A deep brain stimulation system for treating orthostatic hypotension

Abstract

The object of the present invention is to provide a deep brain stimulation system for treating orthostatic hypotension, comprising: a data acquisition module for collecting physiological state information of a patient, and a data fusion module implanted in the subcutaneous region of the pectoralis major muscle for receiving multi-source physiological data output by the data acquisition module, integrating and filtering noise thereof to generate comprehensive physiological state information of the patient (S t ={BP t ,HR t ,ECG t ,Pos t}); a deep brain stimulation module for precisely stimulating a target brain region to enhance sympathetic nerve output; a response module integrated in the data fusion module for analyzing the physiological state information S t and future physiological state prediction value S t+1 , dynamically adjusting the voltage, frequency and pulse width of the deep brain stimulation module, and real-time optimizing the adjustment strategy according to the physiological feedback data of the patient; a deep brain stimulation system providing real-time blood pressure monitoring, posture sensing and intelligent reaction mechanism.

Description

Technical Field

[0001] The present invention belongs to the field of treatment of orthostatic hypotension, and particularly relates to a deep brain stimulation system for treating orthostatic hypotension. Background Art

[0002] Orthostatic hypotension (OH) is a common disease clinically, mostly caused by autonomic nerve dysfunction. It is manifested as a significant decrease in blood pressure when the patient changes body position (especially from lying or sitting to standing), which can lead to a series of discomfort symptoms such as dizziness, blackening in front of the eyes, weakness and even syncope, seriously affecting the quality of life and safety of patients in their daily life. Especially in the elderly population, the incidence of OH is significantly increased, becoming a key issue of clinical concern. Traditional treatment measures, such as drug adjustment, increasing salt and water intake, using elastic stockings, etc., although can relieve symptoms to a certain extent, for some patients, especially those with severe symptoms, their effects are limited and may have side effects.

[0003] In recent years, deep brain stimulation (DBS) technology has achieved remarkable success in the treatment of movement disorders such as Parkinson's disease. It regulates abnormal nerve activities by precisely stimulating specific brain regions and improves the motor function of patients. A pioneering work by Green et al. revealed the potential of DBS in the regulation of the cardiovascular system (Green AL, Wang S, Owen SL, Xie K, Liu X, Paterson DJ, Stein JF, Bain PG, Aziz TZ. Deep brain stimulation can regulate arterial blood pressure in awake humans. Neuroreport. 2005 Nov 7;16(16):1741-5.). They found that by stimulating different parts of the periventricular gray matter (PVG) and periaqueductal gray matter (PAG) regions, blood pressure can be effectively increased, and this effect may be achieved by enhancing sympathetic nerve output and cardiac contractility, as well as increasing vascular tone. In addition, further studies have shown that this kind of stimulation can maintain blood pressure stability without increasing the basal blood pressure in the supine position, demonstrating its ability of fine regulation in treatment.

[0004] Therefore, developing a DBS device that integrates real-time blood pressure monitoring, body position sensing, and intelligent response, which can automatically monitor blood pressure changes when the patient's body position changes, intelligently analyze the OH risk, and timely activate or adjust the DBS stimulation parameters, is of great significance for improving the treatment effect of OH and ensuring the safety of patients. Such a device will fill the gap in the existing technology, represent a major innovation in the field of OH treatment, and is expected to become the preferred solution for treating OH in the future. Summary of the Invention

[0005] The object of the present invention is to provide a deep brain stimulation system with real-time blood pressure monitoring, posture sensing, and intelligent response functions.

[0006] To achieve the above object, the present invention provides the following technical solutions. A deep brain stimulation system for treating orthostatic hypotension includes:

[0007] A data acquisition module for collecting the physiological state information of the patient, including:

[0008] An implantable pressure sensor implanted in the artery for real-time monitoring of blood pressure data (BP t );

[0009] An electrocardiogram sensor integrated in an electronic wristwatch for collecting electrocardiogram signals (ECG t ) and heart rate data (HR t );

[0010] A posture sensor implanted in the subcutaneous area of the pectoralis major muscle for detecting the patient's body position state (Pos t );

[0011] A data fusion module implanted in the subcutaneous area of the pectoralis major muscle for receiving the multi-source physiological data output by the data acquisition module, integrating it, filtering out noise, and generating the patient's comprehensive physiological state information St = {BP t , HR t , ECG t , Pos t};

[0012] A deep brain stimulation module, including:

[0013] A directional electrode implanted in the target brain area, namely the periventricular gray matter (PVG) area and the periaqueductal gray matter (PAG) area of the patient, for precisely stimulating the target brain area to enhance sympathetic nerve output;

[0014] A stimulation power supply component implanted in the subcutaneous area of the pectoralis major muscle for providing voltage (V t ), frequency (f t ) and pulse width (PW t)Adjustable electrical signals that support segmented and directional stimulation; the directional electrodes are composed of multiple independent electrode patches, each of which can be individually controlled for on / off state, and each electrode patch is precisely distributed in the target brain area according to the anatomical structure and treatment goal; the stimulation power supply component controls the on / off of each electrode patch independently;

[0015] A response module, integrated with the data fusion module in the subcutaneous area of the pectoralis major muscle, for analyzing physiological state information S t , dynamically adjusting the voltage, frequency, and pulse width of the deep brain stimulation module, and optimizing the adjustment strategy in real time according to the patient's physiological feedback data;

[0016] A risk prediction module, integrated with the data fusion module in the subcutaneous area of the pectoralis major muscle, for processing the comprehensive historical physiological state data {S t−n ,...,S t}, predicting the patient's future physiological state S t+1 , and transmitting the predicted value to the response module;

[0017] A reinforcement learning module, integrated with the data fusion module in the subcutaneous area of the pectoralis major muscle, for dynamically updating the stimulation parameter adjustment strategy of the response module according to the patient's physiological feedback data through a reinforcement learning algorithm; the working steps of the reinforcement learning module are as follows:

[0018] S1. Receive the current state S t from the data fusion module, obtain the predicted state S t+1 from the risk prediction module, and initialize the current Q(S t ,A t ) value;

[0019] S2. Select an action based on the current Q-value function, using a greedy strategy, with a probability of choosing a random action, and a probability of choosing the current optimal action. The actions include adjusting the voltage, frequency, pulse width, and activating the electrode patch combination;

[0020] S3. According to the selected action A t , activate a single power supply and the parallel switch matrix through the response module; monitor the feedback state S t ' and the reward R t in real time:

[0021] Reward function:

[0022] S4. Update the Q-value using the Q-Learning algorithm:

[0023] Among them, α is the learning rate, which controls the step size of each update, and γ is the discount factor, which measures the importance of future rewards;

[0024] S5. If the Q(S t , A t ) value of a certain state-action combination is stable and performs well in the long term, update it as a new rule to the rule table.

