WO2024027781A1 - Self-diagnosis device, programmable system, and computer-readable storage medium - Google Patents

Abstract

A self-diagnosis device (200), a programmable system (100), and a computer-readable storage medium. The self-diagnosis device (200) is configured to: acquire, when a patient satisfies a preset monitoring condition, first measurement data of health monitoring parameters of the patient using a health monitoring device (300); determine whether the first measurement data of each of the health monitoring parameters is within a corresponding preset range thereof; when it is detected that the first measurement data of one or more of the health monitoring parameters are not within corresponding preset ranges thereof, acquire historical measurement data; acquire actual configuration information on the basis of the historical information about the last N configurations, and make a stimulator deliver electrical stimulation corresponding to the actual configuration information to in-vivo tissues of the patient; acquire second measurement data of health monitoring parameters of the patient using the health monitoring device (300); and detect the presence of faults in the stimulator on the basis of historical measurement data and the second measurement data to obtain a fault diagnosis result. By means of the self-diagnosis device (200), the patient is enabled to acquire a fault result for the stimulator as soon as possible.

Description

Self-diagnostic equipment, program-controlled systems and computer-readable storage media

This application claims priority to the Chinese patent with application number 202210939974.0, which was submitted on August 5, 2022. The above Chinese patent is incorporated by reference in full.

Technical field

This application relates to the technical field of implantable medical devices, such as self-diagnostic equipment, program-controlled systems and computer-readable storage media.

Background technique

In the technical field of implantable medical equipment, a programmable controller is used to establish a programmable connection with the patient's IPG (Implantable Pulse Generator). The doctor adjusts the configuration information of the IPG through the programmable controller to achieve control of the IPG. adjustment of stimulation parameters.

In the related art, the IPG is generally checked when the doctor adjusts the configuration information of the IPG through the program controller, or when the stimulator delivers electrical stimulation to the tissue in the patient's body.

For example, patent CN113426009A discloses a Parkinson's disease treatment device and its application method based on DBS technology. The method includes: when performing electrical stimulation treatment, the electrode stimulation signal is transmitted to the adapter module through the extended wire, and is then sequentially introduced to the signal detection The module detects the signal, and then uses the signal to determine whether the module comparison signal is correct. When the signal is correct, the device operates normally. When the signal is abnormal, the device operates abnormally. During abnormal operation, the operation detection module detects that the main chip and main power supply are shut down or If it is damaged, the signal judgment module determines the abnormality, so that the patient can contact the hospital to repair or replace the IPG neurostimulator. This patent uses the electrode stimulation signal itself to detect whether the stimulator is malfunctioning during electrical stimulation treatment, without considering the patient's own condition.

Based on this, this application provides a self-diagnostic device, a program-controlled system and a computer-readable storage medium to solve the problems existing in the above related technologies.

Contents of the invention

The purpose of this application is to provide a self-diagnostic device, a program-controlled system and a computer-readable storage medium, which can detect whether a fault occurs in the stimulator through historical measurement data and second measurement data based on the patient's first measurement data.

The purpose of this application is achieved using the following technical solutions:

Firstly, this application provides

A self-diagnostic device, the self-diagnostic device is used to perform fault self-diagnosis of a stimulator implanted in a patient, the self-diagnostic device is configured to:

When the patient meets the preset monitoring conditions, use the health monitoring equipment to obtain the first measurement data of the patient's health monitoring parameters;

Detect respectively whether the first measurement data of each of the health monitoring parameters is within its corresponding preset range;

Obtain actual configuration information when it is detected that the first measurement data of one or more health monitoring parameters is not within its corresponding preset range, so that the stimulator delivers the actual configuration information to the patient's body tissue. Corresponding electrical stimulation, the actual configuration information is used to indicate the actual parameter value of each stimulation parameter of the stimulator;

utilizing the health monitoring device to obtain second measurement data of the patient's health monitoring parameters;

Based on the historical measurement data and the second measurement data, it is detected whether a fault occurs in the stimulator to obtain a fault diagnosis result.

In one implementation, the self-diagnosis device is configured to obtain the actual configuration information in the following manner:

Obtain the most recent N historical configuration information of the stimulator and the corresponding historical measurement data of the patient's health monitoring parameters, where N is a positive integer;

The actual configuration information is obtained based on the most recent N times of historical configuration information.

In one implementation, the first measurement data includes one or more of the following: heart rate data, pulse data, electromyography data, and electroencephalography data;

The historical configuration information includes one or more stimulation parameter identifiers and historical parameter values corresponding to each stimulation parameter identifier, and N is a positive integer;

The preset monitoring conditions include one or more of the following: the current time reaches the preset monitoring time; the patient is detected to have fallen, dropped, twitched, self-mutilated or inhaled.

In one implementation, the self-diagnosis device is configured to obtain fault diagnosis results in the following manner:

Input the historical measurement data and the second measurement data into a similarity model to obtain the similarity between the historical measurement data and the second measurement data;

When the similarity is not less than a preset similarity threshold, it is determined that the fault diagnosis result is the stimulus The device did not malfunction;

When the similarity is less than the preset similarity threshold, it is determined that the fault diagnosis result is that the stimulator is faulty;

Wherein, the training process of the similarity model includes:

Obtain a first training set, the first training set includes a plurality of training data, each of the training data includes a first sample object, a second sample object, the first sample object and the second sample object similarity;

For each training data in the first training set, perform the following processing: input the first sample object and the second sample object in the training data into the preset first deep learning model to obtain the first The predicted similarity between the sample object and the second sample object;

Based on the predicted similarity between the first sample object and the second sample object, update the model parameters of the first deep learning model;

Check whether the preset training end condition is met; if so, use the trained deep learning model as the similarity model; if not, use the next training data to continue training the first deep learning model.

In one implementation, when the fault diagnosis result is that the stimulator is faulty, the self-diagnosis device is further configured to:

An alarm signal is sent out using an alarm device, which includes one or more of a sound alarm device, a flash alarm device, or an audible and visual alarm device.

