Systems and methods for non-invasive transcutaneous pressure wave delivery for gastrointestinal mechanoreceptor stimulation
Patent Information
- Application Number
- PCT/IB2026/000177
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-03-27
- Filing Date
- 2026-03-25
- Publication Date
- 2026-10-01
Smart Images
Figure IB2026000177_01102026_PF_FP_ABST
Abstract
Description
Docket No. 233659-010301ZPCT Electronically Filed: March 25, 2026 SYSTEMS AND METHODS FOR NON-INVASIVE TRANSCUTANEOUS PRESSURE WAVE DELIVERY FOR GASTROINTESTINAL MECHANORECEPTOR STIMULATIONCROSS-REFERENCE TO RELATED APPLICATIONS
[0001] This application claims the benefit of priority from U.S. Provisional Application No.63 / 778,702, filed March 27, 2025, which is incorporated herein by reference in its entirety.FIELD OF THE DISCLOSURE
[0002] The present disclosure relates to non-invasive medical device systems and methods, and more particularly to systems and methods for generating and delivering controlled pressure wave pulses transcutaneously to stimulate peripheral mechanoreceptors within the gastrointestinal tract to induce satiety.SUMMARY OF THE DISCLOSURE
[0003] The present disclosure provides systems and methods for non-invasive transcutaneous energy transfer configured to deliver controlled pressure wave pulses through the skin and underlying tissues of a user to stimulate peripheral mechanoreceptors within the gastrointestinal tract to induce an illusory satiety signal without surgical intervention or pharmacological treatment.
[0004] In some embodiments, the system includes a wave generation module mountable to the anterior torso of a user. In some embodiments, the wave generation module includes a pressure wave generator configured to be positioned at the abdominal region of the user to direct wave energy toward the stomach, small intestine, large intestine, or any combination thereof. Nonlimiting form factors include attachable, digestible, implantable, or insertable versions. The system may include wireless communication capability to communicate and transfer data to an external device such as a phone or computer.
[0005] In some embodiments, the system includes a sensor module co-mounted to the user opposite the pressure wave generator that is configured to measure the energy’ level of the pressure wave pulse as it passes through the stomach and other tissues and exits the body. The sensor module enables closed-loop operation of the system by calculating the amount of damping within the body, allowing the system to operate with optimal parameter values. The closed-loop monitoring system continuously evaluates treatment effectiveness, collects relevant data, and automatically adjusts parameters to optimize outcomes while also tracking patient compliance.Docket No. 233659-010301ZPCT Electronically Filed: March 25, 2026
[0006] In some embodiments, a plurality of pressure wave generators may be arranged in a module array, positioned at vertically spaced locations along the anterior torso, or distributed circumferentially around the torso, enabling simultaneous or sequential stimulation of multiple mechanoreceptor sites, convergence of multiple lower-amplitude signals on a single target location, or both. The system facilitates flexible transducer positioning anywhere on the user to address mechanoreceptors distributed across the gastrointestinal tract in any combination.
[0007] In some embodiments, the pressure wave generator delivers pressure wave pulses with controlled parameters including waveform shape, amplitude, pulse width, and repetition frequency. These parameters are selected such that the wave pulse does not damage any of the tissues it passes through while generating sufficient strain on the mechanoreceptors in the stomach and intestinal walls to trigger an illusory satiety signal. Pulse parameters may remain constant during operation or may vary stepwise or continuously within a desired range. The system is configured to operate within a mechanoreceptor activation band, remaining below the threshold at which mechanonociceptive fibers may be recruited.
[0008] In some embodiments, pressure wave pulses propagate through participation media comprising skin, fat layer, and muscle layer as pressure waves or shear waves depending on the tissue composition along the wave path and the propagation advantages offered by each modality7for a given target geometry7. The contact surface geometry7of the pressure wave generator interface is selectable among various geometries, such as flat, convex, concave, and aspheric geometries to shape the emitted wavefront and direct energy toward internal body structures via seismic waves or toward surface structures via surface waves.
[0009] In some embodiments, the system delivers controlled energy across ultrasonic, radiofrequency, and microwave frequency domains. The system may implement phased array technology to achieve dynamic focusing and beam steering, enabling treatment area coverage without mechanical repositioning. Prior to energy delivery, the system may perform treatment planning based on patient-specific anatomical data, simulating wave propagation through heterogeneous tissue structures to estimate energy distribution and establish safety7margins based on tissue type.
[0010] In some embodiments, the system includes a smart adaptive subsystem configured to monitor, analyze, and modify eating behaviors through multimodal sensing and intelligent intervention operating on a closed-loop paradigm of detection, monitoring, intervention, and adaptation. The adaptive subsystem may include electromyographic sensors, stretch sensors, acoustic monitoring, and / or movement pattern recognition to detect eating initiation, and applies progressive intervention mechanisms including haptic feedback, auditory alerts, andDocket No. 233659-010301ZPCT Electronically Filed: March 25, 2026 parameter adjustments based on a continuously updated personalized behavioral model. In some embodiments, system execution involves calling and executing an artificial intelligence and / or machine learning model to support planning, real-time analysis, and dynamic adjustment of system parameters.
[0011] In some embodiments, the system is configured to execute independent thermal monitoring, continuous tissue impedance monitoring, real-time cavitation detection, patient movement detection with automatic beam adjustment, and comprehensive error detection. Power modulation occurs in response to measured tissue temperatures via proportionalintegral-derivative control loops, with automatic termination protocols activated when safety7thresholds are exceeded. All safety events are logged for subsequent analysis.
