Intracranial pressure detection method and device

Abstract

The invention discloses an intracranial pressure detection method and device, and relates to the technical field of medical detection. Body temperature data and blood pressure data of the patient to be detected and a second negative wave of the multiple detected flash visual evoked potentials are obtained; performing signal fusion processing on the plurality of second negative waves to obtain a processed second negative wave; performing filtering processing on the processed second negative wave through wavelet filtering to obtain a filtered second negative wave; extracting the duration of the incubation period corresponding to the filtered second negative wave; the body temperature data, the blood pressure data, the duration of the incubation period, the age data of the to-be-detected patient and the optic nerve pathology data of the to-be-detected patient serve as input of a pre-trained intracranial pressure prediction model for operation, and intracranial pressure detection data of the to-be-detected patient are obtained. According to the intracranial pressure detection method and device, the intracranial pressure of the patient can be safely, accurately and conveniently detected.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical detection, and in particular relates to an intracranial pressure detection method and device. Background Art

[0002] Intracranial pressure (ICP) refers to the pressure exerted by the contents of the cranial cavity (including brain tissue, cerebrospinal fluid and blood) on the cranial cavity wall. The pressure in the lateral ventricle of a normal adult during lumbar puncture or supine lying in a relaxed state is 6-13.5 mmHg. If the intracranial pressure continues to exceed the upper limit of normal, it may cause a series of pathological and physiological changes, including decreased cerebral blood flow and cerebral ischemia, brain shift and brain herniation, cerebral edema, Cushing's reaction, gastrointestinal dysfunction and gastrointestinal bleeding, neurogenic pulmonary edema, etc. Therefore, intracranial pressure detection is of great significance for the diagnosis and treatment of neurosurgical diseases.

[0003] Invasive intracranial pressure detection technology is regarded as the gold standard for estimating intracranial pressure levels due to its high accuracy, and is therefore widely used for intracranial pressure detection in patients. However, invasive intracranial pressure detection technology requires drilling or opening the skull to implant pressure receptors directly into the skull, or implanting a catheter into the ventricle, cisterns, or subarachnoid space through a catheter method, with the sensor placed outside the skull and pressure measured through contact with the liquid or cerebrospinal fluid filled in the catheter. However, both implantation and catheter methods require complex surgery and cause trauma to the head, which can easily lead to infection, bleeding, and other complications, and have certain safety risks.

[0004] Therefore, how to provide an effective solution to safely and conveniently detect the intracranial pressure of a patient has become a difficult problem to be solved in the prior art. Summary of the invention

[0005] The purpose of the present invention is to provide a method and device for detecting intracranial pressure, so as to solve the above-mentioned problems existing in the prior art.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a method for detecting intracranial pressure, comprising: Acquiring body temperature data, blood pressure data and the second negative wave of multiple flash visual evoked potentials detected by the patient to be tested; performing signal fusion processing on the plurality of second negative waves to obtain a processed second negative wave; The processed second negative wave is filtered by wavelet filtering to obtain a filtered second negative wave; Extract the latency duration corresponding to the second negative wave after filtering; The body temperature data, the blood pressure data, the duration of the latent period, the age data of the patient to be tested, and the optic nerve pathology data of the patient to be tested are used as inputs of a pre-trained intracranial pressure prediction model to perform calculations to obtain intracranial pressure detection data of the patient to be tested; The intracranial pressure prediction model is trained using the body temperature data, blood pressure data, latency duration of the second negative wave, age data and optic nerve pathology data corresponding to the sample patients as sample inputs, and the intracranial pressure measurement data of the sample patients as sample outputs.

[0007] Based on the above disclosed content, the present invention obtains the body temperature data, blood pressure data and the second negative wave of multiple flash visual evoked potentials detected by the patient to be tested, performs signal fusion processing on the multiple second negative waves to obtain the processed second negative wave, and performs filtering processing on the processed second negative wave by wavelet filtering to obtain the filtered second negative wave, and then extracts the latency duration corresponding to the filtered second negative wave, so as to reduce the interference of noise, thereby accurately extracting the latency duration corresponding to the second negative wave. Then the body temperature data, blood pressure data, latency duration, age data of the patient to be tested and optic nerve pathology data of the patient to be tested are used as inputs of the pre-trained intracranial pressure prediction model for operation to obtain the intracranial pressure detection data of the patient to be tested, wherein the intracranial pressure prediction model is obtained by training with the body temperature data, blood pressure data, latency duration of the second negative wave, age data and optic nerve pathology data corresponding to the sample patient as sample inputs and the intracranial pressure measurement data of the sample patient as sample output. In this way, the patient's intracranial pressure can be accurately measured based on multiple user data associated with the intracranial pressure data. There is no need for complicated surgery and there will be no safety risks due to surgical trauma. The measurement of intracranial pressure data is simple and fast, which improves the patient's testing experience.

