentration after receiving an LPS injection (a “TNF low responder”). Neuronal firing activity (frequency) may be measured at the left nodose ganglion and may be average neuronal firing rate for 60 seconds to 60 minutes. An autonomic nervous system challenge may comprise a deep breathing challenge. During a deep breathingchallenge the subject may perform up to a five second inhalation and up to a five second exhalation that may be repeated for up to three minutes before the LPS injection. The average firing rate over the deep breathing challenge for up to sixty seconds may be calculated before and after the challenge. A subject may demonstrate increased neurological activity before and after an autonomic nervous system challenge and produce high TNF cytokine concentration after receiving an LPS injection. A subject may demonstrate decreased neurological activity before and after an autonomic nervous system challenge and produce low TNF cytokine concentration after receiving an LPS injection. The neurological activity before and after an autonomic nervous system challenge may show significant difference (p<0.01) between two biotype groups.[000174] FIG. 8 shows example data depicting the cervical average neural firing rate at left nodose ganglion pre-to-post deep breathing challenge between the two biotype subgroups. The hyper-inflammation subgroup exhibited significant differences between pre-challenge and postchallenge neural activity (p<0.05), and the differences in average neural firing rate change between the two subgroups were also significant (p<0.01 ).[000175] FIG. 9 shows example plots of an example feature of an example physiological signal for two subjects, each with a distinct inflammation biotype, consistent with disclosed embodiments. A plot may comprise a Recurrence Plot (RP). An RP may be configured to provide information about a temporal correlation of phase space points. A physiological signal may comprise a heart rate signal. The physiological signal may be captured from a subject in a resting state. A feature of a heart rate signal may comprise R-R intervals. For example, seven-hundred fifty (750) consecutive R-R intervals occurring prior to an LPS injection may be analyzed. A first inflammation biotype may comprise a subject with a high TNF cytokine concentration after receiving an LPS injection (the TNF high responder). A second inflammation biotype may comprise a subject with a low TNF cytokine concentration after receiving an LPS injection (the TNF low responder). In this example, a recurrence matrix ‘X’ (referred to as “matrix X”) may be constructed with time delay (r) and an embedding dimension (m). Time delay r may comprise the first minimum location of an average mutual information function. Embedding dimension m may comprise a result of a False Nearest Neighbor method for each subject. A recurrence plot may be plotted where each point (i, j) is marked if a Euclidean distance between a delayed vector x(i) and x(j) is less than a given threshold a. The threshold a may comprise a percentage of a max delay embedding matrix X. For example, a percentage may comprise ten percent (10%). If a point (i, j)is marked as recurrent, a state j may belong to a neighborhood centered in i of size s. In other words, a state of a system at time i may have some similarity with a state of the system at j. In this example, the TNF high responder subject (left) has more recurrence, implying embedded heartbeat dimensions having higher similarities and thus lower heartbeat dynamics (less chaos), while the TNF low responder subject (right) has higher heartbeat dynamics that are more attuned to stress / environmental change.[000176] In general the methods and apparatuses described herein may predict inflammation severity by comparing baseline resting state (e.g., of sensor data for a cardiac sensed data and / or sensor data for a nerve activity, e.g., the vagus nerve) with those during an autonomic stress challenge.[000177] In some examples recurrence plot (RP) and recurrence quantification analysis (RQA) may be used as important and innovative tools for analyzing time series data, offering unique insights into the dynamics of complex systems. A RP is a graphical representation showing the times at which a state of a dynamical system recurs, suited to detect hidden dynamical patterns and nonlinearities within the system’s phase space. Expounding upon the visualization provided by RPs, RQA provides a set of measures to quantify the observed pattern, yielding metrics that describe the system’s behavior in terms of predictability, periodicity, stability, complexity, and chaoticity.[000178] In some examples, random 300-second segments of consecutive RR intervals recorded during baseline (i.e., prior LPS injection) were used to analyze the non-linear heartbeat dynamics. Because the RP is sensitive to small changes in the system’s dynamics, RP and associated RQA were computed using 100 random segments of baseline for each subject, and the averaged RQA was used for maximum produced cytokine correlation. Shortline segments parallel to the main diagonal are a potentially desirable feature of an RP, indicating that the system is evolving in a similar manner over two different periods. In other words, when the system’s state at time ti is close to its state till another time tn, a diagonal line will be formed, meaning the trajectory of the system follows a similar path for a certain duration between ti and tn. The length of such diagonal line structures may inform the predictability and determinism within the system. On the other hand, vertical lines in an RP represent periods during which the system remains in approximately the same state for an extended time. These lines may occur when a state at time ti is similar to states at several consecutive times ?, Is, ...., but without the system necessarily evolving similarlyafter those times (which would form a diagonal line). The presence of vertical lines may indicate trapping states in the dynamics, implying stability where the system’s state changes little over time, an example of which is shown in FIG. 9. In FIG. 9, Rec quantifies the percentage of recurrent points; in other words, Rec is the ratio of the number of recurrent points with respect to all points in the recurrence plot:[000179] DET is the indicator of the regularity and the determinism of the system dynamics. It computes the proportion of recurrent points that form diagonal lines of at least minimum length (excluding the major diagonal line) in the recurrence plot, relative to all recurrent points:[000180] Where 1 stands for the length of diagonal lines in the matrix, and P(l) is the number of lines of length equal to 1. LMAX quantifies the length of the longest diagonal line segment(excluding the major diagonal line) in the plot.[000181] LMAX = max(Z1, l2, l3... )[000182] Where li stands for the length of the ith-diagonal line. LAM is analogous to DET except that it measures the percentage of recurrent points comprising vertical line structures.[000183] Where v stands for the length of vertical lines in the matrix, and P(v) is the number of lines of length equal to v.[000184] TT is the average length of vertical line structure, representing the length of time that the dynamics remain trapped in a certain state.[000185] In this study, the minimum length for counting as a diagonal line or vertical line is set as 2.[000186] FIGS. 10A-10D show example data plots that illustrate Pearson correlation between inflammation severity and various RQA metrics measured during baseline resting state. In this example, the inflammation severity was identified (i.e., the logarithm of peak TNF-a produced)and showed a significant positive Pearson correlation with LMAX, LAM, and TT (FIGS. 10A- 10D, p = 0.44, 0.52, and 0.6, respectively, p<0.05). The Pearson correlations with DET, though did not reach significance, still showed positive trends (p = 0.35, p=0.099). The result shows that resting-state heartbeats with higher predictability and stability tend to have more severe inflammation.[000187] The graphs in FIGS. 10A-10D illustrate correlation between an example feature of an example physiological signal with an example immune response for each of the twelve subjects, consistent with disclosed embodiments. Plots may comprise Recurrence Quantification analysis (RQA). An RQA may be performed on an RP, such as the RPs shown in FIGS. 9A-9B. Short line segments parallel to a main diagonal may comprise important features of an RP which may indicate that an evolution of states is similar at different times, and that a process may be deterministic. Lenths of such diagonal line structures may rely on a predictability and / or dynamics of a system (for example, periodic, chaotic, and / or stochastic). Vertical or horizontal lines on a RP may denote that a system state does not change (vertical) or may change very slowly in time (horizontal). Diagonal and vertical linear structures may be inherent to a deterministic process but may not for a random process. In FIG. 9, the diagonal line 907 parallel to the main diagonal line informs predictability and determinism during those periods, while the vertical line 905 implies stability for those periods.[000188] A physiological signal may comprise a heart rate signal. A physiological signal may be captured from a subject in a resting state. A feature of a heart rate signal may comprise R-R intervals. A feature of a heart rate signal may comprise HRV. One or more RQA variables may illustrate significant correlation of a feature of a physiological signal with peak TNF cytokine concentrations in subjects after the subjects receive an LPS injection. Examples of RQA variables include, without limitation, Recurrence Rate (%Rec), Percent Determinism (%Det), Maximum Line Length (LMAX), and Trapping Time (TT). The RQA variable %Rec may be employed to quantify a percentage of recurrent points. In other words, %Rec may comprise a ratio of a number of recurrent points with respect to all points in a recurrence plot. The RQA variable %Det may be employed to indicate a regularity and / or a determinism of system dynamics. %Det may be computed as a percentage of recurrence points on diagonal lines. The RQA variable LMAX may be employed to quantify a length of a longest diagonal line segment in a plot. The RQA variable TT may be employed to determine an average length of a vertical line structure, which mayrepresent a length of time that dynamics remain trapped in a certain state. An RQA plot may illustrate a dynamic change in HRV. In these examples, subjects with higher HRV are shown to correlate with less TNF concentration, and subjects with less HRV are shown to correlate with higher TNF concentrations.[000189] FIGS. 13A-13C illustrate one example of the results of a cold pressor test (CPT) in which heart rate change response predicts inflammation severity. In this example, FIG. 13 A shows the HR change during CPT for an exemplary Hypo-inflammation subject. FIG. 13B shows the change in HR over time for an exemplary Hyper-inflammation subject. FIG. 13C shows an exemplary Pearson correlation between inflammation severity and HR gradient change after reaching HR during CPT.[000190] Prior to the LPS challenge, all participants underwent a cold pressor test (CPT). The procedure required subjects to immerse their right hand in ice water for a duration ranging from 3 to 5 minutes. Participants were allowed to withdraw their hand between this window only if they could no longer tolerate the cold stimulus. Then, the gradient slope between each subject’s peak HR and the lowest HR achieved thereafter during the CPT was calculated, as quantified by HR decrease (beat per minute) per sec. The subject exhibiting hypo-inflammation, characterized by lower peak TNF cytokine production during the subsequent LPS challenge, demonstrated a more rapid HR recovery during CPT. In contrast, the hyper-inflammation subject displayed a slower HR control response (FIG. 13 A). Further, there is a significant negative correlation between such slope and the inflammatory immune response, characterized by the peak TNF concentration (p= -0.81, p-0.005) (FIG. 13B).[000191] FIGS. 11A-11C illustrate an example ensemble learning method, in accordance with the present technology, based on three example machine learning models. These figures illustrate a multi-panel example ensemble learning method based on three example machine learning models, consistent with disclosed embodiments. An ensemble learning method may be based on one or more aspects and / or features of one or more neural signals and / or other physiological signals. An ensemble learning method may be employed to classify an inflammation risk for one or more subjects. An ensemble learning method may be employed to classify an inflammation biotype for one or more subjects. FIG. 11 A illustrates a plurality of machine learning models that may be employed in any combination by an ensemble learning method. While not limiting, the ensemble learning method has employed the machine learning models shown in the first panel,namely, a Support Vector Machine (SVM) model, an Extreme Gradient Boosting (XGB) model, and a Linear Discriminate Analysis (LDA) model. Each machine learning model may be optimized individually. A classification outcome may be based on a majority voting from results of more than one machine learning model. A machine learning model may, for example, be based on a five minute sliding time window interval applied to baseline neural signal data and / or other physiological signal data. A machine learning model may, for example, be based on a one minute step size applied to baseline neural signal data and / or other physiological signal data. FIG. 1 IB illustrates an example confusion matrix resulting from employment of an ensemble learning method. FIG. 11C illustrates example features ranked by importance. Feature importance may be estimated and / or ranked by one or more machine learning models. In this example, feature importance is estimated and ranked through employment of the XGB model.