[0012] Energy transfer by wave propagation may further be used to activate or enhance the effect of medicines previously transported to a target location within the body, or to energize, charge, or reposition implants placed within the body, extending the therapeutic utility of the system beyond satiety7induction to a broad range of clinical applications.DESCRIPTIONS OF THE DRAWINGS
[0013] The features and advantages of the disclosure will be apparent from the following description of embodiments as illustrated in the accompanying drawings, in which reference characters refer to the same parts throughout the various views. The drawings are not necessarily to scale, emphasis instead being placed upon illustrating principles of the disclosure:
[0014] FIG. 1 illustrates three configurations for retaining a pressure wave generator on the anterior torso of a user, in accordance with some embodiments of the present disclosure;
[0015] FIG. 2 depicts a closed-loop configuration incorporating a pressure wave sensor module co-mounted with a pressure wave generator, in accordance with some embodiments of the present disclosure;
[0016] FIG. 3 shows a multi-module array of pressure wave generators at the abdominal region of a user, in accordance with some embodiments of the present disclosure;
[0017] FIG. 4 depicts multiple pressure wave generators distributed circumferentially around the torso with wave paths converging at an internal target, in accordance with some embodiments of the present disclosure;
[0018] FIG. 5 illustrates pressure wave generators individually mounted at vertically spaced positions along the anterior torso, in accordance with some embodiments of the present disclosure;Docket No. 233659-010301ZPCT Electronically Filed: March 25, 2026
[0019] FIG. 6A depicts the mechanoreceptor transduction pathway targeted by the system, in accordance with some embodiments of the present disclosure;
[0020] FIG. 6B illustrates an amplitude to activate a mechanoreceptor, in accordance with some embodiments of the present disclosure;
[0021] FIG. 6C illustrates a pulse width for mechanoreceptor activation, in accordance with some embodiments of the present disclosure;
[0022] FIG. 7 depicts propagation of a pressure wave pulse through participation media tow ard a target mechanoreceptor, in accordance with some embodiments of the present disclosure;
[0023] FIG. 8A shows a bench test setup establishing a free-field baseline measurement, in accordance with some embodiments of the present disclosure;
[0024] FIG. 8B illustrates a bench test setup configured to establish an unattenuated reference signal, in accordance with some embodiments of the present disclosure;
[0025] FIG. 8C depicts a bench test setup measuring attenuation and damping through a tissue specimen, in accordance with some embodiments of the present disclosure;
[0026] FIG. 9 shows a dispersion test setup for quantifying waveform deformation across a tissue specimen, in accordance with some embodiments of the present disclosure;
[0027] FIG. 10A illustrates a first non-limiting pressure wave generator source utilizing a rotating cam and cantilever beam, in accordance with some embodiments of the present disclosure;
[0028] FIG. 10B depicts a second non-limiting pressure wave generator source utilizing a piezoelectric film and cantilever beam, in accordance with some embodiments of the present disclosure;
[0029] FIG. 10C shows a third non-limiting pressure w ave generator source utilizing a ceramic piezoelectric element, in accordance with some embodiments of the present disclosure;
[0030] FIG. 11 illustrates four non-limiting contact surface geometries for a pressure wave generator plunger, in accordance with some embodiments of the present disclosure;
[0031] FIG. 12A depicts a three-source transverse cross-section with wave paths converging at an internal target, in accordance with some embodiments of the present disclosure;
[0032] FIG. 12B shows a single-source mechanoreceptor impulse response demonstrating viscoelastic integration, in accordance wdth some embodiments of the present disclosure; and
[0033] FIG. 12C illustrates the cumulative mechanoreceptor response to multi-source wave delivery, in accordance with some embodiments of the present disclosure.DETAILED DESCRIPTIONDocket No. 233659-010301ZPCT Electronically Filed: March 25, 2026
[0034] Obesity is one of the most common and important health problems today. In addition to being a psychological and physiological health problem in itself, it is one of the main causes of many other health problems. Obesity is still being treated with a wide variety' of methods. Classical, endoscopic and laparoscopic surgical interventions, drug therapies and traditional treatments such as acupuncture are a few examples. The instant disclosure relates to a system that can be used in the treatment of obesity’ and does not involve any surgical procedure or medication. The working principle of the system is to create an illusory satiety in patients so that they do not feel hungry and eat less.
[0035] Accordingly, in some embodiments, the disclosed systems and methods provide an Energy Transfer Medical Device System (ETMDS; “the system"’) that provides targeted energy transfer to specific locations within the human body through controlled wave propagation. This framework integrates advanced hardware components with computerized software algorithms, as discussed infra, to deliver precise therapeutic energy waves for various medical applications. The system utilizes multiple wave modalities across different frequency spectra to address a range of physiological conditions while maintaining strict safety parameters to ensure patient well-being. Non-limiting example embodiments of signal generations on nerves with mechanical pulses are provided, which can be utilized as part of the ETMDS, as discussed herein.
[0036] According to some embodiments, the ETMDS framework includes, but is not limited to, a wave generation platform, a targeting and control platform, and a monitoring and feedback platform working in concert. These interconnected components form a comprehensive solution for non-invasive energy delivery' to internal tissue structures.
[0037] The present disclosure will now be described more fully hereinafter with reference to the accompanying drawings, which form a part hereof, and which show, by way of non-limiting illustration, certain example configurations in accordance with some embodiments. Subject matter may, how ever, be embodied in a variety of different forms, as well as combinations of features depicted in non-limiting configurations. Therefore, covered or claimed subject matter is intended to be construed as not being limited to any example configuration of structures or function set forth herein.
[0038] FIG. 1 illustrates system 100 in three configurations for retaining pressure wave generator 110 on the anterior torso of user 101. Energy' transfer can be transcutaneous at any area on human skin 102, through several layers of clothing, or from a distance through participating media (air, water, etc.). Pressure wave generator 110 can be mounted to a portionDocket No. 233659-010301ZPCT Electronically Filed: March 25, 2026 of user 101 by an elastic strap 111, by attaching pressure wave generator 110 to an item of clothing, and / or via an adhesive interface 113.
[0039] As depicted in the left side of FIG. 1, elastic strap 111 tightly wraps the abdominal region 103 of the body, over the stomach and in direct contact with the skin 102. Elastic strap 111 may be configured to encircle the waist of user 101 and secure a wave generator module, such as pressure wave generator 110, against skin 102 at abdominal region 103. Pressure wave generator 110 may be fixed to garment 112 as shown in the middle of FIG. 1, maintaining operative contact with skin 102 at abdominal region 103 while remaining concealed beneath clothing. In some embodiments, pressure wave generator 110 is secured directly to skin 102 at abdominal region 103 via adhesive interface 113 as illustrated in the right side of FIG. 1. Although depicted separately for ease of explanation, a single implementation of the system may use all fixation techniques simultaneously or in any combination of fasteners to achieve the outcomes described herein.
[0040] Turning now to FIG. 2, system 100 is illustrated in a configuration incorporating sensor module 210 co-mounted to the user 101 with pressure wave generator 110. Energy’ transfer may be done in an open-loop fashion without various sensing elements for simplicity, or it may be done in a closed-loop fashion with various sensing elements for achieving resonant coupling between source and target for most efficient and effective energy’ transfer.
[0041] In some embodiments, sensor module 210 is located on the strap 111, at the back of the body, opposite the pressure wave generator 110 generating the pressure wave pulse. Sensor module 210 measures the energy level of the pressure wave pulse as it passes through the stomach and other tissues in its path and leaves the body, and enables calculation of the amount of damping within the body, allowing the system 100 to operate with optimal parameter values. In the configuration shown, pressure wave generator 110 operates as the source and sensor module 210 serves as the sensing element enabling closed-loop operation of system 100. However, the source may be, alternatively or in addition, any wave producing device described herein.
[0042] The closed-loop monitoring system continuously evaluates treatment effectiveness, collects relevant data, and automatically adjusts parameters to optimize outcomes, while also tracking patient compliance. In some embodiments, the monitoring and feedback platform incorporates multiple sensor arrays that continuously measure both incident and reflected wave characteristics. In some embodiments, the pressure wave generator 110 and / or the sensor module 210 includes sensors configured to record temperature changes with sensitivity of 0.1°C, tissue impedance variations within a 10-1000Q range, and micro-displacementDocket No. 233659-010301ZPCT Electronically Filed: March 25, 2026 measurements of 0.01-1.0mm, as non-limiting examples, to provide comprehensive real-time assessment of therapeutic efficacy.
[0043] In some embodiments, system 100 is configured to characterize the mechanical properties of the underlying tissue by analyzing the dynamics of pressure wave generator 110 during pulse delivery. When pressure wave generator 110 emits a pulse, a portion of the pulse energy is transmitted into participation media 700 and a complementary portion is retained as recoil motion of the device itself. By measuring this recoil (e.g., for example, through an accelerometer or inertial sensor integrated into pressure wave generator 110) system 100 can compute the relative energy partition between tissue transmission and device motion. Because the mechanical characteristics of pressure wave generator 110 remain constant across measurements, variations in the recoil signature across sessions and / or positions reflect changes in the acoustic coupling and impedance of the underlying tissue rather than deviceside variability. This recoil-based measurement thus provides a continuous, non-invasive index of tissue mechanical state that can be used to verify consistent device contact, detect changes in body composition at the placement site, and adaptively calibrate pulse parameters to maintain target energy delivery at mechanoreceptor 601.