[0008] In a possible design, filtering the processed second negative wave by wavelet filtering to obtain the filtered second negative wave includes: Decomposing the processed second negative wave at different scales to obtain low-frequency sub-band signals and high-frequency sub-band signals; Performing signal enhancement processing on the low-frequency sub-band signal and the high-frequency sub-band signal; The low-frequency sub-band signal after signal enhancement processing and the high-frequency sub-band signal after signal enhancement processing are subjected to inverse discrete wavelet transform to obtain the second negative wave after filtering.

[0009] In a possible design, performing signal fusion processing on the plurality of second negative waves to obtain a processed second negative wave includes: Superimposing a plurality of the second negative waves to obtain a superimposed second negative wave; The amplitude of each signal in the superimposed second negative wave is divided by the number of superpositions to obtain the processed second negative wave.

[0010] In a possible design, the extraction of the latency duration corresponding to the second negative wave after filtering includes: Determine the timestamp corresponding to the peak of the second negative wave after filtering; Based on the timestamp corresponding to the peak of the second negative wave after filtering, the latency duration corresponding to the second negative wave after filtering is determined.

[0011] In one possible design, the method further includes: Acquire an ultrasonic reflection image of the eye area of ​​the patient to be tested; constructing an ultrasound image of the eye region of the patient to be tested based on the ultrasound reflection image; identifying the optic nerve sheath in the ultrasound image by image recognition; measuring the diameter of the optic nerve sheath in the ultrasound image; Predicting the intracranial pressure data of the patient to be tested based on the optic nerve sheath diameter in the ultrasound image to obtain the intracranial pressure prediction data of the patient to be tested; If the value between the intracranial pressure prediction data and the intracranial pressure detection data is lower than a first preset threshold, the intracranial pressure detection data of the patient to be tested is used as the final intracranial pressure detection data of the patient to be tested.

[0012] In one possible design, the method further includes: When the intracranial pressure detection data of the patient to be tested is higher than a second preset threshold, a warning message is generated.

[0013] In one possible design, the intracranial pressure prediction model is a feedforward neural network model.

[0014] In a second aspect, the present invention provides an intracranial pressure detection device, comprising: An acquisition unit, used for acquiring body temperature data, blood pressure data and the second negative wave of multiple detected flash visual evoked potentials of the patient to be tested; A fusion unit, configured to perform signal fusion processing on the plurality of second negative waves to obtain a processed second negative wave; A filtering unit, used for filtering the processed second negative wave by wavelet filtering to obtain a filtered second negative wave; An extraction unit, used for extracting the latency duration corresponding to the second negative wave after filtering; A calculation unit, used to calculate the body temperature data, the blood pressure data, the duration of the latent period, the age data of the patient to be tested, and the optic nerve pathology data of the patient to be tested as inputs of a pre-trained intracranial pressure prediction model to obtain intracranial pressure detection data of the patient to be tested; The intracranial pressure prediction model is trained using the body temperature data, blood pressure data, latency duration of the second negative wave, age data and optic nerve pathology data corresponding to the sample patients as sample inputs, and the intracranial pressure measurement data of the sample patients as sample outputs.

[0015] In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the intracranial pressure detection method as described in the first aspect or any possible design of the first aspect.

[0016] In a fourth aspect, the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed on a computer, executes the intracranial pressure detection method described in the first aspect or any possible design of the first aspect.

[0017] In a fifth aspect, the present invention provides a computer program product comprising instructions, which, when executed on a computer, causes the computer to execute the intracranial pressure detection method as described in the first aspect or any possible design of the first aspect.