[000192] FIG. 12 illustrates an example deep learning model which may include a convolutional neural network (CNN) to identify higher-level autonomic features of neural and / or physiological signals, consistent with disclosed embodiments. A deep learning model may be based on one or more aspects and / or features of one or more neural signals and / or other physiological signals. A deep learning model may be employed to classify an inflammation risk for one or more subjects. A deep learning model may be employed to classify an inflammation biotype for one or more subjects. In this figure, multiple panels are shown to demonstrate a deep learning model and a confusion matrix. In particular, a first panel (Panel ‘a’) illustrates an example deep learning model. A deep learning model may be based on baseline neural signal data and / or other physiological signal data. A deep learning model may, for example, be based on a five minute sliding time window interval applied to baseline neural signal data and / or other physiological signal data. A deep learning model may, for example, be based on a five minute step size applied to baseline neural signal data and / or other physiological signal data. A deep learning model may, for example, be based on five time window intervals of baseline neural signal data and / or other physiological signal data as a two-dimensional (2D) matrix. A second panel in FIG. 12 (Panel ‘b ’) demonstrates prediction accuracy in a confusion matrix. Specifically, the deep learning model may predict high and low inflammation states based on resting pre-infection or inflammation with high accuracy and area under the curve as may be depicted in the confusion matrix as shown.[000193] FIG. 14 shows a data plot depicting a Pearson correlation between peak miRNA (hsa- miR-210-3p) and sympathetic activity index (SAI)Zparasympathetic activity index (PAI) ratiomeasured during baseline resting state. The example embodiments of the methods and apparatuses for estimating inflammation likelihood, as described herein, accurately reflect inflammation when compared to biomarkers such as miRNA expression, as shown by the graph of FIG. 14.[000194] For example, a sympathetic activity index (SAI) and a parasympathetic activity index (PAI) are two novel metrics that assess the time-varying autonomic nervous system functions separately. The SAI and PAI measures characterize and predict each heartbeat event, given a combination of past information expressed as cardiovascular variability. The SAI and PAI computation convolves heartbeat series through exponentially delayed Laguerre functions to identify time-varying Laguerre coefficients, which are embedded in an autoregressive model combining the input data. The ratio of the two metrics (SAI / PAI) demonstrates the autonomic balanced activity between sympathetic and parasympathetic. Here the ratio during the baseline resting state showed a significant positive correlation with peak hsa-miR-210-3p during LPS. Hsa- miR-210-3p can enhance inflammation in macrophages, which can lead to the expression of proinflammatory cytokines and the downregulation of anti-inflammatory cytokines.Examples[000195] In some embodiments in accordance with the present technology (example 1), an apparatus for determining a subject’s susceptibility to inflammation includes one or more sensors configured to sense an autonomic nerve signal and a cardiac signal; one or more processors in communication with the one or more sensors; and a memory coupled to the one or more processors, the memory storing computer-program instructions, that, when executed by the one or more processors, perform a computer-implemented method, which comprises: receiving, in one or more processors, a plurality of sensor signals from the one or more sensors, wherein the sensor signals are recorded from the subject while the subject is at rest; automatically classifying an inflammation risk and / or an inflammation biotype for the subject based on the plurality of sensor signals; and outputting a notification of the subject’s susceptibility to inflammation based on at least one of the inflammation risk and / or the inflammation biotype.[000196] Example 2 includes the apparatus of example 1 or any of examples 1-15, wherein automatically classifying the subject’s inflammation biotype comprises classifying on a scale of sub-groups including: a hyper-inflammation sub-group, a hypo-inflammation subgroup, and an immunoparalysis sub-group.[000197] Example 3 includes the apparatus of any of examples 1-2 or any of examples 1-15, wherein the one or more sensors comprises an array of electrodes configured to sense a cervical electroneurography (CEN) signal.[000198] Example 4 includes the apparatus of any of examples 1-3 or any of examples 1-15, wherein the one or more sensors comprises a first sensor configured to sense the autonomic nerve signal and a second sensor configured to sense the cardiac signal.[000199] Example 5 includes the apparatus of any of examples 1-4 or any of examples 1-15, wherein the cardiac signal is one of: an electrocardiogram (ECG) signal and / or a heart rate (HR).[000200] Example 6 includes the apparatus of any of examples 1-5 or any of examples 1-15, further comprising a housing coupled to the one or more sensors and enclosing a controller, wherein the housing is configured to be worn by the subject.[000201] Example 7 includes the apparatus of example 6 or any of examples 1-15, wherein the one or more processors are part the controller.[000202] Example 8 includes the apparatus of any of examples 1-7 or any of examples 1-15, wherein the one or more sensors are configured to detect the autonomic nerve signal from a vagus nerve of the subject.[000203] Example 9 includes the apparatus of any of examples 1-8 or any of examples 1-15, wherein the one or more sensors is configured to detect the autonomic nerve signal from a cervical nerve of the subject.[000204] Example 10 includes the apparatus of any of examples 1-9 or any of examples 1-15, wherein the one or more sensors are configured to detect the autonomic nerve signal and the cardiac signal transcutaneously.[000205] Example 11 includes the apparatus of any of examples 1-10 or any of examples 1-15, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by sorting spikes of neural activity identified in the autonomic nerve signal.[000206] Example 12 includes the apparatus of any of examples 1-11 or any of examples 1-15, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by identifying a spatial relationship of spikes in neural activity from the autonomic nerve signal.[000207] Example 13 includes the apparatus of any of examples 1-12 or any of examples 1-15, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by using a trained neural network that is trained on cardiac signal data and autonomic nerve signal data collected during an autonomic stress challenge.[000208] Example 14 includes the apparatus of any of examples 1-13 or any of examples 1-15, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by identifying a spatial relationship of spikes of neural activity from the autonomic nerve signal.[000209] Example 15 includes the apparatus of any of examples 1-14 or any of examples 1-14, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by correlating temporal signal characteristics of one or more of the sensor signals to temporal and / or spatial signal characteristics of previous sensor signals.[000210] In some embodiments in accordance with the present technology (example 16), an apparatus for determining a subject’s susceptibility to inflammation includes one or more sensors configured to sense an autonomic nerve signal and a cardiac signal; one or more processors in communication with the one or more sensors; and a memory coupled to the one or more processors, the memory storing computer-program instructions, that, when executed by the one or more processors, perform a computer-implemented method, which comprises: receiving, in one or more processors, a plurality of sensor signals from the one or more sensors, wherein the sensor signals are recorded from the subject while the subject is at rest; automatically classifying an inflammation risk and / or an inflammation biotype for the subject based on the plurality of sensor signals by comparing the plurality of sensor signals to cardiac signal data and autonomic nerve signal data collected during an autonomic stress challenge that is correlated with inflammation risk and / or inflammation biotype; and outputting a notification of the subject’s susceptibility to inflammation based on at least one of the inflammation risk and / or the inflammation biotype.[000211] In some embodiments in accordance with the present technology (example 17), a method of determining a subject’s susceptibility to inflammation includes receiving, in one or more processors, a plurality of sensor signals comprising a cardiac signal and an autonomic nerve signal, wherein the plurality of sensor signals are recorded from the subject while the subject is at rest;automatically classifying an inflammation risk and / or an inflammation biotype for the subject based on the plurality of sensor signals recorded while the subject is at rest; and outputting a notification of the subject’s susceptibility to inflammation based on at least one of the inflammation risk and / or the inflammation biotype.[000212] Example 18 includes the method of example 17 or any of examples 17-31, wherein automatically classifying the subject’s inflammation biotype comprises classifying on a scale of sub-groups including: a hyper-inflammation sub-group, a hypo-inflammation subgroup, and an immunoparalysis sub-group.[000213] Example 19 includes the method of example 17 or any of examples 17-31, wherein the cardiac signal comprises at least one of an electrocardiogram (ECG) signal.[000214] Example 20 includes the method of example 17 or any of examples 17-31, wherein the autonomic nerve signal comprises a cervical electroneurographic signal.[000215] Example 21 includes the method of example 17 or any of examples 17-31, wherein the plurality of sensor signals is received from one or more wearable sensors.[000216] Example 22 includes the method of example 17 or any of examples 17-31, wherein the plurality of sensor signals is measured noninvasively.[000217] Example 23 includes the method of example 17 or any of examples 17-31, wherein automatically classifying the inflammation risk and / or the inflammation biotype comprises sorting neural firing spikes.[000218] Example 24 includes the method of example 17 or any of examples 17-31, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises using a trained neural network that is trained on cardiac signal data and autonomic nerve signal data collected during an autonomic stress challenge.[000219] Example 25 includes the method of example 17 or any of examples 17-31, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises identifying a spatial relationship of spikes of neural activity from the autonomic nerve signal.[000220] Example 26 includes the method of example 17 or any of examples 17-31, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises correlating temporal signal characteristics of one or more of the sensor signals to temporal and / or spatial signal characteristics of previous sensor signals.[000221] Example 27 includes the method of example 17 or any of examples 17-31, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises classifying the inflammation biotype based on one or more molecular biomarkers.[000222] Example 28 includes the method of example 17 or any of examples 17-31, wherein the sensor signals are recorded from the subject before the subject experiences an event that trigger an immune response.[000223] Example 29 includes the method of example 17 or any of examples 17-31, wherein outputting comprises transmitting the notification to a remote device.[000224] Example 30 includes the method of example 17 or any of examples 17-31, wherein outputting comprises outputting the subject’s inflammation biotype.[000225] Example 31 includes the method of example 17 or any of examples 17-30, wherein receiving comprises receiving while the subject is at rest for five minutes or more.[000226] In some embodiments in accordance with the present technology (example 32), a method of determining a subject’s susceptibility to inflammation includes receiving, in one or more processors, a plurality of sensor signals, wherein the sensor signals are recorded from the subject while the subject is at rest or undergoing an autonomic stress challenge; automatically classifying an inflammation risk and / or an inflammation biotype for the subject based on the plurality of sensor signals; and outputting a notification of the subject’s susceptibility to inflammation based on at least one of the inflammation risk and / or the inflammation biotype.[000227] Example 33 includes the method of example 32 or any of examples 32-48, wherein the plurality of sensor signals comprises at least one of an electrocardiogram (ECG) signal, an electroencephalographic (EEG) signal, an electrogastrography (EGG) signal, a cervical electroneurography (CEN) signal, a cervical magnetoneurography (c-MNG) signal, and a respiration signal.[000228] Example 34 includes the method of example 32 or any of examples 32-48, wherein the autonomic stress challenge is selected from the group consisting of: a deep breathing exercise, exposure to cold water, traumatic event viewing, and traumatic event script reading.