[0025] Furthermore, the data fusion module generates the patient's real-time comprehensive physiological state information St = {BP t , HR t , ECG t , Pos t} through synchronous processing, noise filtering, feature extraction, and weighted fusion of physiological state information such as blood pressure data, heart rate data, electrocardiogram signals, and body position status.

[0026] Furthermore, the stimulation power supply component consists of a single power supply and a parallel switch matrix;

[0027] The single power supply is implanted in the subcutaneous area of the patient's pectoralis major muscle, and it also has a voltage regulator, a pulse generator, and a power control unit inside; it is used to provide adjustable stimulation parameters for the directional electrodes, including voltage, frequency, and pulse width; among them, the voltage regulator adjusts the amplitude of the output voltage to meet the stimulation intensity requirements of different target brain regions; the pulse generator generates the required stimulation frequency by controlling the repetition rate of the pulses, and the adjustment of the frequency affects the rhythm of the stimulation signal and the discharge response of the target neurons; at the same time, the pulse generator controls the pulse width by adjusting the duration of a single pulse, and the size of the pulse width determines the coverage depth and continuous effect of each electrical stimulation signal;

[0028] The parallel switch matrix is located between the single power supply and the directional electrodes and includes multiple independent switches and a switch control logic circuit; among them, each switch is used to control the on-off state of one or a group of electrode plates; the switch control logic circuit receives switch instructions from the response module and determines which switches to turn on or off, so as to configure a specific combination of electrode plates for the purpose of segmental stimulation to activate a specific area or directional stimulation to concentrate the current to a specific path.

[0029] Furthermore, the response module sends the generated stimulation parameter instructions to the voltage regulator and pulse generator of the single power supply, and at the same time, sends electrode activation instructions to the switch control logic circuit to specify the electrode plates that need to be activated.

[0030] Furthermore, a rule table is integrated in the response module. The rule table defines activation strategies and stimulation parameters in different states based on the patient's physiological state and treatment goals, combined with clinical data or individualized diagnosis results; the control methods of the response module include:

[0031] S1. Receive the current comprehensive physiological state data St = {BP t , HR t , ECG t , Pos t} from the data fusion module;

[0032] S2. Determine whether the patient needs to adjust the stimulation and the combination of electrode patches to be activated according to the real-time data;

[0033] S3. Match the current physiological state with the preset rule table. If there is no complete match, select the nearest matching rule or use the default safety parameters to determine the required combination of electrode patches and stimulation parameters;

[0034] S4. First, send the stimulation parameter instruction to a single power supply, and its internal components generate the target electrical stimulation signal; then send the switch instruction to the switch control logic circuit of the parallel switch matrix to activate the target switch and form the target current path matching the electrical stimulation signal;

[0035] S5. Selectively activate the directional electrode patches to achieve segmented and directional stimulation; at the same time, continuously monitor the patient's physiological feedback through the data acquisition module;

[0036] S6. If the feedback parameters do not reach the expected target, rematch the rule table, preferentially adjust the stimulation parameters. If it is still ineffective, gradually increase the number of activated electrode patches or adjust the positions of the electrode patches until the patient's physiological state returns to the safe range.

[0037] Furthermore, after the risk prediction module outputs the predicted physiological state S t+1 ={BP t+1 , H Rt+1 , ECG t+1 , Pos t+1} at the next moment to the response module, the decision logic of the response module is as follows:

[0038] Rule table matching:

[0039] Match the current state S t with the rule table to obtain the immediate stimulation plan, including the combination of electrode patches and stimulation parameters;

[0040] If the predicted state S t+1 exceeds the safe range, match the corresponding rule in the rule table for S t+1 ;

[0041] Handling when the rule table cannot be matched:

[0042] If the current state S t or the future state S t+1 cannot be matched with the rule table;

[0043] The response module automatically generates stimulation parameters, and the newly generated parameters and corresponding status are recorded for dynamically updating the rule table;

[0044] Decision output:

[0045] Comprehensively considering the t matching results of S t+1 and S

[0046] Furthermore, the steps for the response module to automatically generate stimulation parameters are as follows:

[0047] S1. Obtain the current state S through the data fusion module t , and obtain the future state S through the risk prediction module t+1 . At the same time, obtain the blood pressure target value and blood pressure deviation ΔBP through system presetting. The blood pressure target value BP 目标 is defined as: systolic blood pressure target value = baseline systolic blood pressure - 20 mmHg, diastolic blood pressure target value = baseline diastolic blood pressure - 10 mmHg;

[0048] ΔBP = BP 目标 −BPt

[0049] BPt is the currently monitored blood pressure;

[0050] Deviation classification:

[0051] ΔBP > 0: Blood pressure is too low, and the stimulation intensity needs to be increased.

[0052] ΔBP ≤ 0: Blood pressure is normal or high, and no additional stimulation is required.

[0053] S2. Based on the magnitude of ΔBP, generate stimulation parameters according to the following rules:

[0054] The voltage adjustment logic is to calculate the current blood pressure deviation ΔBP; adjust the voltage through V t = V initial + k v ×ΔBP; where k v represents the voltage value to be increased per unit of blood pressure deviation; at the same time, it is also necessary to ensure that the voltage does not exceed the safe range [V min , V max ;

[0055] The frequency adjustment logic is to calculate the current blood pressure deviation ΔBP; adjust the frequency through f t = f 初始 + kf f ×ΔBP; where k f represents the frequency to be increased per unit of blood pressure deviation; at the same time, it is also necessary to ensure that the frequency does not exceed the range tolerable by the nerve [fmin , f max ;

[0056] The pulse width adjustment logic is to calculate the current blood pressure deviation ΔBP; adjust the pulse width through PW t = PW 初始 + k p × ΔBP to adjust the pulse width; where k P represents the pulse width to be increased per unit blood pressure deviation; at the same time, it is also necessary to ensure that the frequency does not exceed the range tolerable by the nerve [PW min , PW max ;

[0057] The selection of the activated electrode patch combination adjustment logic is to calculate the current blood pressure deviation ΔBP; adjust the number of electrode patches through the linear relationship N = N 初始 + (k n × ΔBP) to adjust the number of electrode patches; where k n represents the number of electrode patches to be increased per unit blood pressure deviation; at the same time, it is also necessary to ensure that the number of activated electrode patches does not exceed the maximum supported number N of the device max ;

[0058] S3. According to the above rules, the response module generates stimulation parameters: activated electrode patch combination, stimulation parameters.