[0044] In some embodiments, this body characterization capability can be extended by configuring pressure wave generator 110 to operate in a transmit-receive mode, whereby the transducer alternates between emitting pulses and recording the reflected waveforms returned from tissue interfaces beneath the skin 102. The reflected signal encodes the acoustic impedance profile of the tissue structures along the wave path 410, enabling system 100 to construct a local characterization of the participation media 700 between the device and gastrointestinal tract 501. This approach is analogous in principle to pulse-echo ultrasonic diagnostic imaging, and when combined with the recoil energy analysis described above, provides a comprehensive, hardware-efficient method of body characterization using the existing transducer of pressure wave generator 110 without requiring a separate sensor modality.
[0045] FIG. 3 illustrates system 100 in a multi-module configuration, wherein a plurality of pressure wave generators 110 are arranged in module array 310 and mounted to elastic strap 111 at abdominal region 103 of user 101 to stimulate a plurality of target areas within stomach 301. In some embodiments, instead of triggering mechanoreceptors in the stomach wall in only one region, it may be more effective to trigger them in several different regions. In this case, versions of system 100 with multiple pressure wave generators 110 can be used. These pressure wave generators 110 may work synchronously or asynchronously in various combinations.Docket No. 233659-010301ZPCT Electronically Filed: March 25, 2026
[0046] In the non-limiting configuration depicted in FIG. 3. module array 310 is arranged as a two-by-two grid of pressure wave generators 110 on a common backing seated against skin 102 at abdominal region 103 and retained by elastic strap 111. However, the system facilitates flexible transducer positioning anywhere on the user, enabling either the convergence of multiple lower-amplitude signals on a single target location for enhanced effect or the simultaneous stimulation of multiple distinct areas according to customized treatment protocols.
[0047] FIG. 4 illustrates system 100 in a multi-source focusing configuration, wherein a plurality of pressure wave generators 110 are circumferentially spaced along elastic strap 111 around the torso of user 101, with four wave paths 410 converging at intersection area 401 within the body in this non-limiting example. Different tissues and nerves may be located on the w ave path 410. To avoid stimulating these structures, multiple signals of lower amplitude can be focused on a single point, as shown in FIG. 4. The amount of energy in each wave path 410 is reduced while the total amount of energy' delivered to the target remains the same and tissues are less disturbed, if necessary.
[0048] In some embodiments, the targeting and control platform is configured to produce realtime anatomical mapping through integrated imaging technology, providing spatial resolution of 0.5 mm, for example. This precision allows system 100 to focus energy' waves at depths ranging from superficial (e.g., 0-2 cm) to deep tissue structures (e.g., up to 15 cm), with targeting accuracy maintained within ±1 mm. The system may be configured to adjust wave parameters to compensate for tissue heterogeneity, ensuring consistent energy delivery' at intersection area 401.
[0049] In some embodiments, the system employs phased array technology with 64-512 individual elements to achieve dynamic focusing and beam steering capabilities. The focal zone dimensions may be adjusted from 1 mm x 1 mm x 2 mm for highly concentrated energy delivery to 10 mm x 10 mm x 20 mm for broader coverage. The system achieves focal gains of 5-50 times the source intensity, depending on the selected configuration and tissue properties. In some embodiments, beam steering capabilities allow for treatment area coverage of up to 100 cm2without mechanical repositioning, achieved through electronic phase adjustments across array elements. This feature enables sequential treatment of multiple target sites and complex scan patterns for uniform energy distribution across larger volumes.
[0050] Prior to energy delivery', the system may perform detailed treatment planning based on patient-specific anatomical data. In some embodiments, the system includes a planning module configured to determine different tissue types and their boundaries. Predictive models areDocket No. 233659-010301ZPCT Electronically Filed: March 25, 2026 trained to simulate wave propagation through heterogeneous tissue structures, accounting for reflection, refraction, and attenuation effects to estimate energy distribution within ±10% accuracy. In some embodiments, the planning module is configured to determine primary and secondary treatment volumes, with automatic calculation of approach angles to minimize energy deposition in sensitive structures. Safety margins may be automatically established based on tissue t pe, with typical values ranging from 2 mm for highly controlled applications to 10 mm for treatments near critical structures. In some embodiments, pressure gradients may be generated within tissues ranging from 0.01-5.0 MPa / mm, enabling applications such as thrombolysis, calcification disruption, and fascial release. The system’s precision allows for selective targeting of specific tissue interfaces based on their acoustic impedance differentials, which may include a minimum detectable difference of 0.1 MRayl, as a non-limiting example.
[0051] FIG. 5 illustrates system 100 in a multi-level configuration, wherein a plurality of pressure wave generators 110 are individually mounted via adhesive interfaces 113 at vertically spaced positions along the anterior torso of user 101, each positioned anterior to a distinct region of gastrointestinal tract 501. In addition to the wall of the stomach 301, mechanoreceptors that induce an illusory satiety are also found in the wall of the small intestines 502. System 100 may be used with the same principles in the area of the body to be targeted to the small intestine 502 as shown.
[0052] In some embodiments, an upper pressure wave generator 110 is positioned anterior to stomach 301, a middle pressure wave generator 110 is positioned anterior to small intestine 502, and a lower pressure wave generator 110 is positioned anterior to large intestine 503. Although shown as the same attachment method in FIG. 5, different attachment methods may be used in different areas. System 100 is configured to induce feelings of fullness by delivering pulsed energy with high enough power density’ (e.g., at or above a threshold level) to stimulate peripheral mechanoreceptors in the gastrointestinal tract 501, specifically targeting the stomach 301 and small intestines 502. In the configuration shown, each pressure wave generator 110 is independently retained at its respective position along gastrointestinal tract 501 via individual mount 510, allowing system 100 to address mechanoreceptors distributed across the length of gastrointestinal tract 501 simultaneously or in any combination.
[0053] The projective area of the human stomach on the abdominal surface is substantially larger than the pressure w ave emitting surface of pressure w ave generator 110. Furthermore, the mechanoreceptors 601 targeted by system 100 are distributed throughout the walls of stomach 301 and intestines rather than concentrated at discrete anatomical points. Because the therapeutic objective requires only localized excitation of a subset of mechanoreceptors 601Docket No. 233659-010301 / PCT Electronically Filed: March 25, 2026 rather than simultaneous activation across the entire stomach wall, precise millimeter-level positioning of pressure wave generator 110 is not required for effective operation.
[0054] In some embodiments, a relatively coarse positioning of pressure wave generator 110 with respect to an identifiable surface landmark, such as the umbilicus, is sufficient to place the device within the projective area of stomach 301. For example, a position approximately 5 cm lateral and 10 cm superior to the umbilicus represents a non-limiting reference placement suitable to direct wave energy toward the gastric wall. The same positioning rationale applies to intestinal targets: the distributed arrangement of mechanoreceptors 601 along the walls of small intestine 502 and large intestine 503 similarly tolerates positional variation without loss of therapeutic effect, allowing user self-placement without clinical -grade alignment tools.
