Non-invasive autonomic measures to assess inflammatory response and mental health

Abstract

Systems and methods for assessing inflammatory response and mental health of subjects. The assessments may be based on measurements taken non-invasively. Methods may include classifying an inflammation risk for the subject based on physiological data and estimating a mental health status of the subject. The inflammation risk classification may be used to predict a likelihood of the subject's response to anti-inflammatory treatment. The systems and methods may include the use of machine learning models.

Description

NON-INVASIVE AUTONOMIC MEASURES TO ASSESS INFLAMMATORY RESPONSE AND MENTAL HEALTHCLAIM OF PRIORITY

[0001] This patent application claims priority to U.S. provisional patent application no.63 / 754,517, titled “NON-INVASIVE AUTONOMIC MEASURES TO ASSESS INFLAMMATORY RESPONSE AND MENTAL HEALTH,” and filed on February 5, 2024, which is herein incorporated by reference in its entirety.INCORPORATION BY REFERENCE

[0002] 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.BACKGROUND

[0003] Mental disorders are characterized by clinically significant disturbances in an individual’s cognition, emotional regulation or behavior. For example, post-traumatic stress disorder (PTSD) is a mental disorder that develops after a person has experienced or witnessed a traumatic event and is associated with increased mortality and morbidity. PTSD typically manifest behaviorally by: (1) intrusive symptoms, (2) avoidance, (3) negative cognitions and (4) hyperarousal, and results in significantly impaired functioning. Exposure to military combat can lead to PTSD which is associated with increased mortality and morbidity rates. Estimates of PTSD from the Vietnam War suggest a prevalence of approximately 15% (current) and 31% (lifetime) for Veterans exposed to war-zone trauma. Based on the Post Deployment Health Group file 31% of recently returning Veterans from OEF / OIF and Operation New Dawn (OND) have been diagnosed with PTSD symptoms. Similarly, 31% of Iraq and 19% of Afghanistan returning military personnel endorsed receiving care at mental health clinics for treatment of PTSD following combat-related experiences. The mental health impact of deployment to Iraq and Afghanistan is thought to be significant, as soldiers deployed to these locations reported greater combat exposure (65% and 45%, respectively) than those deployed to other locations (7%), and greater utilization of mental health services (1.1 and 0.85 visits / person, respectively) in contrast to those deployed to other locations (0.6 visits / person). The presence of commonly comorbid conditions that are inflammation related with PTSD increases health care utilization in this population.- 1 - SG Docket No.: 14947-700.600

[0004] Treatments for PTSD may include psychological therapy, medications and / or neuromodulation therapies to help manage symptoms. However, finding effective treatments can be challenging. For example, one type of therapy may be effective in treating some individuals while the same type of therapy may have limited or no effectiveness for other individuals. This may be due to the complexity and severity of trauma and the different ways in which individuals are able to cope with the trauma. Because of this, it is difficult to know which treatments would be most effective for treating any one individual.

[0005] It would be useful to have methods of more targeted approaches to treating mental disorders, such as PTSD, by identifying the differentiating characteristics of subjects related to mental health and identifying types of treatment that are most likely to benefit each subject.SUMMARY OF THE DISCLOSURE

[0006] Described herein are methods and apparatuses (e.g., devices, systems or assemblies) for assessing a subject’s response to an anti-inflammatory treatment of a mental health disorder based on a subject’s inflammation biotype. Also described herein are methods of determining or confirming a subject’s mental health based on the subject’s inflammation biotype. Also described herein are methods of determining a severity of a mental health disorder (including but not limited to post traumatic stress disorder) based on the subject’s inflammation biotype. Also described herein are methods of treating a mental health disorder by determining the subject’s inflammation biotype.

[0007] The subject’s inflammation biotype may include the subject’s inflammatory response. The subject’s inflammation biotype may be determined based on one or more measures of the subject’s autonomic nervous system, including one or both of an autonomic neurography (ANG) signal or score and / or a cardiac autonomic measure (CAM) signal or score. Any of the methods described herein may include collecting autonomic measurements of a subject and using the collected data to categorize the subject’s inflammatory response as an inflammation biotype (also referred to as an autonomic-immune biotype). The inflammation biotype of the subject can be used to predict mental health aspects of the subject, and to predict how likely the subject would respond to certain mental health treatments, particularly anti-inflammatory treatments. The methods may be used to predict, based on a subject’s inflammation biotype, whether the subject may need another treatment if they have recrudescence of symptoms after an initial treatment.

[0008] The methods may be used to assess inflammatory responses of subjects who have mental health disorders or do not have mental health disorders. Mental health disorders may -2 - SG Docket No.: 14947-700.600include, for example, mood disorders, depression, anxiety disorders, psychotic disorders and / or mental disorders related to substance abuse.

[0009] In some examples, the methods may be well-suited for assessing the inflammatory response of a subject that has, or may have, post-traumatic stress disorder (PTSD). Current pharmacological treatments for PTSD target specific biological systems, which may not fully correspond to subjective symptoms. Unlike many physical diseases that use objective tests for diagnosis, mental illnesses like PTSD are typically classified based solely on subjective symptoms. Current approaches can lead to mechanistically heterogeneous patient populations and diluted efficacy of potential treatments, especially for adjuvant anti-inflammatory therapies. The approaches described herein can provide an objective marker for the neuroimmune axis, potentially maximizing the efficacy of anti-inflammatory treatments in selected individuals with PTSD.

[0010] The methods and apparatuses described herein may offer a technical solution to the technical problem of predicting how a subject may response to anti-inflammatory treatments (e.g., neuromodulation or drug therapies) and / or predicting whether a subject may need further treatment (e.g., different treatment) if symptoms reoccur after initial treatment. The methods and apparatuses can thus be implemented to enable healthcare providers to more effectively and efficiently treat their subjects.

[0011] Techniques may include non-invasive measurement techniques, for example, using one or more sensors (e.g., non-physically penetrating sensors). The sensor signals (collected as physiological data) may be collected while the subject is at rest and / or in response to one or more autonomic stress challenges. The resulting physiological data may be used to determine the subject’s likely response to inflammation, should an inflammatory response be triggered in the subject thereafter. Knowing the subject’s inflammation biotype (also referred to as autonomic-immune biotype) may be used to proactively treat the subject or prepare to treat the subject.

[0012] For example, an estimated inflammation biotype of a subject may be used to predict how responsive the subject would be to anti-inflammatory treatments, such as antiinflammatory neuromodulation and / or drug treatments, thereby improving clinical outcomes. The inflammation biotype may be used to distinguish those subjects that are predicted to be more responsive to neuromodulation treatment compared to drug treatment, or vice versa. For example, the subject may be estimated to have a low inflammatory risk biotype or a high inflammatory risk biotype. In some cases, the subject may be estimated to have a low, medium or high inflammatory risk biotype. A low inflammatory risk biotype may be generally associated with a mentally healthy individual. Medium and high inflammatory risk -3 - SG Docket No.: 14947-700.600biotype may be associated with higher inflammatory responses, with the high inflammatory risk biotype associated with a higher degree of inflammatory risk compared to the medium inflammatory risk biotype. The higher the inflammatory risk biotypes may be more responsive to anti-inflammatory treatments, such as anti-inflammatory neuromodulation, compared to low inflammatory risk biotypes.

