System and method for feedback-based audio / optic nerve stimulation

Abstract

A system includes a memory, an input device, an output device, and one or more processors. The memory stores weights of the machine learning model. Weights are trained on training data of the training set. The training data includes patient attributes, types of stimulation, and measured brain response signals. The input device is configured to receive one or more attributes of a patient. The output device is configured to output at least one of audio or visual stimuli to the patient. The one or more processors are configured to determine a type of stimulation for providing to the patient by applying the one or more attributes to the machine learning model, and to generate and transmit a control signal for the output device to cause the output device to output the type of stimulation to the patient.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to and the benefit of U.S. Provisional Application No. 63 / 434,591, filed December 22, 2022, the contents of which are incorporated herein by reference in their entirety.

[0003] public domain

[0004] The present disclosure relates generally to neural stimulation, including but not limited to systems and methods for feedback-based audio and visual neural stimulation.

[0005] background

[0006] Neural oscillations occur in humans and animals and include rhythmic or repetitive neural activity in the central nervous system. Neural tissue can generate oscillatory activity through mechanisms within individual neurons or through interactions between neurons. Oscillations can manifest as periodic fluctuations in membrane potential or rhythmic patterns of action potentials, which can produce oscillatory activation of postsynaptic neurons. The synchronized activity of a group of neurons can give rise to macroscopic oscillations, which can be observed by sensing electric or magnetic fields in the brain using techniques such as electroencephalography (EEG), intracranial EEG (iEEG) (also known as electrocorticography (ECoG)), and magnetoencephalography (MEG).

[0007] Overview

[0008] According to the systems and methods described herein, neural stimulation can be provided via rhythmic light stimulation presented simultaneously with auditory stimulation through music. The combination of music and light stimulation can induce neural oscillation effects or stimulation. The combined stimulation can adjust, control, or otherwise affect the frequency of neural oscillations to provide beneficial effects to one or more cognitive states, cognitive functions, the immune system, or inflammation, while mitigating or preventing adverse consequences to cognitive states or cognitive functions. For example, the systems and methods of the present technology can treat, prevent, prophylactically, or otherwise affect Alzheimer's disease or other cognitive diseases, such as Parkinson's disease, dementia, and the like.

[0009] In various cases, when a patient undergoes treatment or otherwise experiences both audio and visual stimulation as described herein, typically, the stimulation is at a target or specific frequency or frequency band (e.g., in the delta, theta, and / or gamma frequency bands) to stimulate a specific part of the patient's brain. However, some audio or visual stimulation may be more effective for a particular patient than others. For example, certain visual patterns may be more effective than other visual patterns at stimulating a patient's brain at certain frequencies. Similarly, certain music may be more effective at stimulating a patient's brain at certain frequencies than other music.

[0010] In various embodiments, as described in more detail below, the systems and methods described herein can be configured to train a machine learning model to make predictions and / or recommendations related to audio and / or visual stimulation based on or according to a patient's attributes. The machine learning model can be trained on a training set that includes training patient attributes, types of audio and / or visual stimulation, and measured brain responses. Once trained, the machine learning model can be configured to ingest unknown data (such as patient attributes and requested audio or visual stimulation, target frequency, etc.) and generate predictions (e.g., predicted brain responses for the patient, predicted stimulation efficacy) and / or recommendations (e.g., alternative audio signals for audio stimulation, visual patterns for visual stimulation, etc.). Such implementations and embodiments can improve the efficacy of stimulation and treatment.

[0011] In various aspects, the present disclosure relates to systems and methods for feedback-based audio / visual neural stimulation. A memory can store weights of a machine learning model. The weights can be trained on training data of a training set, the training data including patient attributes, stimulation types, and measured brain response signals. An input device can be configured to receive one or more attributes of the patient. An output device can be configured to output at least one of audio or visual stimulation to the patient. One or more processors can be configured to determine the type of stimulation to provide to the patient by applying the one or more attributes to the machine learning model. One or more processors can be configured to transmit and generate control signals for the output device to cause the output device to output the type of stimulation to the patient.

[0012] In some embodiments, the machine learning model is trained to generate predictions of measured brain responses for stimulation types based on one or more attributes of the patient. One or more processors may determine the type of stimulation based on the predictions of the measured brain responses. In some embodiments, the one or more processors may determine the type of stimulation based on the measured brain responses at a target frequency for stimulation. In some embodiments, the machine learning model is trained to generate recommendations for stimulation types based on one or more attributes of the patient. The type of stimulation may include the type of audio signal for audio stimulation or the type of visual pattern for visual stimulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings are not intended to be drawn to scale. Like reference numerals and names in the various drawings represent like elements. For clarity, not every component may be labeled in every figure.

[0015] Figure 1 is a graph of frequencies associated with a particular fundamental musical stimulus and the range of frequencies present in each frequency band, selected by an oscillation selection module (OSM) according to an example embodiment of the present disclosure.

[0016] Figure 2 is a diagram showing, on the left, magnetoencephalographic (MEG) recordings of the human auditory cortex recorded while subjects listened to rhythmic auditory stimuli of two different tempos and highlighting, on the right, some of the brain regions that exhibited such responses.

[0017] Figure 3 is a block diagram of a system for providing neural stimulation according to an example embodiment of the present disclosure.

[0018] Figure 4 is a diagram showing an example embodiment according to the present disclosure Figure 3 Diagram of the operation of the system utilizing the resulting brain stimulation.

[0019] Figure 5-Figure 6 is a diagram showing an example embodiment according to the present disclosure Figure 3 Figure 3 shows example stimuli provided by the system using different songs, where panel A compares the auditory rhythmic frequency (i.e., onset spectrum) of the music with the frequency of auditory 40 Hz pulse trains, and panel B compares the visual frequency stimulated by the system with the frequency of visual 40 Hz pulse trains.

[0020] Figure 7 is a diagram of an output device for delivering visual stimuli according to an example embodiment of the present disclosure.

[0021] Figure 8 is a block diagram of an example system using supervised learning according to an example implementation of the present disclosure.

[0022] Figure 9 is a block diagram of a simplified neural network model according to an example embodiment of the present disclosure.

[0023] Figure 10 is a block diagram of an example computer system according to an example implementation of the present disclosure.

[0024] Detailed description

[0025] Before turning to the drawings showing certain embodiments in detail, it should be understood that the present disclosure is not limited to the details or methods set forth in the description or shown in the drawings. It should also be understood that the terminology used herein is for descriptive purposes only and should not be regarded as limiting.

[0026] Neural oscillations can be characterized by their frequency, amplitude, and phase. These signal characteristics can be observed from neural recordings using time-frequency analysis. For example, EEG can measure oscillatory activity within a group of neurons, and the measured oscillatory activity can be classified into the following frequency bands: delta activity corresponds to the frequency band of 0.5 Hz-4 Hz; theta activity corresponds to the frequency band of 4 Hz-8 Hz; alpha activity corresponds to the frequency band of 8 Hz-13 Hz; beta activity corresponds to the frequency band of 13 Hz-30 Hz; and gamma activity corresponds to the frequency band of 30 Hz and above.

[0027] Neural oscillations in different frequency bands can be associated with cognitive states or functions, such as perception, action, attention, reward, learning, and memory. Depending on the cognitive state or function, neural oscillations in one or more frequency bands may be involved. Furthermore, neural oscillations in one or more frequency bands can have beneficial or adverse consequences for one or more cognitive states or functions.