[0055] In some embodiments, more precise anatomical localization may be achieved by configuring pressure wave generator 110 to operate in a dual-function transmit-receive mode analogous to pulse-echo ultrasonic diagnostic imaging. In this configuration, pressure wave generator 110 emits a probe pulse and captures the reflected waveform returned from underlying tissue interfaces. Because the reflection characteristics of each pulse depend on the acoustic impedance profile of the specific tissue structures beneath the transducer, the reflected signal encodes information about the device’s anatomical position. By processing these reflections, system 100 can confirm placement relative to target structures within gastrointestinal tract 501, enabling software-guided positioning feedback without requiring a separate imaging modality. FIG. 6A illustrates the mechanoreceptor transduction pathway targeted by system 100, including the stimulus-response relationship at mechanoreceptor 601 and the activation thresholds that inform system 100 operating parameters. The human stomach 301 is a flexible organ, and stretches and enlarges with the food eaten. When the amount of stretching reaches a level, mechanoreceptors 601 in the stomach wall detect the level of stretching and trigger a signal in the vagus nervous system 603 to which they are connected and a message of satiety is transmitted to the brain. As shown in FIG. 6A, activation threshold m 605 at mechanoreceptor 601 propagates through nerve bundle 602 along vagus nene 603, producing electrical signal e(m) 604. The mechanoreceptors 601 in the stomach wall work like a strain gage and produce a satiety signal by stretching with food entry into the stomach 301 together with the stomach wall.
[0056] System 100 produces an illusorx satiety signal by locally and temporarily stretching mechanoreceptors 601 in the walls of the stomach 301 without food entry, when the stomach 301 is empty, or during food entry, when the stomach 301 is not yet full. As discussed above, system 100 generates a seismic pressure wave (p-wave) on the skin 102 of the human body.Docket No. 233659-010301ZPCT Electronically Filed: March 25, 2026 The pressure wave passes through the skin 102 and the various tissues underneath with the local speed of sound in the tissues and reaches the stomach 301. After passing through the anterior and posterior walls of the stomach 301, the pressure wave again passes through muscle and skin tissues and leaves the body. As the pressure wave passes through the anterior and posterior walls of the stomach 301, momentary strains occur on the mechanoreceptors 601 in those areas and these strains trigger an illusory satiety signal to the brain via the vagus nervous system 603 even though the stomach 301 is empty.
[0057] Understanding the output physiology of mechanoreceptors 601 informs the design of the stimulation parameters delivered by system 100. When mechanoreceptors 601 (e.g., for example, vagal afferents, enterochromaffin cells, and enteric neurons, and the like) within the stomach walls are strained or stretched, whether by ingested food or by the pressure wave pulses generated by system 100, they produce both rapid electrical responses and sustained biochemical signaling that together coordinate the satiety cascade.
[0058] With respect to a neural output, mechanoreceptors 601 within the muscularis externa of stomach 301 operate as slowly adapting receptors, sustaining their discharge throughout the period of mechanical strain. Their firing pattern comprises three recognizable phases. During the initial dynamic phase, the onset of mechanical loading produces a rapid spike in action potential frequency whose rate correlates with the speed at which strain is applied. As the strain reaches and maintains a steady level, the discharge transitions to a lower static phase firing rate that encodes the sustained magnitude of the stimulus and informs the brainstem of the total deformation present. Upon release of the mechanical stimulus, firing rate transiently drops below baseline before recovering, marking the termination of stimulation.
[0059] With respect to biochemical output, enterochromaffin cells within the gastric epithelium respond to mechanical deformation by releasing serotonin (5 -hydroxy tryptamine.5-HT). This serotonin acts on both the intrinsic enteric nervous system and the extrinsic vagal afferent neurons, driving adaptive gastric relaxation, modulating peristaltic motor patterns, and relaying fullness signals centrally via the vagus nen e 603.
[0060] The functional consequences of this combined electrical and biochemical output include adaptive relaxation, in which the stomach reflexively accommodates increased volume without a proportional rise in intraluminal pressure; initiation of peristalsis through distension-activated enteric motor circuits; and transmission of satiety signals to the brainstem that contribute to the subjective sensation of fullness. System 100 exploits this output pathway by delivering pressure wave pulses calibrated to produce the mechanical strain sufficient to engage this cascade, generating an illusory satiety signal without food ingestion.Docket No. 233659-010301 / PCT Electronically Filed: March 25, 2026
[0061] As shown in FIG. 6B, a minimum amplitude threshold of activation threshold m 605 are met or exceeded to produce electrical signal e(m) 604 in mechanoreceptor 601. Evidence from gastric afferent preparations indicates that low-threshold vagal mechanoreceptors 601 respond within a receptor-level pressure band of approximately 3-6 mmHg, representing a non-limiting example target range for amplitude threshold to elicit a satiety response via vagus nerve 603. In some embodiments, system 100 is configured to operate at or above this threshold while remaining below approximately 20 mmHg at mechanoreceptor 601, a non-limiting example level at which high-threshold mechanonociceptive fibers may be recruited. The specific value of amplitude threshold sufficient to activate mechanoreceptors 601 in a given tissue may confirmed by animal tests and clinical trials.
[0062] As shown in FIG. 6C, a pulse width 611 of activation threshold m 605 for activation of mechanoreceptor 601 is provided by the system. Energy transfer can also be pulsed in time with different pulse shapes, amplitudes, frequencies, and pulse widths 611. Pulse parameters can change with time either continuously or discretely. In some embodiments, pulse width 611 is evaluated across multiple regimes: fast impulses of approximately 5-50 ms, intermediate impulses of approximately 50-300 ms, and phasic plateaus of approximately 0.5-2 s serve as suitable non-limiting examples. The strength-duration relationship between amplitude threshold and pulse width 611 indicates that shorter pulse widths 611 require correspondingly higher amplitudes to achieve activation of mechanoreceptor 601, and system 100 may be configured to sweep across these regimes to establish an optimal operating point for a given subject.
[0063] Where pulse trains are employed, a repetition frequency of approximately 1-10 Hz may be used with duty cycles selected to maintain time-averaged pressure at mechanoreceptor 601 within the low-threshold activation band, leveraging the viscoelastic integration properties of mechanoreceptor 601 without exceeding instantaneous amplitude thresholds. Specific values of amplitude threshold and pulse width 611 to activate mechanoreceptors 601 across the gastrointestinal tract 501, including stomach 301 and small intestine 502, may determined by animal tests and clinical trials, as receptor type, anatomical site, and stimulus mode each contribute to threshold variability.
[0064] FIG. 7 illustrates the propagation of a pressure wave pulse generated by pressure w ave generator 110 through participation media 700, comprising skin 102, fat layer 701, and muscle layer 702, toward target mechanoreceptor 601. Pressure wave pulses (p-wave pulses) are used in system 100 due to the ability to travel through solid, liquid and gaseous environments. As the pressure wave pulse travels through media 700, it is subject to attenuation and dispersion,Docket No. 233659-010301ZPCT Electronically Filed: March 25, 2026 the degree of which depends on the material properties of each layer encountered. System 100 accounts for these propagation effects in configuring the parameters of the pressure wave pulse delivered by pressure wave generator 110. The system 100 is configured to adjust the parameters of the pressure wave pulse (form, amplitude, width, frequency) in such a way that the wave pulse does not damage any of the tissues it passes through in the body, but at the same time generates strains on the mechanoreceptors 601 in the stomach walls at a level to trigger an illusory satiety signal. In some embodiments, the system implements shear wave pulses (s-wave pulses) in applications where only solid and liquid environments are targeted. The selection between p-wave and s-wave modalities is informed by the tissue composition along the wave path 410 and the relative propagation advantages offered by each modality for a given target geometry.
[0065] As depicted in FIG. 8A, test setup 800 establishes a baseline measurement wherein source 810 (e.g., pressure wave generator 110) and sensor 811 (e.g., sensor module 210) are arranged in direct opposition with no intervening material between them. In some embodiments, sensor 811 represents multiple sensor arrays that continuously measure both incident and reflected wave characteristics.