[0059] A deep brain stimulation system for treating orthostatic hypotension proposed by the present invention combines deep brain stimulation technology with modern intelligent algorithms and has the following remarkable beneficial effects:

[0060] 1. Precisely stimulate the target area and improve the treatment effect

[0061] Directional electrode: Through the precise control of independent electrode patches, it can specifically stimulate the periventricular gray matter (PVG) and periaqueductal gray matter (PAG) regions, significantly enhance sympathetic nerve output, improve blood pressure regulation effect, avoid interference with non-target regions, and reduce side effects.

[0062] Segmented and directional stimulation: Dynamically control the activation state of electrode patches through a parallel switch matrix, support segmented stimulation of specific regions and directional concentrated current paths, and further improve the accuracy and efficacy of stimulation.

[0063] 2. Real-time monitoring and dynamic adjustment to ensure safety

[0064] Data acquisition module: Real-time monitor the patient's blood pressure, heart rate, electrocardiogram signal and body position status to ensure comprehensive mastery of the patient's physiological information.

[0065] Data fusion module: Fuse and filter noise from multi-source physiological data to generate real-time comprehensive physiological state information St to ensure the accuracy and reliability of the data.

[0066] Response module: According to the real-time physiological state St and the predicted state St+1, dynamically adjust the stimulation parameters (such as voltage, frequency, and pulse width) to ensure that the stimulation effect reaches the target range while keeping the patient's physiological state within the safe range.

[0067] 3. Intelligent control to enhance adaptability and self-learning ability

[0068] Rule table matching: The response module has a built-in rule table, which can quickly match suitable stimulation parameters and electrode patch activation schemes according to the patient's individual physiological state, reducing the need for manual intervention.

[0069] Risk prediction module: By predicting the future physiological state S t+1 , achieve forward-looking control in the adjustment of stimulation parameters and avoid possible blood pressure fluctuations in advance.

[0070] Reinforcement learning module:

[0071] In the case where the rule table matching is incomplete or the time series prediction deviation is large, dynamically optimize the stimulation strategy through a feedback mechanism.

[0072] It can gradually update and supplement the rule table through the reinforcement learning algorithm, realizing the continuous optimization and adaptive ability of the system, and showing strong advantages especially in complex or emergency situations.

[0073] 4. Personalized treatment to adapt to different patients

[0074] The system can adjust the initial values of the rule table and stimulation parameters according to the patient's individual characteristics (such as age, body type, medical history, etc.) to achieve personalized treatment.

[0075] The risk prediction module can optimize the prediction model based on the patient's long-term monitoring data, and the reinforcement learning module can learn the optimal treatment plan in the long-term feedback.

[0076] 5. The system design is energy-efficient and improves operation stability

[0077] Single power supply and parallel switch matrix:

[0078] Provide adjustable voltage, frequency, and pulse width through a single power supply, reduce hardware complexity, and at the same time support multi-channel output to meet the requirements of electrode patch segmented and directional stimulation.

[0079] The parallel switch matrix dynamically activates the target electrode patches through efficient switching logic, reducing energy consumption and extending the service life of the device.

[0080] 6. Reduce side effects and improve patient comfort

[0081] Precise control: By optimizing the stimulation parameters and the combination of activation electrode patches, over-stimulation or unnecessary energy waste is avoided, reducing possible side effects.

[0082] Dynamic monitoring and adjustment: The system can quickly respond to changes in the patient's physiological state, avoiding dizziness, fatigue or fainting caused by hypotension, and improving the patient's quality of daily life.

[0083] 7. Long-term efficacy optimization driven by data

[0084] Physiological data recording and analysis: The system records the patient's real-time physiological data and feedback results, providing a basis for doctors to evaluate the long-term treatment effect.

[0085] Dynamic update of the rule table: The risk prediction module and the reinforcement learning module work together to continuously optimize the rule table through long-term feedback data, ensuring that the system can adapt to the long-term treatment needs of patients.

[0086] 8. Innovation and clinical application potential

[0087] The system integrates modern biosensing technology, intelligent control algorithms (rule table matching, time series prediction and reinforcement learning), and efficient power management technology, providing an innovative comprehensive solution for the treatment of orthostatic hypotension. Through precise, real-time and personalized treatment methods, this system is very likely to become the standard device for treating orthostatic hypotension in the future, providing a safe and effective long-term treatment option for patients.

[0088] Through the collaborative action of multiple modules, the present invention combines deep brain stimulation technology with intelligent algorithms, solving the problems of poor treatment effect and large side effects in the existing technology for treating orthostatic hypotension. The system shows significant advantages in terms of precision, real-time performance, safety and personalized adaptation, and has extremely high clinical application value and promotion prospects. Brief description of the drawings

[0089] Figure 1 is the overall structural schematic diagram of the present invention;

[0090] Figure 2 is the schematic diagram of module connection in the present invention;

[0091] In the figure, 100, directional electrode; 200, attitude sensor; 300, single power supply; 400, pressure sensor; 500, electronic watch. Detailed implementation manners

[0092] The purpose of the present invention is to provide a deep brain stimulation system for treating orthostatic hypotension. The present invention is a deep brain stimulation system with real-time blood pressure monitoring, attitude sensing and intelligent reaction mechanism.