[0028] Neural entrainment occurs when the brain perceives an external stimulus of a specific frequency or combination of frequencies and triggers neural activity in the brain, causing neurons to oscillate at a frequency related to the specific frequency of the external stimulus. Thus, neural entrainment can refer to the use of an external stimulus to synchronize neural oscillations in the brain so that the neural oscillations occur at a frequency corresponding to the specific frequency of the external stimulus. Neural entrainment can also refer to the use of an external stimulus to synchronize neural oscillations in the brain so that the neural oscillations occur at frequencies that are harmonics, subharmonics, integer ratios, and combinations of the specific frequencies of the external stimulus. Models of neural oscillations and models of neural entrainment predict specific neural oscillation frequencies that can be observed in response to a set of external stimulus frequencies.

[0029] Cognitive functions such as learning and memory involve coordinated activity across distributed subcortical and cortical brain regions, including the hippocampus, cortical and subcortical association areas, sensory areas, and the prefrontal cortex. Across different brain regions, behaviorally relevant information is encoded, maintained, and retrieved through transient increases in the power of neural oscillations reflecting multiple activity frequencies and synchronization between these neural oscillations.

[0030] In particular, oscillatory neural activity in the theta and gamma frequency bands has been associated with encoding, maintenance, and retrieval processes during short-term, working, and long-term memory. Evoked gamma activity has been linked to working memory, with increases in both scalp-recorded gamma band activity and intracranial gamma band activity during working-memory maintenance. Increases in gamma activity power dynamically track the number of items maintained in working memory. Using electrocorticography (ECoG), one study found that working memory load, tracked by gamma power, was enhanced in the hippocampus and medial temporal lobe when participants maintained sequences of letters or faces in working memory. Finally, other evidence suggests that hippocampal gamma activity contributes to episodic memory, using distinct sub-gamma frequency bands corresponding to the encoding and retrieval stages.

[0031] Theta oscillations (4Hz-8 Hz) have been implicated in working memory and episodic memory processes. Intracranial electroencephalogram (iEEG) recordings have shown that during working memory, theta oscillations gate on and off (i.e., increase and maintain amplitude, then rapidly decrease in amplitude) with the encoding, maintenance, and retrieval phases. Other work has observed increases in scalp-recorded theta activity during working memory maintenance. Some studies have concluded that scalp-recorded theta activity from frontal midline electrodes is the most powerful neural correlate of verbal working memory maintenance. Furthermore, frontal midline theta activity tracks working memory load, increasing and maintaining power according to the number of items maintained in working memory.

[0032] Several studies have found that gamma-frequency auditory-visual stimulation can improve biomarkers and pathophysiology associated with dementia or Alzheimer's Disease (AD), and may provide neuroprotection if administered during the early stages of disease progression.

[0033] Music induces and drives neural activity across multiple frequency ranges, and musical stimulation itself can induce and drive oscillatory neural activity associated with learning, memory, and cognition. In various embodiments of the present solution, the systems and methods described herein can detect, determine, identify, or otherwise exploit the brain's natural delta, theta, and gamma frequency responses to music by providing music as the sole auditory stimulus in systems and methods for treating, preventing, prophylactic, or otherwise affecting Alzheimer's disease, dementia, and / or other neurological or cognitive conditions. In some embodiments, audio stimulation is coupled with visual stimulation in the delta, theta, and / or gamma frequency bands, which are programmed to synchronize with the delta, theta, and / or gamma frequency bands of the brain's response to the audio stimulation to enhance the therapeutic effect. In some embodiments, stimulation can be targeted for additional frequencies and frequency bands to treat, prevent, and / or prophylactically affect Alzheimer's disease, dementia, and / or other neurological or cognitive conditions or diseases, such as Parkinson's disease.

[0034] Musical rhythms are organized into well-structured frequency combinations. For example, musical rhythms induce neural activity in the delta and theta frequency ranges by directly stimulating the brain within these frequency ranges. The frequency of the basic beat can correspond to neural activity in the delta band. Subdivisions of the beat typically correspond to neural activity in the theta band. Furthermore, musical rhythms can drive activity at delta and theta frequencies that are not explicitly present in the rhythm because they contain structured frequency combinations. Frequencies observed in brain activity can include harmonics, subharmonics, integer ratios, and combinations of frequencies present in musical rhythms and are predicted by modeling neural oscillations and neural intra- and extra-intra-neural coupling.

[0035] Musical rhythms can drive gamma neural activity in the brain in a manner that is distinct from the internal and external coupling of delta and theta activity. The amplitude of endogenous gamma neural oscillations is modulated so that peak amplitudes are synchronized with musical events (see Figure 2 ). The amplitude modulation of gamma neural activity reflects phase-amplitude coupling with lower frequency (e.g., delta and theta) neural activity.

[0036] Phase-amplitude coupling (PAC) can be or include a statistical dependence between the amplitude of oscillations in one frequency band and the phase of oscillations in another frequency band. For example, in theta-gamma phase-amplitude coupling, the peak of the gamma amplitude corresponds to a specific phase of the resulting theta activity. Thus, the gamma activity is driven by the resulting theta and delta activity.

[0037] The systems and methods described herein can provide feedback-based audio and / or visual stimulation by activating the brain's natural delta, theta, and gamma responses to music in a manner that does not interfere with musical enjoyment. Because enjoyment is critical to patient tolerance and completion of the regimen, the systems and methods described herein can motivate patient compliance with the treatment by avoiding the harsh and unpleasant sounds of added audio waves in the gamma frequency band.

[0038] In some embodiments, the systems and methods described herein can combine, generate, or otherwise provide visual stimulation in the delta, theta, and / or gamma frequency bands to enhance frequencies important in musical enjoyment. Such a solution can enhance the efficacy of stimulation because visual stimulation in the gamma band is less aversive than auditory stimulation in the gamma band. In some embodiments, gamma stimulation can be combined with delta and theta stimulation to produce visual stimulation that mimics the brain's natural response to musical rhythms.

[0039] In the systems and methods described herein, gamma stimulation can be amplitude modulated by phase-amplitude coupling with theta and / or delta frequency oscillations to simulate auditory processing, thereby increasing the efficacy and extent of neural stimulation. In addition, the specific stimulation frequency is determined by the musical stimulation, so the stimulation frequency provided by the present solution will change within the stimulation session, reducing the potential for neural adaptation, thereby increasing the efficacy of stimulation. In some embodiments, the systems and methods described herein can combine music listening with delta, theta and / or gamma frequency visual stimulation to create an engaging and effective audio-visual stimulation for the patient. In some embodiments, additional frequency bands can be employed through audio or visual stimulation.

[0040] In some embodiments, the systems and methods described herein can output a set of improved stimuli that amplify the brain's natural delta, theta, and gamma responses to music in a manner that does not create neural interference between the brain's natural oscillatory response to music and the oscillatory auditory stimulus added within the same frequency band. Specifically, in some embodiments, the systems and methods described herein can use simulations of neural intra- and extra-corporeal coupling to determine the frequencies of the brain's natural delta, theta, and gamma responses to music. The system can then enhance and amplify the natural response to music by delivering the same delta, theta, and / or gamma frequencies in visual stimuli. The simulation can include delta-theta-gamma phase-amplitude coupling to faithfully simulate the brain's auditory response and amplify the effect. Therefore, the visual stimulation may not interfere with or offset the brain's natural oscillatory response to music. Instead, the visual stimulation may amplify the brain's natural oscillatory response to music.