In one implementation, the stimulator includes an IPG and one or more electrode leads;

The self-diagnostic device is configured to determine a fault diagnosis result of the stimulator in the following manner:

Detect respectively whether the impedance data of each electrode lead is within its corresponding preset range;

When it is detected that the impedance data of one or more electrode wires is not within its corresponding preset range, it is determined that the fault diagnosis result is that the electrode wire whose impedance data is not within its corresponding preset range is faulty. occur;

When it is detected that the impedance data of all the electrode leads are within their corresponding preset ranges, it is determined that all the electrode leads are fault-free, and based on the historical measurement data and the second measurement data, continue to detect whether the IPG A fault occurs to obtain the fault diagnosis result.

In one implementation, when the fault diagnosis result is that a fault occurs, the self-diagnosis device Also configured to:

Store the fault information of the stimulator to a preset storage location, and generate fault prompt information to send to the preset user equipment. The fault information of the stimulator includes stimulator identification information, fault time information and fault type information. of one or more.

In one implementation, the self-diagnosis device is further configured to:

Utilize the user equipment to receive the user's fault upload operation;

In response to the fault upload operation, the fault information of the stimulator is sent to a preset service device.

In one implementation, the self-diagnosis device is further configured to:

When the amount of the fault information stored in the preset storage location is not less than the preset number of faults, the latest fault information of the stimulator is sent to the preset service device.

In one implementation, the process of detecting whether the patient falls, falls, twitches, self-mutilates, takes drugs, or has no abnormal events includes:

utilizing visual inspection equipment to obtain real-time images including the patient;

The real-time image is input into the abnormal event model to obtain the event classification result corresponding to the real-time image. The event classification result is falling, falling, twitching, self-mutilation, sucking, or no abnormal event.

In a second aspect, this application also provides a program-controlled system, which includes a health monitoring device and the self-diagnostic device of any one of the first aspects, and the self-diagnostic device and the health monitoring device are communicatively connected. .

In a third aspect, the present application also provides a computer-readable storage medium that stores a computer program. When the computer program is executed by a processor, the self-diagnosis of any one of the first aspects is implemented. Device functionality.

This application provides self-diagnostic equipment, a program-controlled system and a computer-readable storage medium. Using the self-diagnostic equipment provided by this application has at least the following advantages:

The patient's first measurement data will only be obtained when the patient meets the preset monitoring conditions. When the measurement data of one or more health monitoring parameters is not within its corresponding preset range, the actual configuration information will be obtained, and the patient's first measurement data will be obtained. The second measurement data detects a fault condition of the stimulator based on the historical measurement data and the second measurement data, and obtains a fault diagnosis result of the stimulator. On the one hand, the first measurement data of the patient's health monitoring parameters will be obtained through the health monitoring equipment only when the preset monitoring conditions are met. This avoids the discomfort caused to the patient by long-term use of the health monitoring equipment and reduces the cost of the health monitoring equipment. energy consumption, increased risk The user experience of the patient; on the other hand, only when one or more first measurement data are not within its corresponding preset range, the electrical stimulation will be delivered to the tissue in the patient's body through the stimulator to prevent the patient from accidentally falling or falling. After falls, convulsions, self-mutilation or drug abuse, the patient still needs to judge whether fault diagnosis of the stimulator is needed. The patient only needs to cooperate with the doctor and the stimulator configuration for treatment, which is more humane; on the other hand, through preset monitoring conditions Judgment can detect the failure of the stimulator at the first time to clarify whether the cause of the stimulator failure is the stimulator itself or the patient's use, which fundamentally eliminates the possibility of affecting the doctor-patient relationship and improves the harmony of the doctor-patient relationship.

In summary, a self-diagnosis device is provided, which is different from the related technology in which the user (patient or guardian) will judge whether the IPG is faulty based on the feedback of the electrical stimulation treatment only when the doctor (doctor) treats the patient through the stimulator. Obtaining the fault results of the stimulator immediately improves the user experience and the doctor-patient relationship.

Description of the drawings

The present application will be further described below in conjunction with the accompanying drawings and examples.

Figure 1 shows a schematic flowchart of steps executed by a self-diagnostic device provided by an embodiment of the present application.

Figure 2 shows a schematic flowchart of obtaining actual configuration information provided by an embodiment of the present application.

FIG. 3 shows a schematic flowchart of detecting fault occurrence provided by an embodiment of the present application.

FIG. 4 shows a schematic flowchart of determining a fault diagnosis result provided by an embodiment of the present application.

Figure 5 shows a schematic flowchart of fault information uploading provided by an embodiment of the present application.

Figure 6 shows a schematic flowchart of another fault information upload provided by an embodiment of the present application.

Figure 7 shows a schematic flowchart of detecting abnormal events in patients provided by an embodiment of the present application.

Figure 8 shows a structural block diagram of a program control system provided by an embodiment of the present application.

Detailed ways

Below, the present application will be further described with reference to the accompanying drawings and specific embodiments. It should be noted that, on the premise that there is no conflict, the embodiments or technical features described below can be arbitrarily combined to form new embodiments. .

In the embodiment of this application, "multiple" refers to two or more than two. "And/or" describes the association of associated objects, indicating that there can be three relationships, for example, A and/or B, which can mean: A exists alone, A and B exist simultaneously, and B exists alone, where A, B can be singular or plural. character "/" generally indicates that the related objects are an "or" relationship. "At least one of the following" or similar expressions thereof refers to any combination of these items, including any combination of a single item (items) or a plurality of items (items). For example, at least one of a, b or c can mean: a, b, c, a and b, a and c, b and c or a and b and c, where a, b and c can It can be single or multiple. It is worth noting that "at least one item (item)" can also be interpreted as "one item (item) or multiple items (item)".

In the embodiments of this application, words such as "exemplary" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design described herein as "exemplary" or "such as" is not intended to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the words "exemplary" or "such as" is intended to present the concept in a concrete manner.

Below, one of the application fields of the embodiments of the present application (namely, the implantable neurostimulator) will be briefly described.

An implantable neurostimulation system (an implantable medical system) mainly includes a stimulator implanted in the patient's body (i.e., an implantable neurostimulator) and a program-controlled device installed outside the patient's body. Relevant neuromodulation technology mainly involves implanting electrodes into specific structures (i.e. target points) in the body through stereotaxic surgery, and a stimulator implanted in the patient's body sends electrical pulses to the target point through the electrodes to regulate the electrical activity of the corresponding neural structures and networks. activities and their functions, thereby improving symptoms and relieving pain. Among them, the stimulator can be an implantable nerve electrical stimulation device, an implantable cardiac electrical stimulation system (also known as a pacemaker), an implantable drug delivery device (Implantable Drug Delivery System, referred to as IDDS) and a lead. Any type of switching device. Implantable neuroelectric stimulation devices include, for example, Deep Brain Stimulation (DBS), Cortical Nerve Stimulation (CNS), and Spinal Cord Stimulation. , referred to as SCS), implanted sacral nerve electrical stimulation system (Sacral Nerve Stimulation, referred to as SNS), implanted vagus nerve electrical stimulation system (Vagus Nerve Stimulation, referred to as VNS), etc.