[000229] Example 35 includes the method of example 32 or any of examples 32-48, wherein the plurality of sensor signals comprises a cardiac signal and a cervical electroneurographic signal.[000230] Example 36 includes the method of example 32 or any of examples 32-48, wherein the plurality of sensor signals is received from a plurality of wearable sensors.[000231] Example 37 includes the method of example 32 or any of examples 32-48, wherein at least one of the sensor signals comprises a neural signal from the subject.[000232] Example 38 includes the method of example 32 or any of examples 32-48, wherein the plurality of sensor signals is measured noninvasively.[000233] Example 39 includes the method of example 32 or any of examples 32-48, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises sorting spikes in neural activity using a spike sorting algorithm.[000234] Example 40 includes the method of example 32 or any of examples 32-48, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises using a trained neural network.[000235] Example 41 includes the method of example 32 or any of examples 32-48, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises identifying a spatial relationship of spikes of neural activity between two or more of the sensor signals.[000236] Example 42 includes the method of example 32 or any of examples 32-48, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises correlating temporal signal characteristics of one or more of the sensor signals to temporal and / or spatial signal characteristics of previous sensor signals.[000237] Example 43 includes the method of example 32 or any of examples 32-48, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises classifying the inflammation biotype based on one or more molecular biomarkers.[000238] Example 44 includes the method of example 32 or any of examples 32-48, wherein the sensor signals are recorded from the subject before the subject experiences an event that trigger an immune response.[000239] Example 45 includes the method of example 32 or any of examples 32-48, wherein outputting further comprises outputting a graph of the sensor signals.[000240] Example 46 includes the method of example 32 or any of examples 32-48, wherein outputting comprises transmitting the notification to a remote device.[000241] Example 47 includes the method of example 32 or any of examples 32-48, wherein outputting comprises outputting the subject’s inflammation biotype.[000242] Example 48 includes the method of example 32 or any of examples 32-47, wherein automatically classifying the subject’s inflammation biotype comprises classifying on a scale of sub-groups including: a hyper-inflammation sub-group, a hypo-inflammation subgroup, and an immunoparalysis sub-group.[000243] In some embodiments in accordance with the present technology (example 49), a method of determining a subject’s susceptibility to inflammation includes receiving, in one or more processors, a first plurality of sensor signals, wherein the first plurality of sensor signals are recorded from the subject while the subject is undergoing a first autonomic stress challenge; receiving, in one or more processors, a second plurality of sensor signals, wherein the second plurality of sensor signals are recorded from the subject while the subject is undergoing a second autonomic stress challenge that is different from the fist autonomic stress challenge; automatically classifying an inflammation risk and / or an inflammation biotype for the subject based on the first plurality of sensor signals and the second plurality of sensor signals; and outputting a notification based on at least one of the inflammation risk and / or the inflammation biotype.[000244] In some embodiments in accordance with the present technology (example 50), an apparatus for determining a subject’s susceptibility to inflammation includes one or more sensors configured to sense a neural signal and / or a cardiac signal; one or more processors in communication with the one or more sensors; and a memory coupled to the one or more processors, the memory storing computer-program instructions, that, when executed by the one or more processors, perform a computer-implemented method, which includes: receiving, in one or more processors, a plurality of sensor signals, wherein the sensor signals are recorded from the subject while the subject is at rest or undergoing an autonomic stress challenge; automatically classifying an inflammation risk and / or an inflammation biotype for the subject based on the plurality of sensor signals; and outputting a notification of the subject’s susceptibility to inflammation based on at least one of the inflammation risk and / or the inflammation biotype.[000245] Example 51 includes the apparatus of example 50 or any of examples 50-68, wherein the one or more sensors comprises an array of electrodes configured to sense a cervical electroneurography (CEN) signal.[000246] Example 52 includes the apparatus of example 50 or any of examples 50-68, wherein the one or more sensors comprises a first sensor configured to sense a neural signal and a second sensor configured to sense a cardiac signal.[000247] Example 53 includes the apparatus of example 52 or any of examples 50-68, wherein the cardiac signal is one of: an electrocardiogram (ECG) signal and / or a heart rate (HR).[000248] Example 54 includes the apparatus of example 50 or any of examples 50-68, wherein the computer-program instructions are further configured to coordinate receiving the plurality of sensor signals with the performance of the autonomic stress challenge by the subject.[000249] Example 55 includes the apparatus of example 50 or any of examples 50-68, wherein the first autonomic stress challenge is selected from the group consisting of: a deep breathing exercise, exposure to cold water, traumatic event viewing, and traumatic event script reading.[000250] Example 56 includes the apparatus of example 50 or any of examples 50-68, further comprising a receiving unit to which the one or more sensors is coupled, wherein the receiving unit is a wearable receiving unit.[000251] Example 57 includes the apparatus of example 50 or any of examples 50-68, wherein the memory is part of a wearable device.[000252] Example 58 includes the apparatus of example 50 or any of examples 50-68, wherein the one or more processors is part of a wearable one or more processors.[000253] Example 59 includes the apparatus of example 50 or any of examples 50-68, wherein the one or more sensors is configured to detect the neural signal in a vagus nerve of the subject.[000254] Example 60 includes the apparatus of example 50 or any of examples 50-68, wherein the one or more sensors is configured to detect the neural signal in a cervical nerve of the subject. [000255] Example 61 includes the apparatus of example 50 or any of examples 50-68, wherein the plurality of sensor signals comprises one or more of: an electrocardiogram (ECG) signal, an electroencephalographic (EEG) signal, an electrogastrography (EGG) signal, a cervical electroneurography (CEN) signal, a cervical magnetoneurography (c-MNG) signal, and a respiration signal.[000256] Example 62 includes the apparatus of example 50 or any of examples 50-68, wherein the one or more sensors are configured to detect the neural and / or cardiac signal transcutaneously. [000257] Example 63 includes the apparatus of example 50 or any of examples 50-68, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype using a spike sorting algorithm that is configured to sort spikes in neural activity identified in the plurality of neural signals.[000258] Example 64 includes the apparatus of example 50 or any of examples 50-68, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by identifying a spatial relationship of spikes in neural activity between a first neural signal in the plurality of sensor signals and a second neural signal in the plurality of sensor signals.[000259] Example 65 includes the apparatus of example 50 or any of examples 50-68, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by using a trained neural network to identify autonomic features of the neural signals and the physiological signals.[000260] Example 66 includes the apparatus of example 50 or any of examples 50-68, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by correlating present temporal and / or spatial signal characteristics of at least one present sensor signal in the plurality of sensor signals to previous temporal and / or spatial signal characteristics of at least one previous sensor signal in the plurality of sensor signals.[000261] Example 67 includes the apparatus of example 50 or any of examples 50-68, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by correlating clusters of present spikes in neural activity in a plurality of present sensor signals in the plurality of sensor signals to spatial clusters of previous spikes in neural activity in a plurality of previous sensor signals in the plurality of sensor signals.[000262] Example 68 includes the apparatus of example 50 or any of examples 50-67, further comprising a wireless transmitter configured to transmit a remote notification to a remote device over a network, wherein the remote notification comprises at least one of an inflammation risk notification and an information biotype notification.[000263] In some embodiments in accordance with the present technology (example 69), a system includes a wearable sensor; a receiving unit configured to (i) receive a sensor signal communicated from the wearable sensor and (ii) detect a signal type of the received sensor signal, wherein the signal type comprises a neural signal when the receiving unit detects at least a portion of a neural signal of a subject; a memory storing a set of instructions for predicting immuneresponses; and a processor that is configured to execute the set of instructions for predicting immune responses based on the sensor signal.[0002641 Example 70 includes the system of example 69 or any of examples 69-94, wherein the signal type comprises a neural signal when the receiving unit detects a neural signal for the signal type.[000265] Example 71 includes the system of example 70 or any of examples 69-94, wherein the signal type comprises a physiological signal of the subject when the receiving unit detects a physiological signal for the signal type.[000266] Example 72 includes the system of example 69 or any of examples 69-94, wherein the set of instructions for predicting immune responses based on the sensor signal comprises a set of instructions for automatically classifying an inflammation risk for the subject.[000267] Example 73 includes the system of example 72 or any of examples 69-94, wherein the set of instructions for predicting immune responses based on the sensor signal further comprises a set of instructions for automatically creating a notification based on the inflammation risk.[000268] Example 74 includes the system of example 69 or any of examples 69-94, wherein the receiving unit is a wearable receiving unit.[000269] Example 75 includes the system of example 69 or any of examples 69-94, wherein the memory is a wearable memory.[000270] Example 76 includes the system of example 69 or any of examples 69-94, wherein the processor is a wearable processor.[000271] Example 77 includes the system of example 69 or any of examples 69-94, wherein the receiving unit is configured to detect the neural signal in a vagus nerve of the subject.[000272] Example 78 includes the system of example 69 or any of examples 69-94, wherein the receiving unit is configured to detect the neural signal in a cervical nerve of the subject.[000273] Example 79 includes the system of example 69 or any of examples 69-94, wherein the sensor signal comprises one of an electrocardiogram (ECG) signal, an electroencephalographic (EEG) signal, an electrogastrography (EGG) signal, a cervical electroneurography (CEN) signal, a cervical magnetoneurography (c-MNG) signal, and a respiration signal.[000274] Example 80 includes the system of example 69 or any of examples 69-94, wherein the wearable sensor is configured to detect the neural signal transcutaneously.[000275] Example 81 includes the system of example 69 or any of examples 69-94, wherein the sensor signal is a first sensor signal, wherein the receiving unit is further configured to receive a plurality of sensor signals comprising the first sensor signal.[000276] Example 82 includes the system of example 69 or any of examples 69-94, wherein the receiving unit is further configured to differentiate between a plurality of neural signals identified from one or more sensor signals in the plurality of sensor signals.[000277] Example 83 includes the system of example 69 or any of examples 69-94, wherein the set of instructions for predicting immune responses based on the sensor signal comprises a set of instructions for automatically classifying an inflammation biotype for the subject.[000278] Example 84 includes the system of example 83 or any of examples 69-94, wherein the set of instructions for predicting immune responses based on the sensor signal further comprises a set of instructions for automatically creating a notification based on the inflammation biotype.[000279] Example 85 includes the system of example 84 or any of examples 69-94, wherein the set of instructions for automatically classifying the inflammation biotype for the subject further comprises a set of instructions for performing a spike sorting algorithm that is configured to sort spikes in neural activity identified in the plurality of neural signals.[000280] Example 86 includes the system of example 85 or any of examples 69-94, wherein the set of instructions for automatically classifying the inflammation biotype for the subject further comprises a set of instructions for identifying a spatial relationship of spikes in neural activity between a first neural signal in the plurality of neural signals and a second neural signal in the plurality of neural signals.