[0041] The systems and methods described herein relate to output stimulation that induces neural stimulation via rhythmic light stimulation presented simultaneously with musical stimulation. The combination of music and rhythmic light pulses can induce brain wave effects or stimulation. The combined stimulation can adjust, control or otherwise affect the frequency of neural oscillations to provide beneficial effects to one or more cognitive states, cognitive functions, immune systems or inflammation (or other symptoms), while mitigating or preventing adverse consequences to cognitive states or cognitive functions, and maximizing enjoyment, processing tolerance and completion of treatment regimens. For example, the systems and methods of the present technology can treat, prevent, prevent or otherwise affect Alzheimer's disease (or other cognitive diseases or disorders).

[0042] The frequency of the neural oscillations observed in the patient can be affected by or correspond to the frequency of the musical rhythm and the rhythmic light pulses. Therefore, the system and method of the present solution can induce neural intra- and extra-corporeal coupling by outputting multimodal stimulation, such as a musical rhythm and light pulses emitted at a frequency determined by analyzing the musical rhythm. This combined multimodal stimulation can synchronize the electrical activity between groups of neurons based on one or more frequencies caused and driven by the musical rhythm. Based on the aggregate frequency of oscillations generated by the synchronized electrical activity in the neuronal collection throughout the brain, neural intra- and extra-corporeal coupling can be observed.

[0043] In some embodiments, additional outputs from the system may also include one or more stimulation units for generating tactile, vibration, thermal, and / or electrical transcutaneous stimulation. Such stimulation units may include mobile devices, smart watches, gloves, or other devices capable of vibration. In some embodiments, the output device may include a stimulation unit for generating an electromagnetic field or current to deliver transcranial stimulation, such as an array of electromagnets or electrodes.

[0044] refer to Figure 1 , depicts a diagram of frequencies associated with a particular fundamental musical stimulus and the range of frequencies present in each frequency band selected by an oscillation selection module (OSM) according to an example embodiment of the present disclosure. Figure 1 As shown, the graph can include a breakdown of four frequencies associated with fundamental music that can be selected by the systems and methods described herein, as well as the frequency ranges in which they exist. In some embodiments, the systems and methods described herein can select one or more harmonically related frequencies in the delta, theta, and lower gamma (30 Hz-50 Hz) frequency ranges. In some embodiments, the gamma amplitude is modulated by the theta frequency, simulating theta-gamma phase-amplitude coupling. Similarly, in some embodiments, the theta amplitude is modulated by one or more delta frequencies, simulating delta-theta phase-amplitude coupling. Overall, the above thus simulates a delta-theta-gamma oscillation hierarchy in the auditory cortex.

[0045] Continue to refer Figure 1 , shows an exemplary scheme for visual stimulus frequencies in the gamma, theta, and delta frequency bands generated by a system according to an aspect of the present disclosure. Panel A shows the time domain waveform of the musical stimulus over a 4-beat time interval, as well as the onset calculated during preprocessing. Panel B shows the delta-theta-gamma coupled variations in luminance provided by the systems and methods described herein, while Panel C shows the same variations in each frequency band.

[0046] Figure 2 Shown are MEG recordings of the human auditory cortex while subjects listened to rhythms of two different tempos. Figure 2Panel A is a time-frequency plot of signal power changes associated with a rhythmic stimulus presented every 390 ms (2.6 Hz), showing a periodic pattern of signal increases and decreases in the gamma band. Panel B shows the same measurements for a rhythmic stimulus presented every 585 ms (1.7 Hz). In the auditory cortex, gamma is amplitude-modulated by delta and theta, and this pattern is simulated by the systems and methods described herein.

[0047] Figure 1 Panel D shows the stimulation generated by the systems and methods described herein in the frequency domain. In summary, these figures illustrate that gamma oscillations are effectively stimulated by the output provided by the device within a frequency range surrounding the primary frequency. These additional frequencies, known as sidebands, are caused by the amplitude modulation of the theta and delta frequencies by the device and method. Furthermore, each song played by the systems and methods described herein results in a different selection of frequencies within the delta, theta, and gamma ranges. Thus, over the course of several songs played via the systems and methods described herein, the output stimulates a wide range of gamma frequencies.

[0048] Thus, the device simulates the amplitude modulation of stimulation provided in the gamma band by altering the phase of stimulation provided in the delta and theta bands, which mimics the brain's natural gamma-delta-theta phase-amplitude coupling response, thereby enhancing the tolerability and efficacy of the treatment. As described above, Figure 1 Panel D shows that gamma oscillations are efficiently excited in a range of frequencies (sidebands) around the main frequency. These sidebands are caused by the amplitude modulation of the theta and delta frequencies provided by the systems and methods described herein.

[0049] Furthermore, each piece of music played by the system can result in a different selection of frequencies within the delta, theta, and gamma ranges. Thus, over the course of a session, different gamma frequencies are stimulated. In contrast, some solutions may stimulate only a single frequency, often resulting in neural adaptation and reduced neural response. In some embodiments of the present system, varying the frequency can avoid neural adaptation and promote robust neural responses.

[0050] Now refer to Figure 3 and Figure 4 , depicts a block diagram of a system 300 for providing neural stimulation, and a diagram illustrating the operation of the system 300 utilizing the resulting brain stimulation, according to an example embodiment of the present disclosure. The system 300 may include an auditory analysis system (AAS) 302 configured to receive auditory input, filter acoustic signals, detect the onset of acoustic events (e.g., a musical note or drum beat), and adjust the gain of the resulting signal. In some embodiments, the AAS 302 may include a filtering module, an onset detection module, and an optional gain control module to filter the signal, detect the onset of acoustic events, and adjust the gain of the resulting signal, respectively.

[0051] In some embodiments, the AAS 302 can be configured to pre-process auditory stimuli, auditory input, or audio signal 304 to provide multi-channel rhythmic input (e.g., note onsets). In some embodiments, the auditory input or audio signal 304 is provided by the system, such as by or via a built-in audio playback system that can access a library of songs and / or other musical works. In some embodiments, the system 300 may also include a graphical display and input / output accessible to the user (e.g., patient or therapist) to allow the user to select from the library for playback. In other embodiments, in addition to or as an alternative to the built-in audio playback system, the system 300 may include an auxiliary audio input to allow the system 300 to receive input from a secondary playback system, such as a personal music playback device (e.g., iPod, MP3 player, smartphone, etc.). In some embodiments, in addition to or as an alternative to the above-mentioned auditory input, the system 300 may include a microphone or similar device to allow the system 300 to receive auditory input from ambient sounds, such as live musical performances or music broadcast from auxiliary speakers (such as the user's home stereo system). In embodiments where the system receives audio signal 304 through a built-in playback system or an auxiliary input (eg, through an MP3 player), the system may also include headphones or integrated speakers to allow the listener to hear audio signal 304 in real time.