[0013] The methods may include collecting data related to the autonomic nervous system of the patient. For example, one or more cardiac autonomic measure (CAM) tests may be performed to assess the function of the autonomic nervous system by monitoring heart signals, since the autonomic nervous system can influence the heart. CAM test may be used to estimate how well the autonomic nervous system maintains balance between the sympathetic nervous system and the parasympathetic nervous system. CAM tests may be used, for example, cardiac signals such as electrocardiogram (ECG) data (or data derived from ECG data), heart rate (HR), heart rate variability (HRV) and / or other cardiac signals.

[0014] In some examples, autonomic neurography (ANG) tests may be used to assess the function of the autonomic nervous system. In general, ANG is used to record the electrical activity of the autonomic nerves, which control involuntary bodily functions such as heart rate, blood pressure, respiration rate, digestion and / or sweating. These nerve signals may be measured from areas such as a subject’s neck (e.g., vagus nerve and / or the carotid sinus nerve), the subject’s skin and / or other areas of the subject’s body. The methods may include performing one or more neural activity tests to measure electrical signals from autonomic nerves. For example, ventral cervical neuronal activity (activity of neurons located in the ventral (front) region of the cervical spinal cord) may be monitored. Ventral cervical neuronal activity may include activity from one or more neural targets including one or more of the vagus nerve, the hypoglossal nerve, the sympathetic chain and / or ganglia associated with the vagus nerve, the hypoglossal nerve and the sympathetic chain.

[0015] In some examples, both ANG and CAM measurements are collected. The combination of both ANG and CAM may provide more insight and more accurate prediction as to a subject’s inflammation biotype compared to using either ANG or CAM measurements alone. In examples, ANG and / or CAM measurements may be used in combination with other patient-specific measurement data, such as molecular data (e.g., microRNA data, biomarker data, blood assay data), self-report questionnaire data and / or clinical history data.

[0016] The methods and apparatuses described herein may use one or more machine learning algorithms or models to automatically determine an inflammation biotype for the patient and / or predict whether (and / or which) anti-inflammatory treatments would be most beneficial. Any appropriate machining learning model may be used, such as a neural network - 4 - SG Docket No.: 14947-700.600model, a linear regression model, a logistic regression model, a support vector machine model and / or a tree-based model. In some cases, the machine learning model may be a trained neural network, e.g., to classify an inflammation biotype a subject and / or predict appropriate treatment. In some cases, the machine learning model may be a deep learning model.

[0017] 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. Subjects may include non-human subjects (e.g., mammalian subjects) or human subjects.

[0018] According to some examples, a method of treating a subject’s mental health includes: recording autonomic neurography (ANG) data and / or cardiac autonomic measure (CAM) data from the subject, where recording the ANG data includes recording electrical activity of one or more of the subject’s autonomic nerves, and collecting CAM data includes recording activity of the subject’s heart; assigning an inflammation biotype to the subject based on the ANG data and / or the CAM data; predicting the subject’s response to a treatment of a mental health disorder based on the inflammation biotype; and outputting the response to the treatment. The mental health disorder may include one or more of: depression, anxiety, and post-traumatic stress disorder (PTSD). The treatment may include an anti-inflammatory treatment or a pharmaceutical treatment.

[0019] According further examples, a method of assessing a subject’s mental health includes: recording autonomic neurography (ANG) data and / or cardiac autonomic measure (CAM) data from the subject, where recording the ANG data includes recording electrical activity of one or more of the subject’s autonomic nerves, and collecting CAM data includes recording activity of the subject’s heart; assigning an inflammation biotype to the subject based on the ANG data and / or the CAM data; predicting the subject’s mental health based on the inflammation biotype; and outputting the predicted mental health of the subject. The ANG data may include non-invasively recording ANG data. Recording CAM data may include non-invasively recording CAM data. Recording ANG data and / or CAM data may include recording both ANG and CAM data. The ANG data and / or the CAM data may be recorded while the subject is at rest. The ANG data and / or the CAM data may be recorded while the subject is undergoing an autonomic challenge. Assigning the inflammation biotype to the subject may include using a trained neural network, wherein the trained neural network has been trained on previously collected ANG signal data and / or CAM signal data correlated with immune response data from multiple subjects. Immune response data may include - 5 - SG Docket No.: 14947-700.600cytokine release data after lipopolysaccharide (LPS) administration. The previously collected ANG signal data and / or CAM signal data may further have been correlated with previously collected molecular biomarker data and / or patient-reported symptom severity data of the multiple subjects. Molecular biomarker data may include microRNA analysis data. Predicting the subject’s mental health may include estimating a severity of a mental illness. Assigning the inflammation biotype may include estimating whether the subject has a high inflammatory risk biotype or a low inflammatory risk biotype, where the high inflammatory risk biotype is associated with an individual suffering from a mental illness, and the low inflammatory risk biotype is associated with a mentally health individual. Assigning the inflammation biotype may include estimating a severity of a mental illness based on a degree to which the inflammation biotype is high or low, where the method further includes predicting whether the subject would be responsive to an anti-inflammatory treatment based on the estimated severity of the mental illness. The anti-inflammatory treatment may include a neuromodulation treatment and / or an anti-inflammatory drug treatment. The method may further include providing a recommendation for one or more treatments based on the estimated severity of the mental illness. The ANG data may include ventral cervical neuronal activity data. The ventral cervical neuronal activity may include activity from one or more neural targets including the vagus nerve, the hypoglossal nerve, the sympathetic chain and / or ganglia associated with the vagus nerve, the hypoglossal nerve and the sympathetic chain. The CAM data may include electrocardiogram (ECG) data, data derived from the ECG data, heart rate (HR) data, and / or heart rate variability (HRV) data. The subject may have already been diagnosed as having a mental disorder prior to determining the inflammation biotype. Predicting the subject’s mental health may include predicting the subject’s response to an anti-inflammatory treatment.

[0020] According to some examples, a method includes: recording autonomic neurography (ANG) data and cardiac autonomic measure (CAM) data from the subject, wherein recording the ANG data includes recording electrical activity of one or more of the subject’s autonomic nerves, and collecting CAM data includes recording activity of the subject’s heart; assigning an inflammation biotype to the subject based on the ANG data and the CAM data; predicting the subject’s response to an anti-inflammatory treatment of a mental health disorder based on the inflammation biotype; and outputting the response to the anti-inflammatory treatment.

[0021] According to additional examples, an apparatus 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 - 6 - SG Docket No.: 14947-700.600processors, the memory storing computer-program instructions, that, when executed by the one or more processors, perform a computer-implemented method including: receiving, in the one or more processors, the neural signal and / or the cardiac signal from the one or more sensors recorded from the subject, wherein the neural signal includes an autonomic neurography (ANG) signal corresponding to electrical activity of one or more of the subject’s autonomic nerves, and / or the cardiac signal includes a cardiac autonomic measure (CAM) signal corresponding to recorded activity of the subject’s heart; assigning an inflammation biotype to the subject based on the ANG and / or CAM signals; predicting the subject’s response to an anti-inflammatory treatment of a mental health disorder based on the inflammation biotype; and outputting the response to the anti-inflammatory treatment.