The stimulator can include an IPG and electrode leads. The IPG (implantable pulse generator) is placed in the patient's body, receives program-controlled instructions sent by the program-controlled device, and relies on sealed batteries and circuits to provide controllable electrical stimulation energy to tissues in the body. , through implanted electrode leads, deliver one or two controllable specific electrical stimulations to specific areas of tissue in the body. It can also be considered that the electrode lead includes an extension lead and a stimulation section. The extension lead is used in conjunction with the IPG as a transmission medium for electrical stimulation signals to transmit the electrical stimulation signal generated by the IPG to the stimulation section of the electrode lead. Electrode leads pass through multiple stimulation segments Electrode contacts that deliver electrical stimulation to specific areas of tissue in the body. The stimulator is provided with one or more electrode leads on one or both sides. The stimulation section of the electrode lead is provided with multiple electrode contacts. The electrode contacts can be arranged evenly or non-uniformly in the circumferential direction of the electrode lead. As an example, the electrode contacts may be arranged in an array of 4 rows and 3 columns (12 electrode contacts in total) in the circumferential direction of the stimulation section of the electrode lead. The electrode contacts may include stimulation electrode contacts and/or collection electrode contacts. The electrode contacts may be in the shape of, for example, a sheet, a ring, a dot, or the like.

In some possible embodiments, the stimulated body tissue may be the patient's brain tissue, and the stimulated site may be a specific part of the brain tissue. When patients have different types of diseases, the stimulated parts are generally different, the number of stimulation contacts used (single source or multiple sources), one or more channels (single channel or multi-channel) specific electrical stimulation signals The application and stimulation parameter data are also different. The embodiments of this application do not limit the applicable disease types, which may be the disease types applicable to deep brain stimulation (DBS), spinal cord stimulation (SCS), pelvic stimulation, gastric stimulation, peripheral nerve stimulation, and functional electrical stimulation. Among them, the types of diseases that DBS can be used to treat or manage include, but are not limited to: spastic diseases (eg, epilepsy), pain, migraine, mental illness (eg, major depressive disorder (MDD)), bipolar disorder, anxiety disorder, Post-traumatic stress disorder, mild depression, obsessive-compulsive disorder (OCD), behavioral disorders, mood disorders, memory disorders, mental status disorders, mobility disorders (e.g., essential tremor or Parkinson's disease), Huntington's disease, Alzheimer's disease Alzheimer's disease, drug addiction, autism or other neurological or psychiatric diseases and impairments.

In the embodiment of the present application, when the program-controlled device and the stimulator establish a program-controlled connection, the program-controlled device can be used to adjust the stimulation parameters of the stimulator (different stimulation parameters correspond to different electrical stimulation signals), and the stimulator can also be used to sense the deep brain of the patient. The bioelectrical activity is used to collect electrophysiological signals, and the stimulation parameters of the electrical stimulation signal of the stimulator can be continuously adjusted through the collected electrophysiological signals.

Stimulation parameters may include one or more of the following: frequency (for example, the number of electrical stimulation pulse signals per unit time 1 s, in Hz), pulse width (duration of each pulse, in μs), amplitude ( Generally expressed in voltage, that is, the intensity of each pulse, the unit is V), timing (for example, it can be continuous or burst, burst refers to a discontinuous timing behavior composed of multiple processes), stimulation mode (including current mode, voltage mode , one or more of timed stimulation mode and cyclic stimulation mode), doctor control upper and lower limits (the range that the doctor can adjust) and patient control upper and lower limits (the range that the patient can adjust independently).

In a specific application scenario, each stimulation parameter of the stimulator can be adjusted in current mode or voltage mode.

The program-controlled equipment may be a doctor-programmed equipment (that is, a program-controlled equipment used by a doctor) or a patient-programmed equipment (that is, a program-controlled equipment used by a patient). The doctor's program-controlled equipment may be, for example, a tablet computer, a notebook computer, a desktop computer, a mobile phone, or other intelligent terminal equipment equipped with program-controlled software. The patient's program-controlled equipment can be, for example, tablet computers, laptops, desktop computers, mobile phones and other intelligent terminal devices equipped with program-controlled software. The patient's program-controlled equipment can also be other electronic equipment with program-controlled functions (such as chargers, data sets with program-controlled functions). collection equipment).

The embodiments of this application do not limit the data interaction between the doctor's program-controlled equipment and the stimulator. When the doctor remotely programs the device, the doctor's program-controlled equipment can interact with the stimulator through the server and the patient's program-controlled equipment. When the doctor performs face-to-face programming with the patient offline, the doctor's program-controlled equipment can interact with the stimulator through the patient's program-controlled equipment, and the doctor's program-controlled equipment can also directly interact with the stimulator.

In one embodiment, the patient programming device may include a host (in communication with the server) and a slave (in communication with the stimulator), the host and slave being communicably connected. Among them, the doctor's program-controlled equipment can interact with the server through the 3G/4G/5G network, the server can interact with the host through the 3G/4G/5G network, and the host can interact with the slave through the Bluetooth protocol/WIFI protocol/USB protocol. Interaction, the slave machine can interact with the stimulator through the 401MHz-406MHz working frequency band/2.4GHz-2.48GHz working frequency band, and the doctor's program-controlled equipment can directly interact with the stimulator through the 401MHz-406MHz working frequency band/2.4GHz-2.48GHz working frequency band. Data interaction.

In actual application scenarios, when patients fall, collide, etc., problems may occur with the stimulator. In related technologies, it is only when the patient is undergoing electrical stimulation treatment that the IPG is judged based on the feedback from the electrical stimulation treatment. Failure causes the patient to lose the opportunity to detect the stimulator failure as soon as the stimulator fails.

Referring to Figure 1, Figure 1 shows a schematic flowchart of steps performed by a self-diagnostic device provided by an embodiment of the present application.