[0052] System 300 may include a profile manager 306. Profile manager 306 may be or include a processor or internet-enabled software application that accesses non-transitory and / or random access memory that stores data related to one or more users or patients, such as identification information (e.g., name or patient ID number), stored information from previous treatments and / or a library of audio files, and various user preferences, such as song selections. Profile manager 306 may be communicatively coupled with AAS 302 to facilitate selecting, managing, or otherwise controlling auditory input or audio signals.

[0053] In some embodiments, the profile manager 306 may provide a user interface to prompt the user to select his or her own personalized music preferences as auditory stimulation. Such an embodiment may maximize the effectiveness of a given system by stimulating the auditory and reward systems of patients with early stages of dementia and cognitive decline.

[0054] System 300 may include an internal and external coupling simulator 308. ES 308 may receive and process (e.g., from AAS 302) received audio signals to simulate the processing in the human brain. ES 308 may simulate the processing of audio signals to suggest and output oscillation signals to enhance the received audio signals, thereby enhancing the therapeutic effect of the processing. In some embodiments, AAS 302 may be operably connected to ES 308 and provide data to ES 308 in the form of a start signal. In some embodiments, ES 308 may also interface with profile manager 306 to, for example, call patient data from a previous treatment. In some embodiments, ES 308 may simulate the frequency, phase, and amplitude of neural oscillations resulting from the neural response to music to predict humankind.

[0055] ES 308 may include one or more oscillatory neural networks designed to simulate neural intra- and extra-corporeal coupling. In an embodiment, the artificial oscillatory neural network receives pre-processed auditory stimuli (music) and causes simulated neural oscillations to predict the frequency, phase, and relative amplitude of human neural responses to music. In some embodiments, ES 308 may include a deep neural network, an oscillator network, a set of numerical formulas, an algorithm, or any other component configured to simulate an oscillatory neural network. ES 308 may be configured to predict the frequency, phase, and relative amplitude of oscillations caused and driven by any given musical stimulus in a typical human brain. ES 308 may be configured to predict responses in at least the δ (1Hz-4Hz), θ (4Hz-8Hz), and low γ (30Hz-50Hz) frequency bands.

[0056] The system 300 may include an oscillation selection module (OSM) 310. The OSM 310 may be communicatively coupled to the ES 308. The OSM 310 may receive input from the ES 308 and output one or more selected oscillation states as frequencies, amplitudes, and phases for visual stimulation. The OSM 310 may be configured to select the most significant oscillations for visual stimulation in one or more predetermined frequency ranges (in a preferred embodiment, the delta, theta, and gamma bands). In some embodiments, the OSM 310 may couple visual gamma frequency stimulation to the beat and rhythmic structure of the music through phase-amplitude coupling. The OSM 310 may select variable, music-based frequencies within the delta, theta, and gamma ranges for visual stimulation of the user, which stimulation is generated by a brain rhythm stimulator, as described below.

[0057] System 300 may include a brain rhythm stimulator (BRS) 312. BRS 312 may be configured to generate, produce, or otherwise provide a control signal for an output device 314 based on data from OSM 310, ES 308, and / or AAS 302 to provide audio and / or visual stimulation. BRS 312 may be configured to synchronize visual stimulation within a selected frequency range with the rhythm of music via output device 314 (such as an LED light ring) using simulated neural oscillations, as described below. In some embodiments, BRS 312 may output rhythmic visual stimulation to the user. BRS 312 may include a pattern buffer, a generation module, an adjustment module, and a filtering component, and may be operatively connected to an output device 314 comprising an apparatus for displaying rhythmic light stimulation. BRS 314 may also be interfaced with a profile manager 306 that stores data related to one or more users or patients. Therefore, in some embodiments, the information stored by profile manager 306 may also include preferences for previously captured or user-selected patterns, waveforms, or other stimulation parameters, such as user / patient preferred colors.

[0058] Output device 314 may include an LED light, a computer monitor, a TV monitor, goggles, a virtual reality headset, augmented reality glasses, smart glasses, or other suitable stimulation output devices. In some embodiments, output device 314 may be a stimulation unit for generating tactile, vibrational, thermal, and / or electrical transcutaneous stimulation, such as a stimulation unit in a wearable device, smartwatch, or mobile device. In some embodiments, output device 314 may include a stimulation unit for generating an electromagnetic field or current to deliver transcranial stimulation, such as an array of electromagnets or electrodes.

[0059] In general, the BRS can be configured to (1) read a patient's profile from a profile manager, (2) select a pattern based on the profile, (3) retrieve one or more selected oscillatory signals and / or states from the ES / OSM, (4) generate a pattern, (5) adjust the pattern based on the profile, and (6) display or output the rhythmic stimulus on an output device. In some embodiments, the pattern refers to a light pattern and the output device refers to a visual output device.

[0060] System 300 may include a brain oscillation monitor (BOM) 316. BOM 316 can provide neurofeedback, which can be used to optimize the frequency, amplitude and phase of the oscillation of the visual presentation, so as to optimize the frequency, phase and amplitude of the oscillation in the brain. In some embodiments, BOM 316 can provide feedback to system 300 (e.g., to ES 308) so that ES 308 can adjust parameters to optimize the phase of the output oscillation signal. BOM 316 can include electrodes, magnetometers or other components, signal amplifiers, filtering components and feedback interface components arranged to sense brain activity, and be connected to these component interfaces or otherwise communicate. In some embodiments, BOM 316 can provide feedback to ES 308 in the form of EEG signals. BOM 316 can be configured to identify the frequency, phase and amplitude of the brain oscillation caused by stimulation. BOM 316 can be configured to sense the electric field or magnetic field in the brain, amplify brain signals, filter the signals to identify specific neural frequencies, and provide input to ES 308 as described above. BOM 316 can be configured to sense electric or magnetic fields in the brain and can include electrodes connected to an electroencephalogram (EEG), intracranial EEG (iEEG) (also known as electrocorticoencephalogram (ECoG), magnetoencephalogram (MEG)), and other systems for sensing electric or magnetic fields.

[0061] AAS 302, profile manager 306, ES 308, OSM 310, BRS 312, and BOM 316 may each be or include any hardware, including a processor, circuitry, or any other processing component, including those referenced below. Figure 10 any hardware or components described.

[0062] In summary, the system 300 can be configured to (1) receive auditory input, (2) simulate neural intra- and extra-corporeal coupling of a pre-processed auditory signal using one or more extra- and extra-corporeal coupling simulators 308, which can include a network of multi-frequency artificial neural oscillators, (3) couple oscillations within the network using phase-amplitude or phase-phase coupling, (4) adjust coupling parameters and / or intrinsic parameters using an adaptive learning algorithm, and / or (5) select the most significant oscillations in one or more frequency bands to display as visual stimuli via a BRS 312, as described below.

[0063] In an embodiment, the rhythmic visual stimulation (as described below) selected for output to the user can include δ, θ and / or γ frequency, and θ-γ and / or δ-γ phase-amplitude coupling, to enhance the naturally occurring oscillatory response to the musical rhythm. The sensory cortex in the brain (e.g., primary visual cortex and primary auditory cortex) is functionally connected to areas important for learning and memory, such as the hippocampus and medial and lateral prefrontal cortexes. Therefore, coupling complex rhythmic visual stimulation (including δ, θ and γ frequency visual stimulation) with musical rhythm can drive the θ, γ and θ-γ coupling in the brain, activating the neural circuits involved in learning, memory and cognition. This, in turn, can drive the learning and memory circuits involved in music.

