WO2025014855A2 - Simultaneous direct modulation of sympathetic and parasympathetic nervous systems to improve cardiac function and mitigate cardiac arrhythmias - Google Patents

Abstract

Provided herein is a computer-implemented method of controlling autonomic balance in a patient, including receiving, with at least one processor and from at least one sensor, data relating to autonomic tone in the patient, determining, with at least one processor and based at least in part on a machine learning model applied to the data relating to autonomic tone, whether sympathetic tone in the patient should be decreased and/or parasympathetic tone in the patient should be increased, and delivering, through an implantable device and based at least in part on the determination, stimulation to the patient's sympathetic nervous system and/or parasympathetic nervous system, thereby controlling autonomic balance in the patient.

Description

SIMULTANEOUS DIRECT MODULATION OF SYMPATHETIC AND PARASYMPATHETIC NERVOUS SYSTEMS TO IMPROVE CARDIAC FUNCTION AND MITIGATE CARDIAC ARRHYTHMIAS

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to United States Provisional Patent Application No. 63/512,388 filed July 7, 2023, and United States Provisional Patent Application No. 63/558,845 filed February 28, 2024, the disclosures of which are hereby incorporated by reference in their entireties.

STATEMENT REGARDING FEDERAL FUNDING

[0002]This invention was made with government support under HL136836 and DA049630 awarded by the National Institutes of Health. The government has certain rights in the invention.

BACKGROUND OF THE INVENTION

Field of the Invention

[0003] Provided herein are systems and methods for controlling autonomic balance, including to improve cardiac function, to mitigate cardiac arrhythmias, to treat malfunctioning cardiac autonomous nervous systems (CANS), and/or to treat heart disease or heart failure in patients.

Description of the Related Art

[0004] Autonomic imbalance in cardiac patients with myocardial ischemia, myocardial infarction, ventricular arrhythmias, and heart failure may be caused by sympathoexcitation and parasympathetic dysfunction. In this case, sympathoinhibitory neuromodulation techniques such as spinal cord stimulation (SCS), stellate ganglion block (SGB), and thoracic epidural anesthesia (TEA) decrease the sympathoexcitation, and other parasympathetic activation therapies, such as vagus nerve stimulation (VNS), tragus nerve stimulation (TS), or baroreflex activation therapy (BAT) increases the parasympathetic tone. See, e.g., Kuwabara et al., 2024. Pharmacologic, Surgical, and Device-Based Cardiac Neuromodulation. Cardiac Electrophysiology Clinics.

[0005] The rationale behind using sympathoinhibitory techniques or parasympathetic activation techniques alone is that the cardiac autonomic nervous system (CANS) would balance autonomic tone by the reciprocal control of cardiac vagal and sympathetic nervous system. Therefore, when SCS decreases the sympathetic tone, CANS increases the parasympathetic tone, and when VNS increases the parasympathetic tone, CANS decreases the sympathetic tone. However, this mechanism is not complete because of two reasons.

[0006] First, four patterns of autonomic responses could be observed: i) a reciprocal pattern of low cardiac vagal and high sympathetic discharges, ii) a reciprocal pattern of high cardiac vagal and low sympathetic discharges, iii) a nonreciprocal pattern of response in which activity of both parasympathetic and sympathetic efferent are increased, iv) a non-reciprocal pattern in which discharges of both parasympathetic and sympathetic nerves are depressed. See, e.g., Kollai et al., Reciprocal and nonreciprocal action of the vagal and sympathetic nerves innervating the heart. J Auton Nerv Syst 1 , 33-52 (1979), Koizumi et al., Control of reciprocal and non-reciprocal action of vagal and sympathetic efferents: study of centrally induced reactions. J Auton Nerv Syst 3, 483-501 (1981 ), and Paton etal., The yin and yang of cardiac autonomic control: vago-sympathetic interactions revisited. Brain Res Brain Res Rev 49, 555-565 (2005).

[0007] Second, one major impact of SCS and VNS that is ignored is modulation of the afferent pathway directly by direct electrical stimulation and indirectly through the reflex of the cardiac sensory neurons to the impact of the neuromodulation technique on the heart. Although the impact of the afferent modulation and the resulted efferent response have been studied at length, no one is certain how the afferent modulation translates to the modulation of the autonomic tone.

[0008] Accordingly, there is a need in the art for a method and/or device that would simultaneously control both sympathetic and parasympathetic tone and adjust its parameters based on a patient’s autonomic state.

SUMMARY

[0009] Provided herein is a computer-implemented method of controlling autonomic balance in a patient, including receiving, with at least one processor and from at least one sensor, data relating to autonomic tone in the patient, determining, with at least one processor and based at least in part on a machine learning model applied to the data relating to autonomic tone, whether sympathetic tone in the patient should be increased and/or decreased and/or parasympathetic tone in the patient should be increased and/or decreased, and delivering, through an implantable device and based at least in part on the determination, stimulation to the patient’s sympathetic nervous system and/or parasympathetic nervous system, thereby controlling autonomic balance in the patient.

[0010] Also provided herein is a system for controlling autonomic balance in a patient, including an implantable device, at least one sensor configured to receive data relating to autonomic tone in the patient, and at least one processor programmed to receive, from the at least one sensor, the data relating to autonomic tone in the patient, determine, based at least in part on a machine learning model applied to the data relating to autonomic tone, whether sympathetic tone in the patient should be decreased and/or parasympathetic tone in the patient should be increased, and based at least in part on the determination, cause the implantable device to deliver stimulation to the patient’s sympathetic nervous system and/or parasympathetic nervous system, thereby controlling autonomic balance in the patient.

[0011] Further embodiments or aspects are set forth in the following numbered clauses:

[0012] Clause 1 : A computer-implemented method of controlling autonomic balance in a patient, comprising: receiving, with at least one processor and from at least one sensor, data relating to autonomic tone in the patient; determining, with at least one processor and based at least in part on a machine learning model applied to the data relating to autonomic tone, whether: sympathetic tone in the patient should be decreased; and/or parasympathetic tone in the patient should be increased, and delivering, through an implantable device and based at least in part on the determination, stimulation to the patient’s sympathetic nervous system and/or parasympathetic nervous system, thereby controlling autonomic balance in the patient.

[0013] Clause 2: The computer-implemented method of clause 1 , wherein the at least one sensor comprises an electrocardiogram (ECG) sensor, and the data relating to autonomic tone is one or more parameters derivable from an ECG signal.

[0014] Clause 3: The computer-implemented method of clause 1 or clause 2, wherein the one or more parameters is the patient’s heart-rate variability.

[0015] Clause 4: The computer-implemented method of any of clauses 1 -3, wherein the at least one sensor comprises a blood pressure sensor, and the data relating to autonomic tone is the patient’s blood pressure.

[0016] Clause 5: The computer-implemented method of any of clauses 1 -4, wherein the implantable device is configured to deliver stimulation to one or more of the patient’s spinal cord, sympathetic chain, renal sympathetic nerve, carotid sinus, brain sympathetic pathway, and/or cardiac nervous system sympathetic pathway.