[000281] Example 87 includes the system of example 85 or any of examples 69-94, wherein the plurality of sensor signals comprise neural signals and physiological signals, wherein the set of instructions for automatically classifying the inflammation biotype for the subject further comprises a set of instructions for utilizing a Convolutional Neural Network (CNN) to identify autonomic features of the neural signals and the physiological signals.[000282] Example 88 includes the system of example 69 or any of examples 69-94, wherein the set of instructions for automatically classifying the inflammation biotype for the subject further comprises a set of instructions for correlating present temporal signal characteristics of at least one present sensor signal in the plurality of sensor signals to previous temporal signal characteristics of at least one previous sensor signal in the plurality of sensor signals.[000283] Example 89 includes the system of example 69 or any of examples 69-94, wherein the set of instructions for automatically classifying the inflammation biotype for the subject further comprises a set of instructions for correlating present spatial signal characteristics of at least one present sensor signal in the plurality of sensor signals to previous spatial signal characteristics of at least one previous sensor signal in the plurality of sensor signals.[000284] Example 90 includes the system of example 69 or any of examples 69-94, wherein the set of instructions for automatically classifying the inflammation biotype for the subject further comprises a set of instructions for correlating clusters of present spikes in neural activity in a plurality of present sensor signals in the plurality of sensor signals to spatial clusters of previous spikes in neural activity in a plurality of previous sensor signals in the plurality of sensor signals.[000285] Example 91 includes the system of example 69 or any of examples 69-94, further comprising a plurality of wearable sensors, wherein the wearable sensor is a first wearable sensor in the plurality of wearable sensors.[000286] Example 92 includes the system of example 91 or any of examples 69-94, further comprising a flexible surface electrode array comprising the plurality of wearable sensors.[000287] Example 93 includes the system of example 91 or any of examples 69-94, further comprising a flexible surface magnetometer array comprising the plurality of wearable sensors.[000288] Example 94 includes the system of example 69 or any of examples 69-93, further comprising a wireless transmitter configured to transmit a remote notification to a remote device over a network, wherein the remote notification comprises at least one of an inflammation risk notification and an information biotype notification.[000289] In some embodiments in accordance with the present technology (example 95), a method for predicting immune responses includes automatically receiving, by a receiving unit communicably connected to a processor, a plurality of sensor signals associated with a subject; analyzing the sensor signals to determine an immune response data associated with the subject; and automatically creating a display output based on the immune response data.[000290] Example 96 includes the method of example 95 or any of examples 95-117, wherein the analyzing the sensor signals includes automatically classifying an inflammation risk for the subject based on the sensor signals.[000291] Example 97 includes the method of example 95 or any of examples 95-117, wherein the analyzing the sensor signals includes automatically classifying an inflammation biotype for the subject based on the sensor signals.[000292] Example 98 includes the method of example 95 or any of examples 95-117, wherein the immune response data includes an immune response parameter or immune response data set that is predictive of the subject’s immune response to a particular pathogen and / or at a particular anatomic structure of the subject’s body.[000293] Example 99 includes the method of example 98 or any of examples 95-117, wherein the immune response data is predictive of the subject’s immune response based on determining signal characteristics within the sensor data that are indicative of concentration changes over a time period of one or more cytokine concentrations due to the particular pathogen within the anatomic structure of the subject.[000294] Example 100 includes the method of example 99 or any of examples 95-117, wherein determination of the immune response data includes processing signal spike characteristics of the sensor signals with respect to an immune response data model.[000295] Example 101 includes the method of example 100 or any of examples 95-117, wherein the immune response data model includes at least one of a machine learning model or a deep learning model trained on sensor data acquired over a plurality of subjects within known pathogens in known anatomical structures.[000296] Example 102 includes the method of example 100 or any of examples 95-117, wherein the signal spike characteristics include a frequency of signal spikes over a time interval, for multiple time intervals, where, for each interval, the signal spikes represent an ensemble of neurons emitting action potentials in response to a cytokine concentration.[000297] Example 103 includes the method of example 95 or any of examples 95-117, wherein the plurality of sensor signals comprises at least one of an electrocardiogram (ECG) signal, an electroencephalographic (EEG) signal, an electrogastrography (EGG) signal, a cervical electroneurography (CEN) signal, a cervical magnetoneurography (c-MNG) signal, and a respiration signal.[000298] Example 104 includes the method of example 95 or any of examples 95-117, wherein the plurality of sensor signals is received from a plurality of wearable sensors.[000299] Example 105 includes the method of example 104 or any of examples 95-117, wherein at least one of the sensor signals comprises a neural signal of the subject.[000300] Example 106 includes the method of example 105 or any of examples 95-117, wherein at least one of the wearable sensors is configured to detect the neural signal transcutaneously.[000301] Example 107 includes the method of example 95 or any of examples 95-117, wherein automatically classifying an inflammation biotype comprises sorting spikes in neural activity by way of a spike sorting algorithm.[000302] Example 108 includes the method of example 95 or any of examples 95-117, wherein automatically classifying an inflammation biotype comprises utilizing a Convolutional Neural Network (CNN) to identify autonomic features.[000303] Example 109 includes the method of example 95 or any of examples 95-117, wherein automatically classifying an inflammation biotype comprises identifying a spatial relationship of spikes in neural activity between two or more of the sensor signals.[000304] Example 110 includes the method of example 95 or any of examples 95-117, wherein automatically classifying an inflammation biotype comprises correlating temporal signal characteristics of one or more of the sensor signals to temporal signal characteristics of previous sensor signals.[000305] Example 111 includes the method of example 95 or any of examples 95-117, wherein automatically classifying an inflammation biotype comprises correlating spatial signal characteristics of one or more of the sensor signals to spatial signal characteristics of previous sensor signals.[000306] Example 112 includes the method of example 95 or any of examples 95-117, wherein automatically classifying an inflammation biotype comprises classifying the inflammation biotype based on one or more molecular biomarkers.[000307] Example 113 includes the method of example 95 or any of examples 95-117, wherein the inflammation risk and the inflammation biotype are automatically classified for the subject before the subject experiences an event that trigger an immune response.[000308] Example 114 includes the method of example 95 or any of examples 95-117, further comprising automatically plotting sensor signals as data points in a plot and visually outputting the plot of the sensor signals on a display.[000309] Example 115 includes the method of example 95 or any of examples 95-117, further comprising automatically transmitting the display output to a remote device.[000310] Example 116 includes the method of example 115 or any of examples 95-117, wherein the display output includes a notification.[000311] Example 117 includes the method of example 116 or any of examples 95-116, wherein the notification comprises at least one of an inflammation risk classified for the subject and an inflammation biotype classified for the subject.[000312] In some embodiments in accordance with the present technology (example 118), a surface electrode array configured to detect multi-channel cervical neuronal activity includes a first polyimide layer; a second polyimide layer; a plurality of wearable sensors placed between the first polyimide layer and the second polyimide layer; electrical wiring to a power source; and data communication wiring to a processor that is configured to detect channel-specific neural signals of a subject.[000313] Example 119 includes the surface electrode array of example 118 or any of examples 118-120, wherein each wearable sensor in the plurality of wearable sensors comprises an electrode. [000314] Example 120 includes the surface electrode array of example 118 or any of examples 118-119, further comprising an adhesive that is configured to apply the plurality of wearable sensors transcutaneously to a vagus nerve area of the subject.Conclusion[000315] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as examples of forms of implementing the claimed invention.[000316] In this specification, “a” and “an” and similar phrases are to be interpreted as “at least one” and “one or more.” References to “a”, “an”, and “one” are not to be interpreted as “only one”. In this specification, the term “may” is to be interpreted as “may, for example.” In other words, the term “may” is indicative that the phrase following the term “may” is an example of one of a multitude of suitable possibilities that may, or may not, be employed to one or more of the various embodiments. In this specification, the phrase “based on” is indicative that the phrase following the term “based on” is an example of one of a multitude of suitable possibilities that may, or maynot, be employed to one or more of the various embodiments. References to “an” embodiment in this disclosure are not necessarily to the same embodiment.[0003171 Many of the elements described in the disclosed embodiments may be implemented as operations. An operation is defined here as an element which, in isolation, performs a defined function and has a defined interface to other elements. The operations described in this disclosure may be implemented in hardware, a combination of hardware and software, firmware, wetware (in other words, hardware with a biological element), or a combination thereof, all of which are behaviorally equivalent. For example, operations may be implemented using computer hardware in combination with software routine(s) written in a computer language (for example, Java, HTML, XML, PHP, Python, ActionScript, JavaScript, Ruby, Prolog, SQL, VBScript, Visual Basic, Perl, C, C++, Objective-C, Rust, or the like). Additionally, it may be possible to implement operations using physical hardware that incorporates discrete or programmable analog, digital, and / or quantum hardware. Examples of programmable hardware include: computers, microcontrollers, microprocessors, application-specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), and complex programmable logic devices (CPLDs). Computers, microcontrollers, and microprocessors are programmed using languages such as assembly, C, C++, or the like. FPGAs, ASICs, and CPLDs are often programmed using hardware description languages (HDL), such as very high speed integrated circuit (VHSIC) hardware description language (VHDL) or Verilog, which configure connections between internal hardware operations with lesser functionality on a programmable device. Finally, it needs to be emphasized that the above-mentioned technologies may be used in combination to achieve the result of a functional operation. Automatic operations are performed automatically and do not require human intervention to complete once executed. Automatic as defined herein does not include any time limitations unless otherwise noted.[000318] Some embodiments may employ processing hardware. Processing hardware may include one or more processors, computer equipment, embedded systems, machines, and / or the like. The processing hardware may be configured to execute instructions. The instructions may be stored on a machine-readable medium. According to some embodiments, the machine-readable medium may be a medium configured to store data in a machine-readable format that may be accessed by an automated sensing device. Examples of machine-readable media include: flashmemory, memory cards, electrically erasable programmable read-only memory (EEPROM), solid state drives, optical disks, barcodes, magnetic ink characters, and / or the like.