[0093] To achieve the above object, the present invention provides the following technical solution: A deep brain stimulation system for treating orthostatic hypotension, comprising: a data acquisition module, a data fusion module, a deep brain stimulation module, a response module, a risk prediction module, and a reinforcement learning module; the data acquisition module is used to collect the physiological state information of the patient, including: an implantable micro pressure sensor implanted in the upper limb artery of the patient, which senses the change of blood flow pressure through a capacitive diaphragm structure and outputs the pressure value in real time through an LC resonant circuit integrated on an electronic watch; having the working characteristics of high sensitivity, and monitoring the blood pressure data BP in real time t . Integrated in an electronic wristwatch, an electrode-based single-lead electrocardiogram sensor supporting QRS wave detection is used to collect electrocardiogram signals (ECG t ) and heart rate data (HR t ). Implanted in the subcutaneous area of the pectoralis major muscle, it is internally provided with a 6-axis IMU (inertial measurement unit), an attitude sensor integrating an accelerometer and a gyroscope, for detecting the body position state of the patient (Pos t ).

[0094] In such a closed-loop regulation system, BP t directly reflects the severity of OH and is the "main target variable" of system control; HR t assists in evaluating the autonomic nerve balance and cardiac compensation status; ECG t provides more comprehensive cardiac state information for safety monitoring and fine-tuning of stimulation strategies; Pos t accurately detects body position changes, is the key signal for triggering OH events, and can also be used as a prospective reference for risk prediction.

[0095] Among them, for the convenience of understanding the relationship between the three dependent variables of BP t , HR t , and ECG t , the detailed roles played by BP t , HR t , and ECG t in the whole system are explained in detail;

[0096] BP t (blood pressure data), the core role is the most direct indicator for judging whether the patient has orthostatic hypotension (OH), and it is also the main reference basis for adjusting stimulation strategies (especially voltage, frequency, pulse width).

[0097] Usage scenarios in the system:

[0098] Judging whether to start stimulation: When BP t is within the safe range or slightly on the low side, the system may not perform or only perform the lowest-intensity stimulation; when BP tWhen it falls below a certain threshold, the rule table or risk prediction module triggers the action of "increasing stimulation" or "changing the electrode activation method".

[0099] Real-time closed-loop feedback: After stimulation parameters are adjusted, BP t The change in blood pressure is the key to judging whether the stimulation is effective; if the blood pressure still does not recover, it is necessary to further increase the stimulation or adjust the activation electrode.

[0100] HR t (Heart rate data) is often closely related to the regulation of blood pressure and the state of the autonomic nervous system. Especially when OH occurs, some patients will experience a compensatory increase in heart rate (sympathetic nerve excitement), and there may also be a situation where heart rate changes are out of sync with blood pressure fluctuations. These can indicate the patient's current autonomic nervous function state.

[0101] Usage scenarios in the system:

[0102] Assist in judging the balance of sympathetic / parasympathetic nerves: If blood pressure drops but heart rate does not rise significantly, it may indicate insufficient autonomic nervous response, and stronger DBS stimulation is needed to increase sympathetic output; if heart rate is too high but blood pressure is still low, it indicates insufficient vasoconstriction or ineffective heart rhythm compensation, and targeted stimulation is also needed;

[0103] Warning of abnormal situations: whether the heart rate is too fast, too slow or ectopic rhythm occurs, which also serves as a reminder of the DBS safety boundary.

[0104] ECG t (Electrocardiogram signal) can reflect more cardiac electrophysiological characteristics, such as whether abnormalities such as premature contractions, atrial fibrillation, and premature ventricular beats occur. In patients with orthostatic hypotension, arrhythmias may sometimes occur.

[0105] Usage scenarios in the system:

[0106] Safety monitoring: If ECG t If severe arrhythmia is displayed, the system will be more cautious when adjusting DBS parameters to avoid excessive stimulation frequency or current that increases the burden on the heart;

[0107] Optimizing stimulation strategies: In some cases, PVG / PAG stimulation may affect the vagus nerve or other neural circuits, potentially affecting heart rhythm, ECG t These changes can be captured in time and the system can be assisted to make corresponding corrections.

[0108] The data fusion module is implanted in the subcutaneous area of ​​the pectoralis major muscle to receive the multi-source physiological data output by the data acquisition module, integrate it, filter the noise, and generate the patient's comprehensive physiological status information (S t ={BP t ,HRt , ECG t , Pos t};

[0109] Within the above two modules, the specific working steps are as follows

[0110] S1. First, the 6-axis IMU sensor (Inertial Measurement Unit) implanted by the system records the acceleration and angular velocity data of the patient in real time.

[0111] Determine the body position change through the following analysis steps:

[0112] Static posture: Detect the current acceleration direction of the patient through the accelerometer to distinguish standing, lying flat, and sitting postures.

[0113] Dynamic posture: Record the angular velocity through the gyroscope to judge the posture transition (such as the transition from lying flat to standing).

[0114] Analysis of posture transition rate:

[0115] Calculate the acceleration value and time interval Δt of the body position change, and evaluate the change rate: ; If the rate v > v 阈值 (such as standing up quickly), mark it as a possible hypotensive trigger event.

[0116] Combining the posture state (standing) and rate (quick standing), the system preliminarily marks potential hypotensive events and enters the further data acquisition link.

[0117] S2. The implantable pressure sensor monitors the blood pressure data (BP t ); The optical heart rate sensor collects the heart rate data (HR t ); The electrocardiogram sensor collects the electrocardiogram signal (ECG t ); Integrate the data to form the current state:

[0118] The data fusion module integrates the posture state and real-time physiological data to generate the current comprehensive state: S t = {BP t , HR t , ECG t , Pos t}

[0119] S3. The data fusion module receives {BP t , HR t , ECG t , Pos t}:

[0120] Synchronous sampling: Align the timestamps of each signal to ensure data consistency.

[0121] Noise filtering: The fluctuating noise of the pressure sensor is eliminated through a Kalman filter.

[0122] Feature extraction: Features such as the blood pressure change rate ΔBP and the heart rate change trend are extracted to enhance the state assessment.