[0017] Clause 6: The computer-implemented method of any of clauses 1 -5, wherein the implantable device is configured to deliver stimulation to one or more of the patient’s vagus nerve, tragus nerve, baroreceptors, and/or brain parasympathetic pathway.

[0018] Clause 7: The computer-implemented method of any of clauses 1 -6, wherein the determination is further based at least in part on an application of the machine learning model to: data relating to medications taken by the patient; and/or data relating to a diagnosis of the patient.

[0019] Clause 8: The computer-implemented method of any of clauses 1 -7, wherein the machine learning model is a classification machine learning model.

[0020] Clause 9: The computer-implemented method of any of clauses 1 -8, wherein the implantable device delivers electrical stimulation, ultrasound stimulation, magnetic stimulation, and/or pharmacological stimulation to the patient’s sympathetic nervous system and/or parasympathetic nervous system.

[0021] Clause 10: The computer-implemented method of any of clauses 1 -9, wherein the implantable device is configured to deliver electrical stimulation to the patient’s sympathetic nervous system and parasympathetic nervous system.

[0022] Clause 1 1 : The computer-implemented method of any of clauses 1 -10, wherein the implantable device is configured to deliver electrical pulses to the patient’s sympathetic nervous systems at a frequency of 1 kHz, and wherein the pulses have a pulse width of 30 ps and an intensity of 90% of a maximum tolerated amplitude.

[0023] Clause 12: The computer-implemented method of any of clauses 1 -1 1 , wherein the implantable device is configured to deliver electrical pulses to the patient’s parasympathetic nervous system at a frequency of 5 Hz, and wherein the pulses have a pulse width of 250 ps and an intensity of 90% of a maximum tolerated amplitude.

[0024] Clause 13: The computer-implemented method of any of clauses 1 -12, further comprising: determining with at least one processor and based at least in part on the data relating to autonomic tone, that the patient is or is likely to experience an adverse event; and triggering, with at least one processor, an alarm.

[0025] Clause 14: A system for controlling autonomic balance in a patient, comprising: an implantable device; at least one sensor configured to receive data relating to autonomic tone and/or a condition of the nervous system (e.g., biomarkers) in the patient; and at least one processor programmed to: receive, from the at least one sensor, the data relating to autonomic tone in the patient; determine, based at least in part on a machine learning model applied to the data relating to autonomic tone, whether: sympathetic tone in the patient should be decreased; and/or parasympathetic tone in the patient should be increased; and based at least in part on the determination, cause the implantable device to deliver stimulation to the patient’s sympathetic nervous system and/or parasympathetic nervous system, thereby controlling autonomic balance in the patient.

[0026] Clause 15: The system of clause 14, wherein the at least one processor is external to the patient.

[0027] Clause 16: The system of clause 14 or clause 15, wherein the at least one sensor comprises an electrocardiogram (ECG) sensor, and the data relating to autonomic tone is one or more parameters derivable from an ECG signal.

[0028] Clause 17: The system of any of clauses 14-16, wherein the one or more parameters is the patient’s heart-rate variability.

[0029] Clause 18: The system of any of clauses 14-17, wherein the at least one sensor comprises a blood pressure sensor, and the data relating to autonomic tone is the patient’s blood pressure.

[0030] Clause 19: The system of any of clauses 14-18, wherein the implantable device is configured to deliver electrical stimulation, ultrasound stimulation, magnetic stimulation, optical stimulation, and/or pharmacological stimulation to the patient’s sympathetic nervous system and/or parasympathetic nervous system.

[0031] Clause 20: The system of any of clauses 14-19, wherein the implantable device is configured to deliver electrical stimulation to the patient’s sympathetic nervous system and parasympathetic nervous system.

[0032] Clause 21 : The system of any of clauses 14-20, wherein the implantable device is configured to deliver stimulation to one or more of the patient’s spinal cord, sympathetic chain, renal sympathetic nerve, carotid sinus, brain sympathetic pathway, and/or cardiac nervous system sympathetic pathway.

[0033] Clause 22: The system of any of clauses 14-21 , wherein the implantable device is configured to deliver stimulation to one or more of the patient’s vagus nerve, tragus nerve, baroreceptors, brain parasympathetic pathway, cardiac nervous system parasympathetic pathway, and/or brain parasympathetic pathway. [0034] Clause 23: The system of any of clauses 14-22, wherein the implantable device is a pulse generator, and further comprises at least two leads or cuffs, at least one lead or cuff configured to be placed in proximity to one or more of the patient’s spinal cord, sympathetic chain, renal sympathetic nerve, carotid sinus, brain sympathetic pathway, and/or cardiac nervous system sympathetic pathway and at least one lead or cuff configured to be placed in proximity to the patient’s vagus nerve, tragus nerve, baroreceptors, brain parasympathetic pathway, cardiac nervous system parasympathetic pathway, and/or brain parasympathetic pathway.

[0035] Clause 24: The system of any of clauses 14-23, wherein the at least one processor is further programmed to determine that sympathetic tone in the patient should be decreased and/or parasympathetic tone in the patient should be increased based at least in part on application of the machine learning model to: data relating to medications taken by the patient; and/or data relating to a diagnosis of the patient.

BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Additional advantages and details of the methods and devices are explained in greater detail below with reference to the exemplary embodiments and aspects, and the following figures in which:

[0037] FIG. 1 shows a schematic describing autonomic imbalance in a patient and adverse events specific to the cardiac system;

[0038] FIG. 2 shows a schematic representation of neural connections between the central nervous system and the heart;

[0039] FIGS. 3A-3B show (3A) a schematic of a closed loop of a device according to nonlimiting embodiments described herein and (3B) a schematic of components of a device for neuromodulation according to non-limiting embodiments described herein;

[0040] FIG. 4 is a schematic diagram of example components of one or more devices of FIG. 3B, according to non-limiting embodiments described herein;

[0041] FIG. 5 shows a diagram of a closed-loop, multimodal, artificial intelligence-assisted neuromodulation device to treat heart failure according to non-limiting embodiments described herein;

[0042] FIG. 6 shows a proposed neuromodulation approach with a device according to non-limiting embodiments described herein; and [0043] FIG. 7 shows a table that compares a device according to non-limiting embodiments described herein (top row) with currently-available neuromodulation devices.

DESCRIPTION OF THE INVENTION

[0044] The use of numerical values in the various ranges specified in this application, unless expressly indicated otherwise, are stated as approximations as though the minimum and maximum values within the stated ranges are both preceded by the word "about". In this manner, slight variations above and below the stated ranges can be used to achieve substantially the same results as values within the ranges. Also, unless indicated otherwise, the disclosure of these ranges is intended as a continuous range including every value between the minimum and maximum values. For definitions provided herein, those definitions refer to word forms, cognates and grammatical variants of those words or phrases.

[0045] The figures accompanying this application are representative in nature, and should not be construed as implying any particular scale or directionality, unless otherwise indicated. For purposes of the description hereinafter, the terms “upper”, “lower”, “right”, “left”, “vertical”, “horizontal”, “top”, “bottom”, “lateral”, “longitudinal” and derivatives thereof shall relate to the invention as it is oriented in the drawing figures. However, it is to be understood that the invention may assume various alternative variations and step sequences, except where expressly specified to the contrary. Hence, specific dimensions and other physical characteristics related to the embodiments disclosed herein are not to be considered as limiting.