Embodiments of the present application provide a self-diagnostic device, which is used to perform fault self-diagnosis of a stimulator implanted in a patient's body. The self-diagnostic device is configured to perform the following steps:

Step S101: When the patient meets the preset monitoring conditions, use the health monitoring device to obtain the first measurement data of the patient's health monitoring parameters.

Step S102: Detect whether the first measurement data of each health monitoring parameter is within its corresponding preset range.

Step S103: Obtain actual configuration information when it is detected that the first measurement data of one or more health monitoring parameters is not within its corresponding preset range, so that the stimulator can deliver the first measurement data to the patient's body tissue. Actual configuration information corresponding to electrical stimulation. The actual configuration information is used to indicate the actual parameter value of each stimulation parameter of the stimulator.

Step S104: Use the health monitoring device to obtain second measurement data of the patient's health monitoring parameters.

Step S105: Based on the historical measurement data and the second measurement data, detect whether a fault occurs in the stimulator to obtain a fault diagnosis result.

Wherein, the first measurement data may include one or more of the following: heart rate data, pulse data, electromyographic data and electroencephalographic data;

The historical configuration information may include one or more stimulation parameter identifiers and historical parameter values corresponding to each stimulation parameter identifier, and N is a positive integer;

The preset monitoring conditions may include one or more of the following: reaching the preset monitoring time at the current time; detecting that the patient has fallen, dropped, twitched, self-mutilated or sucked.

In related technologies, when a stimulator malfunctions, the electrical stimulation delivered to the tissue in the patient's body becomes abnormal, the therapeutic effect of the electrical stimulation cannot be guaranteed, and the patient's pain cannot be relieved. At this time, the patient will generally seek help from a doctor (or hospital), and the doctor Reconfigure the stimulation parameters of the patient's stimulator. When the disease symptoms still cannot be effectively controlled after the reconfiguration, the patient may not be able to accurately determine the problem and may suspect the physical discomfort caused by the stimulator failure to the treatment method of electrical stimulation therapy. In itself, it reduces the patient's experience and is not conducive to prompting patients to cooperate with doctors for treatment. In addition, even if both doctors and patients are aware of the possibility of the stimulator itself malfunctioning, and eventually detect that the stimulator does malfunction, they still cannot confirm the cause of the malfunction, whether it is damage caused by the patient's use, or the quality of the stimulator product itself. Problems may eventually lead to medical disputes and affect the market prospects of implantable medical devices such as stimulators.

When a malfunction occurs due to various reasons on the patient's side, being able to discover immediately and clarify whether the cause of the stimulator's malfunction is its own quality problem or a malfunction caused by the patient's use can nip medical disputes in the cradle. Different from the above related technologies, the actual configuration information is used to configure the stimulation parameters of the stimulator, so that the duration of the electrical stimulation corresponding to the actual configuration information delivered by the stimulator to the patient's body tissue is much shorter than The normal electrical stimulation treatment time, such as several minutes to tens of minutes, is performed when the patient meets the preset monitoring conditions and the measurement data of the first measurement data is not within its corresponding preset range. The self-diagnosis of the stimulator allows the user (patient or guardian) to obtain the failure results of the stimulator as soon as the stimulator fails, improving the user experience.

Therefore, the patient's first measurement data will be obtained only when the patient meets the preset monitoring conditions. When the measurement data of one or more health monitoring parameters is not within its corresponding preset range, the actual configuration information will be obtained, and The patient's second measurement data is obtained, a fault condition of the stimulator is detected based on the historical measurement data and the second measurement data, and a fault diagnosis result of the stimulator is obtained. On the one hand, the first measurement data of the patient's health monitoring parameters will be obtained through the health monitoring equipment only when the preset monitoring conditions are met, avoiding the discomfort caused to the patient by long-term use of the health monitoring equipment, and also reducing the cost of the health monitoring equipment. Energy consumption improves the patient's experience; on the other hand, only when one or more first measurement data are not within its corresponding preset range, electrical stimulation will be delivered to the patient's body tissue through the stimulator, preventing the patient from inadvertently After falling, falling, convulsing, self-mutilation or smoking, the patient still needs to judge whether the stimulator needs to be fault diagnosed. The patient only needs to cooperate with the doctor and the stimulator configuration for treatment, which is more humane; on the other hand, through The judgment of preset monitoring conditions can detect the failure of the stimulator at the first time to clarify whether the cause of the stimulator failure is the stimulator itself or the patient's use. This fundamentally eliminates the possibility of affecting the doctor-patient relationship and improves the doctor-patient relationship. The rapport of the relationship.

In summary, a self-diagnosis device is provided, which is different from the related technology in which the user (patient or guardian) will judge whether the IPG is faulty based on the feedback of the electrical stimulation treatment only when the doctor (doctor) treats the patient through the stimulator. Obtaining the fault results of the stimulator immediately improves the user experience and the doctor-patient relationship.

The fault diagnosis result is, for example, "the patient's stimulator is faulty" or "the patient's stimulator is not faulty".

This application does not limit the health monitoring equipment. The health monitoring equipment may be a wearable device, such as a health monitoring vest with integrated health monitoring function, a health monitoring bracelet, etc., or an implantable medical device, such as an implantable cardiac device. Electrical monitor, etc. Specifically, the health monitoring device is, for example, an electroencephalogram monitoring device, an electrocardiogram monitoring device, a myoelectricity monitoring device, a heart rate monitoring device, a pulse monitoring device or a visual monitoring device.

The preset monitoring time is, for example: 10 hours later, 12:00, or 10:13 am on working days (Monday to Friday). Detecting that the patient has fallen, dropped, convulsed, self-mutilated or inhaled, for example, means that the patient falls while standing, the patient falls from the bed to the ground, the patient has general convulsions, the patient is detected by a visual detection device (camera, etc.) Localized epilepsy, patients injuring their own limbs, or patients inhaling objects. Depend on Stimulators implanted in patients can provide electrical stimulation treatment for drug addiction. Patients may relapse to drugs or similar substances after abstaining from addiction. The drug or analogue is selected from the group consisting of heroin, morphine, opiate concentrate, fentanyl, opium, nicodeine, hydrocodeine, poppy shells, thebaine, codeine, levmethorphan, betaine Any one of oxymorphine, dextropropoxyphene, pholcodine, Ritalin, sodium caffeine, methamphetamine or a combination thereof.