[0018] Beneficial effects: The present invention provides an intracranial pressure detection method and device, which can measure the intracranial pressure of a patient based on multiple user data associated with the intracranial pressure data, without the need for complex surgery, and without causing safety risks due to surgical trauma. The intracranial pressure data is simple and fast to measure, which improves the patient's detection experience. When measuring the latent period of the second negative wave used for intracranial pressure detection, the signal fusion and wavelet filtering of multiple second negative waves can reduce the interference of noise, and accurately extract the latent period corresponding to the second negative wave, thereby ensuring that the intracranial pressure data can be accurately measured, which is convenient for practical application and promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flow chart of a method for detecting intracranial pressure provided in an embodiment of the present application; Figure 2 A schematic block diagram of an intracranial pressure detection device provided in an embodiment of the present application; Figure 3 A schematic block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0021] It should be understood that although the terms first, second, etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another unit. For example, a first unit can be referred to as a second unit, and similarly, a second unit can be referred to as a first unit without departing from the scope of the exemplary embodiments of the present invention.

[0022] It should be understood that the term "and / or" that may appear in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can represent three situations: A exists alone, B exists alone, and A and B exist at the same time. The term " / and" that may appear in this article describes another type of association object relationship, indicating that two relationships may exist. For example, A / and B can represent two situations: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this article generally indicates that the previous and next associated objects are in an "or" relationship.

[0023] In order to facilitate the detection of intracranial pressure, an embodiment of the present application provides an intracranial pressure detection method and device, which can safely, accurately and conveniently detect the intracranial pressure of a patient to be tested.

[0024] The intracranial pressure detection method provided in the embodiment of the present application can be applied to a medical terminal or a server. It can be understood that the execution subject does not constitute a limitation on the embodiment of the present application.

[0025] The intracranial pressure detection method provided in the embodiments of the present application will be described in detail below.

[0026] like Figure 1 As shown, it is a flow chart of the intracranial pressure detection method provided in the first aspect of the embodiment of the present application. The intracranial pressure detection method may include but is not limited to the following steps S101-S105.

[0027] Step S101. Acquire the body temperature data, blood pressure data and the second negative waves of multiple flash visual evoked potentials detected by the patient.

[0028] Among them, the body temperature data of the patient to be tested can be directly detected by a thermometer, and the blood pressure data of the patient to be tested can be directly detected by a blood pressure meter.

[0029] When measuring the second negative wave of multiple flash visual evoked potentials of the patient to be tested, a flashing light source can be used to emit flashing light multiple times at a certain time interval and record the timestamp of each flashing light emission. At the same time, the flash visual evoked potential (FVEP) induced after each flashing light is recorded, and then the second negative wave (i.e., N2 wave) of the multiple flash visual evoked potentials is extracted.

[0030] Step S102: Perform signal fusion processing on multiple second negative waves to obtain processed second negative waves.

[0031] In one or more embodiments, when performing signal fusion processing on multiple second negative waves, the multiple second negative waves may be subjected to superposition and averaging processing, that is, the multiple second negative waves are first subjected to superposition processing (the amplitudes at the same time point in the multiple second negative waves are superimposed) to obtain the superimposed second negative wave. Then, the amplitude of each signal in the superimposed second negative wave is divided by the number of superpositions to obtain the processed second negative wave.

[0032] Since the signal is regular and the noise is random, as the number of superpositions increases, the signal energy becomes larger and larger, while the noise energy tends to be stable. The total noise of the second negative wave after processing is the lower energy part, and the higher energy part is the signal component, so it can effectively reduce the interference of noise.

[0033] Step S103: Filter the processed second negative wave by wavelet filtering to obtain a filtered second negative wave.

[0034] Specifically, filtering the processed second negative wave by wavelet filtering may include but is not limited to the following steps S1031-S1033.

[0035] Step S1031: Decompose the processed second negative wave at different scales to obtain a low-frequency sub-band signal and a high-frequency sub-band signal.

[0036] Among them, the low-frequency sub-band signal mainly contains the main characteristics of the signal, while the high-frequency sub-band signal contains the detailed information of the signal.

[0037] When filtering the processed second negative wave by wavelet filtering, a suitable wavelet basis can be selected according to the characteristics of the flash visual evoked potential signal and the application requirements. For example, in the case where fine resolution is required, a wavelet basis with a higher vanishing moment, such as the dbN (Daubechies) wavelet basis, can be selected.

[0038] Step S1032: Perform signal enhancement processing on the low-frequency sub-band signal and the high-frequency sub-band signal.

[0039] Among them, for low-frequency sub-band signals, signal enhancement can be performed by, but not limited to, mean filtering, median filtering, etc., and for high-frequency sub-band signals, signal enhancement can be performed by, but not limited to, bandpass filtering, notch filtering, etc. Signal enhancement can improve the signal-to-noise ratio of the signal, making the useful signal more prominent and the noise signal suppressed.