[0046] As used herein, the term “comprising” and like terms are open-ended. The term “consisting essentially of” limits the scope of a claim to the specified materials or steps and those that do not materially affect the basic and novel characteristics of the claimed invention. The term “consisting of” excludes any element, step, or ingredient not specified in the claim.

[0047] As used herein, the terms “a” and “an” refer to one or more.

[0048] As used herein, the term “patient” is any mammal, including humans, and a “human patient” is any human.

[0049] As used herein, the term "computing device" may refer to one or more electronic devices configured to process data. A computing device may, in some examples, include the necessary components to receive, process, and output data, such as a processor, a display, a memory, an input device, a network interface, and/or the like. A computing device may be a mobile device. As an example, a mobile device may include a cellular phone (e.g., a smartphone or standard cellular phone), a portable computer, a wearable device (e.g., watches, glasses, lenses, clothing, and/or the like), a personal digital assistant (PDA), and/or other like devices. A computing device may also be a desktop computer or other form of non-mobile computer.

[0050] As used herein, the terms “communication” and “communicate” refer to the receipt, transmission, or transfer of one or more signals, messages, commands, or other type of data. For one unit or device to be in communication with another unit or device means that the one unit or device is able to receive data from and/or transmit data to the other unit or device. A communication can use a direct or indirect connection, and can be wired and/or wireless in nature. Additionally, two units or devices can be in communication with each other even though the data transmitted can be modified, processed, routed, etc., between the first and second unit or device. For example, a first unit can be in communication with a second unit even though the first unit passively receives data and does not actively transmit data to the second unit. As another example, a first unit can be in communication with a second unit if an intermediary unit processes data from one unit and transmits processed data to the second unit. It will be appreciated that numerous other arrangements are possible. Any known electronic communication protocols and/or algorithms can be used such as, for example, TCP/IP (including HTTP and other protocols), WLAN (including 802.11 a/b/g/n and other radio frequency-based protocols and methods), analog transmissions, Global System for Mobile Communications (GSM), 3G/4G/LTE, BLUETOOTH, ZigBee, EnOcean, TransferJet, Wireless USB, and the like known to those of skill in the art.

[0051] As used herein, “electrical communication,” for example in the context of transmitting electrical pulses from a pulse generator to an electrode refers to sending an electrical pulse produced by a pulse generator to a skin surface electrode, an electrode lead, a magnetic coil, or like devices capable of generating electrical current to stimulate a nerve or neuron as described herein, typically through an electrically conductive lead, such as a wire.

[0052] Heart failure (HF) is a chronic medical condition in which the heart becomes weakened and unable to pump blood efficiently to meet the body's demands and requires long-term management and treatment. According to the Heart Failure Society of America (HFSA), HF affects 6.5 million Americans over the age of 20 and while HF can occur in individuals of various ages, HF is more prevalent among older adults who have high mortality risk.

[0053] The problem is of great significance to the affected population as HF severely impacts their daily lives, causing debilitating symptoms such as fatigue, shortness of breath, and fluid retention (Albert et al., Signs and symptoms of heart failure: are you asking the right questions? American Journal of Critical Care 19, 443-452 (2010)). HF often necessitates frequent hospitalizations and is associated with high mortality risk, highlighting the urgency for effective interventions. Currently, the management of HF involves a combination of medication regimens, lifestyle modifications (such as dietary changes and exercise), and implantable devices like pacemakers or defibrillators (Murphy et al., Heart failure with reduced ejection fraction: a review. Jama 324, 488- 504 (2020)). Advanced HF patients may also be considered for heart transplantation or left ventricular assist devices as treatment options. However, these approaches have limitations, and there is a need for innovative strategies to improve outcomes and enhance the quality of life for HF patients.

[0054] Accordingly, provided herein are systems and methods for controlling autonomic balance, including in the cardiac autonomic nervous system (CANS). Systems and methods described herein provide advantages, for example through the algorithms that allow for extraction of actionable data from various physiological parameters of a patient, to allow for more rapid and accurate detection and treatment of autonomic imbalance in a patient. These systems and methods thus improve treatment outcomes in populations where autonomic imbalance is a significant risk, such as, for example, in individuals experiencing cardiac insufficiency and/or heart failure. While such conditions are exemplified herein, those of skill will appreciate that the disclosed systems and methods may be useful in a variety of conditions in which autonomic imbalance may be implicated, for example, heart disease, myocardial ischemia, myocardial infarction, arrhythmias, heart failure, hypotension, hypertension, Autonomic Neuropathy, Parkinson's Disease, Pure Autonomic Failure (PAF), Postural Orthostatic Tachycardia Syndrome (POTS), Diabetic Autonomic Neuropathy, and/or Vasovagal Syncope.

[0055] Turning to FIG. 1 , cardiac sensory neurons sense the failing heart, therefore the cardiac sensory neurons become hyperactive, which in turn ask the cardiac nervous system to increase the sympathetic tone (to increase heart rate and contractility) and decrease the parasympathetic tone (to not decrease the heart rate) as a compensatory mechanism to maintain cardiac output (Grassi et al., Central and peripheral sympathetic activation in heart failure. Cardiovascular Research 1 18, 1857- 1871 (2022)). This compensatory mechanism, which is manifested by autonomic imbalance, is initially functional, however, when the compensatory mechanism becomes persistent, patients can experience many issues, including myocardial remodeling, worsening of the HF symptoms, and initiating fatal ventricular arrhythmias (Grassi etal., Sympathetic activation in congestive heart failure: an updated overview. Heart Failure Reviews 26, 173-182 (2021 )).

[0056] FIG. 2 demonstrates the role of spinal cord stimulation (SCS) in regulating sympathoexcitation. The cardiac sympathetic efferent signaling originates from the preganglionic sympathetic neurons in the intermediolateral (IML) nucleus column of the spinal cord. In the setting of myocardial ischemia, the cardiac sensory neurons are activated in the ischemia region of the heart and this excitatory afferent neurotransmission will result in a reflex efferent sympathoexcitation. The cell bodies of some of the cardiac afferents are located in the upper thoracic dorsal root ganglia and terminate in the dorsal horn (DH) of the spinal cord, and the rest of the cell bodies are located in the nodose ganglia on the vagus nerve which terminates in the brainstem. The DH network connections combined with descending projections from the higher centers control sympathetic preganglionic neuron (SPNs) output in the IML nucleus. Therefore, the sympathetic outflow can be modulated at the level of the spinal cord as a central point by directly or indirectly affecting the SPNs.

[0057] Still referring to FIG. 2, the vagus nerve is the tenth cranial nerve and is the main parasympathetic nerve in the cardiac autonomic nervous system (CANS). The vagus nerve originates from the medulla oblongata and extends through the jugular foramen, then travels into the carotid sheath to the neck, chest, and abdomen, where it innervates the visceral organ. The vagus nerve consists of both afferent (80%) and efferent (20%) fibers. Vagus nerve stimulation (VNS) modulates the vagal afferent and parasympathetic efferent fibers, and VNS directly impacts the parasympathetic tone. VNS also increases the level of acetylcholine (Ach), a neurotransmitter that activates muscarinic receptors to induce negative chronotropic, ionotropic, and dromotropic effects. Neuromodulatory therapies, including VNS, reduce ischemia-driven ventricular arrhythmias. Furthermore, VNS reduces inflammation, decreases production of radical oxygen species, and limits cell apoptosis. Activation of parasympathetic efferent projections to the heart by VNS stabilizes peripheral reflex function. VNS also restores a physiological balance between energy demands and energy supply of the failing myocardium.