[0123] Weighting process: Weights are set according to the importance of the data. In this embodiment, the weight of blood pressure data is set higher than that of the posture state:

[0124] S4. At the same time, a low blood pressure risk assessment is also performed by the calculation module on the data fusion module;

[0125] First, it is judged whether the current blood pressure BP is lower than the blood pressure target value (BP target). Here, the BP target is defined as: systolic blood pressure target value = baseline systolic blood pressure - 20 mmHg, diastolic blood pressure target value = baseline diastolic blood pressure - 10 mmHg; if the patient's real-time systolic blood pressure < baseline systolic blood pressure - 20 mmHg, the system marks it as a low blood pressure risk. If the heart rate HRt > 100 bpm, it is assisted to determine as compensatory hypotension (with compensation but insufficient compensation); the posture state Pos t = standing is an important condition for triggering the risk. At this time, it belongs to the need for low-intensity stimulation; if the patient's real-time systolic blood pressure < baseline systolic blood pressure - 20 mmHg, the system marks it as a low blood pressure risk. If the heart rate HR t < 100 bpm, it is assisted to determine as uncompensated hypotension (the heart has not compensated); the posture state Pos t = standing is an important condition for triggering the risk. At this time, it belongs to the need for high-intensity stimulation.

[0126] Deep brain stimulation module, including:

[0127] Directional electrodes are implanted in the periventricular gray matter (PVG) and periaqueductal gray matter (PAG) regions of the patient to accurately stimulate the target brain area to enhance sympathetic nerve output;

[0128] The stimulation power supply component is implanted in the subcutaneous area of the pectoralis major muscle to provide an adjustable voltage (V t )), frequency (f t )), and pulse width (PW t )), to support segmented and directional stimulation and avoid interference with non-target areas;

[0129] The response module is integrated with the data fusion module in the subcutaneous area of the pectoralis major muscle to analyze the physiological state information S t , dynamically adjust the voltage, frequency, and pulse width of the deep brain stimulation module, and optimize the adjustment strategy in real time according to the patient's physiological feedback data;

[0130] A risk prediction module, which is integrated with the data fusion module in the subcutaneous region of the pectoralis major muscle, is used to process the historical data of the comprehensive physiological state {S t−n ,...,S t}, predict the future physiological state S t+1 of the patient, and transmit the predicted value to the response module for prospective adjustment of the deep brain stimulation parameters;

[0131] A reinforcement learning module, which is integrated with the data fusion module in the subcutaneous region of the pectoralis major muscle, is used to dynamically update the stimulation parameter adjustment strategy of the response module according to the patient's physiological feedback data through a reinforcement learning algorithm.

[0132] In one embodiment, the directional electrode is composed of a plurality of independent electrode sheets, and the on-off state of each electrode sheet can be controlled independently. At the same time, each electrode sheet is accurately distributed in the periventricular gray matter (PVG) and periaqueductal gray matter (PAG) regions according to the anatomical structure and treatment target; wherein, the stimulation power supply component avoids the influence on non-target regions by independently controlling the on-off of each electrode sheet, improves the pertinence and safety of stimulation, and realizes accurate stimulation of a specific target brain region (such as PVG or PAG).

[0133] The stimulation power supply component consists of a single power supply and a parallel switch matrix; the single power supply is implanted in the subcutaneous region of the patient's pectoralis major muscle, and a voltage regulator, a pulse generator and a power control unit are also arranged therein; it is used to provide adjustable stimulation parameters for the directional electrode, including voltage (V t ), frequency (f t ), and pulse width (PW t ); wherein, the voltage regulator adjusts the amplitude of the output voltage (V t ) to meet the requirements of different target brain regions for the stimulation intensity; the pulse generator generates the required stimulation frequency (f t ) by controlling the repetition rate of the pulse, and the adjustment of the frequency (f t ) affects the rhythm of the stimulation signal and the discharge response of the target neurons; at the same time, the pulse generator controls the pulse width (PW t ) by adjusting the duration of a single pulse, and the size of the pulse width (PW t ) determines the coverage depth and continuous effect of each electrical stimulation signal; at the same time, a power control unit is also arranged in the single power supply: the power control unit realizes the power distribution and protection functions, is responsible for monitoring the output power, preventing overload or short circuit, and ensuring the stable operation of the system.

[0134] A parallel switch matrix, located between a single power supply and a directional electrode, includes a plurality of independent switches and switch control logic circuits; wherein, each switch is used to control the on-off state of one or a group of electrode plates; the switch control logic circuit receives switch instructions from the response module and determines which switches to turn on or off, so as to configure a specific electrode plate activation combination for segmented stimulation (activating a specific area) or directional stimulation (concentrating the current to a specific path).

[0135] In one embodiment, the response module sends the generated stimulation parameter instructions to the voltage regulator and pulse generator of the single power supply, and at the same time, sends electrode activation instructions to the switch control logic circuit to specify the electrode plates to be activated.

[0136] A rule table is provided in the response module. The rule table defines activation strategies and stimulation parameters in different states based on the patient's physiological state and treatment goals, combined with clinical data or individualized diagnostic results; here, the establishment process of the rule table is shown in detail:

[0137] First is the initial establishment process of the rule table; before the system is officially used or implanted, usually an "initialization" or "calibration" process will be carried out to establish the initial rule table. Its typical process is as follows:

[0138] S1. Data collection and baseline measurement

[0139] Collect the patient's resting blood pressure BP t , heart rate HR t , electrocardiogram ECG t and body position Pos t (lying position, sitting position, standing position, etc.) of the baseline values in different daily situations;

[0140] Collect the fluctuations of blood pressure and heart rate when the patient changes from lying position to standing position under the condition of "DBS stimulation not started", and evaluate the severity, occurrence rate and tolerance of the patient's OH.

[0141] S2. Posture change induction test

[0142] In a controllable environment (such as hospital monitoring conditions), let the patient change body position (lying position → sitting position or lying position → standing position), and measure the fluctuations of blood pressure BPt, heart rate HRt, and electrocardiogram ECGt in real time;

[0143] According to the amplitude of blood pressure drop and the threshold of symptoms such as dizziness or fainting, initially determine the required stimulation voltage, frequency, and pulse width range;

[0144] Determine the minimum effective stimulation value (the stimulation parameters that can initially counteract the blood pressure drop) and the maximum safety threshold (to avoid overstimulation).

[0145] Segmented / Oriented Electrode Activation Test

[0146] Within the adjustable range, activate the electrode patches of PVG (Periventricular Gray) and PAG (Periaqueductal Gray) sequentially / combinatorially, and observe which activation combination is most effective in raising blood pressure with the least side effects;

[0147] According to the test results, record the "most effective brain region stimulation combination" as the basic rule.