[0022] According to further examples, an apparatus 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 including: receiving, in the one or more processors, the neural signal and / or the cardiac signal from the one or more sensors recorded from the subject, wherein the neural signal includes an autonomic neurography (ANG) signal corresponding to electrical activity of one or more of the subject’s autonomic nerves, and / or the cardiac signal includes a cardiac autonomic measure (CAM) signal corresponding to recorded activity of the subject’s heart; assigning an inflammation biotype to the subject based on the ANG and / or CAM signals; predicting the subject’s mental health based on the inflammation biotype; and outputting a notification of the predicted mental health of the subject. Recording ANG data may include non-invasively recording ANG data. Recording CAM data may include non-invasively recording CAM data.Recording ANG data and / or CAM data may include recording both ANG and CAM data. Assigning the inflammation biotype to the subject may include using a trained neural network, wherein the trained neural network has been trained on previously collected ANG signal data and CAM signal data correlated with immune response data from multiple subjects. Immune response data may include cytokine release data after lipopolysaccharide (LPS) administration. The previously collected ANG signal data and CAM signal data may have further been correlated with previously collected molecular biomarker data and / or patient-reported symptom severity data of the multiple subjects. The molecular biomarker data may include miRNA analysis data. Predicting the subject’s mental health may include estimating a severity of a mental illness.- 7 - SG Docket No.: 14947-700.600

[0023] 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.

[0024] These and other aspects and details are described herein.BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Novel features of embodiments described herein are set forth with particularity in the appended claims. Abetter understanding of the features and advantages of the embodiments may be obtained by reference to the following detailed description that sets forth illustrative embodiments and the accompanying drawings.

[0026] FIG. l is a flowchart indicating an example method for estimating and determining mental health and inflammation biotypes and predicting a likelihood of response to anti-inflammatory treatments for a subject.

[0027] FIG. 2A is an example diagram showing the impacts of stress and trauma to the immune system and inflammation.

[0028] FIG. 2B is an example diagram showing how lipopolysaccharide (LPS) can be recognized by sensor receptors on the vagus nerve peripheral afferents, nodose and jugular ganglion.

[0029] FIG. 2C is an example diagram showing how pathogen fragments can stimulate release of proinflammatory cytokines.

[0030] FIGS. 3A-3D are graphs showing example results of recurrence quantification analysis (RQA) of resting state cardiac autonomic measure (CAM), demonstrating the relationship between cardiac autonomic modulation and inflammatory severity levels measured by peak TNF cytokine levels post-LPS injection.

[0031] FIG. 4 illustrates the correlation between CAM and peak microRNA (miRNA) miR-210-3p levels following LPS injection. CAM was quantified using the ratio of resting sympathetic activity index (SAI) to parasympathetic activity index (PAI).

[0032] FIG. 5 is a graph showing the result of symptom severity as a function of autonomic neurography (ANG) at rest, estimated in spikes per second.

[0033] FIGS. 6A-6C are graphs showing example results of CAM and ANG measures that correlate with inflammation and symptom severity during the autonomic stress challenge, the cold pressor test (CPT).

[0034] FIGS. 7 A and 7B are graphs showing examples of inflammatory pain-related differences between combat veterans after LPS injection.

[0035] FIG. 8 is a diagram showing an example of how autonomic task-based ANG neural firing changes during the autonomic stress challenge, the cold pressor test.- 8 - SG Docket No.: 14947-700.600

[0036] FIGS. 9 A and 9B show exemplary sensor placement for bilateral ANG recordings, using both surface electrodes and optically pumped magnetometers.

[0037] FIG. 10A shows example CAM and ANG data collected for mentally healthy individuals and individuals suffering from PTSD while undergoing a cold pressor test (CPT) autonomic challenge.

[0038] FIG. 10B shows example CAM and ANG data collected for mentally healthy individuals and individuals suffering from PTSD while undergoing a deep breath autonomic challenge.

[0039] FIG. 10C shows an example timeline of LPS administration and data collection for subjects.

[0040] FIG. 10D shows an example diagram of a deep learning model for classifying mental health disorder severity and inflammatory biotypes based on collected physiological and molecular data.

[0041] FIGS. 10E and 10F show example diagrams of how immune response data may be used to provide an inflammation endotype to individuals.

[0042] FIGS. 11 A and 11B show example diagrams of CAM collected from resting state positively correlates with mental health measures.

[0043] FIGS. 12A-12D show diagrams of neural activity change ratio of ANG pre-to-post LPS injection positively correlate with mental health measures.

[0044] FIGS. 13A-13H show diagrams of multivariate regression for estimating various mental health measures using CAM collected from resting state and ANG neural activity changes (pre-to-post LPS injection) as predictors.

[0045] FIGS. 14A and 14B show an example diagram of miRNA collected during resting state positively correlates with mental health measures.

[0046] FIGS. 15A and 15B show diagrams of miRNA change ratio pre-to-post LPS injection positively correlates with mental health measures.

[0047] FIG. 16 shows a diagram illustrating an example computing system to perform methods described herein.DETAILED DESCRIPTION

[0048] The apparatuses (e.g., devices, system or assemblies) and methods described herein relate to mental health assessment of subjects based on inflammatory responses of the subjects. The assessment can be made based on collecting autonomic measurement data and using this data to determine an inflammation biotype for a subject, which indicates the subject’s susceptibility to inflammation and may be used to estimate the mental health of the - 9 - SG Docket No.: 14947-700.600subject. The inflammation biotype can be a score or characteristic value. If the subject is suffering from a mental illness, the inflammation score may be used to predict whether the subject is likely to be responsive to anti-inflammatory treatments or drug therapies. In some examples, the inflammation biotype may be used to predict whether a different type of treatment is needed, for example, if symptoms persist or recur after an initial treatment.

[0049] The neuroimmune system plays an important role in regulating inflammation in the body in that the nervous system can signal the immune system to initiate inflammatory responses. A healthy neuroimmune system helps to maintain a balanced inflammatory response, preventing excessive inflammation while allowing for appropriate immune reactions for protecting against pathogens or tissue damage. Mental disorders and neuropsychiatric conditions can significantly impact the immune system by suppressing immune function and increasing inflammatory markers. The methods and systems described herein can be used to objectively assess the mental health of subjects by determining their inflammation biotypes and using these inflammation biotypes to predict which treatments the subjects may be most responsive to. The methods and systems described herein can also provide a mental health severity prediction platform for determining the severity of mental disorders with respect to inflammatory response.

[0050] FIG. l is a high-level flowchart indicating an example method for determining and using an inflammation biotype for a subject, according to embodiments described herein. At block 101, autonomic physiological data is collected from the subject. The autonomic physiological data may include data that can be collected in a non-invasive manner and that is readily measurable. For example, cardiac and / or autonomic neural signals may be sensed by one or more sensors placed on the subject, and these signals may be stored as cardiac and / or autonomic data in memory of one or more computers. The cardiac data may include one or more cardiac autonomic measures (CAM), such as ECG signal data (or data derived from ECG signal data, which may be 1-lead ECG data, 3 -lead ECG data, 12-lead ECG data, etc.), heart rate (HR), heart rate variability (HRV) and / or other cardiac signal measures (or measures derived from cardiac signals). Neural data may include data from autonomic nervous system nerve(s), for example, using autonomic neurography (ANG) and / or other techniques for measuring activity of the autonomic nervous system. The neural activity of vagus nerve and / or sympathetic nerve may include (but is not limited to) spike frequency and / or distribution.