[0058] With the foregoing in mind, and turning to FIGS. 3A-3B, shown are schematics of a non-limiting embodiment of a system 1000 for controlling autonomic balance. System 1000 may include a device 100 for delivering stimulation to the sympathetic nervous system (SNS) and/or parasympathetic nervous system (PNS) of a patient by any suitable route. For example, and without limitation, device 100 may provide electrical, ultrasound, magnetic, pharmacological, and/or temperature-based stimulation. While electrical stimulation is exemplified in the attached drawings, those of skill in the art will appreciate that the disclosure is not so limited. Accordingly, while FIG. 3B shows one or more electrode lead(s) 1 10 (which may also be cuffs) in electrical communication with pulse generator(s) 120, it is to be appreciated that one or more lead(s) 1 10 may be one or more leads with magnetic elements at a distal end thereof, to deliver magnetic stimulation, may be one or more heating and/or cooling elements (such as Peltier heaters and/or coolers) for delivering temperature stimulation, may be one or more ultrasound transducers for delivering ultrasound stimulation, and/or may be one or more fluid conduits for delivering pharmacological stimulation, for example, one or more neurotransmitters, receptor agonists and/or antagonists, peptide binding compounds, and/or ion channel blockers/activators as are known in the art.

[0059] In non-limiting embodiments, systems and methods described herein may make use of one or more electrode leads for stimulation and/or for sensing one or more biomarkers. In non-limiting embodiments, useful electrodes may be those configured to permit selective stimulation of one or more discrete regions of various anatomical areas, such that selective stimulation of the SNS and/or PNS are possible. In non-limiting embodiments, electrode leads that are useful for discrete stimulation of various regions of the vagus nerve may be used. Such electrodes may be those suitable for selective vagus nerve stimulation, and are described in, for example, Fitchett et al., Selective neuromodulation of the vagus nerve, Front. Neuroscience, 2021 , 15: 685872. In non-limiting embodiments, useful electrodes may include one or more anodes and one or more cathodes arranged in any useful configuration on the one or more leads, including in discrete regions along a longitudinal axis of the lead, as discrete patches and/or segments (of any suitable shape and size), one or more rings arranged about a circumference of the electrode lead(s), and the like. Those of skill in the art will appreciate that various configurations of anodes and/or cathodes on an electrode lead may be used, to provide discrete stimulation of regions of interest within the CNS and/or PNS, for example the vagus nerve. In non-limiting embodiments, electrodes useful for SCS (e.g., for stimulating the SNS), may be those commercially available from, for example, Boston Scientific, St Jude Medical, and Abbott, including those available under the tradenames Penta, Tripole, Exclaim, Lamitrode, Artisan, Coveredge, and Specify.

[0060] As described above, useful electrode leads may be useful for both delivering stimulation and for detecting one or more biomarkers. For example, an electrode lead may include one or more anodes and/or cathodes for delivering stimulation and may include one or more anodes and/or cathodes for detecting neural activity (e.g., electrical activity), which may be incorporated into one or more algorithms as described herein. For example, neural activity detected by one or more anodes and/or cathodes may be indicative and/or predictive of arrhythmia, and the systems and methods described herein may utilize that information to deliver stimulation to a region of interest (e.g., stimulation of the SNS and/or PNS, as appropriate).

[0061] With continuing reference to FIG. 3B, device 100 may include one or more stimulators 120, though as noted above, stimulator(s) 120 need not be limited to electrical stimulators (e.g., pulse generators), and may also include reservoirs for pharmacological compositions and/or devices for generating magnetic fields, ultrasound waves, and/or temperature differences at desired locations in the SNS and/or PNS. In non-limiting embodiments, device 100 includes processing circuitry 150, which may be configured to receive input data (e.g., physiological data from one or more sensors 140, data relating to one or more medications being taken by a patient being treated with system 1000, and/or data relating to a diagnosis applied to the patient), to process such input data. Received data may be processed by processing circuity 150 (e.g., with an analog to digital converter (ADC), analog front end, and/or signal processing hardware and/or software, and processing circuitry 150 and/or control circuitry 130 may analyze the processed data to determine whether stimulation should be delivered to the SNS and/or PNS.

[0062] Any component of processing circuitry 150 and/or control circuity 130 may include one or more components as shown in FIG. 4 and described herein below. In non-limiting embodiments, physiological data, such as, without limitation, electrocardiogram (ECG) data, blood pressure (BP) data, body temperature data, blood oxygen data, pulse data, and/or the like, is received by control circuitry 130 in the form of an analog signal. This analog signal may be amplified, filtered, and/or processed by an analog front end (AFE), and the amplified, filtered, and/or processed analog data may then be converted to a digital signal by an analog to digital converter (ADC). A signal processor, such as a digital bio-signal processor, may process the converted digital signal, for example, in the case of ECG data, by deriving, isolating, and/or extracting a parameter, such as heart-rate variability (HRV) data, therefrom. As used herein, “HRV data” means the fluctuation in time interval between adjacent heartbeats and includes a fluctuation in interval between adjacent R waves (of the QRS signal of an ECG). Control circuity 130, implementing one or more algorithms and/or learning machine models as described herein (for example, a classification machine learning model), may analyze the derived, isolated, and/or extracted parameter (e.g., HRV data) to determine whether stimulation should be delivered to the SNS, PNS, or both, and control circuity 130 may then cause stimulators (e.g., pulse generators) 120 to deliver stimulation. As noted above, stimulation may be of any suitable modality; however, in non-limiting embodiments, the stimulation is electrical stimulation.

[0063] The electrical stimulation described herein can include electrical pulses that can have any suitable characteristic, so long as the stimulation is effective to achieve the desired physiological response. As such, the terms "electrical stimulation" and "electrical pulses" are used interchangeably herein. As will be recognized by a person of skill in the art, characteristics of the electrical pulses, including, without limitation, amplitude (pulse strength, referring to the magnitude or size of a signal voltage or current), voltage, amperage, duration (e.g., pulsewidth), frequency, polarity, phase, relative timing, and symmetry of positive and negative pulses in biphasic stimulation, and/or wave shape (e.g., square, sine, triangle, sawtooth, or variations or combinations thereof) may be varied in order to provide the desired physiological response. So long as other characteristics of the electrical signals (e.g., without limitation, amplitude, voltage, amperage, duration, polarity, phase, relative timing and symmetry of positive and negative pulses in biphasic stimulation, and/or wave shape) are within useful ranges, modulation of the pulse frequency will achieve the desired physiological response.