[0066] In FIG. 8B, test setup 800 is configured with source 810 in direct contact with test sensor 811. The waveform captured by test sensor 811 in this configuration represents the unattenuated reference signal against which subsequent measurements are compared.
[0067] The FIG. 8C configuration measures the combined attenuation and damping introduced by a participation media 700, including one or more of skin 102, fat layer 701, and muscle layer 702, as the pressure wave pulse travels from source 810 through participation media 700 to test sensor 811. Comparison of the waveform recorded by test sensor 811 against the FIG. 8B baseline quantifies the energy loss and waveform deformation attributable to tissue 820.
[0068] FIG. 9 illustrates dispersion test setup 900, wherein source 810 is coupled laterally to tissue 820 and sensor 811 (e.g., piezoelectric film) is mounted to the opposing surface of tissue 820 to capture the propagated waveform after traversal through participation media 700. Dispersion test setup 900 isolates waveform deformation effects attributable to tissue 820, enabling system 100 to be configured with pulse parameters that preserve waveform integrity at mechanoreceptor 601. By comparing the waveform emitted by source 810 against the waveform recorded by sensor 811, dispersion test setup 900 quantifies pulse broadening and shape distortion introduced as the pressure wave traverses tissue 820 across skin 102, fat layer 701, and / or muscle layer 702.Docket No. 233659-010301ZPCT Electronically Filed: March 25, 2026
[0069] Energy transfer can be continuous in time with different waveform shapes, amplitudes, and frequencies. Waveform parameters can change with time either continuously or discretely. Energy transfer can also be pulsed in time with different pulse shapes, amplitudes, frequencies, and pulse widths. Pulse parameters can change with time either continuously or discretely. The results of dispersion test setup 900 inform the selection of multiple pulse parameters, including, as identified in FIG. 9: shape, amplitude, pulse width, and repetition frequency.
[0070] With respect to shape, a pulse shape is selected that minimizes attenuation and dispersion through participation media 700, with a soliton waveform representing a nonlimiting candidate. With respect to amplitude, values between 24 to 500 Hz, for example, have been found to be effective. In some embodiments, the source amplitude is set such that after propagation losses through participation media 700, the pressure at mechanoreceptor 601 remains within the low-threshold activation band described in connection with FIG. 6. With respect to pulse width, the duration is selected to satisfy the mechanoreceptor 601 responsetime requirements established through the strength-duration characterization of FIG. 6C. With respect to repetition frequency, the minimum rate required to sustain the desired mechanoreceptor 601 response is applied, leveraging the viscoelastic integration properties of mechanoreceptor 601 described herein.
[0071] One, several, or all of the parameters of the pressure wave pulse may remain constant during operation, or may vary stepwise or continuously within the desired range of values. This testing methods described herein may be used to maximize the effect of the pressure wave pulse on mechanoreceptors 601 in the stomach walls. In some embodiments, wave amplitude modulation occurs in real-time, with rise / fall times as short as 50 ps, allowing for precise temporal control of energy delivery. Pulsed operation modes feature duty cycles ranging from 0.1% to 100% with pulse repetition frequencies of 1 Hz to 10 kHz, enabling the deliver)’ of high peak powers while maintaining acceptable time-averaged exposure levels. The pulse parameters established through dispersion test setup 900 may be further refined through animal tests and clinical trials.
[0072] FIG. 10A illustrates a first non-limiting electromechanical source 1010 for pressure wave generator 110, designated, wherein rotating cam 1011 acts upon cantilever beam 1012 to drive plunger 1013 into participation media 700 to generate a mechanical pressure pulse. In some embodiments, the pressure wave generator 110 includes one or more of these components to generate the pressure wave pulse. As shown in the first stage 1014 of FIG. 10A, cantilever beam 1012 is anchored at one end and positioned above plunger 1013, which is aligned over participation media 700, while rotating cam 1011 is positioned adjacent to the free end ofDocket No. 233659-010301 / PCT Electronically Filed: March 25, 2026 cantilever beam 1012. As shown in the second stage 1015, continued rotation of cam 1011 progressively deflects cantilever beam 1012. storing elastic energy in the beam as it bends toward plunger 1013. As shown in the third stage 1016, further rotation of cam 1011 releases cantilever beam 1012, causing the free end of cantilever beam 1012 to rapidly return and strike plunger 1013, transmitting a short-duration mechanical impact pulse into participation media 700. In some embodiments, the rotary motion of cam 1011 is converted through the elastic energy of cantilever beam 1012 into a repeatable, controlled impact at plunger 1013, the characteristics of which are governed by the pulse parameters discussed in connection with FIG. 9.
[0073] FIG. 10B illustrates a second non-limiting source 1020 for pressure wave generator 110, where piezoelectric film 1021 is coupled to cantilever beam 1012 and driven by electrical input 1022 to strike plunger 1013 into participation media 700 to generate a mechanical pressure pulse. As shown in the first stage 1023 of FIG. 10B, cantilever beam 1012 is anchored at one end with piezoelectric film 1021 bonded along its upper surface. Plunger 1013 is aligned below the free end of cantilever beam 1012 over participation media 700, and electrical input 1022 is present but inactive. As shown in the second stage 1024, activation of electrical input 1022 causes piezoelectric film 1021 to deform, bending cantilever beam 1012 downward toward plunger 1013. As shown in the third stage 1025, deactivation of electrical input 1022 causes cantilever beam 1012 to rapidly return, striking plunger 1013 and transmitting a short-duration mechanical impact pulse into participation media 700.
[0074] The electrical drive of the source design depicted in FIG. 10B accommodates a range of operating frequencies and power levels. For example, such oscillators can operate within frequency ranges of 20 kHz to 3 GHz, allowing for application-specific energy' transfer. In some embodiments, the system utilizes solid-state amplifiers with adjustable output power ranging from 0.1 W to 100 W, depending on the therapeutic requirements and target tissue characteristics. The operating point within these ranges is selected in accordance with the pulse parameters established through the dispersion and threshold characterization described herein.
[0075] FIG. 10C illustrates a third non-limiting source for pressure wave generator 110, designated electronic source 1030, where ceramic piezoelectric disc 1031 is driven directly by electrical input 1022 to generate a mechanical pressure pulse into participation media 700 without the intermediate mechanical elements of the designs depicted in FIG. 10A and FIG.10B. As shown in first stage 1032, ceramic piezoelectric element 1031 is positioned against participation media 700 with electrical input 1022 present but inactive. As shown in second stage 1033, activation of electrical input 1022 causes ceramic piezoelectric disc 1031 toDocket No. 233659-010301ZPCT Electronically Filed: March 25, 2026 undergo rapid mechanical deformation, transmitting an impact pulse directly into participation media 700.
[0076] FIG. 10C may also represent wave generation module that includes one or more oscillators capable of producing waves across ultrasonic, radiofrequency, and microwave spectra. In some embodiments, electronic source 1030 is configured to operate across multiple frequency domains to address various therapeutic needs. Low-frequency ultrasound (20-100 kHz) may be utilized for mechanical disruption of fibrous structures, enhanced drug delivery, and stimulation of cellular repair mechanisms, producing wavelengths of 15-75 mm with penetration depths of 8-15 cm, suitable for deep tissue applications. Mid-frequency ultrasound (100 kHz-1 MHz) may be employed for thermal effects, increased perfusion, and enhancement of lymphatic drainage, providing wavelengths of 1.5-15 mm with penetration depths of 5-10 cm. High-frequency ultrasound (1-10 MHz) may be implemented for precise ablation procedures, localized hyperthermia, and microvessel stimulation, generating wavelengths of 0.15-1.5 mm with penetration depths of 2-5 cm. Radiofrequency (100 kHz-10 MHz) may be applied for controlled tissue heating, collagen remodeling, and nerve modulation, providing penetration depths of 1-8 cm with wavelengths of 3-3000 m in tissue. Microwave (915 MHz-2.45 GHz) may be utilized for rapid thermal effects, tumor ablation, and targeted hyperthermia treatments, achieving penetration depths of 1-4 cm with wavelengths of 1.8-4.7 cm in tissue. The operating frequency and power level of electronic source 1030 are selected in accordance with the pulse parameters and target tissue characteristics established through the characterization described herein.