The preset range corresponding to the first measurement data is, for example, pulse rate 60 beats/minute to 100 beats/minute, electromyography 450 Hz to 500 Hz, etc.

The historical configuration information is, for example, the configuration information of the stimulator that is pre-stored in the self-diagnosis device, on a local area network server, or on a cloud server.

The stimulation parameter identification can be represented by one or more of Chinese, letters, numbers and special symbols, such as any one of "A001", "voltage", "amplitude" or "#01" or a combination thereof. The historical parameter value and the actual parameter value are, for example, frequency 120Hz, pulse width 65μs or amplitude 3.1V.

The historical measurement data and the second measurement data are, for example, pulse data, electrocardiogram curve, or electroencephalogram curve. When the historical measurement data and the second measurement data are curves respectively, it can be performed based on each point of the curve, the shape of the curve (Hausdorff distance calculation), the segmentation of the curve (such as one-way distance method (One Way Distance)), etc. Compare to obtain the similarity between the two. When the similarity between the two is higher than a preset degree of familiarity (for example, 0.98, 0.95), it can be considered that the similarity between the historical measurement data and the second measurement data is high. No stimulator malfunction occurred.

Referring to Figure 2, Figure 2 shows a schematic flow chart of obtaining actual configuration information provided by an embodiment of the present application.

In one embodiment, the self-diagnosis device is configured to obtain the actual configuration information in the following manner:

Step S201: Obtain the most recent N historical configuration information of the stimulator and the corresponding historical measurement data of the patient's health monitoring parameters, where N is a positive integer. The historical measurement data can be used together with the second measurement data to detect whether a malfunction has occurred in the stimulator.

Step S202: Obtain the actual configuration information based on the last N times of historical configuration information.

Therefore, on the one hand, when N is 1, the most recent historical configuration information of the stimulator and the corresponding historical measurement data of the patient's health monitoring parameters are selected. Generally speaking, the most recent historical configuration information can best reflect the recent The patient's condition can be reduced while providing electrical stimulation to the patient's body. According to the amount of calculations, the degree of intelligence is high; on the other hand, when N is a positive integer other than 1, multiple historical configuration information can be reasonably utilized to avoid fluctuations in individual historical configuration information causing damage to the electrical stimulation delivered to the patient's body tissue. bias to improve the objectivity of the second measurement data obtained.

In a specific application, the preset range corresponding to patient A is heart rate data from 55 beats/minute to 100 beats/minute, and N is 1. The camera set up in the patient's room obtained the information about the fall of epilepsy patient A, which met the preset detection conditions of patient A. The health monitoring equipment obtained the patient's first measurement data: the heart rate data was 110 beats/minute. Because the first measurement data is not within its corresponding preset range, the most recent historical configuration information (voltage 2V) of patient A and its corresponding historical measurement data (pulse curve) of the patient's health monitoring parameters are obtained. Configure the stimulation parameters to a voltage of 2V according to the historical configuration information, deliver electrical stimulation corresponding to the stimulation parameters to the patient's body tissues, and obtain corresponding second measurement data (pulse curve). Wherein, the historical measurement data and the second measurement data may each include a continuous pulse curve after the electrical stimulation is delivered to the tissue in the patient's body, and the patient's symptoms have been relieved (or asymptomatic) after the electrical stimulation. According to the historical measurement data and the second measurement data, it is detected that the stimulator does not malfunction. The entire judgment process does not require patient A's operation. Patient A only needs to cooperate with the treatment with peace of mind and has a high level of intelligence.

In another specific application, the preset range corresponding to patient A is heart rate data from 60 beats/minute to 100 beats/minute, and N is 4. The camera set up in the patient's room obtained information about the fall of epilepsy patient A. Patient A met the preset detection conditions. The health monitoring equipment obtained the patient's first measurement data: the heart rate data was 105 beats/minute, and the first measurement data was not in Its own corresponding preset range obtains the last 4 historical configuration information of patient A (voltage 2V, voltage 2.1V, voltage 1.9V, voltage 2V) and the corresponding historical measurement data of the patient's health monitoring parameters (4 pulse curves fitting curve). The stimulation parameters are configured to a voltage of 2V based on the average of the four historical configuration information, and electrical stimulation corresponding to the stimulation parameters is delivered to the patient's body tissue and corresponding second measurement data (pulse curve) is obtained. The historical measurement data and the second measurement data may each include a continuous pulse curve after the electrical stimulation is delivered to the tissue in the patient's body, and the patient's symptoms have been relieved (or asymptomatic) after the electrical stimulation. Based on the historical measurement data and the second measurement data, it is detected that the stimulator is faulty.

Referring to Figure 3, Figure 3 shows a schematic flowchart of a fault detection method provided by an embodiment of the present application.

In one embodiment, step S105 may include:

Step S301: Input the historical measurement data and the second measurement data into the similarity model to obtain the similarity between the historical measurement data and the second measurement data;

Step S302: When the similarity is not less than the preset similarity threshold, determine that the fault diagnosis result is that the stimulator is not faulty;

Step S303: When the similarity is less than the preset similarity threshold, determine that the fault diagnosis result is that the stimulator is faulty.

Wherein, the training process of the similarity model includes:

Obtain a first training set, the first training set includes a plurality of training data, each of the training data includes a first sample object, a second sample object, the first sample object and the second sample object similarity;

For each training data in the first training set, perform the following processing: input the first sample object and the second sample object in the training data into the preset first deep learning model to obtain the first The predicted similarity between the sample object and the second sample object;

Based on the predicted similarity between the first sample object and the second sample object, update the model parameters of the first deep learning model;

Check whether the preset training end condition is met; if so, use the trained deep learning model as the similarity model; if not, use the next training data to continue training the first deep learning model.

The beneficial effect of this technical solution is that the similarity model can be trained by a large amount of training data, and can predict corresponding output data (i.e., historical measurement data and the second measurement data) for different input data (i.e., historical measurement data and second measurement data). The similarity between the two measurement data), has a wide range of applications and a high level of intelligence. Through design, establish an appropriate number of neuron computing nodes and a multi-layer computing hierarchy, and select the appropriate input layer and output layer to obtain the preset first deep learning model. Through the learning of the preset first deep learning model and tuning, establish the functional relationship from input to output. Although the functional relationship between input and output cannot be found 100%, it can approximate the realistic correlation relationship as much as possible. The similarity model obtained by training can be based on each The similarity between the historical measurement data and the second measurement data is obtained respectively, and the calculation result is highly accurate and reliable.