[0064] Now refer to Figure 5 and Figure 6 , depicts a diagram illustrating example stimuli using different songs and visual stimuli according to an example embodiment of the present disclosure. Specifically, Figure 5 and Figure 6 Shown is a comparison of auditory and visual stimulation provided by the systems and methods described herein compared to a 40 Hz pulse train. Figure 5 and Figure 6 Different frequencies of both the audio and visual stimulation and the 40 Hz pulse trains provided by the systems and methods of the present disclosure are shown. Figure 5 and Figure 6 Each shows stimulation provided by a different song.As can be seen, the 40 Hz pulse train provides both audio and visual stimulation at a single frequency, which can be easily compared to the wide frequency range at which the systems and methods described herein provide audio and visual stimulation.

[0065] Now refer to Figure 7 , depicts an example of an output device 314 for providing visual stimulation. Output device 314 is provided via a visual stimulation ring 700, which includes an LED light 702 operably connected to system 300 including BRS 312. In some embodiments, visual stimulation ring 700 is positioned in front of a participant, who is instructed to focus at the center indicated by reference symbol 701. In some embodiments, visual stimulation ring 700 is positioned at an appropriate distance to stimulate the retina at a specific viewing angle. For example, ring 700 can be positioned at an appropriate distance to stimulate the retina at a viewing angle between 0 and 15 degrees, or between 10 and 60 degrees, or between 15 and 50 degrees, or between 15 and 25 degrees, or between 18 and 22 degrees, or between 19 and 21 degrees. In some embodiments, visual stimulation ring 700 can be positioned at an appropriate distance to stimulate the retina at a viewing angle of 20 degrees, at which the maximum density of rods in the retina is found.

[0066] Although shown as a stimulation ring 700, various other output devices 314 may be used as part of the system 300, in conjunction with or in addition to the stimulation ring 700. For example, in some embodiments, the output device 314 may include a head-mounted device. The head-mounted device may include a display and / or one or more speakers of a speaker system. The head-mounted device may include augmented reality glasses, virtual reality goggles, etc. The display of the head-mounted device may present visual patterns to the user. For example, if the head-mounted device includes augmented reality glasses, the augmented reality glasses may utilize visual patterns to enhance the user's environment visible through the glasses. As another example, if the head-mounted device includes virtual reality goggles (or other non-AR goggles), the goggles may display visual patterns on a display adjacent to the patient's eyes. In some embodiments, the display of the head-mounted device may display separate visual patterns on each of the patient's eyes and at different angles to provide visual stimulation to the patient. The one or more speakers may include in-ear speakers or earbuds for each ear of the patient, headphones, a speaker system (e.g., locally on the head-mounted device), etc. One or more speakers may be configured to present audio signals 304 to provide audio stimulation to the patient.

[0067] In some embodiments, the output device 314 may include multiple output devices 314. For example, the output device 314 may include an audio output device 314 and a visual output device 314. The audio output device 314 may be configured to receive a control signal from the BRS 312 for presenting the audio signal 304 as audio stimulation to the patient. Similarly, the visual output device 314 may be configured to receive a control signal from the BRS 312 for presenting a visual pattern as visual stimulation to the patient. The audio output device 314 may be or include headphones, earbuds, a speaker system, etc. The visual output device 314 may include a stimulation ring 700, a display device (e.g., a television, tablet computer, smartphone, or other display), a head-mounted device including a display, etc.

[0068] Therefore, in a method according to one embodiment of the present solution, the system may perform the following process:

[0069] (A) receiving auditory input,

[0070] (B) Filtering the acoustic signal,

[0071] (C) detecting the onset of an acoustic event,

[0072] (D) using one or more multi-frequency neural oscillator networks to simulate neural intra- and extra-corporeal coupling to pre-processed auditory signals,

[0073] (E) using phase-amplitude or phase-phase coupling to couple oscillations within the network,

[0074] (F) using an adaptive learning algorithm to adjust coupling parameters and / or intrinsic parameters,

[0075] (G) selecting the most significant oscillations in the delta, theta and / or gamma frequency bands for display,

[0076] (H) generating a light pattern, and

[0077] (I) Displaying rhythmic light on a visual output device.

[0078] In some embodiments, prior to receiving audio input, the system may perform a process of prompting the user to select an audio input source and / or select from a library of songs or musical works stored on the system.

[0079] In brain regions including the hippocampus, auditory cortex, and frontal lobe areas important for long-term memory, self-selected music, i.e., music chosen by the individual patient and familiar to him / her, can be more effective in engaging larger brain activity networks than music chosen by others or music unfamiliar to the patient. Therefore, listening to familiar music may be more effective in driving brain activity in older adults, and it activates more brain regions. Importantly, familiar music can drive greater activation of the hippocampus, a key area for memory.

[0080] Compared to music selected by researchers, music selected by listeners may be more pleasing and familiar to the listener and may more effectively activate brain activity. Specifically, in addition to activating the auditory system, self-selected music can increase activity in the dopamine reward system, the default mode network, and predictive brain processes. Prolonged music listening may also increase functional connectivity from the sensory cortex to the dopamine reward system, which is responsible for various motivated behaviors.

[0081] Thus, in some embodiments, auditory stimulation can include music selected by the patient themselves, which has the practical effect of maximizing overall brain function. The systems and methods described herein can facilitate receiving music recordings from a patient while the patient simultaneously views an engaging audio-visual display including delta, theta, and gamma frequency stimulation, further improving patient compliance with the disclosed treatment regimen.

[0082] In some embodiments, before generating and displaying the light pattern, the system 300 may prompt the user to select a profile from an input device and / or user interface integrated in or coupled to the system 300. The system 300 may perform one or more of the following processes: (G2) reading the patient's profile from the profile manager 306, (G3) selecting a light pattern based on the profile, (G4) retrieving one or more oscillation signals from the ES 308, (H) generating the light pattern, and (H2) adjusting the light pattern based on the profile.

[0083] In some embodiments, the system 300 may also optimize the frequency, phase, and / or amplitude of the output oscillating signal based on data received from the BOM 316. Thus, the system 300 may intermittently or continuously perform one or more of the following additional processes: (J) receiving input from the BOM 316, (K) providing input to the ES 308, (L) coupling the input via phase-to-phase coupling, and (M) using an adaptive learning algorithm to adjust coupling parameters and / or intrinsic parameters to optimize the frequency, phase, and amplitude of the output oscillating signal.

[0084] Thus, the systems and methods of the present solution may provide neural stimulation to a user via at least the presentation of rhythmic visual stimulation simultaneously, synchronously, and in coordination with musical stimulation.

[0085] For example, in some embodiments, the system 300 can generate and display light patterns to be displayed simultaneously with the musical stimulus based on system self-selection or based on profile data stored for an individual user. In some embodiments, the system 300 can perform one or more of the following additional processes:

[0086] (A) selecting one or more oscillations in the delta, theta and / or gamma frequency bands,

[0087] (B) generating a light pattern using the selected one or more oscillations, and

[0088] (C) Displaying the light pattern on a visual output device 314 .

[0089] The system 300 may also consult the user's profile and select a light pattern based on the profile. The system 300 may first prompt the user to select a profile from an input device and / or user interface integrated into or coupled to the system 300, and read the patient's profile from the profile manager 306 to determine the appropriate light pattern to display.