[0148] S3. Form the initial rule table

[0149] Summarize the above data, combine the experience of clinicians and safety margins, and define several rules (Rule), each rule corresponding to the mapping relationship of "current state / predicted state → target stimulation scheme";

[0150] For example, if the blood pressure is too low (BP t < X1), and the heart rate is high (HR t > Y1), then activate the electrodes in the low voltage + high frequency + PVG area; if the blood pressure is very low (BP t < X2), then the pulse width can be superimposed and more electrode patches can be activated, etc. These rules can support most of the system's decisions during the startup phase.

[0151] Among them, the control methods of the response module include:

[0152] S1. Receive the current comprehensive physiological state data (S t ={BP t , HR t , ECG t , Pos t}) from the data fusion module;

[0153] S2. Judge whether the patient needs to adjust the stimulation according to the real-time data, as well as the position and quantity of the electrode patches to be activated;

[0154] S3. Match the current physiological state with the preset rule table. If it is not fully matched, select the nearest matching rule or use the default safety parameters to determine the required activation area (PVG area, PAG area, or both simultaneously), activation quantity (the quantity and distribution of the activated electrode patches), and stimulation parameters (voltage (Vt), frequency (ft), and pulse width (PWt));

[0155] S4. First, send the stimulation parameter instruction to a single power supply, and its internal components (voltage regulator, pulse generator) generate the target electrical stimulation signal; then send the switch instruction to the switch control logic circuit of the parallel switch matrix to activate the target switch and form a target current path matching the electrical stimulation signal;

[0156] S5. Selectively activate the directional electrode patches to achieve segmented and directional stimulation; at the same time, continuously monitor the patient's physiological feedback (such as blood pressure BP t , heart rate HR t , etc.) through the data acquisition module;

[0157] S6. If the feedback parameters do not reach the expected target, re-match the rule table, and preferentially adjust the stimulation parameters (such as voltage). If it is still ineffective, gradually increase the number of activated electrode patches or adjust the electrode patch positions until the patient's physiological state returns to the safe range.

[0158] In one embodiment, the risk prediction module outputs the predicted physiological state S at the next moment through the time series model t+1 ={BP t+1 ,HR t+1 ,ECG t+1 ,Pos t+1} to the response module, and the decision logic of the response module is as follows:

[0159] Rule table matching:

[0160] The current state S t , match the rule table to obtain the immediate stimulation plan (including electrode patch activation and stimulation parameters);

[0161] If the predicted state S t+1 , exceeds the safe range, preferentially match the rules corresponding to S t+1 ;

[0162] Handling when the rule table cannot be matched:

[0163] If the current state S t or the future state S t+1 cannot match the rule table;

[0164] The risk prediction module automatically generates stimulation parameters, and the newly generated parameters and the corresponding states are recorded for dynamically updating the rule table;

[0165] Decision output:

[0166] Taking into account the matching results of S t and S t+1 , generate the final stimulation instruction, including: the combination of activated electrode patches (PVG area, PAG area, or both), the stimulation parameter voltage (V t ), frequency (f t ), and pulse width (PW t ).

[0167] Taking into account S t and St+1 When setting different weights, the final parameter = α × current state parameter + β × predicted state parameter; α and β are weight coefficients that can be adjusted according to the actual situation.

[0168] Combined with the patient's physiological feedback data (such as the real-time changes in blood pressure and heart rate), the output parameters are further adjusted to form a closed-loop optimization; each newly generated parameter and its corresponding state are recorded in the rule table for subsequent rapid matching, improving the system response speed and efficiency.

[0169] Furthermore, the steps for the response module to automatically generate stimulation parameters are as follows:

[0170] S1. Obtain the current state S through the data acquisition module t , and obtain the future state S through the risk prediction module t+1 , and at the same time obtain the blood pressure target value and blood pressure deviation (ΔBP) through system preset. The blood pressure target value (BP 目标 ) is defined as: systolic blood pressure target value = baseline systolic blood pressure - 20 mmHg, diastolic blood pressure target value = baseline diastolic blood pressure - 10 mmHg;

[0171] ΔBP = BP 目标 −BP t

[0172] BPt is the currently measured blood pressure in real time.

[0173] Deviation classification:

[0174] ΔBP > 0: Blood pressure is too low, and the stimulation intensity needs to be increased.

[0175] ΔBP ≤ 0: Blood pressure is normal or high, and no additional stimulation is required.

[0176] S2. Based on the magnitude of ΔBP, generate stimulation parameters according to the following rules:

[0177] The voltage controls the intensity of the stimulation signal, which directly determines the amplitude of the stimulation current. A higher voltage can more strongly activate the target nerve area but may cause unnecessary side effects (such as overstimulation); its adjustment logic is to calculate the current blood pressure deviation ΔBP; adjust the voltage through V t = V initial + k v ×ΔBP to increase or decrease the stimulation intensity; where k v represents the voltage value that needs to be increased per unit of blood pressure deviation; at the same time, it is also necessary to ensure that the voltage does not exceed the safe range [V min , V max ;

[0178] The frequency determines the rhythm of the stimulation signal and affects the frequency and efficiency of nerve excitation. A higher frequency can rapidly accumulate the stimulation effect but may lead to nerve adaptation and reduce the therapeutic effect. Its adjustment logic is to calculate the current blood pressure deviation ΔBP; through f t =f 初始 +kf f ×ΔBP to adjust the frequency and control the stimulation rhythm; where k f represents the frequency that needs to be increased per unit blood pressure deviation; at the same time, it is also necessary to ensure that the frequency does not exceed the range tolerable by the nerve [f min ,f max ;

[0179] The pulse width defines the duration of each stimulation and affects the cumulative intensity of the stimulation. Prolonging the pulse width can increase the stimulation effect of each pulse but may increase power consumption. Its adjustment logic is to calculate the current blood pressure deviation ΔBP; through PW t =PW 初始 +k p ×ΔBP to adjust the pulse width and prolong the single stimulation effect; where k P represents the pulse width that needs to be increased per unit blood pressure deviation; at the same time, it is also necessary to ensure that the frequency does not exceed the range tolerable by the nerve [PW min ,PW max ;

[0180] Activating more electrode pads can expand the stimulation range and improve the treatment effect. According to anatomy and the target area (such as PVG and PAG), reasonably select the combination of activated electrode pads. Its adjustment logic is to calculate the current blood pressure deviation ΔBP; through the linear relationship N=N 初始 +(k n ×ΔBP) to adjust the number of electrode pads and increase the stimulation coverage; where k n represents the number of electrode pads that needs to be increased per unit blood pressure deviation; at the same time, it is also necessary to ensure that the number of activated electrode pads does not exceed the maximum supported number N max ;

[0181] S3. The response module generates stimulation parameters according to the above adjustment rules: the combination of activated electrode pads (quantity N and target area (PVG, PAG, or both)), the stimulation parameter voltage (V t ), the frequency (f t ) and the pulse width (PW t ).