In one embodiment, this application can use the above training process to train and obtain a similarity model. In other optional implementations, this application can use a pre-trained similarity model.

In one embodiment, for example, data mining can be performed on historical data to obtain training data. Of course, the first sample object and the second sample object can also be automatically generated using the generation network of the GAN model. of.

Among them, the GAN model is a Generative Adversarial Network, which consists of a generative network and a discriminative network. The generative network randomly samples from the latent space as input, and its output results need to imitate the real samples in the training set as much as possible. The input of the discriminant network is a real sample or the output of the generative network, and its purpose is to distinguish the output of the generative network from the real sample as much as possible. The generative network must deceive the discriminant network as much as possible. The two networks compete with each other and constantly adjust parameters. The ultimate goal is to make the discriminant network unable to judge whether the output results of the generating network are true.

The predicted similarity can be expressed as a number or a percentage. When expressed as a number, the predicted similarity is, for example, 60, 80, or 90; when expressed as a percentage, the predicted similarity is, for example, 50%, 70%, or 90%. The higher the value, the better the predicted similarity. The higher the similarity.

This application does not limit the preset similarity threshold, which can be 70%, 80% or 90%.

This application does not limit the preset training end condition. For example, it can be that the number of training times reaches the preset number of times (the preset number of times is, for example, 1 time, 3 times, 10 times, 100 times, 1000 times, 10000 times, etc.), or it can The training data in the training set have completed one or more trainings, or the total loss value obtained in this training is not greater than the preset loss value.

In one embodiment, when the fault diagnosis result is that the stimulator is faulty, the self-diagnosis device is further configured to:

An alarm signal is sent out using an alarm device, which includes one or more of a sound alarm device, a flash alarm device, or an audible and visual alarm device.

Therefore, for example, when some patients are older or suffer from mental illness, alarming through the alarm device can attract the attention of people around the patient, so that the patient or patient guardian can learn the diagnosis result as soon as possible, and provide timely treatment. Seek help from a professional (doctor or stimulator provider).

The alarm device may be one of a horn (speaker), a buzzer, a display screen, etc. or a combination thereof.

Referring to Figure 4, Figure 4 shows a schematic flowchart of determining a fault diagnosis result provided by an embodiment of the present application.

In one embodiment, the stimulator includes an IPG and one or more electrode leads;

The self-diagnostic device is configured to determine a fault diagnosis result of the stimulator in the following manner:

Step S401: Detect whether the impedance data of each electrode wire is in its corresponding preset state. set scope;

Step S402: When it is detected that the impedance data of one or more of the electrode wires is not within its corresponding preset range, determine that the fault diagnosis result is the electrode whose impedance data is not within its corresponding preset range. A fault occurs in the wire;

Step S403: When it is detected that the impedance data of all the electrode wires are within the corresponding preset range, determine that all the electrode wires are fault-free, and continue to detect all the electrode wires based on the historical measurement data and the second measurement data. Check whether a fault occurs in the IPG to obtain the fault diagnosis result.

In specific applications, since the outer diameter of the electrode lead is generally only about 1-1.5mm and the length of the electrode lead is about 500-550mm, when the patient falls, collides, etc., the electrode lead is more likely to malfunction (open circuit, etc.). If the electrode lead where the electrode contact is located is short-circuited, the electrical stimulation output by it may generate excessive current, which may cause damage to the body tissue receiving specific stimulation or to the tissue directly contacting the electrode contact at the short-circuit point; or, the electrode If the conductive path in the body where the contact is located is broken, the electrical stimulation will be output directly at the electrode contact at the broken point, so it cannot deliver effective treatment to the patient's designated internal tissue.

Therefore, the impedance data of the electrode lead is first detected, and then it is determined whether the IPG needs to be detected based on the detection result of the electrode lead. On the one hand, by first testing the electrode leads, the fault of the stimulator can be determined with a high probability, which is more targeted and improves the response speed of the patient's self-diagnosis of the stimulator; on the other hand, the stimulator implanted in the patient's body can There is more than one electrode lead. By detecting and comparing the impedance data of each electrode lead, the faulty electrode lead can be quickly determined. Before the problem of the faulty electrode lead is solved, other electrode leads can be used to treat the patient, thus avoiding Delay patient care.

In summary, follow the detection sequence of electrode impedance and IPG. Compared with the related technology of using CT or nuclear magnetic equipment to determine the faulty electrode lead, this application uses the impedance data of each electrode lead to determine the fault condition of the electrode lead. The problem can be preliminarily confirmed at the first time without going to the hospital and using professional equipment. Stimulator failure has minimal impact on patient treatment.

Among them, the circuit of the IPG may include a circuit inspection module. The circuit inspection module can detect the IPG and determine the fault condition of the IPG, such as IPG power module failure, signal transmission failure, etc. The impedance data of each electrode lead can be provided by IPG with a fixed voltage value, and the current value passing through each electrode lead can be measured to obtain the impedance data of each electrode lead; it can also be provided by IPG with a supply current value and measured with each electrode. The voltage value of the wire is then obtained to obtain the impedance data of each electrode wire.

In one embodiment, when the fault diagnosis result is that a fault occurs, the self-diagnosis device also is configured to execute:

Step S106: Store the fault information of the stimulator in a preset storage location, and generate fault prompt information to send to the preset user equipment. The fault information of the stimulator includes one or more of stimulator identification information, fault time information and fault type information.

Generally speaking, when a stimulator malfunctions, the electrical stimulation that the patient receives often undergoes major changes (such as sudden cessation of stimulation, lags, etc.), which makes the patient suspect that his or her condition is getting worse or that he or she is not suitable for the stimulator. treatment (destroying the patient's confidence in their own treatment), or the doctor's stimulation parameters set by the stimulator are unreasonable (the doctor is unprofessional or irresponsible), etc.

Therefore, if the self-diagnosis equipment finds that the stimulator is faulty, the user (the patient or the patient's guardian) will be informed of the fault condition through the user device as soon as possible to avoid the patient's negative resistance to the treatment of the stimulator, and the degree of intelligence relatively high.