[0064] One characteristic of the electrical signals used to produce a desired response, as described above, is the frequency of the electrical pulse. Although effective ranges (e.g., frequencies able to produce a stated effect) may vary from subject-to-subject, and the controlling factor is achieving a desired outcome, certain, non-limiting exemplary ranges may be as follows. In non-limiting embodiments, for example when the stimulation is delivered to the PNS, the frequency does not exceed 10 Hz. In nonlimiting embodiments or aspects, the stimulation is delivered at a frequency of about 0.1 Hz to about 10 Hz, about 1 Hz to about 10 Hz, about 3 Hz to about 10Hz, about 4 Hz to about 10 Hz, about 5 Hz to about 10 Hz, about 6 Hz to about 10 Hz, about 7 Hz to about 10Hz, about 8 Hz to about 10 Hz, about 9 Hz to about 10 Hz, about 1 Hz to about 9 Hz, about 2 Hz to about 8 Hz, about 3 Hz about 7 Hz, about 4 Hz to about 6 Hz, about 5 Hz, and/or about 7 Hz, all values and subranges therebetween inclusive. In non-limiting embodiments, where the stimulation is delivered to the SNS, useful frequencies may range from about 0 Hz to about 1 MHz, in non-limiting embodiments about 100 Hz to about 900 kHz, about 200 Hz to about 800 kHz, about 300 Hz to about 700 kHz, about 400 Hz to about 600 kHz, about 500 Hz to about 500 kHz, about 600 Hz to about 400 kHz, about 700 Hz to about 300 kHz, about 800 Hz to about 200 kHz, about 900 Hz to about 100 kHz, in non-limiting embodiments about 100 Hz to about 1 kHz, about 200 Hz to about 900 Hz, about 300 Hz to about 800 Hz, about 400 Hz to about 700 Hz, about 500 Hz to about 600 Hz, all values and subranges therebetween inclusive. In non-limiting embodiments, the electrical pulses are delivered with a pulse width of about 30 ps to about 250 ps, all values and subranges therebetween inclusive. Stimulation as described herein may be delivered in one or more patterns, for example, burst, continuous, tonic, pulsed, modulated, randomized, and/or sequential stimulation patterns. Stimulation, once delivered, may be delivered for any suitable period, for example, until one or more biomarker(s) indicate that stimulation should be changed (e.g., turned one, turned off, increased, decreased, and/or ramped).

[0065] As indicated above, a characteristic of electrical pulses is their intensity which in a medium of stable or relatively stable resistance, such as mammalian tissue, can be characterized as relating to current (I, typically measured in mA), or voltage (V, typically measured in mV or V), based on Ohm's Law. It should, therefore, be understood that the intensity of the stimulation is a matter of both V and I, and as such, both are increased, e.g., proportionally or substantially proportionally, with increased intensity of stimulation. As such, one characteristic of the pulses is the current that is applied to produce a physiological response. Stimulation of any type (e.g., of the SNS and/or the PNS) can be achieved in a typical range of from about 0Hz to about 1 MHz, with a pulsewidth of about 0 ms to about 10 s, at an intensity of about 0 mA to about 20 mA and/or about 0 V to about 20 V, all subranges and values therebetween inclusive.

[0066] Another characteristic of the intensity of the pulses is voltage. Stimulation can be achieved in a typical range of from 1 mV to 20 V, all subranges and values therebetween inclusive. In non-limiting embodiments or aspects, the stimulation is delivered with electrical pulses having a voltage of from about 0.8 V to about 16 V, about 2 V to about 16 V, about 4 V to about 16 V, about 6 V to about 16 V, about 0.9 V, about 1 V, about 2 V, about 3 V, about 4V, about 6 V, or any subrange or value therebetween.

[0067] In non-limiting embodiments, characteristics of the stimulation delivered to the SNS may be the same as, or different than, characteristics of the stimulation delivered to the PNS. For example, in non-limiting embodiments, stimulation delivered to the SNS may be pulses at a frequency of about 1 kHz, with a pulse width of about 30 ps, with an intensity that is below a maximum tolerated amplitude, for example 80%, 85%, and/or 90% of a maximum tolerated amplitude and/or voltage, in non-limiting embodiments 90% of a sensation threshold. In non-limiting embodiments, stimulation delivered to the PNS may be pulses at a frequency of about 5 Hz, with a pulse width of about 250 ps, with an intensity that is 90% of a maximum tolerated amplitude and/or voltage.

[0068] As indicated above, the waveform of the pulses may vary, so long as the desired physiological response is realized. One skilled in the art will appreciate that other types of electrical stimulation may also be used in accordance with the present invention. Monophasic or biphasic stimuli, or a mixture thereof, may be used. Damage to nerves by the application of an electrical current may be minimized, as is known in the art, by application of biphasic pulses or biphasic waveforms to the nerve(s), as opposed to monophasic pulses or waveforms that can damage nerves in some instances of long-term use. "Biphasic current," "biphasic pulses," or "biphasic waveforms" refer to two or more pulses that are of opposite polarity that may be of equal or substantially equal net charge (hence, biphasic and charge balanced), and may be symmetrical, asymmetrical, or substantially symmetrical. This is accomplished, for example, by applying through an electrode one or more positive pulses, followed by one or more negative pulses, typically of the same amplitude and duration as the positive pulses, or vice versa, such that the net charge applied to the target of the electrode is zero, or approximately zero. For charge-balanced biphasic stimulation, the opposite polarity pulses may have different amplitudes, profiles, or durations, so long as the net applied charge by the biphasic pulse pair (the combination of the positive and negative pulses) is approximately zero.

[0069]The waveform may be of any useful shape, including without limitation: sine, square, rectangular, triangular, sawtooth, rectilinear, pulse, exponential, truncated exponential, or damped sinusoidal. The pulses may increase or decrease over the stimulation period. In non-limiting embodiments, the waveform is rectangular. The pulses may be applied continuously or intermittently as needed. For example, the stimulation may be applied for short intervals (e.g., 1 -10 minutes) or longer intervals (360 minutes or even longer, for example days, weeks, months, or even years) to achieve longer-lasting physiological responses, in terms of hours, days, weeks, months, or years. In aspects, the stimulation is applied for at least 5 minutes. In nonlimiting embodiments, the stimulation is applied for about 1 minute, at 1 -minute intervals (e.g., 1 minute of stimulation, followed by 1 minute of no stimulation). In nonlimiting embodiments, the stimulation is delivered until 5 minutes of total stimulation is delivered. In non-limiting embodiments, intermittent stimulation is followed a period of continuous stimulation. In non-limiting embodiments or aspects, the stimulation is delivered only when the physiological response is desired. In non-limiting embodiments, when the device starts and/or stops delivering stimulation, the stimulation is ramped up and/or down (over a duration of time that is calculated by system 1000 to effectively treat and/or correct autonomic imbalance in the patient), rather than immediately ceasing or turning on to 100% intensity. Without wishing to be bound by the theory, it is believed that the ANS reacts to the neuromodulation therapies via its afferent pathways. This reaction has a higher chance of occurrence if the neuromodulation therapy is turned on or off rapidly. Therefore, in non-limiting embodiments, the stimulation may be ramped over a time interval. This time interval can change based on the patients ANS response to the stimulation initiation and/or cessation. A computing device implementing an artificial intelligence (Al) algorithm as described herein may use autonomic response data from previous stimulation initiation and/or cessation on that patient to alter stimulation tapering duration.