[0077] FIG. 11 illustrates four non-limiting contact surface geometries for plunger 1013 of pressure wave generator 110, each presenting a distinct contour at the interface between plunger 1013 and skin 102 to shape the emitted pressure wave prior to propagation through participation media 700. In some embodiments, one or more plungers 1013 may include a flat geometry 1101, convex geometry 1102, concave geometry 1103, or aspheric geometry 1104. Each geometry produces a distinct wavefront profile at the skin 102 interface, influencing the downstream propagation characteristics of the pressure wave through participation media 700. In some embodiments, a custom aspheric geometry 1104 provides an optimal wave shape for minimal attenuation and dispersion through participation media 700. The selection among flat geometry 1101, convex geometry 1102, concave geometry 1103, and aspheric geometry 1104 may be informed by the target depth, tissue composition, and the pulse parameter characterization described herein.Docket No. 233659-010301 / PCT Electronically Filed: March 25, 2026
[0078] Wave propagation may targeted to an area inside body with seismic (body) waves or to another area on the skin 102 with surface waves. The contact surface geometry of plunger 1013 represents a tunable parameter for directing energy toward either of these propagation modes. Seismic waves can be used to excite, exercise, rejuvenate, heal, relocate, dislocate, or destroy the target. Similarly, surface waves can be used to exercise, rejuvenate target skin areas and to aid treating wounds and neuropathic symptoms. Accordingly, the geometry of plunger 1013 may be selected or customized based on the intended wave mode and therapeutic application of system 100.
[0079] As shown in FIG. 12A, three wave sources 1201, 1202, and 1203, (e.g., pressure wave generators 110) are positioned circumferentially around torso 1210 cross-section, with path 1, path 2, and path 3 converging at target 1220 as the central target. Spine 1230 is identified at the posterior of torso 1210 as an anatomical reference. The system 100 generates and propagates energy waves with precisely controlled parameters to achieve therapeutic outcomes while minimizing collateral effects. In this non-limiting example, the local speed of sound through the tissues of torso 1210 is approximately 1500 m / s, with path length differences among path 1, path 2, and path 3 on the order of a few centimeters, corresponding to time-of-flight differences on the order of 6 / 106seconds per centimeter. Accordingly, the disclosed systems and methods provide an Energy' Transfer Medical Device System (ETMDS) that provides targeted energy transfer to specific locations within the human body through controlled wave propagation. In the configuration of FIG. 12A. the distribution of pressure wave generators 110 around torso cross-section reduces the energy burden on any single wave path, consistent with the multi-source focusing principles described herein.
[0080] As shown in FIG. 12B, single-source impulse response 1240 illustrates the response of mechanoreceptor 601 to a mechanical impulse delivered along a single wave path. As described above, mechanoreceptor 601 exhibits viscoelastic tissue behavior, producing a finite-rise peak in electrical signal e(m) 604 followed by a characteristic decay. This viscoelastic integration property7of mechanoreceptor 601 temporally smooths the received impulse, such that the response at mechanoreceptor 601 reflects the cumulative mechanical input over a window of time rather than a single instantaneous stimulus.
[0081] As shown in FIG. 12C, cumulative response 1250 illustrates the summed response of mechanoreceptor 601 to impulses delivered along path 1, path 2, and path 3. The overlaid individual responses combine to produce a broader and elevated composite response at mechanoreceptor 601. Due to the viscoelastic integration behavior demonstrated in singlesource impulse response 1240, path length timing differences among path 1, path 2, and pathDocket No. 233659-010301 / PCT Electronically Filed: March 25, 2026 3 are accommodated without requiring tight inter-source synchronization. In some embodiments, the ETMDS software framework provides comprehensive control over all system parameters while ensuring safety and efficacy through continuous monitoring and adaptive algorithms. Where additional timing precision is desired, the system is configured to implement adaptive control configured to continuously adjust wave parameters based on realtime feedback. In some embodiments, the system operates at update rates of 100-1000 Hz, enabling immediate response to changing tissue conditions. In some embodiments, the system may implement a phase correction to compensate for tissue movement with latency under 10 ms, maintaining accurate targeting during physiological motion (e.g., respiration, cardiac movement).
[0082] In some embodiments, the system includes a wearable, mobile, rechargeable energy transfer unit and a mobile application platform. The system may be configured for patient selfadministration both inside and outside a clinical setting. In some embodiments, the mobile application platform is configured to control operation of the energy' transfer unit, including on / off function, and to set and adjust treatment parameters including pulse shape, pulse width, pulse amplitude, pulse period, and session duration. The mobile application platform may be configured to record user data including lifestyle data, weight, and comorbidities, as well as usage data including treatment time, session length, and treatment results. In some embodiments, the mobile application platform enables remote monitoring by a physician, allowing a treating physician to track patient progress and adjust treatment plans. The mobile application platform may additionally provide artificial intelligence driven personalization for individualized treatment programs, adherence-enhancing tools including session reminders and outcome reports, and integration with third-party' digital health devices through sensor fusion, including smartwatches, rings, and continuous glucose monitoring devices. In addition, the system includes wireless communication capability such as Bluetooth® or Wi-Fi to communicate and transfer data to a phone or computer. This communication capability enables system 100 to transmit operational data, treatment logs, and real-time feedback to an external device for monitoring, adjustment, and patient compliance tracking.
[0083] While primarily conceived as a wearable solution, alternative form factors including digestible, implantable, or insertable versions are also viable. In addition to the configurations depicted in FIG. 1 through FIG. 12, source 810 (e.g., pressure wave generator 110) and sensor module 210 may be implemented in form factors adapted to specific clinical contexts, including configurations intended for ingestion, implantation, or insertion within the body.Docket No. 233659-010301 / PCT Electronically Filed: March 25, 2026
[0084] Energy transfer by wave propagation can be used to activate or enhance effect of medicines that previously were transported to a target location within human body. Transportation may be done by ingesting, injecting, by blood, diffusing, or wave propulsion. Accordingly, system 100 may be configured to operate in conjunction with pharmacological agents that have been delivered to a target tissue site, using wave energy to potentiate or trigger the therapeutic effect of those agents at the intended location. Energy transfer by wave propagation can be used to energize or charge various implants that are placed deep inside body. In some embodiments, the system is configured to move implants to a new location within body. Thus, system 100 provides a non-invasive mechanism for interacting with implanted devices or materials without requiring surgical access.
[0085] In some embodiments, for radiofrequency and microwave applications, the system interacts with tissues through oscillating electromagnetic fields that induce molecular rotation and vibration. These interactions generate controlled heating with specific absorption rates (SAR) ranging from 1 W / kg to 100 W / kg in target tissues. In some embodiments, the electromagnetic wavelengths are optimized for the dielectric properties of the target tissue, with frequencies selected to provide the appropriate penetration depth and energy absorption profile. The system accounts for tissue-specific conductivity (0.01-2.0 S / m) and relative permittivity (1-80) to predict and control energy' distribution.