The preset storage location is, for example, the memory of the patient's programming device. The fault prompt information can be a voice message, a pop-up window message, or a text message. For example, the text message is "The stimulator implanted in patient A has failed. Please contact doctor B in time for further diagnosis. The contact number is 13000000000."

The user equipment is, for example, a mobile phone, laptop computer, desktop computer, tablet computer or patient program controller owned by the patient himself or the patient's guardian or caregiver.

The fault type information is, for example, "Patient's left brain 1# electrode lead fault", "Stimulator fault", "I PG fault", etc.

In a specific application, the fault information is "Patient C, at 12:13 on January 1, 2020, the stimulator failed."

Referring to Figure 5, Figure 5 shows a schematic flow chart of fault information uploading provided by an embodiment of the present application.

In one embodiment, the self-diagnosis device may also be configured to:

Step S107: Use the user equipment to receive the user's fault upload operation;

Step S108: In response to the fault upload operation, send the fault information of the stimulator to a preset service device.

Therefore, only when the user actively performs a fault upload operation, the fault information of the stimulator will be sent to the preset service device, which respects the user's right to choose. Compared with normal people, patients undergoing stimulator treatment are in a lower mood. This group of users can be given enough respect so that patients can actively cooperate with doctors for treatment, which is more conducive to later communication between doctors and patients.

Among them, the user's fault upload operation includes, for example, clicking on the upload selection menu in the user's device to upload, issuing a voice command to the user's device through the voice function "Please upload this fault information", etc.

The default service equipment is, for example, a local area network server of a hospital, a community, or a stimulator manufacturer, or a wide area network server for cross-regional data connection.

Doctors or stimulator manufacturers can know the user's actual stimulator usage in a timely manner, and can prescribe appropriate treatment for stimulator failures caused by patients falling down. For example, when a certain proportion of patients have faulty stimulators with electrode lead lengths exceeding 650mm, then stimulator manufacturers will technically consider how to solve the problem of unstable quality of electrode leads that are too long. Doctors will also consider reducing the length of electrode leads for patients who will be implanted with stimulators to avoid unstable electrode leads. Defects.

In one embodiment, the self-diagnostic device is further configured to:

When it is detected that the first measurement data of any of the health monitoring parameters is within its corresponding preset range, a fault-free duration is obtained. The fault-free duration is used to indicate the current moment and the latest generation of the fault prompt information. the length of time between moments;

When the fault-free time period is greater than the preset time period, the self-diagnosis strategy of the self-diagnosis device is obtained to determine whether a fault occurs in the stimulator.

Therefore, by comparing the fault-free time and the preset time, it is possible to avoid the failure of the health monitoring equipment itself or the signal transmission failure between the health monitoring equipment and the self-diagnostic equipment. The stimulator in the patient's body can also be performed at a reasonable time point. Self-diagnosis.

Referring to Figure 6, Figure 6 shows a schematic flowchart of yet another fault information uploading process provided by an embodiment of the present application.

In one embodiment, the self-diagnostic device is further configured to:

Step S109: When the number of fault information stored in the preset storage location is not less than the preset number of faults, send the latest fault information of the stimulator to the preset service device.

When the patient does not choose to send fault information to the preset service device (doctor or stimulator manufacturer), the patient himself will also bear the risk of physical injury caused by the electrical stimulation delivered to the patient himself when the stimulator fails.

Therefore, on the premise of fully respecting the user's right to choose, an appropriate preset number of faults is selected so that when the stimulator has a number of faults not less than the preset number of faults, the doctor or stimulator manufacturer can promptly receive the latest Based on the fault information, doctors or suppliers can promptly contact patients or their guardians based on the content of the fault information to prevent patients from suffering undue harm.

Among them, the preset number of faults is, for example, 3 times, 5 times, 8 times, 11 times, etc.

Referring to Figure 7, Figure 7 shows a schematic flowchart of detecting abnormal events in patients provided by an embodiment of the present application.

In one embodiment, the process of detecting whether the patient falls, falls, twitches, self-mutilates, takes drugs, or has no abnormal events includes:

Step S501: Use visual detection equipment to obtain real-time images including the patient;

Step S502: Input the real-time image to the abnormal event model to obtain event classification results corresponding to the real-time image. The event classification result is falling, falling, convulsing, self-mutilation, inhalation or no abnormal event. In other words, when no falling, falling, convulsions, self-mutilation or ingestion events are detected, the patient can be considered to have no abnormal events.

As a result, images including patients are acquired in real time through visual detection equipment, and the images are input into the abnormal event model to obtain event classification results corresponding to the real-time images with high accuracy.

Wherein, the training process of the abnormal event model can be as follows:

A second training set is obtained, where the second training set includes a plurality of training images and their corresponding annotation data of the labeled classification results. The labeled data can be falling events, falling events, twitching events, self-mutilation events, smoking events or no abnormal events.

The second training set is used to train the preset second deep learning model to obtain the abnormal event model.

Specifically, during the training process of the abnormal event model, using the second training set to train a preset second deep learning model may include the following steps:

For each training image in the second training set, input the training image into a preset second deep learning model to obtain prediction data of mark detection results corresponding to the training image;

Update the model parameters of the preset second deep learning model based on the prediction data and annotation data of the mark detection results corresponding to the training image;

Detect whether the preset second training end condition is met. If so, stop training and use the preset second deep learning model obtained by training as the abnormal event model. If not, use the next The training data continues to train the preset second deep learning model.

Therefore, the second training end condition at the end of training can be configured based on actual needs, and the abnormal event model obtained by training has strong robustness and low overfitting risk.

Use the second training set to train the preset second deep learning model to obtain a trained abnormal event model. The abnormal event model can be trained with a large amount of training data and can predict corresponding mark detection for a variety of input data. As a result, it has a wide range of applications and a high level of intelligence. Through design, establish an appropriate number of neuron computing nodes and a multi-layer computing hierarchy, and select the appropriate input layer and output layer to obtain the preset second deep learning model. Through the learning of the preset second deep learning model and tuning to establish the functional relationship from input to output. Although the functional relationship between input and output cannot be found 100%, it can approximate the realistic correlation relationship as much as possible. The abnormal event model obtained by training can realize imaging The self-diagnosis function of identification is high, and the diagnostic results are highly reliable.

The visual detection device may be a camera or a device including a camera.