[0070] With continuing reference to FIG. 3, and with reference to FIG. 4, as noted above, any component of control circuity 130 may have one or more elements of device 200 shown in FIG. 4. With regard to FIG. 4, shown is a diagram of example components of a device 200 according to non-limiting embodiments. Device 200 may correspond to any element of FIG. 3, including, as an example, control circuity 130. In some non-limiting embodiments, such systems or devices may include at least one device 200 and/or at least one component of device 200. The number and arrangement of components shown are provided as an example. In some non-limiting embodiments, device 200 may include additional components, fewer components, different components, or differently arranged components than those shown. Additionally, or alternatively, a set of components (e.g., one or more components) of device 200 may perform one or more functions described as being performed by another set of components of device 200.

[0071] As shown in FIG. 4, device 200 may include a bus 202, a processor 204, memory 206, a storage component 208, an input component 210, an output component 212, and a communication interface 214. Bus 202 may include a component that permits communication among the components of device 200. In some non-limiting embodiments, processor 204 may be implemented in hardware, firmware, or a combination of hardware and software. For example, processor 204 may include a processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), etc.), a microprocessor, a digital signal processor (DSP), and/or any processing component (e.g., a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), etc.) that can be programmed to perform a function. Memory 206 may include random access memory (RAM), read only memory (ROM), and/or another type of dynamic or static storage device (e.g., flash memory, magnetic memory, optical memory, etc.) that stores information and/or instructions for use by processor 204.

[0072] With continued reference to FIG. 4, storage component 208 may store information and/or software related to the operation and use of device 200. For example, storage component 208 may include a hard disk (e.g., a magnetic disk, an optical disk, a magneto-optic disk, a solid-state disk, etc.) and/or another type of computer-readable medium. Input component 210 may include a component that permits device 200 to receive information, such as via user input (e.g., a touch screen display, a keyboard, a keypad, a mouse, a button, a switch, a microphone, etc.). Additionally, or alternatively, input component 210 may include a sensor for sensing information (e.g., a global positioning system (GPS) component, an accelerometer, a gyroscope, an actuator, etc.). Sensors useful here may include biochemical sensors, electrochemical sensors, sensors for detecting autonomic tone, senses for detecting sympathetic tone, and/or the like. Output component 212 may include a component that provides output information from device 200 (e.g., a display, a speaker, one or more light-emitting diodes (LEDs), etc.). Communication interface 214 may include a transceiver-like component (e.g., a transceiver, a separate receiver and transmitter, etc.) that enables device 200 to communicate with other devices, such as via a wired connection, a wireless connection, or a combination of wired and wireless connections. Communication interface 214 may permit device 200 to receive information from another device and/or provide information to another device. For example, communication interface 214 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wi-Fi® interface, a cellular network interface, and/or the like.

[0073] Device 200 may perform one or more processes described herein. Device 200 may perform these processes based on processor 204 executing software instructions stored by a computer-readable medium, such as memory 206 and/or storage component 208. A computer-readable medium may include any non-transitory memory device. A memory device includes memory space located inside of a single physical storage device or memory space spread across multiple physical storage devices. Software instructions may be read into memory 206 and/or storage component 208 from another computer-readable medium or from another device via communication interface 214. When executed, software instructions stored in memory 206 and/or storage component 208 may cause processor 204 to perform one or more processes described herein. Additionally, or alternatively, hardwired circuitry may be used in place of or in combination with software instructions to perform one or more processes described herein. Thus, embodiments described herein are not limited to any specific combination of hardware circuitry and software. The term “configured to,” as used herein, may refer to an arrangement of software, device(s), and/or hardware for performing and/or enabling one or more functions (e.g., actions, processes, steps of a process, and/or the like). For example, “a processor configured to” may refer to a processor that executes software instructions (e.g., program code) that cause the processor to perform one or more functions.

[0074] One or more elements of control circuity 130 of device 100 may be received within a housing with, for example, stimulator(s) 120, which may in non-limiting embodiments be implantable or may be external to the patient. In non-limiting embodiments, device 100, including pulse generator(s) 100, electrodes and/or leads 1 10, and one or more components of control circuity 130 is implanted in the patient. In non-limiting embodiments, device 100, including pulse generator(s) 100 and one or more components of control circuity 130 is arranged externally of the patient, while leads and/or cuffs 1 10 are implanted in the patient. In non-limiting embodiments, one or more components of control circuity 130 are in device 100 that is implanted, are in device 100 which is external to the patient, and/or are distributed (e.g., one or more components of control circuity 130 are implanted within patient and one or more components of control circuity 130 are external to the patient).

[0075] In non-limiting embodiments, device 100 is implanted in the patient and includes stimulator(s) 120 to deliver stimulation to electrode lead(s) and/or cuff(s) 1 10, and control circuity 130 is provided in the form of a distinct computing device that may be part of system 1000, such as from a controller app or software on a smartphone, tablet, laptop, personal computer, workstation, server, and/or computer network. In non-limiting embodiments, control circuity 130 is password protected, such that a patient may not alter any stimulation parameters (in non-limiting embodiments, a doctor may access control circuity 130 to update stimulation parameters). In nonlimiting embodiments, control circuitry 130 is configured such that a doctor and/or patient may enter data to be analyzed by control circuity 130, such as an update to medications and/or diagnoses. In non-limiting embodiments, device 100, whether implantable or not, may include one or more power sources, which may be rechargeable, for example through inductive charging.

[0076] In non-limiting embodiments, device 100 may be on communication with one or more computing devices at a healthcare provider, such that if input data is received that is indicative of an adverse event, device 100 may trigger an alarm (e.g., in the form of an audible, visual, and/or tactile indication) at the healthcare provider. Such an alarm may also, or alternatively, be triggered at device 100 or on a computing device used by the patient to control device 100.

[0077] System 1000 allows for simultaneous control of both sympathetic and parasympathetic tone based on the patient’s state (including autonomic state) using, for example, their ECG and/or BP. While ECG, HRV, and BP are exemplified herein, any biomarker indicative of sympathetic and/or parasympathetic tone may be considered useful, including, without limitation, respiratory rate, skin galvanic response, temperature, cardiac output, pre-ejection period, blood volume, adiponectin levels, hormone levels, cytokine levels, neurotransmitter levels, peptide levels, neural activity (including direct neural activity) of any part of the ANS, any hemodynamic parameter, perspiration, and the like. While the foregoing biomarkers relate, primarily, to the ANS as it relates to the cardiac system in the body, those of skill will appreciate that other systems may involve other biomarkers, for example, diuresis as it relates to the renal system. Such other systems and biomarkers are within the scope of the present disclosure. System 1000 allows for restoring the autonomic balance in a patient by simultaneous and direct modulation of the SNS and PNS. The neuromodulatory device can be used to provide autonomic balance in any disease including heart failure, heart diseases, autonomic neuropathy, neurodegenerative disorders, dysautonomia, myocardial ischemia, myocardial infarction, arrhythmias, heart failure, hypotension, hypertension or other autonomic related disease such as Autonomic Neuropathy, Parkinson's Disease, Pure Autonomic Failure (PAF), Postural Orthostatic Tachycardia Syndrome (POTS), Diabetic Autonomic Neuropathy, and/or Vasovagal Syncope.