[0003191 While various embodiments have been described above, it should be understood that they have been presented by way of example, and not limitation. It will be apparent to persons skilled in the relevant art(s) that various changes in form and detail can be made therein without departing from the spirit and scope. In fact, after reading the above description, it will be apparent to one skilled in the relevant art(s) how to implement alternative embodiments. Thus, the present embodiments should not be limited by any of the above-described exemplary embodiments. In particular, it should be noted that, for example purposes, various embodiments have been described as communicating with at least one remote device. Persons skilled in the art will recognize that systems communicating with remote devices may vary from a traditional system / device relationship over a network such as the Internet. For example, a system may be collective based: portable equipment, broadcast equipment, virtual, application(s) distributed over a broad combination of computing sources, part of a cloud, combinations thereof, and / or the like. Similarly, for example, a remote device may be a user-based client, portable equipment, broadcast equipment, virtual, application(s) distributed over abroad combination of computing sources, part of a cloud, combinations thereof, and / or the like. Additionally, it should be noted that, for example purposes, several of the various embodiments were described as comprising operations. However, one skilled in the art will recognize that many various languages and frameworks may be employed to build and use embodiments of the present invention.[000320] In this specification, various embodiments are disclosed. Limitations, features, and / or elements from the disclosed example embodiments may be combined to create further embodiments within the scope of the disclosure. Moreover, the scope includes any and all embodiments having equivalent elements, modifications, omissions, adaptations, or alterations based on the present disclosure. Further, aspects of the disclosed methods can be modified in any manner, including by reordering aspects, or inserting or deleting aspects.[000321] In addition, it should be understood that any figures that highlight any functionality and / or advantages, are presented for example purposes only. The disclosed architecture is sufficiently flexible and configurable, such that it may be utilized in ways other than that described and / or shown. For example, the steps listed in any flowchart for any process or method may be reordered or only optionally used in some embodiments.[000322] Furthermore, many features presented above are described as being optional through the use of “may” or the use of parentheses. For the sake of brevity and legibility, the present disclosure does not explicitly recite each and every permutation that may be obtained by choosing from the set of optional features. However, the present disclosure is to be interpreted as explicitly disclosing all such permutations. For example, a system described as having three optional features may be embodied in eight different ways, namely, with none of the three possible features, with just one of the three possible features, with any two of the three possible features, or with all three of the three possible features.[000323] All publications and patent applications mentioned in this specification are herein incorporated by reference in their entirety to the same extent as if each individual publication or patent application was specifically and individually indicated to be incorporated by reference. Furthermore, it should be appreciated that all combinations of the foregoing concepts and additional concepts discussed in greater detail below (provided such concepts are not mutually inconsistent) are contemplated as being part of the inventive subject matter disclosed herein and may be used to achieve the benefits described herein.[000324] Any of the methods (including user interfaces) described herein may be implemented as software, hardware or firmware, and may be described as a non-transitory computer-readable storage medium storing a set of instructions capable of being executed by a processor (e.g., computer, tablet, smartphone, etc.), that when executed by the processor causes the processor to control perform any of the steps, including but not limited to: displaying, communicating with the user, analyzing, modifying parameters (including timing, frequency, intensity, etc.), determining, alerting, or the like. For example, any of the methods described herein may be performed, at least in part, by an apparatus including one or more processors having a memory storing a non-transitory computer-readable storage medium storing a set of instructions for the processes(s) of the method. [000325] While various embodiments have been described and / or illustrated herein in the context of fully functional computing systems, one or more of these example embodiments may be distributed as a program product in a variety of forms, regardless of the particular type of computer-readable media used to actually carry out the distribution. The embodiments disclosed herein may also be implemented using software modules that perform certain tasks. These software modules may include script, batch, or other executable files that may be stored on a computer- readable storage medium or in a computing system. In some embodiments, these software modulesmay configure a computing system to perform one or more of the example embodiments disclosed herein.[0003261 As described herein, the computing devices and systems described and / or illustrated herein broadly represent any type or form of computing device or system capable of executing computer-readable instructions, such as those contained within the modules described herein. In their most basic configuration, these computing device(s) may each comprise at least one memory device and at least one physical processor.[000327] The term “memory” or “memory device,” as used herein, generally represents any type or form of volatile or non-volatile storage device or medium capable of storing data and / or computer-readable instructions. In one example, a memory device may store, load, and / or maintain one or more of the modules described herein. Examples of memory devices comprise, without limitation, Random Access Memory (RAM), Read Only Memory (ROM), flash memory, Hard Disk Drives (HDDs), Solid-State Drives (SSDs), optical disk drives, caches, variations or combinations of one or more of the same, or any other suitable storage memory.[000328] In addition, the term “processor” or “physical processor,” as used herein, generally refers to any type or form of hardware-implemented processing unit capable of interpreting and / or executing computer-readable instructions. In one example, a physical processor may access and / or modify one or more modules stored in the above-described memory device. Examples of physical processors comprise, without limitation, microprocessors, microcontrollers, Central Processing Units (CPUs), Field-Programmable Gate Arrays (FPGAs) that implement softcore processors, Application-Specific Integrated Circuits (ASICs), portions of one or more of the same, variations or combinations of one or more of the same, or any other suitable physical processor.[000329] Although illustrated as separate elements, the method steps described and / or illustrated herein may represent portions of a single application. In addition, in some embodiments one or more of these steps may represent or correspond to one or more software applications or programs that, when executed by a computing device, may cause the computing device to perform one or more tasks, such as the method step.[000330] In addition, one or more of the devices described herein may transform data, physical devices, and / or representations of physical devices from one form to another. Additionally or alternatively, one or more of the modules recited herein may transform a processor, volatile memory, non-volatile memory, and / or any other portion of a physical computing device from oneform of computing device to another form of computing device by executing on the computing device, storing data on the computing device, and / or otherwise interacting with the computing device.[000331] The term “computer-readable medium,” as used herein, generally refers to any form of device, carrier, or medium capable of storing or carrying computer-readable instructions. Examples of computer-readable media comprise, without limitation, transmission-type media, such as carrier waves, and non-transitory-type media, such as magnetic-storage media (e.g., hard disk drives, tape drives, and floppy disks), optical-storage media (e.g., Compact Disks (CDs), Digital Video Disks (DVDs), and BLU-RAY disks), electronic-storage media (e.g., solid-state drives and flash media), and other distribution systems.[000332] A person of ordinary skill in the art will recognize that any process or method disclosed herein can be modified in many ways. The process parameters and sequence of the steps described and / or illustrated herein are given by way of example only and can be varied as desired. For example, while the steps illustrated and / or described herein may be shown or discussed in a particular order, these steps do not necessarily need to be performed in the order illustrated or discussed.[000333] The various exemplary methods described and / or illustrated herein may also omit one or more of the steps described or illustrated herein or comprise additional steps in addition to those disclosed. Further, a step of any method as disclosed herein can be combined with any one or more steps of any other method as disclosed herein.[000334] The processor as described herein can be configured to perform one or more steps of any method disclosed herein. Alternatively or in combination, the processor can be configured to combine one or more steps of one or more methods as disclosed herein.[000335] In general, any of the apparatuses and methods described herein should be understood to be inclusive, but all or a sub-set of the components and / or steps may alternatively be exclusive and may be expressed as “consisting of’ or alternatively “consisting essentially of’ the various components, steps, sub-components or sub-steps.[000336] As used herein in the specification and claims, including as used in the examples and unless otherwise expressly specified, all numbers may be read as if prefaced by the word "about" or “approximately,” even if the term does not expressly appear. The phrase “about” or “approximately” may be used when describing magnitude and / or position to indicate that the valueand / or position described is within a reasonable expected range of values and / or positions. For example, a numeric value may have a value that is + / - 0.1% of the stated value (or range of values), + / - 1% of the stated value (or range of values), + / - 2% of the stated value (or range of values), + / - 5% of the stated value (or range of values), + / - 10% of the stated value (or range of values), etc. Any numerical values given herein should also be understood to include about or approximately that value, unless the context indicates otherwise. For example, if the value "10" is disclosed, then "about 10" is also disclosed. Any numerical range recited herein is intended to include all subranges subsumed therein. It is also understood that when a value is disclosed that "less than or equal to" the value, "greater than or equal to the value" and possible ranges between values are also disclosed, as appropriately understood by the skilled artisan. For example, if the value "X" is disclosed the "less than or equal to X" as well as "greater than or equal to X" (e.g., where X is a numerical value) is also disclosed. It is also understood that the throughout the application, data is provided in a number of different formats, and that this data, represents endpoints and starting points, and ranges for any combination of the data points. For example, if a particular data point “10” and a particular data point “15” are disclosed, it is understood that greater than, greater than or equal to, less than, less than or equal to, and equal to 10 and 15 are considered disclosed as well as between 10 and 15. It is also understood that each unit between two particular units are also disclosed. For example, if 10 and 15 are disclosed, then 11, 12, 13, and 14 are also disclosed.[000337] Although various illustrative embodiments are described above, any of a number of changes may be made to various embodiments without departing from the scope of the invention as described by the claims. Optional features of various device and system embodiments may be included in some embodiments and not in others. Therefore, the foregoing description is provided primarily for exemplary purposes and should not be interpreted to limit the scope of the invention as it is set forth in the claims.[000338] The examples and illustrations included herein show, by way of illustration and not of limitation, specific embodiments in which the subject matter may be practiced. As mentioned, other embodiments may be utilized and derived there from, such that structural and logical substitutions and changes may be made without departing from the scope of this disclosure. Such embodiments of the inventive subject matter may be referred to herein individually or collectively by the term “invention” merely for convenience and without intending to voluntarily limit the scope of this application to any single invention or inventive concept, if more than one is, in fact,disclosed. Thus, although specific embodiments have been illustrated and described herein, any arrangement calculated to achieve the same purpose may be substituted for the specific embodiments shown. This disclosure is intended to cover any and all adaptations or variations of various embodiments. Combinations of the above embodiments, and other embodiments not specifically described herein, will be apparent to those of skill in the art upon reviewing the above description.