[0051] In some implementations, the subject may undergo one or more autonomic stress challenges while (and / or before) the autonomic physiological data is collected, which may be coordinated (applied, started, stopped, etc.) by the methods and apparatuses described herein.- 10 - SG Docket No.: 14947-700.600Autonomic 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 include temperature-based challenges, such as the cold pressor test (CPT), a respiratory challenge (such as a timed deep breathing test, Valsalva maneuver), exercise challenges and / or postural stress tests (e.g., orthostatic challenge, tilt table test, etc.).

[0052] In some implementations, the autonomic physiological data is collected while the subject is at rest, i.e., while the subject does not undergo an autonomic stress challenge. In some cases, the at-rest physiological data may be used as a baseline for comparison with physiological data collected under autonomic stress challenge conditions. In other cases, the at-rest physiological data is used alone (i.e., without comparison with data collected under autonomic stress challenge conditions).

[0053] At block 103, an inflammation biotype of the subject is estimated. In general, the inflammation biotype may be a qualitative and / or quantitative measure that indicates the subject’s susceptibility to inflammation. The inflammation biotype may represent a resting state immune response of the subject. Individuals found to have a low-risk inflammation biotype are predicted to have a lower inflammatory risk than those individuals found to have a high-risk inflammation biotype.

[0054] The inflammation biotype may be estimated by correlating the collected autonomic physiological data (at block 101) with previously collected data. The previously collected data may include previously collected cardiac data (e.g., CAM data) and / or neural data (e.g., ANG data) that has been correlated with direct measurements of inflammatory response, such as cytokine levels (e.g., TNF), micro-RNA (miRNA) and / or sick symptom severity changes (e.g., self-reported) after administration of an inflammatory agent.Inflammatory agents may include, for example, pathogen-associated molecular patterns (PAMPs) (e.g., lipopolysaccharide (LPS)) or damage-associated molecular patterns (DAMPs).

[0055] The methods and systems described herein may include an inflammation biotype classifier which may include computer instructions that (when executed by a processor) automatically classify an inflammation biotype for a subject based on collected physiological data (e.g., sensor signals). In general, the inflammation biotype classifier may correlate the collected data with previously collected data. The inflammation biotype classifier may automatically classify an inflammation biotype for a subject based on neural signal data (e.g.,- 11 - SG Docket No.: 14947-700.600one or more clusters of spikes in neural activity in one or more sensor signals and / or cardiac signal data (e.g., ECG signals).

[0056] In some examples, correlation between the collected autonomic physiological data (at block 101) with the previously collected data may be implemented using a machine learning model, such as a neural network model. For example, sensor signal characteristics of collected CAM and ANG signal data may be processed by comparing the sensor signal characteristics to signatures indicative of inflammatory response using the machine learning model(s). The machine learning model may automatically find correlations among the collected data specific to the subject and different sets of previously collected data and provide an estimated inflammation biotype for the subject.

[0057] At block 105, the subject’s mental health may be predicted based on the inflammation biotype determined at block 103. As discussed herein, a subject’s inflammation biotype is correlated with mental health of the subject. Thus, individuals found to have a low inflammation biotype may be predicted to have better mental health than individuals found to have a high inflammation biotype. In some cases, subjects may be classified on a scale including hypo- and hyper- inflammatory biotypes. For example, inflammatory biotype may include: very low inflammation biotype, low inflammation biotype, modest inflammation biotype, high inflammation biotype or very high inflammation biotype. The inflammatory biotype 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. In some examples, such classification and scaling of inflammatory biotypes may be determined by the machine learning model(s).

[0058] At block 107, the inflammation biotype may optionally be used to predict likelihood of patient response to treatment based on the inflammation biotype. Treatments may include anti-inflammatory treatment (e.g., neurotherapy and / or drug), pharmaceutical treatment, and / or other types of treatment. Such prediction may be based on the severity of the inflammation biotype. For example, if the subject is found to have a modest, high or very high inflammation biotype, the subject may be estimated to respond well to one or more antiinflammatory treatment(s); whereas, if the subject is found to have a very low or low inflammation biotype, the subject may be predicted to not benefit from one or more antiinflammatory treatment(s). In such cases, if needed, the subject may benefit more from other treatment(s), such as non-anti-inflammatory treatment. In this way, the methods and systems described herein can be used to non-invasively assess a subject’s inflammatory biotype and provide a targeted approach to treatment.- 12 - SG Docket No.: 14947-700.600

[0059] FIG. 2A is an example diagram showing the impacts of stress and trauma to the immune system and inflammation. Stress and trauma associated with conditions such as post-traumatic stress disorder (PTSD), generalized anxiety disorder (GAD), major depressive disorder (MDD) and hyper-fear appraisal can lead to chronic hyper-sympathetic signaling directed to immune cells. This results in increased cytokine release in the peripheral and central nervous system. Primed immune cells and increased peripheral and central nervous system inflammation can recursively increase anxiety and depression behavior. Many inflammatory and immune-related cytokines (e.g., IL-6, IL-2, IL-4, IL- 12, TNF, INF) are associated mental disorders such as depression, anxiety and PTSD.

[0060] Innate immune responses and low parasympathetic tone are likely to pose a predeployment risk factor for development of the PTSD in veterans after deployment. Low parasympathetic tone can also predict eventual rheumatoid arthritis (RA) symptom severity in healthy subjects deemed at risk of RA disease development. In summary, some aspects of PTSD biology may be similar to those observed in RA (e.g., increased inflammation, and low parasympathetic tone), raising the possibility that, like RA, vagal mechanisms may apply to PTSD. As has been demonstrated, immune responses are activated by pathogen-associated molecular patterns (PAMPs) and damage-associated molecular patterns (DAMPs) that can then be recognized by sensor receptors on the vagus nerve peripheral afferents, nodose and jugular ganglion (FIG. 2B), immune cell surface or in intracellular compartments through both Toll-like receptors (TLRs), nucleotide binding oligomerization domain-like receptors (NLRs) and IL-ip receptors which may individually or collectively activate signal cascades that stimulate release of proinflammatory cytokines (FIG. 2C). It is well established that intravenously injected LPS will significantly increase peripheral blood cytokine levels (i.e., over a seven-hour protocol used in studies described herein).