[0040] Step S1033: Perform inverse discrete wavelet transform on the low-frequency sub-band signal after signal enhancement processing and the high-frequency sub-band signal after signal enhancement processing to obtain the second negative wave after filtering.

[0041] It is understandable that in some other embodiments, the plurality of second negative waves may be firstly filtered by wavelet filtering, and then the plurality of filtered second negative waves may be superimposed and averaged.

[0042] Step S104: extracting the latency duration corresponding to the second negative wave after filtering.

[0043] Specifically, the timestamp corresponding to the peak of the second negative wave after filtering can be determined first, and then based on the timestamp corresponding to the peak of the second negative wave after filtering, the latency duration corresponding to the second negative wave after filtering can be determined. In the embodiment of the present application, the latency duration corresponding to the second negative wave is the time difference between the timestamp corresponding to the peak of the second negative wave and the timestamp when the flash visual evoked potential is triggered.

[0044] Step S105. The body temperature data, blood pressure data, incubation period, age data of the patient to be tested and optic nerve pathology data of the patient to be tested are used as inputs of the pre-trained intracranial pressure prediction model to perform calculations to obtain intracranial pressure detection data of the patient to be tested.

[0045] The intracranial pressure prediction model is obtained by training with the body temperature data, blood pressure data, latency duration of the second negative wave, age data and optic nerve pathology data corresponding to the sample patient as sample input, and the intracranial pressure measurement data of the sample patient as sample output. The intracranial pressure prediction model can be, but is not limited to, a feed-forward neural network (FFNN) model or a multilayer perceptron (MLP) model. In the embodiment of the present application, the intracranial pressure prediction model is a feed-forward neural network model.

[0046] There is a mutual influence between intracranial pressure and body temperature. When intracranial pressure increases, it may affect the normal function of the body temperature regulation center, resulting in fluctuations in body temperature. For example, when intracranial hypertension causes an inflammatory response or stress response, body temperature tends to rise. Intracranial pressure can also affect blood pressure data. When intracranial pressure increases, it may exert a certain pressure on brain tissue and cerebral blood vessels, increase the resistance to blood flow, and thus increase blood pressure. In addition, increased intracranial pressure may also lead to insufficient brain tissue perfusion, ischemia and hypoxia of brain tissue, and agitation, further causing an increase in blood pressure. As for the second negative wave of flash visual evoked potential, since neurons and their fibers need to continuously obtain energy from the blood circulation for excitation and conduction, when intracranial pressure increases, it will cause ischemia and hypoxia of neurons and their fibers, as well as metabolic disorders, resulting in nerve conduction blockage, which makes the latency of the second negative wave of flash visual evoked potential become. For optic nerve pathology data, different types of optic neuropathy may also be related to changes in intracranial pressure. For example, inflammatory lesions such as optic papillitis and optic neuritis may be related to increased intracranial pressure, while degenerative lesions such as optic atrophy may be caused by necrosis or atrophy of optic nerve fibers due to long-term increased intracranial pressure. In addition, there will be certain differences in intracranial pressure data for people of different age groups. For example, with the increase of age, various tissues and organs of the human body will undergo degenerative changes, the volume of the cranial cavity may gradually decrease, while the volume of brain tissue is relatively stable, which may lead to an increase in intracranial pressure. In the middle-aged and elderly population, due to factors such as brain atrophy and skull deformation, the volume of the cranial cavity may be further reduced, making it more likely to increase intracranial pressure. Because the patient's corresponding body temperature data, blood pressure data, the duration of the second negative wave's latency, age data, and optic nerve pathology data are closely related to the patient's intracranial pressure. Therefore, by using the sample patient's corresponding body temperature data, blood pressure data, latency duration of the second negative wave, age data and optic nerve pathology data as sample input and the sample patient's intracranial pressure measurement data as sample output, the trained intracranial pressure prediction model can more accurately predict the intracranial pressure detection data of the patient to be tested.

[0047] When the intracranial pressure increases, the amount of cerebrospinal fluid in the sheath increases, and the intracranial pressure increases, which will cause the optic nerve sheath diameter (ONSD) to expand. The intracranial pressure can also be measured by measuring the optic nerve sheath diameter. Therefore, in one or more embodiments, the intracranial pressure data of the patient to be tested can also be measured by the optic nerve sheath diameter to verify the intracranial pressure detection data of the patient to be tested. Specifically, the process of verifying the intracranial pressure detection data of the patient to be tested by measuring the intracranial pressure data of the patient to be tested by the optic nerve sheath diameter can include but is not limited to the following steps S201-S206.