[0182] In one embodiment, when the rule table matching is incomplete or the risk prediction module predicts a large deviation, the reinforcement learning module optimizes the stimulation parameter adjustment strategy through a feedback mechanism; the working steps of the reinforcement learning module are as follows:

[0183] S1. Receive the current state S from the data fusion module t , and obtain the predicted state S from the risk prediction module t+1 , and initialize the current Q(S t , A t ) value;

[0184] S2. Select an action based on the current Q-value function, using a greedy strategy, select a random action with a probability (exploration), select the current optimal action with a probability (exploitation). The actions include adjusting the voltage, frequency, pulse width, and activating the electrode patches;

[0185] S3. According to the selected action A t , activate a single power supply and the parallel switch matrix through the response module; monitor the feedback state S t ' and the reward R t :

[0186] Reward function:

[0187] S4. Update the Q-value using the Q-Learning algorithm:

[0188] where α is the learning rate, controlling the step size of each update, and γ is the discount factor, measuring the importance of future rewards;

[0189] S5. If the Q(S t , A t ) value of a certain state-action combination is stable and performs well in the long term, update it as a new rule to the rule table.

[0190] Here, a detailed explanation of the dynamic update of the rule table is given; during the long-term operation of the system, the rule table is not static, but will be dynamically updated with the continuous feedback of the reinforcement learning module and the risk prediction module:

[0191] S1. Feedback from the reinforcement learning module

[0192] When the system finds that the existing rule table cannot well solve some extreme or unexpected situations, it will try new stimulation strategies; if the new strategy achieves good results (such as a rapid increase in blood pressure without side effects), the new strategy will be written into the rule table. In the long run, the rule table will be richer and more personalized.

[0193] S2. Risk prediction deviation correction

[0194] If the predicted value of future blood pressure by the risk prediction module (based on the time series model) deviates significantly from the actual value, the system will record the rules triggered at that time and their execution effects, which are used to correct or refine the corresponding rules while updating the prediction model.

[0195] 4. Example Structure of the Rule Table

[0196] For a more intuitive understanding, a simplified example rule table is given below (for reference only, the actual system may be more complex):

[0197]

[0198] "Suggested activation of electrodes" may correspond to multiple electrode combinations, which are only roughly described in the table.

[0199] The circuits and controls involved in the present invention are all prior arts and will not be elaborated here.

[0200] The above are only embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be similarly included in the patent protection scope of the present invention.

Claims

1. A deep brain stimulation system for treating postural hypotension, characterized in that: include: The data acquisition module is used to collect the patient's physiological status information, including: Implantable pressure sensor, implanted in the artery, is used to monitor blood pressure data (BP) in real time. t ); ECG sensor, integrated into electronic wristwatch, used to collect ECG signals (ECG t ) and heart rate data (HR t ); The posture sensor is implanted in the subcutaneous area of ​​the pectoralis major muscle to detect the patient's posture (Pos t ); The data fusion module is implanted in the subcutaneous area of ​​the pectoralis major muscle and is used to receive the multi-source physiological data output by the data acquisition module, integrate and filter the noise, and generate the patient's comprehensive physiological state information St = {BP t ,HR t ,ECG t ,Pos t }; Deep Brain Stimulation Module, including: Directional electrodes are implanted in the target brain regions, namely the patient's periventricular gray matter (PVG) and periaqueductal gray matter (PAG) regions, to precisely stimulate the target brain regions to enhance sympathetic nerve output; The stimulation power supply assembly is implanted in the subcutaneous area of ​​the pectoralis major muscle and is used to provide voltage (V t ), frequency (f t ) and pulse width (PW t ) adjustable electrical signals, supporting segmented and directional stimulation; the directional electrode is composed of a plurality of independent electrode pieces, each of which can be individually controlled to be on and off, and each electrode piece is precisely distributed in the target brain area according to the anatomical structure and treatment target; the stimulation power supply component independently controls the on and off of each electrode piece; The response module is integrated with the data fusion module in the subcutaneous area of ​​the pectoralis major muscle to analyze the physiological state information S t , dynamically adjust the voltage, frequency and pulse width of the deep brain stimulation module, and optimize the adjustment strategy in real time according to the patient's physiological feedback data; The risk prediction module is integrated with the data fusion module in the subcutaneous area of ​​the pectoralis major muscle to process the comprehensive physiological status historical data {S t−n ,...,S t }, predict the patient's future physiological state S t+1 , and pass the predicted value to the response module; The reinforcement learning module is integrated with the data fusion module in the subcutaneous area of ​​the pectoralis major muscle, and is used to dynamically update the stimulation parameter adjustment strategy of the response module according to the patient's physiological feedback data through the reinforcement learning algorithm; the working steps of the reinforcement learning module are as follows: S1, receive the current state S from the data fusion module t , obtain the predicted status S from the risk prediction module t+1 , initialize the current Q(S t ,A t )value; S2, select actions based on the current Q-value function, using Greedy strategy, Probabilistically choose a random action, Probabilistically select the current optimal action, which includes adjusting the voltage, frequency, pulse width and activation electrode combination; S3, according to the selected action A t , activate the single power supply and parallel switch matrix through the response module; monitor the feedback state S after stimulation in real time t ′ and reward R t : Reward function: ; S4. Update the Q-value using the Q-Learning algorithm: Among them, α is the learning rate, which controls the step size of each update, and γ is the discount factor, which measures the importance of future rewards; S5. If Q(S t ,A t ) value is stable for a long time and performs well, update it into the rule table as a new rule.

2. A deep brain stimulation system for treating orthostatic hypotension according to claim 1, characterized in that: The data fusion module generates the patient's real-time comprehensive physiological state information St = {BP t ,HR t ,ECG t ,Pos t }.