[0090] As described herein, in some embodiments, the AAS 302 may receive auditory input via a microphone or auxiliary audio input, filter the acoustic signal, detect the onset of an acoustic event (eg, a musical note or drum beat), and adjust the gain of the resulting signal.

[0091] As described herein, in some embodiments, the ES 308 can receive auditory input from the AAS 302, use the input to simulate neural intra- and extra-neural coupling of pre-processed auditory signals using one or more multi-frequency neural oscillator networks, couple oscillations within the network using phase-amplitude or phase-phase coupling, adjust coupling parameters and / or intrinsic parameters using an adaptive learning algorithm, and select oscillations within a predetermined frequency range for display based on the retrieved profile. The ES 308 can also receive input from the BOM 316, provide input to the one or more multi-frequency neural networks, couple the neural inputs via phase-phase coupling, and adjust the coupling parameters using an adaptive learning algorithm to optimize the amplitude and phase of the output oscillatory signal.

[0092] As described herein, in some embodiments, the BRS 312 can read the patient's profile from the profile manager 306, select a light pattern based on the profile, read one or more oscillating signals from the ES 308, select at least one of a delta frequency, a theta frequency, a gamma frequency, and / or a combination of these frequencies, whose frequency, amplitude, and phase are determined by the ES 308, generate a rhythmic light pattern based on the selected frequencies, adjust the light pattern based on the profile, and display the rhythmic visual stimulation directed toward the eye on an LED, computer monitor, TV monitor, or other suitable light output device.

[0093] The results of the systems and methods described herein can be that the system senses electric or magnetic fields in the brain, amplifies brain signals, and filters the signals to identify specific neural frequencies. In some embodiments, the system then collects output from the user's brain based on the brain's reception of visual and auditory stimuli and returns this feedback to the ES 308 to further optimize the visual and auditory stimuli.

[0094] The system and method can induce and drive oscillatory neural activity involved in learning, memory and cognition. By providing music as the only auditory stimulus, coupled with visual stimulation in the delta, theta and / or gamma frequency bands, the present system and method can be used as a method for treating, preventing, prophylactic or otherwise affecting Alzheimer's disease and dementia.

[0095] In various cases, when a patient undergoes treatment or otherwise experiences both audio and visual stimulation as described herein, typically, the stimulation is at a target or specific frequency or frequency band (e.g., in the delta, theta, and / or gamma frequency bands) to stimulate a specific part of the patient's brain. However, some audio or visual stimulation may be more effective for a particular patient than others. For example, certain visual patterns may be more effective than other visual patterns at stimulating a patient's brain at certain frequencies. Similarly, certain music may be more effective at stimulating a patient's brain at certain frequencies than other music.

[0096] In various embodiments, as described in more detail below, the systems and methods described herein can be configured to train a machine learning model to make predictions and / or recommendations related to audio and / or visual stimulation based on or according to the patient's attributes. The machine learning model can be trained on a training set that includes training patient attributes, types of audio and / or visual stimulation, and measured brain responses. Once trained, the machine learning model can be configured to ingest unknown data (such as patient attributes and requested audio or visual stimulation, target frequency, etc.) and generate predictions (e.g., predicted brain responses for the patient, predicted stimulation efficacy) and / or recommendations (e.g., alternative audio signals for audio stimulation, visual patterns for visual stimulation, etc.). Such implementations and embodiments can be stimulation and treatment efficacy.

[0097] Brief Reference Figure 8 and Figure 9 , depicts example systems 800, 900 for machine learning or artificial intelligence. Systems 800, 900 can be incorporated into system 300 (such as ES 308, BRS 312, etc.). Systems 800, 900 can be configured to generate recommendations and / or predict brain responses for a specific patient. Systems 800, 900 can be trained on a training set that includes data from a patient pool. The patient pool can be or include living patients (e.g., currently undergoing or previously undergoing treatment), test patients, etc. The data of the training set can include patient attributes, stimulation types, and measured brain responses. Patient attributes can include, for example, patient age, type or severity of cognitive disease, hearing ability (e.g., complete hearing, partial hearing loss, or complete hearing loss), patient medical condition, diagnostic data, heart rate, etc. The type of stimulation can include frequencies or frequency bands for audio and / or visual stimulation, types of music or audio signals 304, light patterns for visual stimulation, etc. The measured brain responses may include measured brain oscillations from the BOM 316 , such as an EEG signal or other feedback generated by the BOM 316 .

[0098] As described in more detail below, the systems 800, 900 can be configured to generate predictions and / or recommendations for a particular patient (e.g., using the patient's attributes as input). Such predictions can include predictions of measured brain responses to particular types of stimulation (e.g., responses to particular combinations of delta / theta / gamma frequencies at particular corresponding amplitudes), which in turn can be used to provide recommendations (e.g., selecting a different type of stimulation). Additionally or alternatively, the systems 800, 900 can be used to recommend different or specific types of audio signals (e.g., different musical genres, specific songs, etc.) or visual patterns that will have a greater measured brain response (e.g., a higher amplitude at a target frequency).

[0099] refer to Figure 8, a block diagram of an example system using supervised learning is shown. In some embodiments, Figure 8 The system shown in can be included, incorporated into, or otherwise used by the above-mentioned ES 308. For example, ES 308 can be configured to use supervised learning to generate a recommendation for a specific visual or audio stimulus for a specific patient. As another example, ES 308 can be configured to use supervised learning to generate a recommendation for a specific frequency or amplitude at which to provide audio or visual stimulation. Supervised learning is a method for training a machine learning model given an input-output pair. An input-output pair is an input and an associated known output (e.g., an expected output).

[0100] The machine learning model 804 can be trained on known input-output pairs so that the machine learning model 804 can learn how to predict known outputs given known inputs. Once the machine learning model 804 has learned how to predict known input-output pairs, the machine learning model 804 can operate on unknown inputs to predict outputs. The machine learning model 804 can be trained based on general data and / or granular data (e.g., patient-specific data based on previous stimuli and outcomes) so that the machine learning model 804 can be trained specifically for a particular patient.

[0101] The machine learning model 804 may be provided with training inputs 802 and actual outputs 810. The training inputs 802 may include attributes of the patient, such as cognitive disorders, age, heart rate, medications, diagnostic test results, patient medical history, etc. The training inputs 802 may also include audio or visual stimuli selected by the ES 308 and provided to the patient via the output device 314. The actual outputs 810 may include feedback from the BOM 316 (such as EEG data or other brain signals measured by the BOM 316).

[0102] The input 802 and the actual output 810 can be received from the ES, the BOM 316 and stored in one or more data repositories. For example, the data repository can contain a data set that includes a plurality of data entries corresponding to past treatments. Each data entry can include, for example, attributes of the patient, audio / video stimulation provided to the patient, and feedback data from the BOM 316. Thus, the machine learning model 804 can be trained based on the training input 802 and the actual output 810 used to train the machine learning model 804 to predict feedback data for different types of stimulation for different types of patients (e.g., patients with different types of cognitive diseases, patients of different ages, etc.).