[0078] The system 1000 uses, in non-limiting embodiments, an Al algorithm, provided in control circuity 130, to identify features associated with autonomic imbalance and may increase and/or decrease sympathetic tone by modulating the spinal cord, for example by causing spinal cord stimulation (SCS) and/or increase and/or decrease parasympathetic tone, for example by activating the PNS, for example by modulating the vagus nerve via vagus nerve stimulation (VNS) to provide autonomic balance. While decreasing sympathetic tone and increasing parasympathetic tone are exemplified herein, those of skill will appreciate that the systems and methods disclosed herein could be used to decrease parasympathetic tone and increase sympathetic tone, for example to treat vasovagal syncope.

[0079] In non-limiting embodiments, the Al algorithm is implemented by control circuitry 130 in one or more modes. In non-limiting embodiments, the Al algorithm is implemented in a training mode, in which In this training time, the Al will monitor the data from one or more biomarkers, for example in real time, and identifies key features in these biomarker(s) that can predict arrhythmias in that patient. For example, the Al might find that if the heart rate is increasing over 100 beat per minute and at the same time the low frequency component of the HRV component is increasing, the chance of having ventricular arrhythmias increases by 200% and that stimulation should be initiated.

[0080] In non-limiting embodiments, the Al algorithm is implemented in a closed-loop mode. In non-limiting embodiments, once the Al receives sufficient data from that patient to identify the key features in the biomarker(s) that can predict the arrhythmias or cardiac events, then the Al will control the stimulations. In non-limiting embodiments, in this mode the Al is still learning the patients ANS response to the stimulation, so the Al can adjust the stimulation parameters including but not limited to the intensity, on/off time, tapering duration, etc. Such learning may be a feature in the Al’s decision in turning the stimulation on and off, and will improve over time based on the data acquisition. For example, if the patient’s ANS reactivity to the stimulation changes over time and/or if the biomarker(s) features changes over time (for instance due to the changes in the patient’s lifestyle), then the Al module will adapt its decision to turn on/off the device, change ramping time, etc., based on the new data from that patient.

[0081] In non-limiting embodiments, the patient is in urgent need of neuromodulation therapy. In such circumstances, instead of going to the training mode, a device/system may switch to a closed-loop, non-AI mode, in which the device will use one or more main biomarker(s) based on physician recommendations (which could be any of the biomarkers that are monitored by the sensors) and will run the stimulation based on changes in that biomarker.

[0082] In non-limiting embodiments, the Al algorithm applies adaptive therapy principles, which means the Al algorithm is constantly measuring a patient's autonomic tone using different biomarkers, such as ECG, BP, and/or temperature, or any parameter described herein, and will deliver the therapy only when the patient needs it, e.g., when the Al algorithm finds a pattern/feature that is associated with autonomic imbalance via biomarkers. Thus, the Al algorithm detects and predicts autonomic imbalance based on each patient's biomarkers. The Al algorithm may be regulated by a controller or computing device, for example with an app (e.g., smartphone, smart device, etc.). In non-limiting embodiments, the Al algorithm analyzes custom architectures combining convolutional and fully connected layers with dropout and regularization. The Al algorithm may use the biomarkers (e.g., ECG, BP, temperature, heartrate, or any other biomarker described herein and/or known to those of skill in the art) and user inputs, such as a patient’s previous medical diagnoses, current and/or past medications, and feedback from physiological parameters, to learn the patientspecific stimulation parameters needed for effective stimulation in order to restore autonomic balance smoothly. As the patient and/or device 100 restores balance, the stimulation intensity will reduce or ultimately power off. The primary mode of the external controller uses a current stimulator with tunable and accurate pulse amplitude, width, frequency, duty cycle, and decay profiles (exponential, alpha) which replicate clinically applied stimulations. In non-limiting embodiments, as the Al algorithm receives and processes more data (for example, using a classification or other machine learning model), such data, and/or analysis and processing thereof, may be stored in memory (as described herein) and used to further refine the machine learning model and the Al algorithm, thus providing an iterative method that increases the speed, sensitivity, and/or accuracy of detecting and responding to changes in sympathetic and/or parasympathetic tone in the patient. In non-limiting embodiments, the Al algorithm is capable of predicting, based on the received data, potential adverse events and stimulates the patient’s SNS and/or PNS to reduce the likelihood of and/or prevent the adverse event.

[0083]Turning to FIGS. 5 and 6, electrode lead(s) and/or cuff(s) 110 may be positioned in any suitable location within the SNS and/or the PNS to provide the physiological effect described herein. In non-limiting embodiments, one or more electrode lead(s) and/or cuffs 1 10 may be arranged to be in proximity to and/or in contact with one or more regions of the patient’s SNS, including one or more of the patient’s spinal cord (e.g., the dorsal root ganglion), sympathetic chain, renal sympathetic nerve, carotid sinus, brain sympathetic pathway, and/or cardiac nervous system sympathetic pathway. In non-limiting embodiments, one or more electrode lead(s) and/or cuffs 1 10 may be arranged to be in proximity to one or more regions of the patient’s PNS, including one or more of the patient’s vagus nerve (e.g., the nodose ganglion), tragus nerve, baroreceptors, and/or brain parasympathetic pathway. In non-limiting embodiments, for example as shown in FIGS. 5 and 6, at least one electrode lead and/or cuff 1 10 is positioned in proximity to and/or in contact with the patient’s spinal cord (e.g., the cervical, lumbar, or sacral spinal cord) and at least one electrode lead and/or cuff is positioned in proximity to and/or in contact with the patient’s vagus nerve. In non-limiting embodiments, device 100 determines whether to provide stimulation to the patient’s spinal cord and/or vagus nerve based on ECG and/or BP data. [0084] With continuing reference to FIGS. 5 and 6, as described above in non-limiting embodiments the vagus nerve and/or spinal cord are monitored, at least indirectly, and/or adjusted in a closed loop system that monitors at least a patient’s BP and/or ECG in real time. The device 100 in and its respective Al algorithm may control stimulation of the spinal cord and/or the vagus nerve, for example simultaneously, to regulate a patient’s sympathetic and parasympathetic tones, respectively, and to treat various diseases or conditions. The Al algorithm may control a patient’s sympathetic and parasympathetic tones by recognizing patterns and features in the patient’s body via the patient’s biomarkers, such as BP, ECG, and temperature. The Al algorithm responds to the patient’s biomarkers by raising or lowering the patient’s sympathetic and parasympathetic tones through the stimulation as described herein.

[0085] Turning to FIG. 7, the device 100 of the present disclosure is compared to other available neuromodulation devices for HF patients. In particular, FIG. 7 compares the devices on the basis of whether each is a closed-loop system, an Al-assisted system, includes sympathetic modulation, includes parasympathetic modulation, and whether the device is implantable. As indicated on FIG. 7, the device of the present disclosure, is the only device listed that meets all of the aforementioned specifications.