[0086] In some embodiments, the system is configured to precisely control temperature elevations within target tissues, with capabilities ranging from mild hyperthermia (41-43°C) for enhanced drug delivery and immune response stimulation to ablative temperatures (55-90°C) for tissue destruction. Temperature ramp rates can be adjusted from 0. l°C / s for gradual heating to 10°C / s for rapid ablation procedures. In some embodiments, the thermal dose is measured in cumulative equivalent minutes at 43°C (CEM43), with the system capable of delivering controlled doses ranging from 1 CEM43 to 240 CEM43. In some embodiments, the system 100 is configured to ensure that temperature elevations in non-target tissues remain below 2°C, with active cooling mechanisms available for surface protection when required.
[0087] In some embodiments, the system delivers controlled energy with power density ranging from 0.1 W / cm2to 500 W / cm2, adjustable in 0.1 W / cm2increments. For thermal applications, the system typically operates in the 10-100 W / cm2range, while mechanical effects are achieved at 0.5-50 W / cm2. The peak negative pressure for ultrasonic applications ranges from 0.1 to 20 MPa, with mechanical index values maintained below 1.9 for diagnostic procedures and up to 4.0 for therapeutic applications under controlled conditions.Docket No. 233659-010301 / PCT Electronically Filed: March 25, 2026
[0088] According to some embodiments, for applications utilizing mechanical effects, the system is configured to generate controlled acoustic cavitation with cavitation indices ranging from 0.2 (stable cavitation) to 1.0 (inertial cavitation). In some embodiments, the resulting mechanical bioeffects include enhanced membrane permeability (sonoporation) with pore sizes of 10-500 nm, microstreaming-induced shear forces of 0.1-10 Pa, and radiation forces capable of displacing tissue structures by 0.1-1000 pm.
[0089] In some embodiments, power modulation occurs in response to measured tissue temperatures, with proportional-integral-derivative (PID) control loops maintaining target temperatures within ±0.5°C. Advanced predictive models anticipate thermal buildup with 90% accuracy up to 5 seconds in advance, allowing preemptive adjustments to prevent thermal overshoot. In some embodiments, the software continuously monitors over 50 system parameters to ensure safe operation. These include reflected power ratios (threshold: > 20%), unexpected temperature gradients (> 2°C / mm), and pattern recognition algorithms to detect potential cavitation in unintended locations. The safety' system employs a hierarchical decision structure with response times under 5 ms for critical parameters.
[0090] In some embodiments, automatic termination protocols activate when safety- thresholds are exceeded, with graduated responses ranging from power reduction to complete shutdown depending on the severity- of the detected anomaly. All safety- events are logged with microsecond timestamps for subsequent analysis and quality improvement. In some embodiments, the ETMDS adheres to stringent safety standards and regulatory requirements for medical devices. The system implements multiple redundant safety mechanisms, including: independent thermal monitoring yvith 0.1 °C resolution and automatic shutdown at predefined thresholds; continuous tissue impedance monitoring to detect unexpected tissue changes; realtime cavitation detection with spectral analysis of backscattered signals; patient movement detection and automatic beam adjustment or suspension; and comprehensive error detection and fault isolation systems. In some embodiments, the frameyvork complies with applicable sections of IEC 60601 for medical electrical equipment safety-, IEC 62359 for acoustic output measurement, and IEC 62304 for medical device software life cycle processes. Electromagnetic compatibility is maintained in accordance with IEC 60601-1-2, with emissions and immunity levels suitable for hospital environments.
[0091] Accordingly, as discussed herein, the disclosed Energy Transfer Medical Device System provides a computerized frameyvork for delivering controlled energy- to targeted locations within the human body through yvave propagation. By integrating advanced wave generation technology- with precise targeting capabilities and comprehensive monitoringDocket No. 233659-010301ZPCT Electronically Filed: March 25, 2026 systems, the ETMDS provides a versatile platform for numerous therapeutic applications. The system's ability’ to operate across multiple frequency domains with adjustable power levels and focusing parameters enables customized treatments tailored to specific patient conditions and anatomical considerations.
[0092] In some embodiments, such adaptive control algorithms, which can be utilized for planning, real-time analysis, dynamic adjustment, and the like, can involve the system calling and executing an artificial intelligence and / or machine learning (AI / ML) and / or LLM model, the system calling and executing an artificial intelligence and / or machine learning (Al / ML) and / or LLM model. Accordingly, in some embodiments, the AI / ML models can be any ty pe of known or to be known, specifically trained AI / ML model, particular machine learning model architecture, particular machine learning model type (e.g., convolutional neural network (CNN), recurrent neural network (RNN), autoencoder, support vector machine (SVM), and the like), or any other suitable definition of an AI / ML model or any suitable combination thereof.
[0093] In some embodiments, an LLM can be leveraged, as discussed herein, whether known or to be known. As discussed above, an LLM is a type of Al system designed to understand and generate human-like text based on the input it receives. The LLM can implement technology^ that involves deep learning, training data and NLP. Large language models are built using deep learning techniques, specifically using a type of neural network called a transformer. These networks have many layers and millions or even billions of parameters. LLMs can be trained on vast amounts of text data from the internet, books, articles, and other sources to leam grammar, facts, and reasoning abilities. The training data helps them understand context and language patterns. LLMs can use NLP techniques to process and understand text. This includes tasks like tokenization, part-of-speech tagging, and named entity recognition.
[0094] LLMs can include functionality related to. but not limited to, text generation, language translation, text summarization, question answering, conversational Al, text classification, language understanding, content generation, and the like. Accordingly, LLMs can generate, comprehend, analyze and output human-like outputs (e.g., text, speech, audio, video, and the like) based on a given input, prompt or context. Accordingly, LLMs, which can be characterized as transformer-based LLMs, involve deep learning architectures that utilizes selfattention mechanisms and massive-scale pre-training on input data to achieve NLP understanding and generation. Such current and to-be-developed models can aid Al systems in handling human language and human interactions therefrom.
[0095] In some embodiments, such model can be configured to identify and utilize one or more AI / ML techniques selected from, but not limited to, computer vision, feature vector analysis,Docket No. 233659-010301ZPCT Electronically Filed: March 25, 2026 decision trees, boosting, support-vector machines, neural networks, nearest neighbor algorithms. Naive Bayes, bagging, random forests, logistic regression, and the like.
[0096] In some embodiments and, optionally, in combination of any embodiment described above or below, a neural network technique can be one of, without limitation, feedforward neural network, radial basis function network, recurrent neural network, convolutional network (e.g., U-net) or other suitable network. In some embodiments and, optionally, in combination of any embodiment described above or below, an implementation of Neural Network can be executed as follows.a. define Neural Network architecture / model,b. transfer the input data to the neural network model,c. train the model incrementally,d. determine the accuracy for a specific number of timesteps,e. apply the trained model to process the newly received input data,f. optionally and in parallel, continue to train the trained model with a predetermined periodicity.