Claims

CLAIMSWhat is claimed is:

1. An apparatus for determining a subject’s susceptibility to inflammation, the apparatus comprising: one or more sensors configured to sense an autonomic nerve signal and a cardiac signal; one or more processors in communication with the one or more sensors; and a memory coupled to the one or more processors, the memory storing computer-program instructions, that, when executed by the one or more processors, perform a computer- implemented method comprising: receiving, in one or more processors, a plurality of sensor signals from the one or more sensors, wherein the sensor signals are recorded from the subject while the subject is at rest; automatically classifying an inflammation risk and / or an inflammation biotype for the subject based on the plurality of sensor signals; and outputting a notification of the subject’s susceptibility to inflammation based on at least one of the inflammation risk and / or the inflammation biotype.

2. The apparatus of claim 1, wherein automatically classifying the subject’s inflammation biotype comprises classifying on a scale of sub-groups including: a hyper-inflammation subgroup, a hypo-inflammation subgroup, and an immunoparalysis sub-group.

3. The apparatus of any of claims 1-2, wherein the one or more sensors comprises an array of electrodes configured to sense a cervical electroneurography (CEN) signal.

4. The apparatus of any of claims 1-3, wherein the one or more sensors comprises a first sensor configured to sense the autonomic nerve signal and a second sensor configured to sense the cardiac signal.

5. The apparatus of any of claims 1-4, wherein the cardiac signal is one of: an electrocardiogram (ECG) signal and / or a heart rate (HR).

6. The apparatus of any of claims 1 -5, further comprising a housing coupled to the one or more sensors and enclosing a controller, wherein the housing is configured to be worn by the subject.

7. The apparatus of claim 6, wherein the one or more processors are part the controller.

8. The apparatus of any of claims 1-7, wherein the one or more sensors are configured to detect the autonomic nerve signal from a vagus nerve of the subject.

9. The apparatus of any of claims 1-8, wherein the one or more sensors is configured to detect the autonomic nerve signal from a cervical nerve of the subject.

10. The apparatus of any of claims 1-9, wherein the one or more sensors are configured to detect the autonomic nerve signal and the cardiac signal transcutaneously.

11. The apparatus of any of claims 1-10, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by sorting spikes of neural activity identified in the autonomic nerve signal.

12. The apparatus of any of claims 1-11, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by identifying a spatial relationship of spikes in neural activity from the autonomic nerve signal.

13. The apparatus of any of claims 1-12, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by using a trained neural network that is trained on cardiac signal data and autonomic nerve signal data collected during an autonomic stress challenge.

14. The apparatus of any of claims 1-13, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by identifying a spatial relationship of spikes of neural activity from the autonomic nerve signal.

15. The apparatus of any of claims 1 -14, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by correlating temporal signal characteristics of one or more of the sensor signals to temporal and / or spatial signal characteristics of previous sensor signals.