Referring to Figure 8, Figure 8 shows a structural block diagram of a program control system 100 provided by an embodiment of the present application.

The program-controlled system 100 includes a health monitoring device 300 and the self-diagnostic device 200 provided in any of the above embodiments. The self-diagnostic device 200 and the health monitoring device 300 are communicatively connected.

Embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, it implements the self-diagnosis device described in any of the above embodiments. Function.

The terms "first", "second", "third", "fourth", etc. (if present) in the description and claims of this application and the above-mentioned drawings are used to distinguish similar objects without necessarily using Used to describe a specific order or sequence. It is to be understood that data so used are interchangeable under appropriate circumstances so that the embodiments of the application described herein, for example, can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "include" and "corresponding to" and any variations thereof are intended to cover non-exclusive inclusions, e.g., a process, method, system, product, or device that includes a series of steps or units and need not be limited to those explicitly listed may include other steps or elements not expressly listed or inherent to the process, method, product or apparatus.

Claims (12)

1. A self-diagnostic device, the self-diagnostic device is used to perform fault self-diagnosis of a stimulator implanted in a patient, the self-diagnostic device is configured to:

   When the patient meets the preset monitoring conditions, use the health monitoring equipment to obtain the first measurement data of the patient's health monitoring parameters;

   Detect respectively whether the first measurement data of each of the health monitoring parameters is within its corresponding preset range;

   Obtain actual configuration information when it is detected that the first measurement data of one or more health monitoring parameters is not within its corresponding preset range, so that the stimulator delivers the actual configuration information to the patient's body tissue. Corresponding electrical stimulation, the actual configuration information is used to indicate the actual parameter value of each stimulation parameter of the stimulator;

   utilizing the health monitoring device to obtain second measurement data of the patient's health monitoring parameters;

   Based on the historical measurement data and the second measurement data, it is detected whether a fault occurs in the stimulator to obtain a fault diagnosis result.
2. The self-diagnostic device according to claim 1, wherein the self-diagnostic device is configured to obtain the actual configuration information in the following manner:

   Obtain the most recent N historical configuration information of the stimulator and the corresponding historical measurement data of the patient's health monitoring parameters, where N is a positive integer;

   The actual configuration information is obtained based on the most recent N times of historical configuration information.
3. The self-diagnosis device according to claim 1, wherein the first measurement data includes one or more of the following: heart rate data, pulse data, electromyography data and electroencephalography data;

   The historical configuration information includes one or more stimulation parameter identifiers and historical parameter values corresponding to each stimulation parameter identifier, and N is a positive integer;

   The preset monitoring conditions include one or more of the following: the current time reaches the preset monitoring time; the patient is detected to have fallen, dropped, twitched, self-mutilated or inhaled.
4. The self-diagnosis device according to claim 1, wherein the self-diagnosis device is configured to obtain fault diagnosis results in the following manner:

   The historical measurement data and the second measurement data are input into the similarity model to obtain the historical measurement data. The similarity between the historical measurement data and the second measurement data;

   When the similarity is not less than the preset similarity threshold, it is determined that the fault diagnosis result is that the stimulator is not faulty;

   When the similarity is less than the preset similarity threshold, it is determined that the fault diagnosis result is that the stimulator is faulty;

   Wherein, the training process of the similarity model includes:

   Obtain a first training set, the first training set includes a plurality of training data, each of the training data includes a first sample object, a second sample object, the first sample object and the second sample object similarity;

   For each training data in the first training set, perform the following processing: input the first sample object and the second sample object in the training data into the preset first deep learning model to obtain the first The predicted similarity between the sample object and the second sample object;

   Based on the predicted similarity between the first sample object and the second sample object, update the model parameters of the first deep learning model;

   Check whether the preset training end condition is met; if so, use the trained deep learning model as the similarity model; if not, use the next training data to continue training the first deep learning model.
5. The self-diagnosis device according to claim 4, wherein when the fault diagnosis result is that the stimulator is faulty, the self-diagnosis device is further configured to:

   An alarm signal is sent out using an alarm device, which includes one or more of a sound alarm device, a flash alarm device, or an audible and visual alarm device.
6. The self-diagnostic device of claim 1, wherein the stimulator includes an IPG and one or more electrode leads;

   The self-diagnostic device is configured to determine a fault diagnosis result of the stimulator in the following manner:

   Detect respectively whether the impedance data of each electrode lead is within its corresponding preset range;

   When it is detected that the impedance data of one or more electrode wires is not within its corresponding preset range, it is determined that the fault diagnosis result is that the electrode wire whose impedance data is not within its corresponding preset range is faulty. occur;

   When it is detected that the impedance data of all the electrode leads are within their corresponding preset ranges, it is determined that all the electrode leads are fault-free, and based on the historical measurement data and the second measurement data, continue to detect the Check whether a fault occurs in the IPG to obtain the fault diagnosis result.
7. The self-diagnosis device according to claim 6, wherein when the fault diagnosis result is that a fault occurs, the self-diagnosis device is further configured to:

   Store the fault information of the stimulator to a preset storage location, and generate fault prompt information to send to the preset user equipment. The fault information of the stimulator includes stimulator identification information, fault time information and fault type information. of one or more.
8. The self-diagnostic device according to claim 7, wherein the self-diagnostic device is further configured to:

   Utilize the user equipment to receive the user's fault upload operation;

   In response to the fault upload operation, the fault information of the stimulator is sent to a preset service device.
9. The self-diagnostic device according to claim 7, wherein the self-diagnostic device is further configured to:

   When the amount of the fault information stored in the preset storage location is not less than the preset number of faults, the latest fault information of the stimulator is sent to the preset service device.
10. The self-diagnosis device according to claim 1, wherein the process of detecting whether the patient falls, falls, twitches, self-mutilates, sucks, or has no abnormal event includes:

    utilizing visual inspection equipment to obtain real-time images including the patient;

    The real-time image is input into the abnormal event model to obtain the event classification result corresponding to the real-time image. The event classification result is falling, falling, twitching, self-mutilation, sucking, or no abnormal event.
11. A program-controlled system, the program-controlled system includes a health monitoring device and the self-diagnostic device of any one of claims 1 to 10, and the self-diagnostic device and the health monitoring device are communicably connected.
12. A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the function of the self-diagnostic device described in any one of claims 1-10 is implemented.