[0061] While there is an established link between PTSD and inflammation, clinical trials have not shown consistent efficacy of anti-inflammatory drugs for PTSD treatment. Although elevated inflammatory markers may predict PTSD development, it has been unclear if these individuals respond better to anti-inflammatory treatments compared to other types of treatment. Conventional treatments for PTSD have shown varying responses among subgroups, identified through invasive and costly blood tests that are unlikely to be available in diverse socioeconomic clinical settings. This highlights the need for low-cost, equitable, non-invasive bioindicators that may guide anti-inflammatory treatment therapy. Results of studies described herein show that non-invasively collected ANG and CAM data can be correlated with and predict the subject’s inflammatory response.- 13 - SG Docket No.: 14947-700.600

[0062] FIGS. 3A-3D, 4, 5 and 6A-6C show results from studies showing CAM and neural activity data during rest and autonomic stress challenges correlate to peak inflammatory response, miRNA response, and symptom severity to LPS administration. Continuous ECG was recorded for one hour prior to LPS injection, and various CAM features were derived from the extracted RR intervals who also underwent the autonomic stress challenge, i.e., CPT. Recurrence quantification analysis (RQA) was applied to quantify the cardiac autonomic modulation from a dynamic systems perspective with the aim to compare these at-rest measures to the inflammatory severity (i.e., peak TNF levels post-LPS injection). The RQA parameters determinism (DET) (FIG. 3 A) and line-max (LMAX) (FIG.3B) demonstrate the predictivity of system dynamics, while laminarity (LAM) (FIG. 3C) and trapping time (TT) (FIG. 3D) indicate system stability. Previous studies have shown elevated RQA measures (DET, LMAX, LAM, and TT) during mental arithmetic stress challenges and examination testing, suggesting that higher RQA measures are typically associated with increased stress levels and greater sympathetic activity. Linear regression analysis was performed between each RQA parameter and the LPS peak tumor necrosis factor (TNF) levels. Peak TNF was calculated as the TNF concentration post-LPS injection. Results revealed significant positive correlations between inflammation severity for LMAX (p<0.05). These findings indicate that at-rest heartbeat exhibiting higher predictability and stability tends to correspond with more severe inflammation. High predictability in heart rate (HR) dynamics denotes the recurrence of similar periodic patterns (HR change) over time, while high stability reflects the extent of constant HR dynamic change. This analysis shows that specific features of RQA at-rest predict peak inflammatory (TNF) in response to the LPS challenge.

[0063] FIG. 4 shows at-rest CAM Sympathetic Activity Index (SAI) and Parasympathetic Activity Index (PAI) ratio (SAI / PAI) correlates with miRNA miR-210-3 p levels post-LPS injection. SAI and PAI both have demonstrated superior efficacy in tracking autonomic variation compared to frequency-domain measures (i.e., LF / HF). These results reveal that the at-rest SAI / PAI ratio was highly predictive (r=0.88 p=.0003) of peak miRNA-210-3p post-LPS injection. miRNA-210-3p is a miRNA known to regulate NF-KB mediated cytokine regulation and is itself modulated by cold water exposure. This preliminary analysis shows that specific CAM at-rest features (SAI / PAI) predict peak miR-210-3 p expression (known to regulate NF-KB mediated cytokine expression) in response to the LPS challenge.

[0064] FIG. 5 shows symptom severity as a function of ANG at rest measured in spikes per second. These results show at rest, ANG measures predict a peak post-LPS peak inflammatory sick symptom response in (N=19) HC participants (r=-0.53, p=.O19). Symptom - 14 - SG Docket No.: 14947-700.600severity was measured using self-reported symptoms on a standard Likert scale for headache, nausea, rigor, and back pain post-LPS injection. Results indicated that subjects with lower at-rest ANG (spike / sec) exhibited higher post-LPS sick symptom severity; it may translate as an at-rest bio-indicator of potential response to targeted anti-inflammatory treatments.

[0065] FIGS. 6A-6C show results of CAM and ANG measures across cold pressor test (CPT). In a subset of subjects (N=10) parasympathetic nervous system (PNS) efficacy was assessed by the rapidity of HR regulation across the CPT autonomic task. A significant negative relationship was observed between the HR regulation slope (reduction in HR during the CPT) and peak TNF levels (r=-0.81 p=0.005), indicating a link between PNS efficacy and inflammatory response (FIG. 6A). These findings collectively support the potential of across-CPT CAM measures in predicting inflammatory responses and may provide an opportunity to optimize anti-inflammatory treatments. In the same group (N=10), the relationship between pre-LPS CAM across CPT and peak symptom severity was investigated. Traditional heart rate variability (HRV) measures have limitations in delineating dynamic change in sympathetic and parasympathetic activity especially in brief autonomic tasks such as the CPT which occur over minutes time. Therefore, this study employed the SAI and PAI, known to dynamically predict autonomic state. Results revealed a significant positive relationship between the SAI / PAI ratio and symptom severity (r=0.73, p=0.016), indicating that subjects with higher sympathetic activity tend to report more severe symptoms (FIG. 6B).Additionally, the average ANG-derived firing rate during the cold pressor test showed a significant positive correlation with peak symptom severity (r=0.65, p=0.041, FIG. 6C). The finding is supported by a recent report that demonstrated increased sympathetic firing rate across CPT when comparing (N=14) PTSD to (N=14) HC. In aggregate, it suggests an observable association between autonomic nervous system balance and the intensity of symptoms experienced following LPS injection. Further, this relationship may also be distinguishable between Veterans with and without PTSD.

[0066] FIGS. 7 A and 7B show results showing significant inflammatory pain-related differences between combat veterans with PTSD (N=ll) and HC (N=10). Following intramuscular capsaicin injection (a prolonged pain and stress task), PTSD subjects exhibited markedly elevated pain intensity and unpleasantness ratings that persisted over time, in contrast to the decreasing ratings observed in HC. Across the capsaicin injection, pain was reported as measured with the visual analog scale (VAS) after capsaicin injection for pain unpleasantness. Compared to the combat control group (CC), the PTSD group showed continued elevated levels of reported spontaneous pain unpleasantness (F(l, 18) = 6.5, P = 0.019) (FIG. 7A), and intensity (F(l , 18) = 6.5, P = 0.02) (FIG. 7B). Notably, these pain- 15 - SG Docket No.: 14947-700.600disparities remained robust even after controlling for potential confounding factors such as depression and childhood trauma. The amplified pain responses in PTSD subjects correlated strongly with elevated levels of pro-inflammatory cytokines, particularly TNF-a, (r=0.83 p=.01). Further, data in this cohort also demonstrate significantly elevated plasma cytokines (Interferon gamma, IL-6, IL-8 p< 02) in veterans with PTSD compared to combat controls 20 minutes post-capsaicin injection (unpublished). These findings demonstrate that veterans with PTSD exhibit heightened cytokine and prolonged pain responses to a controlled stimulus. These results indicate that veterans with PTSD may demonstrate greater inflammatory responses and increased “sick symptoms” following LPS challenge compared to controls.

[0067] FIG. 8 illustrates how autonomic task-based ANG neural activity and CAM changes during the cold pressor test (CPT). Before LPS injection, veterans can undergo continuous ANG and CAM for the CPT-validated stress test. The CPT requires participants to submerge their hand in ice water for up to 5 minutes or until they reach their pain tolerance threshold. This approach combines innovative electrode placement with established stress tests to comprehensively study autonomic stress responses and their relationship to LPS-induced inflammation. ANG measured as neural firing rate (spikes / sec), and CAM measured as R-R intervals are recorded during the CPT. All autonomic and physiological measures, including electroneurography (ENG), magnetoneurography (MNG), and ECG, may be acquired. From CPT start to CPT end, ANG neural activity (including ENG and MNG) and ECG waves (for estimating CAM) are recorded. Left-sided ENG measured with gold-plated electroencephalography (EEG) surface electrodes recorded an increase in neural amplitude and firing rate, while ECG measurements demonstrate a change in cardiac measures (e.g., heart rate).