[0097] In some embodiments and, optionally, in combination of any embodiment described above or below, the trained neural network model can specify a neural network by at least a neural network topology7, a series of activation functions, and connection weights. For example, the topology of a neural network can include a configuration of nodes of the neural network and connections between such nodes. In some embodiments and, optionally, in combination of any embodiment described above or below, the trained neural network model can also be specified to include other parameters, including but not limited to, bias values / functions and / or aggregation functions. For example, an activation function of a node can be a step function, sine function, continuous or piecewise linear function, sigmoid function, hyperbolic tangent function, or other type of mathematical function that represents a threshold at which the node is activated. In some embodiments and, optionally, in combination of any embodiment described above or below, the aggregation function can be a mathematical function that combines (e.g., sum, product, and the like) input signals to the node. In some embodiments and, optionally, in combination of any embodiment described above or below, an output of the aggregation function can be used as input to the activation function. In some embodiments and, optionally, in combination of any embodiment described above or below, the bias can be a constant value or function that can be used by the aggregation function and / or the activation function to make the node more or less likely to be activated.Docket No. 233659-010301ZPCT Electronically Filed: March 25, 2026
[0098] The instant disclosure outlines a smart adaptive system designed to monitor, analyze, and modify eating behaviors through multimodal sensing and intelligent intervention. The system operates on a closed-loop paradigm of detection, monitoring, intervention, and adaptation. The system employs multiple sensing modalities to accurately detect the onset of eating behaviors, including biosensors that may include EMG sensors to detect mastication muscle activity, wearable strap technology that incorporates stretch sensors detecting physical changes associated with eating movements or abdominal expansion, acoustic monitoring with specialized microphones featuring tailored spectral response characteristics to detect both oral food processing sounds and gastric activity, and movement pattern recognition algorithms that identify' characteristic arm-to-mouth movements associated with eating. This multi-sensor approach provides redundancy and improves detection accuracy across varied eating scenarios and environments.
[0099] In some embodiments, a non-limiting operational workflow begins with automated activation, where the system employs machine learning algorithms to identify' eating initiation cues, enabling autonomous activation without user intervention. Once activated, the system initiates continuous monitoring, tracking eating patterns, speed, duration, and potentially volume through its sensor array. The system then features a progressive intervention mechanism beginning with a passive monitoring phase without intervention, followed by parameter adjustments to increase deterrent effects, then direct user notifications via connected interfaces, and finally generation of mild aversive stimuli such as auditory warnings and haptic feedback. Upon cessation of eating activity, the system enters standby mode to conserve power and reduce user awareness.
[0100] The system continuously builds a personalized model of the user's eating behaviors through temporal pattern analysis identifying regular eating schedules, contextual association correlating eating with environmental, emotional, or situational triggers, effectiveness assessment evaluating which intervention methods produce desired behavior modifications, and predictive activation utilizing predictive algorithms to activate preventatively before anticipated eating events. This adaptive learning allows the system to become increasingly personalized and effective with continued use.
[0101] The hardware components can include, but are not limited to, a sensory subsystem including acoustic monitoring with specialized microphones optimized for gastric activity detection, physical monitoring with stretch sensors integrated into wearable components to detect bodily changes associated with eating, and a processing unit with a low-power microcontroller running edge-based machine learning algorithms. The intervention subsystemDocket No. 233659-010301ZPCT Electronically Filed: March 25, 2026 includes haptic feedback with integrated muscle wire actuators in the strap that can contract to create mild discomfort, a user interface connected application for status information and warning messages, and audio output with a small speaker for audible alerts and warnings.
[0102] Several engineering challenges have been addressed, including power efficiency implementing hierarchical activation protocols where only necessary7sensors remain active, false positive reduction using multiple sensor confirmation requirements before intervention, user comfort designing the wearable components to be unobtrusive during normal activity', and intervention calibration with personalized adjustment of haptic feedback intensity7to be effective without causing undue discomfort.
[0103] As described above, the instant system has applications beyond general weight management, including medical applications assisting patients with prescribed dietary restrictions, behavioral research providing quantitative data on eating patterns and intervention effectiveness, dietary monitoring supporting nutrition tracking with automatic meal detection, and eating disorder management providing objective monitoring and graduated intervention for clinical populations. The system may incorporate nutritional content estimation through spectroscopic analysis to estimate macronutrient content, emotional state correlation with integration with stress and emotional state monitors, social context awareness modify ing intervention strategies based on detected social situations, and enhanced predictive capabilities using deeper learning algorithms to anticipate eating events with greater accuracy. As such, among other benefits and technological advancements, the disclosed system provides an innovative approach to automated dietary behavior modification combining advanced sensing technology7with responsive intervention strategies.
[0104] While some embodiments have been described for purposes of this disclosure, such embodiments should not be deemed to limit the teaching of this disclosure to those embodiments. Various changes and modifications may be made to the elements and operations described above to obtain a result that remains within the scope of the systems and processes described in this disclosure.
Claims
Docket No. 233659-010301ZPCT Electronically Filed: March 25, 2026CLAIMSWhat is claimed is:
1. A method comprising:mounting a pressure wave generator to an abdominal region of a user; providing, by the pressure wave generator, pressure wave pulses to a user; and stimulating, by the pressure wave pulses, mechanoreceptors in a gastrointestinal tract of the user.
2. The method of claim 1, further comprising localizing the pressure wave pulses to a target associated with the gastrointestinal tract.
3. The method of claim 2, further comprising monitoring the pressure wave pulses using a sensor module.
4. The method of claim 3, further comprising adjusting the pressure wave pulses based on the monitoring.
5. The method of claim 4, wherein adjusting the pressure wave pulses comprises adjusting one or more of a waveform shape, an amplitude, a pulse width, and a repetition frequency of the pressure wave pulses.
6. The method of claim 1, further comprising securing the pressure wave generator directly to skin of the user via one or more of an elastic strap, a garment, and an adhesive interface.
7. The method of claim 1, further comprising positioning a sensor module on the user; and measuring, via the sensor module, an energy level of the pressure wave pulses exiting the user.
8. The method of claim 1, further comprising distributing a plurality of pressure wave generators on the user.Docket No. 233659-010301ZPCT Electronically Filed: March 25, 2026 9. The method of claim 8. further comprising focusing wave paths from each of the plurality of pressure wave generators to converge at an intersection area within the user.
10. The method of claim 1, further comprising detecting an initiation of an eating behavior of the user with an artificial intelligence model.
11. A sy stem compri sing :a pressure wave generator configured to be mounted to an abdominal region of a user, wherein the pressure wave generator is configured to provide pressure wave pulses to the user, andwherein the pressure wave pulses are configured to stimulate mechanoreceptors in a gastrointestinal tract of the user.
12. The system of claim 11, further comprising a targeting mechanism configured to localize the pressure wave pulses to a target associated with the gastrointestinal tract.
13. The system of claim 12, further comprising a sensor module configured to monitor the pressure wave pulses.
14. The system of claim 13, wherein the system is further configured to adjust the pressure wave pulses based on signals received from the sensor module.
15. The system of claim 14, wherein adjustment of the pressure wave pulses comprises adjusting one or more of a waveform shape, an amplitude, a pulse width, and a repetition frequency of the pressure wave pulses.
16. The system of claim 11, wherein the pressure wave generator is configured to be secured directly to skin of the user via one or more of an elastic strap, a garment, and an adhesive interface.
17. The system of claim 11, further comprising a sensor module configured to be positioned on the user, the sensor module configured to measure an energy level of the pressure wave pulses exiting the user.Docket No. 233659-010301ZPCT Electronically Filed: March 25, 2026 18. The system of claim 11, further comprising a plurality' of pressure wave generators configured to be distributed on the user.
19. The system of claim 18, wherein the system is further configured to focus wave paths from each of the plurality of pressure wave generators to converge at an intersection area within the user.
20. The system of claim 11, further comprising an artificial intelligence model configured to detect an initiation of an eating behavior of the user.