[0086] Also provided herein are methods of controlling autonomic balances in a patient, using systems and devices as described herein, for treating one or more conditions in a patient. Suitable conditions treatable by the present systems and devices include those relating to an imbalance in SNS and/or PNS tone. In non-limiting embodiments, the condition is HF, and the system receives data from the patient’s ECG and/or BP. This data may be, in non-limiting embodiments, analyzed to provide the patient’s HRV data, and, based on the patient’s HRV data, stimulation may be delivered through a device (implantable or otherwise) to the patient’s SNS and/or PNS as described herein. In non-limiting embodiments, in determining whether to deliver stimulation to the patient’s SNS and/or PNS, a device as described herein takes into account the patient’s diagnoses, past medications, and/or current medications.

[0087] Stimulation to the patient’s SNS and/or PNS may be delivered by any medium, delivery regimen, and location as described herein. In non-limiting embodiments, a device as described herein may also provide an alarm, to the patient and/or a healthcare professional, concerning data received and/or used in the determination of delivery of stimulation to the patient’s SNS and/or PNS. For example, and without limitation, if received data is indicative of an adverse event, an alarm may be triggered (e.g., an audible, visual, and/or tactile indication), so that the patient seeks medical attention and/or the healthcare professional can deliver an intervention.

[0088] While the present invention is described with reference to several distinct aspects or embodiments, those skilled in the art may make modifications and alterations without departing from the scope and spirit. Accordingly, the above detailed description is intended to be illustrative rather than restrictive.

Claims

THE INVENTION CLAIMED IS:

1. A computer-implemented method of controlling autonomic balance in a patient, comprising: receiving, with at least one processor and from at least one sensor, data relating to autonomic tone in the patient; determining, with at least one processor and based at least in part on a machine learning model applied to the data relating to autonomic tone, whether: sympathetic tone in the patient should be decreased; and/or parasympathetic tone in the patient should be increased, and delivering, through an implantable device and based at least in part on the determination, stimulation to the patient’s sympathetic nervous system and/or parasympathetic nervous system, thereby controlling autonomic balance in the patient.

2. The computer-implemented method of claim 1 , wherein the at least one sensor comprises an electrocardiogram (ECG) sensor, and the data relating to autonomic tone is one or more parameters derivable from an ECG signal.

3. The computer-implemented method of claim 2, wherein the one or more parameters is the patient’s heart-rate variability.

4. The computer-implemented method of claim 1 , wherein the at least one sensor comprises a blood pressure sensor, and the data relating to autonomic tone is the patient’s blood pressure.

5. The computer-implemented method of claim 1 , wherein the implantable device is configured to deliver stimulation to one or more of the patient’s spinal cord, sympathetic chain, renal sympathetic nerve, carotid sinus, brain sympathetic pathway, and/or cardiac nervous system sympathetic pathway.

6. The computer-implemented method of claim 1 , wherein the implantable device is configured to deliver stimulation to one or more of the patient’s vagus nerve, tragus nerve, baroreceptors, and/or brain parasympathetic pathway.

7. The computer-implemented method of claim 1 , wherein the determination is further based at least in part on an application of the machine learning model to: data relating to medications taken by the patient; and/or data relating to a diagnosis of the patient.

8 The computer-implemented method of claim 1 , wherein the machine learning model is a classification machine learning model.

9. The computer-implemented method of claim 1 , wherein the implantable device delivers electrical stimulation, ultrasound stimulation, magnetic stimulation, and/or pharmacological stimulation to the patient’s sympathetic nervous system and/or parasympathetic nervous system.

10. The computer-implemented method of claim 9, wherein the implantable device is configured to deliver electrical stimulation to the patient’s sympathetic nervous system and parasympathetic nervous system.

1 1. The computer-implemented method of claim 10, wherein the implantable device is configured to deliver electrical pulses to the patient’s sympathetic nervous systems at a frequency of 1 kHz, and wherein the pulses have a pulse width of 30 ps and an intensity of 90% of a maximum tolerated amplitude.

12. The computer-implemented method of claim 10 or claim 1 1 , wherein the implantable device is configured to deliver electrical pulses to the patient’s parasympathetic nervous system at a frequency of 5 Hz, and wherein the pulses have a pulse width of 250 ps and an intensity of 90% of a maximum tolerated amplitude.

13. The computer-implemented method of claim 1 , further comprising: determining with at least one processor and based at least in part on the data relating to autonomic tone, that the patient is or is likely to experience an adverse event; and triggering, with at least one processor, an alarm.

14. A system for controlling autonomic balance in a patient, comprising: an implantable device; at least one sensor configured to receive data relating to autonomic tone in the patient; and at least one processor programmed to: receive, from the at least one sensor, the data relating to autonomic tone in the patient; determine, based at least in part on a machine learning model applied to the data relating to autonomic tone, whether: sympathetic tone in the patient should be decreased; and/or parasympathetic tone in the patient should be increased; and based at least in part on the determination, cause the implantable device to deliver stimulation to the patient’s sympathetic nervous system and/or parasympathetic nervous system, thereby controlling autonomic balance in the patient.

15. The system of claim 14, wherein the at least one processor is external to the patient.

16. The system of claim 14 or claim 15, wherein the at least one sensor comprises an electrocardiogram (ECG) sensor, and the data relating to autonomic tone is one or more parameters derivable from an ECG signal.

17. The system of claim 16, wherein the one or more parameters is the patient’s heart-rate variability.

18. The system of claim 14, wherein the at least one sensor comprises a blood pressure sensor, and the data relating to autonomic tone is the patient’s blood pressure.

19. The system of claim 14, wherein the implantable device is configured to deliver electrical stimulation, ultrasound stimulation, magnetic stimulation, optical stimulation, and/or pharmacological stimulation to the patient’s sympathetic nervous system and/or parasympathetic nervous system.

20. The system of claim 14, wherein the implantable device is configured to deliver electrical stimulation to the patient’s sympathetic nervous system and parasympathetic nervous system.

21. The system of claim 14, wherein the implantable device is configured to deliver stimulation to one or more of the patient’s spinal cord, sympathetic chain, renal sympathetic nerve, carotid sinus, brain sympathetic pathway, and/or cardiac nervous system sympathetic pathway.

22. The system of claim 14, wherein the implantable device is configured to deliver stimulation to one or more of the patient’s vagus nerve, tragus nerve, baroreceptors, brain parasympathetic pathway, cardiac nervous system parasympathetic pathway, and/or brain parasympathetic pathway.

23. The system of claim 14, wherein the implantable device is a pulse generator, and further comprises at least two leads or cuffs, at least one lead or cuff configured to be placed in proximity to one or more of the patient’s spinal cord, sympathetic chain, renal sympathetic nerve, carotid sinus, brain sympathetic pathway, and/or cardiac nervous system sympathetic pathway and at least one lead or cuff configured to be placed in proximity to the patient’s vagus nerve, tragus nerve, baroreceptors, brain parasympathetic pathway, cardiac nervous system parasympathetic pathway, and/or brain parasympathetic pathway.

24. The system of claim 14, wherein the at least one processor is further programmed to determine that sympathetic tone in the patient should be decreased and/or parasympathetic tone in the patient should be increased based at least in part on application of the machine learning model to: data relating to medications taken by the patient; and/or data relating to a diagnosis of the patient.