[0068] Responses to the CPT are heterogeneous. Some subjects show increases in neural firing or heart rate, while others demonstrate decreases. An autonomic challenge test (e.g., CPT) can be performed prior to LPS injection to investigate the relationship between autonomic responses and subsequent changes in inflammatory biomarkers and sick symptoms. This approach reveals individual variations in the stress response and its correlation with inflammatory response and subjective symptom report, enhancing the understanding of autonomic-immune interactions in stress-related conditions. Ultimately, this methodology could lead to the development of a cost-effective, non-invasive screening tool to assess the responsiveness of subjects to anti-inflammatory therapies. By linking autonomic function to inflammatory responses, this approach provides valuable insights for personalizing treatments in conditions such as PTSD, where autonomic dysregulation and inflammation often coexist.- 16 - SG Docket No.: 14947-700.600

[0069] FIGS. 9 A and 9B show example electrode setup for bilateral ANG recordings. In some cases, two proximal and distal targets are selected for bilateral ANG recordings.Positioning of sensors may be first marked by target visualization using ultrasound imaging. For the left side: left nodose ganglion (LNG) and left carotid artery (LCA) sites, the superficial skin may first be abraded and cleaned with alcohol. Sticker electrodes or gold-plated electroencephalography (EEG) surface electrodes may be used to record electroneurography (ENG) and are applied using conductive gel and secured with medical tape. CAM measures may be obtained with ECG electrodes placed on the right upper chest and left lower rib (not shown in FIGS. 9A and 9B). For the right side: optically pumped magnetometers (OPMs) measuring magnetoneurography (MNG) may be attached overlying the right nodose ganglion (RNG) and right carotid artery (RCA) sites using adhesive medical tape and Velcro. The OPMs may be oriented with their x-axis normal to the skin surface, aligned longitudinally with the vagus nerve and carotid sinus. The placement of electrodes and OPMs is interchangeable on both sides. This comprehensive setup may allow for simultaneous electrical and magnetic measurements of autonomic activity at key ventral cervical sites.

[0070] As discussed, non-invasive ANG and CAM data have been found to predict postlipopolysaccharide (post-LPS) inflammatory response of cytokine and miRNA concentrations in veterans with PTSD and in healthy controls. FIGS. 10A-10F illustrate aspects of an example study showing results that show how ANG and CAM data can predict post-LPS inflammatory response.

[0071] FIG. 10A shows an example of CAM data (heart rate) and ANG data collected for mentally healthy individuals and individuals suffering from PTSD while undergoing a cold pressor test (CPT) autonomic challenge. In this example, the CPT involved placing the subject’s hand in an ice water bath. The mentally healthy individuals exhibited decreasing heart rate in response to the cold pressor test - and is referred to as a cold pressor test decreaser (CPTd). The individuals suffering from PTSD exhibited increasing heart rate in response to the cold pressor test - and is referred to as a cold pressor test increaser (CPTi). The ANG data shows that the individuals suffering from PTSD (CPTi) exhibited increased autonomic nerve activity during the CPT compared to the mentally healthy individuals (CPTd).

[0072] FIG. 10B shows comparative data of ANG neural activity and spike frequency data (derived from ANG data as described herein) between mentally healthy individuals (CPTd) and individuals suffering from PTSD (CPTi) during a deep breath autonomic challenge. During this three-minute autonomic challenge, participants were instructed to - 17 - SG Docket No.: 14947-700.600perform controlled breathing cycles consisting of five-second deep inhalations followed by five-second deep exhalation. Mentally healthy individuals (CPTd) exhibit a hypo-inflammatory endotype, i.e., less inflammatory cytokine production, and demonstrate decreased ANG neural firing activity post-to-pre deep breathing; however, the individuals suffering from PTSD (CPTi) demonstrate hyper-inflammatory endotype and increased ANG neural activity post-to-pre deep breathing.

[0073] FIG. 10C shows a timeline of data collection and LPS dosing. The ANG and CAM data during the autonomic challenge (cold pressor test and deep breathing) prior to administration of LPS (3 ng / kg) for 45 human subjects. The subjects were continuously monitored for 60 minutes before and 300 minutes after LPS administration by periodic blood collection, blood pressure measurements, and symptom measurements (e.g., self-reported). The study ended 360 minutes after LPS administration. The pre-LPS and post-LPS data are used as input in a deep learning / machine learning model to develop models for predicting post-LPS data inflammatory response using ANG and CAM data.

[0074] It is noted that some seemingly healthy individuals exhibited endotype specific variable inflammation in response to LPS administration, indicating autonomic dysregulation in these seemingly healthy individuals.

[0075] FIGS. 10D shows a diagram of an example deep learning model designed to classify mental health disorder severity and / or inflammatory biotypes using both physiological features (derived from ANG and CAM) and molecular biomarkers. Given the established relationship between mental health and inflammatory responses, this model can be further optimized to assess inflammatory response risk levels.

[0076] FIGS. 10E and 10F illustrate an example of how immune response data may be used to provide an inflammation endotype to individuals. As discussed herein, an inflammation biotype may be a qualitative and / or quantitative measure that indicates a subject’s susceptibility to inflammation and may include subjects that are mentally healthy. Inflammation endotype may refer to a subclassification of mentally unhealthy individuals (e.g., subjects who have been diagnosed with PTSD). FIG. 10E illustrates an example of an individual characterized as having a low inflammatory response (Endotype A) associated with low cytokine release in response during testing. FIG. 10F illustrates an example of an individual characterized as having a high inflammatory response (Endotype B) associated with high cytokine release in response during testing.

[0077] FIGS. 11 A and 11B show examples of CAM at rest correlating with mental health measures. We measured at-rest CAM Sympathetic Activity Index (SAI) and Parasympathetic Activity Index (PAI) ratio (SAI / PAI) to predict mental health measures. The short-form - 18 - SG Docket No.: 14947-700.600McGill Pain Questionnaire (SF-MPQ-2) assesses both neuropathic and non-neuropathic pain conditions, while the PTSD Checklist for DSM5 (PCL-5) measures the presence and severity of PTSD symptoms. Higher scores on both the SF-MPQ-2 and PCL-5 indicate greater severity of pain and PTSD symptoms, respectively. These findings indicate that more sympathetic-driven individuals tend to have more severe pain and PTSD symptoms.

[0078] FIGS. 12A-12D show mental health measures as a function of the ANG change ratio. The ANG change ratio represents the neural activity measured at 2 hours post-LPS injection normalized to baseline activity, which quantifies the acute effect of immune system activation to inflammatory stimuli. It positively correlates with pain / mental / depression / anxiety health scores measured prior to the LPS injection. The shortform McGill Pain Questionnaire (SF-MPQ-2) assesses both neuropathic and non-neuropathic pain conditions. The PTSD Checklist for DSM5 (PCL-5) measures the presence and severity of PTSD symptoms. The Beck Anxiety Inventory score (BAI-score) measures the severity of physical and cognitive anxiety symptoms experienced over the past week, while the Beck’s Depression Inventory (BDI-v2) assesses the severity of depression symptoms over a two-week period. These findings suggest that individuals with pre-existing conditions of pain, PTSD, anxiety, and depression demonstrate heightened inflammatory responses of greater intensity and acuity.