[0103] The system 300 may include one or more machine learning models 804. In an embodiment, a first machine learning model 804 may be trained to predict data related to different types of processed feedback data. For example, the first machine learning model 804 may use training inputs 802 of patient attributes and stimulation type to predict an output 806 of predicted feedback for the patient by applying the current state of the first machine learning model 804 to the training inputs 802. A comparator 808 may compare the predicted output 806 with an actual output 810 of the feedback from the patient to determine the amount of error or difference. For example, a predicted EEG signal (e.g., predicted output 806) may be compared with an actual EEG signal (e.g., actual output 810) from the BOM 316.

[0104] In other embodiments, the second machine learning model 804 can be trained to make one or more recommendations to the user 832 based on the predicted output from the first machine learning model 804. For example, the second machine learning model 804 can use the training inputs 802 of the patient attributes and feedback from the BOM 316 to predict the output 806 of a particular recommended stimulus by applying the current state of the second machine learning model 804 to the training inputs 802. The comparator 808 can compare the predicted output 806 to the actual output 810 of a selected type of stimulus (e.g., audio stimulation of a particular frequency or amplitude, visual stimulation of a particular frequency or amplitude) to determine the amount of error or difference.

[0105] In some embodiments, a single machine learning model 804 can be trained to make one or more recommendations to a user 832 based on patient data received from the system 300. That is, a single machine learning model can be trained using training inputs of patient attributes, stimulation type, and feedback from the BOM 316 to predict an output 806 of the optimal stimulation type by applying the current state of the machine learning model 804 to the training input 802. A comparator 808 can compare the predicted output 806 with the actual output 810 (e.g., the stimulation type used and the generated EEG signal from the BOM 316) to determine the amount of error or difference. The actual output 810 can be determined based on historical data associated with recommendations to the user 832.

[0106] During training, the error determined by the comparator 808 (represented by the error signal 812) can be used to adjust the weights in the machine learning model 804 so that the machine learning model 804 changes (or learns) over time. For example, the machine learning model 804 can be trained using a backpropagation algorithm. The backpropagation algorithm operates by propagating the error signal 812. The error signal 812 can be calculated at each iteration (e.g., each pair of training inputs 802 and associated actual outputs 810), batch, and / or epoch and propagated through the algorithm weights in the machine learning model 804 so that the algorithm weights are adapted based on the amount of error. The error is minimized using a loss function. Non-limiting examples of loss functions can include a squared error function, a root mean square error function, and / or a cross entropy error function.

[0107] The weighting coefficients of the machine learning model 804 can be adjusted to reduce the amount of error, thereby minimizing the difference between the predicted output 806 and the actual output 810 (or otherwise converging). The machine learning model 804 can be trained until the error determined at the comparator 808 is within a certain threshold (or a threshold number of batches, rounds, or iterations has been reached). The trained machine learning model 804 and associated weighting coefficients can then be stored in a memory 816 or other data repository (e.g., a database) so that the machine learning model 804 can be used for unknown data (e.g., not the training input 802). Once trained and validated, the machine learning model 804 can be employed during testing (or inference phase). During testing, the machine learning model 804 can ingest unknown data (e.g., patient attributes) to generate recommendations and / or predict brain response data (e.g., generate recommendations about specific types of stimulation, predict EEG responses to different types of stimulation, etc.).

[0108] refer to Figure 9 , a block diagram of a simplified neural network model 900 is shown. Similar to system 800, neural network 800 can be incorporated into system 300 to provide recommendations about stimulation types and / or predict brain responses to different types of stimulation. Neural network model 900 can include a stack of different layers (oriented vertically) that transform a variable number of inputs 902 taken by an input layer 904 into outputs 906 at an output layer 908.

[0109] The neural network model 900 may include multiple hidden layers 910 between the input layer 904 and the output layer 908. Each hidden layer has a corresponding number of nodes (212, 914, and 916). In the neural network model 900, the first hidden layer 910-1 has nodes 912, and the second hidden layer 910-2 has nodes 914. Nodes 912 and 914 perform specific calculations and are interconnected to nodes in adjacent layers (e.g., node 912 in the first hidden layer 910-1 is connected to node 914 in the second hidden layer 910-2, and node 914 in the second hidden layer 910-2 is connected to node 916 in the output layer 908). Each node (212, 914, and 916) sums the values ​​from adjacent nodes and applies an activation function, thereby allowing the neural network model 900 to detect nonlinear patterns in the input 902. Each node (212, 914, and 916) is interconnected by weights 920-1, 920-2, 920-3, 920-4, 920-5, 920-6 (collectively, weights 920). Weights 920 are adjusted during training to adjust the strength of the nodes. Adjusting the strength of the nodes contributes to the ability of the neural network to predict accurate outputs 906.

[0110] In some embodiments, output 906 can be one or more numbers. For example, output 906 can be a real number vector that is subsequently classified by any classifier. In one example, a real number can be input into a softmax classifier. The softmax classifier uses a softmax function or a normalized exponential function to convert a real number input into a normalized probability distribution on a predicted output category. For example, a softmax classifier can indicate the probability that the output is in category A, B, C, etc. Therefore, due to the ability of the classifier to classify various categories, this softmax classifier can be adopted. Other classifiers can be used to perform other classifications. For example, a sigmoid function makes a binary determination about the classification of a category (that is, label A can be used to classify the output, or label A can not be used to classify the output).

[0111] Figure 10An example block diagram of an example computer system 1000 is depicted. Computer system or computing device 1000 may include or be used to implement a data processing system or components thereof. Computing system 1000 includes at least one bus 1005 or other communication component for communicating information, and at least one processor 1010 or processing circuitry coupled to bus 1005 for processing information. Computing system 1000 may also include one or more processors 1010 or processing circuitry coupled to bus 1005 for processing information. Computing system 1000 also includes at least one main memory 1015, such as a random access memory (RAM) or other dynamic storage device, coupled to bus 1005 for storing information and instructions to be executed by processor 1010. Main memory 1015 may be used to store information during execution of instructions by processor 1010. Computing system 1000 may also include at least one read-only memory (ROM) 1020 or other static storage device coupled to bus 1005 for storing static information and instructions for processor 1010. A storage device 1025 , such as a solid-state device, magnetic disk, or optical disk, may be coupled to bus 1005 for persistently storing information and instructions.

[0112] The computing system 1000 may be coupled to a display 1035, such as a liquid crystal display or an active matrix display, via the bus 1005 for displaying information to a user. An input device 1030, such as a keyboard or a voice interface, may be coupled to the bus 1005 for communicating information and commands to the processor 1010. The input device 1030 may include a touch screen display 1035. The input device 1030 may also include a cursor control, such as a mouse, a trackball, or cursor direction keys, for communicating direction information and command selections to the processor 1010 and for controlling cursor movement on the display 1035.

[0113] The processes, systems, and methods described herein can be implemented by the computing system 1000 in response to the processor 1010 executing an arrangement of instructions contained in the main memory 1015. Such instructions can be read into the main memory 1015 from another computer-readable medium, such as the storage device 1025. Execution of the arrangement of instructions contained in the main memory 1015 causes the computing system 1000 to perform the illustrative processes described herein. One or more processors in a multi-processing arrangement can also be used to execute the instructions contained in the main memory 1015. Hard-wired circuitry can be used with the systems and methods described herein in place of or in combination with software instructions. The systems and methods described herein are not limited to any specific combination of hardware circuitry and software.