3. A deep brain stimulation system for treating orthostatic hypotension according to claim 1, characterized in that: The stimulation power supply assembly is composed of a single power supply and a parallel switch matrix; A single power supply is implanted in the subcutaneous area of ​​the pectoralis major muscle of the patient, and is also provided with a voltage regulator, a pulse generator and a power control unit; it is used to provide adjustable stimulation parameters for the directional electrodes, including voltage, frequency and pulse width; wherein the voltage regulator adjusts the amplitude of the output voltage to meet the stimulation intensity requirements of different target brain areas; the pulse generator generates the required stimulation frequency by controlling the repetition rate of the pulse, and the adjustment of the frequency affects the rhythm of the stimulation signal and the discharge response of the target neuron; at the same time, the pulse generator controls the pulse width by adjusting the duration of a single pulse, and the pulse width determines the coverage depth and continuous effect of each electrical stimulation signal; A parallel switch matrix is ​​located between the single power supply and the directional electrode, and includes a plurality of independent switches and a switch control logic circuit; wherein each switch is used to control the on / off state of one or a group of electrode sheets; the switch control logic circuit receives a switch instruction from the response module and determines which switches are turned on or off, thereby achieving the purpose of configuring a specific electrode sheet combination for segmented stimulation to activate a specific area or directional stimulation to concentrate current to a specific path.

4. A deep brain stimulation system for treating orthostatic hypotension according to claim 3, characterized in that: The response module sends the generated stimulation parameter instruction to the voltage regulator and pulse generator of the single power supply, and at the same time, sends the electrode activation instruction to the switch control logic circuit to specify the electrode sheet that needs to be activated.

5. A deep brain stimulation system for treating orthostatic hypotension according to claim 1, characterized in that: The response module is integrated with the rule table, which defines activation strategies and stimulation parameters under different states based on the patient's physiological state and treatment goals in combination with clinical data or individualized diagnosis results; The control method of the response module includes: S1, receiving the current comprehensive physiological state data St = {BP t ,HR t ,ECG t ,Pos t }; S2. judging whether the patient needs to adjust the stimulation and the electrode combination that needs to be activated according to the real-time data; S3, matching the current physiological state with the preset rule table, if not completely matched, selecting the most recently matched rule or using the default safety parameters to determine the required electrode combination and stimulation parameters; S4, first sending a stimulation parameter instruction to the single power supply, so that its internal components generate a target electrical stimulation signal; then sending a switch instruction to the switch control logic circuit of the parallel switch matrix, activating the target switch, and forming a target current path matching the electrical stimulation signal; S5, selectively activating the directional electrode sheet to achieve segmented and directional stimulation; and continuously monitoring the patient's physiological feedback through the data acquisition module; S6. If the feedback parameters do not reach the expected target, re-match the rule table and adjust the stimulation parameters first. If it is still ineffective, gradually increase the number of activated electrodes or adjust the position of the electrodes until the patient's physiological state returns to a safe range.

6. A deep brain stimulation system for treating orthostatic hypotension according to claim 1, characterized in that: The risk prediction module outputs the predicted physiological state S at the next moment through the time series model t+1 ={BP t+1 ,H Rt+1 ,ECG t+1 ,Pos t+1 } to the response module, the decision logic of the response module is as follows: Rule table matching: Current Status t Match the rule table to obtain the immediate stimulation plan, including electrode combination and stimulation parameters; If the predicted state S t+1 Out of the safety range, matching rule table S t+1 Corresponding rules; Processing when the rule table cannot be matched: If the current state S t or future state S t+1 Unable to match the rule table; The response module automatically generates stimulus parameters, and the newly generated parameters and corresponding states are recorded for dynamic updating of the rule table; Decision output: Comprehensive consideration t and S t+1 The matching results generate the final stimulation instructions, including: activation electrode combination and stimulation parameters.

7. A deep brain stimulation system for treating orthostatic hypotension according to claim 6, characterized in that: The steps of automatically generating stimulation parameters by the response module are as follows: S1. Obtain the current state S through the data fusion module t , obtain the future state S through the risk prediction module t+1 At the same time, the blood pressure target value and the blood pressure deviation ΔBP are obtained through system preset. The blood pressure target value BP 目标 The definition is: systolic blood pressure target value = baseline systolic blood pressure - 20 mmHg, diastolic blood pressure target value = baseline diastolic blood pressure - 10 mmHg; ΔBP=BP 目标 −BPt BPt is the current blood pressure monitored in real time; Deviation classification: ΔBP>0: blood pressure is too low and stimulation intensity needs to be increased; ΔBP≤0: blood pressure is normal or high, no need to increase stimulation; S2. Based on the size of ΔBP, the stimulation parameters are generated according to the following rules: The voltage adjustment logic is to calculate the current blood pressure deviation ΔBP; through V t =Vinitial+k v ×ΔBP adjusts the voltage; where k v Indicates the voltage value that needs to be increased for each unit of blood pressure deviation; at the same time, it is also necessary to ensure that the voltage does not exceed the safety range [V min ,V max ]; The frequency adjustment logic is to calculate the current blood pressure deviation ΔBP; through f t =f 初始 +kf f ×ΔBP adjustment frequency; where k f Indicates the frequency that needs to be increased for each unit of blood pressure deviation; at the same time, it is necessary to ensure that the frequency does not exceed the range that the nerve can tolerate [f min ,f max ]; The pulse width adjustment logic is to calculate the current blood pressure deviation ΔBP; through PW t =PW 初始 +k p ×ΔBP adjusts the pulse width; where k P Indicates the pulse width that needs to be increased for each unit of blood pressure deviation; at the same time, it is necessary to ensure that the frequency does not exceed the range that the nerve can tolerate [PW min ,PW max ]; Select the activated electrode combination adjustment logic to calculate the current blood pressure deviation ΔBP; through the linear relationship N=N 初始 +(k n ×ΔBP) to adjust the number of electrodes; where k n Indicates the number of electrodes that need to be added for each unit of blood pressure deviation; at the same time, it is also necessary to ensure that the number of activated electrodes does not exceed the maximum supported number N of the device max ; S3. The response module generates stimulation parameters according to the above rules: activation electrode combination and stimulation parameters.

Images