[0079] FIGS. 13A-13H show multivariate regression results estimating mental health measures using resting-state CAM data and ANG neural activity changes (pre-to-post LPS injection) as predictors, analyzed via ordinary least squares (OLS) regression. FIGS. 13A-B, C-D, E-F, and G-H showed the multivariate results for SF-MPQ2, PCL-5, BAI-score and BDI-v2 correspondingly. The short-form McGill Pain Questionnaire (SF-MPQ-2) assesses both neuropathic and non-neuropathic pain conditions. The PTSD Checklist for DSM5 (PCL-5) measures the presence and severity of PTSD symptoms. The Beck Anxiety Inventory score (BAI-score) measures the severity of physical and cognitive anxiety symptoms experienced over the past week, while the Beck’s Depression Inventory (BDI-v2) assesses the severity of depression symptoms over a two-week period. FIGS. 13A, C, E and G showed the coefficient analysis from the OLS regression model. Each subplot displays the estimated coefficient, standard error, and statistical significance of the coefficient. FIGS. 13B, D, F, H are the residual plots visualizing the differences between the model-predicted value and the actual value, along with the coefficient of determination (R2) and the overall model p-value.Multivariate regression achieved statistically significant results for estimating various mental health scores. These findings suggest combining CAM and ANG measurements may improve the robustness of the model’s performance.- 19 - SG Docket No.: 14947-700.600

[0080] FIGS. 14A and 14B demonstrate that resting-state expression levels of miRNAs (miR-126-3p and let-7c-5p) significantly correlate with pain and anxiety scores. These findings suggest that elevated miRNA expression levels are associated with increased severity of mental health symptoms.

[0081] FIGS. 15A and 15B demonstrate that the change ratio of miRNA miR-206, measured at 2 hours post-LPS injection normalized to baseline expression, exhibits a positive correlation with mental health scores. There is evidence for miR-206 contribution to the pathophysiology of depression. This result illustrates that the miRNA change ratio is associated with the severity of mental health symptoms.

[0082] FIG. 16 shows an example computing system configured for performing methods described herein. The computing system includes a computing device 1600, which includes a processor 1601, memory 1603 and input / output interface 1609. The memory 1603 can include various types of information, including data 1605 and computing device executable instructions 1607. The data 1605 can include various types of data, which may be organized in database structures. The data 1605 can include physiological data (e.g., ANG data, CAM data), molecular data (e.g., microRNA data, biomarker data, blood assay data), clinical data (e.g., medical history, lab results), and / or patient-reported data.

[0083] The computing device executable instructions 1607 can be used to interact with the other components of the computing device 1600 and / or one or more external devices (e.g., via network connection) and can be used to store information, such as instructions for manipulating one or more files. The computing device executable instructions 1607 may include instructions for calculating one or more values derived from sense data, molecular data, clinical data and / or patient-reported data (when executed by the processor 1601). For example, the instructions may include instructions for estimating the inflammatory biotype, predicting the mental health, and / or estimating the mental disorder severity of individuals derived from sense data, molecular data, clinical data and / or patient-reported data. This calculated / estimated information may also be stored as data 1605. The computing device executable instructions 1607 may include instructions for presenting information to a user via one or more user interfaces.

[0084] The computing device 1600 can be configured to communicate with one or more external devices via an input / output interface 1609 configured for sending and / or receiving information. For example, the input / output interface 1609 may be configured to communicate with one or more sensing devices (e.g., ANG device, CAM device), one or more external databases (e.g., that stores sense data, molecular data, clinical data and / or patient-reported data) and / or one or more external computing devices 1617 (e.g., that include one or more - 20 - SG Docket No.: 14947-700.600processors). In some examples, the computing device 1600 is configured to receive and / or send information from / to one or more medical databases (e.g., electronic health records). The input / output interface 1609 may be configured for wired and / or wireless communication. The input / output interface 1609 may be configured for communication with a computer network (e.g., local network, wide area network, the Internet). The computing device 1600 may be configured to send / receive information to / from one or more machine learning models (e.g., neural network(s)).

[0085] The input / output interface 1609 may also be configured to send and / or receive information to / from one or more user interfaces devices, such as computer display(s), computer mouse / mice, keyboard(s), touch screens, printer(s), scanner(s), etc.

[0086] 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.

[0087] The process parameters and sequence of 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. The various example methods described and / or illustrated herein may also omit one or more of the steps described or illustrated herein or include additional steps in addition to those disclosed.

[0088] 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.

[0089] 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- 21 - SG Docket No.: 14947-700.600embodiments 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 modules may configure a computing system to perform one or more of the example embodiments disclosed herein.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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 - 22 - SG Docket No.: 14947-700.600processor, volatile memory, non-volatile memory, and / or any other portion of a physical computing device from one form 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] When a feature or element is herein referred to as being “on” another feature or element, it can be directly on the other feature or element or intervening features and / or elements may also be present. In contrast, when a feature or element is referred to as being “directly on” another feature or element, there are no intervening features or elements present. It will also be understood that, when a feature or element is referred to as being “connected”, “attached” or “coupled” to another feature or element, it can be directly connected, attached or coupled to the other feature or element or intervening features or elements may be present. In contrast, when a feature or element is referred to as being “directly connected”, “directly attached” or “directly coupled” to another feature or element, there are no intervening features or elements present. Although described or shown with - 23 - SG Docket No.: 14947-700.600respect to one embodiment, the features and elements so described or shown can apply to other embodiments. It will also be appreciated by those of skill in the art that references to a structure or feature that is disposed “adjacent” another feature may have portions that overlap or underlie the adjacent feature.

[0100] Terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. For example, as used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” and / or “comprising,” when used in this specification, specify the presence of stated features, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof. As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed items and may be abbreviated as “ / ”.

[0101] Spatially relative terms, such as “under”, “below”, “lower”, “over”, “upper” and the like, may be used herein for ease of description to describe one element or feature's relationship to another element(s) or feature(s) as illustrated in the figures. It will be understood that the spatially relative terms are intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures. For example, if a device in the figures is inverted, elements described as “under” or “beneath” other elements or features would then be oriented “over” the other elements or features. Thus, the exemplary term “under” can encompass both an orientation of over and under. The device may be otherwise oriented (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly. Similarly, the terms “upwardly”, “downwardly”, “vertical”, “horizontal” and the like are used herein for the purpose of explanation only unless specifically indicated otherwise.

[0102] Although the terms “first” and “second” may be used herein to describe various features / elements (including steps), these features / elements should not be limited by these terms, unless the context indicates otherwise. These terms may be used to distinguish one feature / element from another feature / element. Thus, a first feature / element discussed below could be termed a second feature / element, and similarly, a second feature / element discussed below could be termed a first feature / element without departing from the teachings of the present invention.

[0103] Throughout this specification and the claims which follow, unless the context requires otherwise, the word “comprise”, and variations such as “comprises” and “comprising” means various components can be co-jointly employed in the methods and - 24 - SG Docket No.: 14947-700.600articles (e.g., compositions and apparatuses including device and methods). For example, the term “comprising” will be understood to imply the inclusion of any stated elements or steps but not the exclusion of any other elements or steps.

[0104] 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.

[0105] 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 value and / 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 sub-ranges 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.

[0106] 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. For example, the order in which various described method steps are performed may often be changed in alternative embodiments, and in other - 25 - SG Docket No.: 14947-700.600alternative embodiments one or more method steps may be skipped altogether. 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.