[0114] Although already Figure 10An example computing system is described in the specification, but the subject matter, including the operations described in this specification, may be implemented in other types of digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this specification and their structural equivalents, or in a combination of one or more of them.

[0115] Now that some illustrative implementations have been described, it will be apparent that the foregoing implementations are illustrative rather than restrictive and have been presented by way of example. Specifically, although many of the examples presented herein involve specific combinations of method actions or system elements, those actions and those elements can be combined in other ways to achieve the same objectives. Actions, elements, and features discussed in conjunction with one implementation are not intended to be excluded from similar roles in other implementations or implementations.

[0116] The hardware and data processing components for implementing the various processes, operations, illustrative logic, logic blocks, modules and circuits described in conjunction with the embodiments disclosed herein can be implemented or executed using a general-purpose single-chip or multi-chip processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components or any combination thereof designed to perform the functions described herein. A general-purpose processor can be a microprocessor, or any conventional processor, controller, microcontroller or state machine. A processor can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors combined with a DSP core, or any other such configuration. In some embodiments, specific processes and methods can be performed by circuits specific to a given function. Memory (e.g., memory, memory unit, storage device, etc.) can include one or more devices (e.g., RAM, ROM, flash memory, hard disk storage device, etc.) for storing data and / or computer code to complete or facilitate the various processes, layers and modules described in this disclosure. The memory may be or may include volatile memory or non-volatile memory and may include database components, object code components, script components, or any other type of information structure for supporting the various activities and information structures described in this disclosure. According to an exemplary embodiment, the memory is communicatively connected to the processor via the processing circuitry and includes computer code for executing (e.g., by the processing circuitry and / or the processor) one or more processes described herein.

[0117] The present disclosure contemplates methods, systems, and program products on any machine-readable medium for completing each operation. Embodiments of the present disclosure can be implemented using existing computer processors, or by a dedicated computer processor of an appropriate system introduced for this purpose or another purpose, or by a hard-wired system. Embodiments within the scope of the present disclosure include program products that include a machine-readable medium for carrying or having machine-executable instructions or data structures stored thereon. Such machine-readable media can be any available medium that can be accessed by a general-purpose or special-purpose computer or other machine with a processor. For example, such machine-readable media can include RAM, ROM, EPROM, EEPROM, or other optical disk storage devices, magnetic disk storage devices, or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of machine-executable instructions or data structures and can be accessed by a general-purpose or special-purpose computer or other machine with a processor. The above combinations are also included within the scope of machine-readable media. Machine-executable instructions include, for example, instructions and data that cause a general-purpose computer, a special-purpose computer, or a dedicated processing machine to perform a certain function or a group of functions.

[0118] The phraseology and terminology used herein are for descriptive purposes and should not be construed as limiting. The use of "including," "comprising," "having," "includes," "involving," "characterized by," "characterized by," and variations thereof herein is meant to encompass the items listed thereafter, their equivalents and additional items, and alternative implementations consisting solely of the items listed thereafter. In one implementation, the systems and methods described herein consist of one, each combination of more than one, or all of the described elements, acts, or components.

[0119] Any reference herein to an implementation or element or action of a system or method mentioned in the singular may also include implementations that include a plurality of such elements, and any reference herein to any implementation or element or action in the plural may also include implementations that include only a single element. Reference in the singular or plural is not intended to limit the presently disclosed systems or methods, their components, actions, or elements to a single configuration or plural configurations. Reference to any action or element based on any information, action, or element may include implementations in which the action or element is based, at least in part, on any information, action, or element.

[0120] Any implementation disclosed herein may be combined with any other implementation or embodiment, and references to "implementations," "some implementations," "an implementation," etc. are not necessarily mutually exclusive and are intended to indicate that a particular feature, structure, or characteristic described in connection with the implementation may be included in at least one implementation or embodiment. These terms as used herein are not necessarily all referring to the same implementation. Any implementation may be combined with any other implementation, inclusively or exclusively, in any manner consistent with the aspects and implementations disclosed herein.

[0121] Where a technical feature in the drawings, detailed description, or any claims is followed by a reference sign, the reference sign is included to enhance the intelligibility of the drawings, detailed description, and claims. Therefore, neither the reference sign nor its absence shall have any limiting effect on the scope of any claim element.

[0122] The systems and methods described herein may be embodied in other specific forms without departing from their characteristics. Unless expressly stated otherwise, references to any degree terms include variations of + / - 10% from the given measurement, unit, or range. Coupled elements may be coupled electrically, mechanically, or physically to each other directly, or with the use of intermediate elements. The scope of the systems and methods described herein is therefore indicated by the appended claims, rather than the foregoing description, and changes that come within the meaning and range of equivalents of the claims are embraced therein.

[0123] The term "coupled" and variations thereof include two members being directly or indirectly joined to one another. Such joining may be static (e.g., permanent or fixed) or removable (e.g., removable or releasable). Such joining may be achieved by direct coupling of the two members or coupling to one another, by coupling the two members to one another using a separate intermediate member and any additional intermediate members, or by coupling the two members to one another using an intermediate member integrally formed as a single unitary body with one of the two members. If "coupled" or variations thereof are modified by additional terms (e.g., directly coupled), the general definition of "coupled" provided above is modified by the plain language meaning of the additional terms (e.g., "directly coupled" means the joining of two members without any separate intermediate member), resulting in a narrower definition than the general definition of "coupled" provided above. Such coupling may be mechanical, electrical, or fluidic.

[0124] References to "or" are to be construed as inclusive, such that any term described using "or" may refer to any of a single, more than one, and all of the terms. References to "at least one of 'A' and 'B'" may include only "A," only "B," and both "A" and "B." Such references used in conjunction with "including" or other open-ended terms may include additional items.

[0125] Without materially departing from the teachings and advantages of the subject matter disclosed herein, modifications may be made to the described elements and actions, such as changes in the dimensions, size, structure, shape and proportions of the various elements, parameter values, mounting arrangements, material usage, color, orientation. For example, an element shown as integrally formed may be composed of multiple parts or elements, the positions of elements may be reversed or otherwise changed, and the nature, number, or position of discrete elements may be changed or varied. Other substitutions, modifications, changes, and omissions may also be made in the design, operating conditions, and arrangement of the disclosed elements and actions without departing from the scope of the present disclosure.

Claims

1. A system comprising: a memory storing weights for a machine learning model, the weights trained on training data in a training set, the training data including patient attributes, stimulation types, and measured brain response signals; an input device configured to receive one or more attributes of a patient; an output device configured to output at least one of audio or visual stimulation to the patient; and One or more processors, the one or more processors configured to: determining a type of stimulation to provide to the patient by applying the one or more attributes to the machine learning model; and A control signal for the output device is generated and transmitted so that the output device outputs the type of stimulation to the patient.

2. The system according to claim 1, wherein: The machine learning model is trained to generate predictions of measured brain responses to a type of stimulation based on the one or more attributes of the patient, and wherein the one or more processors determine the type of stimulation based on the predictions of the measured brain responses.

3. The system according to claim 2, wherein: The one or more processors are configured to determine a type of stimulation based on a brain response measured at a target frequency for the stimulation.

4. The system according to claim 1, wherein: The machine learning model is trained to generate a recommendation for a type of stimulation based on the one or more attributes of the patient, the type of stimulation comprising a type of audio signal for audio stimulation or a type of visual pattern for visual stimulation.

Images