16. An apparatus for determining a subject’s susceptibility to inflammation, the apparatus comprising: one or more sensors configured to sense an autonomic nerve signal and a cardiac signal; one or more processors in communication with the one or more sensors; and a memory coupled to the one or more processors, the memory storing computer-program instructions, that, when executed by the one or more processors, perform a computer- implemented method comprising: receiving, in one or more processors, a plurality of sensor signals from the one or more sensors, wherein the sensor signals are recorded from the subject while the subject is at rest; automatically classifying an inflammation risk and / or an inflammation biotype for the subject based on the plurality of sensor signals by comparing the plurality of sensor signals to cardiac signal data and autonomic nerve signal data collected during an autonomic stress challenge that is correlated with inflammation risk and / or inflammation biotype; and outputting a notification of the subject’s susceptibility to inflammation based on at least one of the inflammation risk and / or the inflammation biotype.

17. A method of determining a subject’s susceptibility to inflammation, the method comprising: receiving, in one or more processors, a plurality of sensor signals comprising a cardiac signal and an autonomic nerve signal, wherein the plurality of sensor signals are recorded from the subject while the subject is at rest; automatically classifying an inflammation risk and / or an inflammation biotype for the subject based on the plurality of sensor signals recorded while the subject is at rest; andoutputting a notification of the subject’s susceptibility to inflammation based on at least one of the inflammation risk and / or the inflammation biotype.

18. The method of claim 17, wherein automatically classifying the subject’s inflammation biotype comprises classifying on a scale of sub-groups including: a hyper-inflammation subgroup, a hypo-inflammation subgroup, and an immunoparalysis sub-group.

19. The method of claim 17, wherein the cardiac signal comprises at least one of an electrocardiogram (ECG) signal.

20. The method of claim 17, wherein the autonomic nerve signal comprises a cervical electroneurographic signal.

21. The method of claim 17, wherein the plurality of sensor signals is received from one or more wearable sensors.

22. The method of claim 17, wherein the plurality of sensor signals is measured noninvasively.

23. The method of claim 17, wherein automatically classifying the inflammation risk and / or the inflammation biotype comprises sorting neural firing spikes.

24. The method of claim 17, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises using a trained neural network that is trained on cardiac signal data and autonomic nerve signal data collected during an autonomic stress challenge.

25. The method of claim 17, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises identifying a spatial relationship of spikes of neural activity from the autonomic nerve signal.

26. The method of claim 17, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises correlating temporal signal characteristics of one or more of the sensor signals to temporal and / or spatial signal characteristics of previous sensor signals.

27. The method of claim 17, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises classifying the inflammation biotype based on one or more molecular biomarkers.

28. The method of claim 17, wherein the sensor signals are recorded from the subject before the subject experiences an event that trigger an immune response.

29. The method of claim 17, wherein outputting comprises transmitting the notification to a remote device.

30. The method of claim 17, wherein outputting comprises outputting the subject’s inflammation biotype.

31. The method of claim 17, wherein receiving comprises receiving while the subject is at rest for five minutes or more.

32. A method of determining a subject’s susceptibility to inflammation, the method comprising: receiving, in one or more processors, a plurality of sensor signals, wherein the sensor signals are recorded from the subject while the subject is at rest or undergoing an autonomic stress challenge; automatically classifying an inflammation risk and / or an inflammation biotype for the subject based on the plurality of sensor signals; and outputting a notification of the subject’s susceptibility to inflammation based on at least one of the inflammation risk and / or the inflammation biotype.

33. The method of claim 32, wherein the plurality of sensor signals comprises at least one of an electrocardiogram (ECG) signal, an electroencephalographic (EEG) signal, an electrogastrography (EGG) signal, a cervical electroneurography (CEN) signal, a cervical magnetoneurography (c-MNG) signal, and a respiration signal.

34. The method of claim 32, wherein the autonomic stress challenge is selected from the group consisting of: a deep breathing exercise, exposure to cold water, traumatic event viewing, and traumatic event script reading.

35. The method of claim 32, wherein the plurality of sensor signals comprises a cardiac signal and a cervical electroneurographic signal.

36. The method of claim 32, wherein the plurality of sensor signals is received from a plurality of wearable sensors.

37. The method of claim 32, wherein at least one of the sensor signals comprises a neural signal from the subject.

38. The method of claim 32, wherein the plurality of sensor signals is measured noninvasively.

39. The method of claim 32, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises sorting spikes in neural activity using a spike sorting algorithm.

40. The method of claim 32, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises using a trained neural network.

41. The method of claim 32, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises identifying a spatial relationship of spikes of neural activity between two or more of the sensor signals.

42. The method of claim 32, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises correlating temporal signal characteristics of one or more of the sensor signals to temporal and / or spatial signal characteristics of previous sensor signals.

43. The method of claim 32, wherein automatically classifying the inflammation risk and / or an inflammation biotype comprises classifying the inflammation biotype based on one or more molecular biomarkers.

44. The method of claim 32, wherein the sensor signals are recorded from the subject before the subject experiences an event that trigger an immune response.

45. The method of claim 32, wherein outputting further comprises outputting a graph of the sensor signals.

46. The method of claim 32, wherein outputting comprises transmitting the notification to a remote device.

47. The method of claim 32, wherein outputting comprises outputting the subject’s inflammation biotype.

48. The method of claim 32, wherein automatically classifying the subject’s inflammation biotype comprises classifying on a scale of sub-groups including: a hyper-inflammation subgroup, a hypo-inflammation subgroup, and an immunoparalysis sub-group.

49. A method of determining a subject’s susceptibility to inflammation, the method comprising: receiving, in one or more processors, a first plurality of sensor signals, wherein the first plurality of sensor signals are recorded from the subject while the subject is undergoing a first autonomic stress challenge; receiving, in one or more processors, a second plurality of sensor signals, wherein the second plurality of sensor signals are recorded from the subject while the subject is undergoing a second autonomic stress challenge that is different from the fist autonomic stress challenge; automatically classifying an inflammation risk and / or an inflammation biotype for the subject based on the first plurality of sensor signals and the second plurality of sensor signals; and outputting a notification based on at least one of the inflammation risk and / or the inflammation biotype.

50. An apparatus for determining a subject’s susceptibility to inflammation, the apparatus comprising: one or more sensors configured to sense a neural signal and / or a cardiac signal; one or more processors in communication with the one or more sensors; anda memory coupled to the one or more processors, the memory storing computer-program instructions, that, when executed by the one or more processors, perform a computer- implemented method comprising: receiving, in one or more processors, a plurality of sensor signals, wherein the sensor signals are recorded from the subject while the subject is at rest or undergoing an autonomic stress challenge; automatically classifying an inflammation risk and / or an inflammation biotype for the subject based on the plurality of sensor signals; and outputting a notification of the subject’s susceptibility to inflammation based on at least one of the inflammation risk and / or the inflammation biotype.

51. The apparatus of claim 50, wherein the one or more sensors comprises an array of electrodes configured to sense a cervical electroneurography (CEN) signal.

52. The apparatus of claim 50, wherein the one or more sensors comprises a first sensor configured to sense a neural signal and a second sensor configured to sense a cardiac signal.

53. The apparatus of claim 52, wherein the cardiac signal is one of: an electrocardiogram (ECG) signal and / or a heart rate (HR).

54. The apparatus of claim 50, wherein the computer-program instructions are further configured to coordinate receiving the plurality of sensor signals with the performance of the autonomic stress challenge by the subject.

55. The apparatus of claim 50, wherein the first autonomic stress challenge is selected from the group consisting of: a deep breathing exercise, exposure to cold water, traumatic event viewing, and traumatic event script reading.

56. The apparatus of claim 50, further comprising a receiving unit to which the one or more sensors is coupled, wherein the receiving unit is a wearable receiving unit.

57. The apparatus of claim 50, wherein the memory is part of a wearable device.

58. The apparatus of claim 50, wherein the one or more processors is part of a wearable one or more processors.

59. The apparatus of claim 50, wherein the one or more sensors is configured to detect the neural signal in a vagus nerve of the subject.

60. The apparatus of claim 50, wherein the one or more sensors is configured to detect the neural signal in a cervical nerve of the subject.

61. The apparatus of claim 50, wherein the plurality of sensor signals comprises one or more of: an electrocardiogram (ECG) signal, an electroencephalographic (EEG) signal, an electrogastrography (EGG) signal, a cervical electroneurography (CEN) signal, a cervical magnetoneurography (c-MNG) signal, and a respiration signal.

62. The apparatus of claim 50, wherein the one or more sensors are configured to detect the neural and / or cardiac signal transcutaneously.

63. The apparatus of claim 50, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype using a spike sorting algorithm that is configured to sort spikes in neural activity identified in the plurality of neural signals.

64. The apparatus of claim 50, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by identifying a spatial relationship of spikes in neural activity between a first neural signal in the plurality of sensor signals and a second neural signal in the plurality of sensor signals.

65. The apparatus of claim 50, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by using a trained neural network to identify autonomic features of the neural signals and the physiological signals.

66. The apparatus of claim 50, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by correlating present temporal and / or spatial signal characteristics of at least one present sensor signal in the plurality of sensor signals to previous temporal and / or spatial signal characteristics of at least one previous sensor signal in the plurality of sensor signals.