[0107] 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.- 26 - SG Docket No.: 14947-700.600

Claims

CLAIMSWhat is claimed is:

1. A method of treating a subject’s mental health, the method comprising:recording autonomic neurography (ANG) data and / or cardiac autonomic measure (CAM) data from the subject, wherein recording the ANG data includes recording electrical activity of one or more of the subject’s autonomic nerves, and collecting CAM data includes recording activity of the subject’s heart;assigning an inflammation biotype to the subject based on the ANG data and / or the CAM data;predicting the subject’s response to a treatment of a mental health disorder based on the inflammation biotype; andoutputting the response to the treatment.

2. The method of claim 1, wherein the mental health disorder comprises one or more of: depression, anxiety, and post-traumatic stress disorder (PTSD).

3. The method of claim 1, wherein the treatment includes an anti-inflammatory treatment or a pharmaceutical treatment.

4. A method of assessing a subject’s mental health, the method comprising:recording autonomic neurography (ANG) data and / or cardiac autonomic measure (CAM) data from the subject, wherein recording the ANG data includes recording electrical activity of one or more of the subject’s autonomic nerves, and collecting CAM data includes recording activity of the subject’s heart;assigning an inflammation biotype to the subject based on the ANG data and / or the CAM data;predicting the subject’s mental health based on the inflammation biotype; and outputting the predicted mental health of the subject.

5. The method of any of claims 1-4, wherein recording ANG data comprises non-invasively recording ANG data.

6. The method of any of claims 1-5, wherein recording CAM data comprises non-invasively recording CAM data.

7. The method of any of claims 1-6, wherein recording ANG data and / or CAM data comprises recording both ANG and CAM data.- 27 - SG Docket No.: 14947-700.6008. The method of any of claims 1-7, wherein the ANG data and / or the CAM data are recorded while the subject is at rest.

9. The method of any of claims 1-8, wherein the ANG data and / or the CAM data are recorded while the subject is undergoing an autonomic challenge.

10. The method of any of claims 1-9, wherein assigning the inflammation biotype to the subject includes using a trained neural network, wherein the trained neural network has been trained on previously collected ANG signal data and / or CAM signal data correlated with immune response data from a plurality of subjects.

11. The method of claim 10, wherein immune response data includes cytokine release data after lipopolysaccharide (LPS) administration.

12. The method of claim 11, wherein the previously collected ANG signal data and / or CAM signal data has further been correlated with previously collected molecular biomarker data and / or patient-reported symptom severity data of the plurality of subjects.

13. The method of claim 12, wherein molecular biomarker data includes miRNA analysis data.

14. The method of any of claims 1-13, wherein predicting the subject’s mental health includes estimating a severity of a mental illness.

15. The method of any of claims 1-14, wherein assigning the inflammation biotype includes estimating whether the subject has a high inflammatory risk biotype or a low inflammatory risk biotype, wherein the high inflammatory risk biotype is associated with an individual suffering from a mental illness, and the low inflammatory risk biotype is associated with a mentally health individual.

16. The method of any of claims 1-15, wherein assigning the inflammation biotype includes estimating a severity of a mental illness based on a degree to which the inflammation biotype is high or low, wherein the method further comprises predicting whether the subject would be responsive to an anti-inflammatory treatment based on the estimated severity of the mental illness.

17. The method of claim 16, wherein the anti-inflammatory treatment includes a neuromodulation treatment and / or an anti-inflammatory drug treatment.- 28 - SG Docket No.: 14947-700.60018. The method of claim 17, further comprising providing a recommendation for one or more treatments based on the estimated severity of the mental illness.

19. The method of claims 1-18, wherein the ANG data includes ventral cervical neuronal activity data.

20. The method of claim 19, wherein the ventral cervical neuronal activity includes activity from one or more neural targets including the vagus nerve, the hypoglossal nerve, the sympathetic chain and / or ganglia associated with the vagus nerve, the hypoglossal nerve and the sympathetic chain.

21. The method of claims 1-20, wherein the CAM data includes electrocardiogram (ECG) data, data derived from the ECG data, heart rate (HR) data, and / or heart rate variability (HRV) data.

22. The method of claims 1-21, wherein the subject has already been diagnosed as having a mental disorder prior to determining the inflammation biotype.

23. The method of any of claims 3-22, wherein predicting the subject’s mental health comprises predicting the subject’s response to an anti-inflammatory treatment.

24. A method, the method comprising:recording autonomic neurography (ANG) data and cardiac autonomic measure (CAM) data from the subject, wherein recording the ANG data includes recording electrical activity of one or more of the subject’s autonomic nerves, and collecting CAM data includes recording activity of the subject’s heart;assigning an inflammation biotype to the subject based on the ANG data and the CAM data;predicting the subject’s response to an anti-inflammatory treatment of a mental health disorder based on the inflammation biotype; andoutputting the response to the anti-inflammatory treatment.

25. An apparatus, 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:- 29 - SG Docket No.: 14947-700.600receiving, in the one or more processors, the neural signal and / or the cardiac signal from the one or more sensors recorded from the subject, wherein the neural signal includes an autonomic neurography (ANG) signal corresponding to electrical activity of one or more of the subject’s autonomic nerves, and / or the cardiac signal includes a cardiac autonomic measure (CAM) signal corresponding to recorded activity of the subject’s heart;assigning an inflammation biotype to the subject based on the ANG and / or CAM signals;predicting the subject’s response to an anti-inflammatory treatment of a mental health disorder based on the inflammation biotype; andoutputting the response to the anti-inflammatory treatment.

26. An apparatus, 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 the one or more processors, the neural signal and / or the cardiac signal from the one or more sensors recorded from the subject, wherein the neural signal includes an autonomic neurography (ANG) signal corresponding to electrical activity of one or more of the subject’s autonomic nerves, and / or the cardiac signal includes a cardiac autonomic measure (CAM) signal corresponding to recorded activity of the subject’s heart;assigning an inflammation biotype to the subject based on the ANG and / or CAM signals;predicting the subject’s mental health based on the inflammation biotype; and outputting a notification of the predicted mental health of the subject.

27. The apparatus of any of claims 25-26, wherein recording ANG data comprises non- invasively recording ANG data.

28. The apparatus of any of claims 25-27, wherein recording CAM data comprises non- invasively recording CAM data.- 30 - SG Docket No.: 14947-700.60029. The apparatus of any of claims 25-28, wherein recording ANG data and / or CAM data comprises recording both ANG and CAM data.

30. The apparatus of any of claims 25-29, wherein assigning the inflammation biotype to the subject includes using a trained neural network, wherein the trained neural network has been trained on previously collected ANG signal data and CAM signal data correlated with immune response data from a plurality of subjects.

31. The apparatus of claim 30, wherein immune response data includes cytokine release data after lipopolysaccharide (LPS) administration.

32. The apparatus of claim 30, wherein the previously collected ANG signal data and CAM signal data has further been correlated with previously collected molecular biomarker data and / or patient-reported symptom severity data of the plurality of subjects.

33. The apparatus of claim 32, wherein molecular biomarker data includes miRNA analysis data.

34. The apparatus of any of claims 26-33, wherein predicting the subject’s mental health includes estimating a severity of a mental illness.- 31 - SG Docket No.: 14947-700.600

Images