67. The apparatus of claim 50, wherein the computer-program instructions are further configured to automatically classify the inflammation risk and / or an inflammation biotype by correlating clusters of present spikes in neural activity in a plurality of present sensor signals in the plurality of sensor signals to spatial clusters of previous spikes in neural activity in a plurality of previous sensor signals in the plurality of sensor signals.

68. The apparatus of claim 50, further comprising a wireless transmitter configured to transmit a remote notification to a remote device over a network, wherein the remote notification comprises at least one of an inflammation risk notification and an information biotype notification.

69. A system comprising: a wearable sensor; a receiving unit configured to (i) receive a sensor signal communicated from the wearable sensor and (ii) detect a signal type of the received sensor signal, wherein the signal type comprises a neural signal when the receiving unit detects at least a portion of a neural signal of a subject; a memory storing a set of instructions for predicting immune responses; and a processor that is configured to execute the set of instructions for predicting immune responses based on the sensor signal.

70. The system of claim 69, wherein the signal type comprises a neural signal when the receiving unit detects a neural signal for the signal type.

71. The system of claim 70, wherein the signal type comprises a physiological signal of the subject when the receiving unit detects a physiological signal for the signal type.

72. The system of claim 69, wherein the set of instructions for predicting immune responses based on the sensor signal comprises a set of instructions for automatically classifying an inflammation risk for the subject.

73. The system of claim 72, wherein the set of instructions for predicting immune responses based on the sensor signal further comprises a set of instructions for automatically creating a notification based on the inflammation risk.

74. The system of claim 69, wherein the receiving unit is a wearable receiving unit.

75. The system of claim 69, wherein the memory is a wearable memory.

76. The system of claim 69, wherein the processor is a wearable processor.

77. The system of claim 69, wherein the receiving unit is configured to detect the neural signal in a vagus nerve of the subject.

78. The system of claim 69, wherein the receiving unit is configured to detect the neural signal in a cervical nerve of the subject.

79. The system of claim 69, wherein the sensor signal comprises one of an electrocardiogram (ECG) signal, an electroencephalographic (EEG) signal, an electrogastrography (EGG) signal, a cervical electroneurography (CEN) signal, a cervical magnetoneurography (c-MNG) signal, and a respiration signal.

80. The system of claim 69, wherein the wearable sensor is configured to detect the neural signal transcutaneously.

81. The system of claim 69, wherein the sensor signal is a first sensor signal, wherein the receiving unit is further configured to receive a plurality of sensor signals comprising the first sensor signal.

82. The system of claim 69, wherein the receiving unit is further configured to differentiate between a plurality of neural signals identified from one or more sensor signals in the plurality of sensor signals.

83. The system of claim 69, wherein the set of instructions for predicting immune responses based on the sensor signal comprises a set of instructions for automatically classifying an inflammation biotype for the subject.

84. The system of claim 83, wherein the set of instructions for predicting immune responses based on the sensor signal further comprises a set of instructions for automatically creating a notification based on the inflammation biotype.

85. The system of claim 84, wherein the set of instructions for automatically classifying the inflammation biotype for the subject further comprises a set of instructions for performing a spike sorting algorithm that is configured to sort spikes in neural activity identified in the plurality of neural signals.

86. The system of claim 85, wherein the set of instructions for automatically classifying the inflammation biotype for the subject further comprises a set of instructions for identifying a spatial relationship of spikes in neural activity between a first neural signal in the plurality of neural signals and a second neural signal in the plurality of neural signals.

87. The system of claim 85, wherein the plurality of sensor signals comprise neural signals and physiological signals, wherein the set of instructions for automatically classifying the inflammation biotype for the subject further comprises a set of instructions for utilizing a Convolutional Neural Network (CNN) to identify autonomic features of the neural signals and the physiological signals.

88. The system of claim 69, wherein the set of instructions for automatically classifying the inflammation biotype for the subject further comprises a set of instructions for correlating present temporal signal characteristics of at least one present sensor signal in the plurality of sensor signals to previous temporal signal characteristics of at least one previous sensor signal in the plurality of sensor signals.

89. The system of claim 69, wherein the set of instructions for automatically classifying the inflammation biotype for the subject further comprises a set of instructions for correlating present spatial signal characteristics of at least one present sensor signal in the plurality of sensor signals to previous spatial signal characteristics of at least one previous sensor signal in the plurality of sensor signals.

90. The system of claim 69, wherein the set of instructions for automatically classifying the inflammation biotype for the subject further comprises a set of instructions for correlating clusters of present spikes in neural activity in a plurality of present sensor signals in the plurality of sensor signals to spatial clusters of previous spikes in neural activity in a plurality of previous sensor signals in the plurality of sensor signals.91 . The system of claim 69, further comprising a plurality of wearable sensors, wherein the wearable sensor is a first wearable sensor in the plurality of wearable sensors.

92. The system of claim 91, further comprising a flexible surface electrode array comprising the plurality of wearable sensors.

93. The system of claim 91, further comprising a flexible surface magnetometer array comprising the plurality of wearable sensors.

94. The system of claim 69, further comprising a wireless transmitter configured to transmit a remote notification to a remote device over a network, wherein the remote notification comprises at least one of an inflammation risk notification and an information biotype notification.

95. A method for predicting immune responses comprising: automatically receiving, by a receiving unit communicably connected to a processor, a plurality of sensor signals associated with a subject; analyzing the sensor signals to determine an immune response data associated with the subject; and automatically creating a display output based on the immune response data.

96. The method of claim 95, wherein the analyzing the sensor signals includes automatically classifying an inflammation risk for the subject based on the sensor signals.

97. The method of claim 95, wherein the analyzing the sensor signals includes automatically classifying an inflammation biotype for the subject based on the sensor signals.

98. The method of claim 95, wherein the immune response data includes an immune response parameter or immune response data set that is predictive of the subject’s immune response to a particular pathogen and / or at a particular anatomic structure of the subject’s body.

99. The method of claim 98, wherein the immune response data is predictive of the subject’s immune response based on determining signal characteristics within the sensor data that are indicative of concentration changes over a time period of one or more cytokine concentrations due to the particular pathogen within the anatomic structure of the subject.

100. The method of claim 99, wherein determination of the immune response data includes processing signal spike characteristics of the sensor signals with respect to an immune response data model.

101. The method of claim 100, wherein the immune response data model includes at least one of a machine learning model or a deep learning model trained on sensor data acquired over a plurality of subjects within known pathogens in known anatomical structures.

102. The method of claim 100, wherein the signal spike characteristics include a frequency of signal spikes over a time interval, for multiple time intervals, where, for each interval, the signal spikes represent an ensemble of neurons emitting action potentials in response to a cytokine concentration.

103. The method of claim 95, wherein the plurality of sensor signals comprises at least one of an electrocardiogram (ECG) signal, an electroencephalographic (EEG) signal, an electrogastrography (EGG) signal, a cervical electroneurography (CEN) signal, a cervical magnetoneurography (c-MNG) signal, and a respiration signal.

104. The method of claim 95, wherein the plurality of sensor signals is received from a plurality of wearable sensors.

105. The method of claim 104, wherein at least one of the sensor signals comprises a neural signal of the subject.

106. The method of claim 105, wherein at least one of the wearable sensors is configured to detect the neural signal transcutaneously.

107. The method of claim 95, wherein automatically classifying an inflammation biotype comprises sorting spikes in neural activity by way of a spike sorting algorithm.

108. The method of claim 95, wherein automatically classifying an inflammation biotype comprises utilizing a Convolutional Neural Network (CNN) to identify autonomic features.

109. The method of claim 95, wherein automatically classifying an inflammation biotype comprises identifying a spatial relationship of spikes in neural activity between two or more of the sensor signals.

110. The method of claim 95, wherein automatically classifying an inflammation biotype comprises correlating temporal signal characteristics of one or more of the sensor signals to temporal signal characteristics of previous sensor signals.

111. The method of claim 95, wherein automatically classifying an inflammation biotype comprises correlating spatial signal characteristics of one or more of the sensor signals to spatial signal characteristics of previous sensor signals.

112. The method of claim 95, wherein automatically classifying an inflammation biotype comprises classifying the inflammation biotype based on one or more molecular biomarkers.

113. The method of claim 95, wherein the inflammation risk and the inflammation biotype are automatically classified for the subject before the subject experiences an event that trigger an immune response.

114. The method of claim 95, further comprising automatically plotting sensor signals as data points in a plot and visually outputting the plot of the sensor signals on a display.

115. The method of claim 95, further comprising automatically transmitting the display output to a remote device.

116. The method of claim 115, wherein the display output includes a notification.

117. The method of claim 116, wherein the notification comprises at least one of an inflammation risk classified for the subject and an inflammation biotype classified for the subject.

118. A surface electrode array configured to detect multi-channel cervical neuronal activity, said surface electrode array comprising: a first polyimide layer; a second polyimide layer;a plurality of wearable sensors placed between the first polyimide layer and the second polyimide layer; electrical wiring to a power source; and data communication wiring to a processor that is configured to detect channel -specific neural signals of a subject.

119. The surface electrode array of claim 118, wherein each wearable sensor in the plurality of wearable sensors comprises an electrode.

120. The surface electrode array of claim 118, further comprising an adhesive that is configured to apply the plurality of wearable sensors transcutaneously to a vagus nerve area of the subject.

Images