[0048] Step S201: Acquire an ultrasonic reflection image of the eye area of ​​the patient to be tested.

[0049] In the embodiment of the present application, ultrasonic waves can be emitted to the eye region of the patient to be tested through a high-frequency linear array ultrasonic probe, and an ultrasonic reflection image reflected back from the eye region of the patient to be tested can be received.

[0050] Step S202: construct an ultrasonic image of the eye area of ​​the patient to be tested based on the ultrasonic reflection image.

[0051] Step S203: Identify the optic nerve sheath in the ultrasound image through image recognition.

[0052] In the embodiment of the present application, the optic nerve sheath of the ultrasound image can be identified by target recognition technology, which is a prior art and will not be described in detail in the embodiment of the present application. It can be understood that in some other embodiments, the ultrasound image can also be manually annotated.

[0053] Step S204: measuring the diameter of the optic nerve sheath in the ultrasound image.

[0054] In the embodiment of the present application, the optic nerve sheath diameter (ONSD) can be directly measured by a measuring tool on an ultrasonic device.

[0055] Step S205: Based on the optic nerve sheath diameter in the ultrasound image, the intracranial pressure data of the patient to be tested is predicted to obtain the intracranial pressure prediction data of the patient to be tested.

[0056] In an embodiment of the present application, the optic nerve sheath diameters of multiple sample patients and the intracranial pressure data of multiple sample patients can be used to fit the function between the optic nerve sheath diameter and the intracranial pressure data, thereby estimating the intracranial pressure prediction data of the patient to be tested based on the function and the optic nerve sheath diameter in the ultrasound image.

[0057] Step S206: If the difference between the intracranial pressure prediction data and the intracranial pressure detection data is lower than a first preset threshold, the intracranial pressure detection data of the patient to be tested is used as the final intracranial pressure detection data of the patient to be tested.

[0058] Among them, the first preset threshold can be set according to actual conditions and is not specifically limited in the embodiments of the present application.

[0059] In one or more embodiments, a second preset threshold value indicating excessive intracranial pressure can also be pre-set. When the intracranial pressure detection data of the patient to be tested is higher than the second preset threshold value, an early warning message can be automatically generated to remind medical personnel that the intracranial pressure of the patient to be tested is too high so that corresponding measures can be taken in time.

[0060] In summary, the intracranial pressure detection method provided by the present invention obtains the body temperature data, blood pressure data and the second negative wave of multiple flash visual evoked potentials detected by the patient to be tested, performs signal fusion processing on the multiple second negative waves to obtain a processed second negative wave, filters the processed second negative wave by wavelet filtering to obtain a filtered second negative wave, and extracts the latent period corresponding to the filtered second negative wave, and then uses the body temperature data, blood pressure data, latent period, age data of the patient to be tested and optic nerve pathology data of the patient to be tested as inputs of a pre-trained intracranial pressure prediction model for calculation to obtain intracranial pressure detection data of the patient to be tested, wherein the intracranial pressure prediction model is trained using the body temperature data, blood pressure data, latent period of the second negative wave, age data and optic nerve pathology data corresponding to the sample patient as sample inputs, and the intracranial pressure measurement data of the sample patient as sample output. In this way, the patient's intracranial pressure can be measured based on multiple user data associated with the intracranial pressure data, without the need for complex surgery, and without safety risks caused by surgical trauma. The measurement of intracranial pressure data is simple and fast, which improves the patient's detection experience. When measuring the latency of the second negative wave used for intracranial pressure detection, the signal fusion and wavelet filtering of multiple second negative waves can reduce the interference of noise, and accurately extract the latency corresponding to the second negative wave, thereby ensuring that the intracranial pressure data can be accurately measured, which is convenient for practical application and promotion.

[0061] See also Figure 2 The second aspect of the embodiment of the present application provides an intracranial pressure detection device, the intracranial pressure detection device comprising: An acquisition unit, used for acquiring body temperature data, blood pressure data and the second negative wave of multiple detected flash visual evoked potentials of the patient to be tested; A fusion unit, configured to perform signal fusion processing on the plurality of second negative waves to obtain a processed second negative wave; A filtering unit, used for filtering the processed second negative wave by wavelet filtering to obtain a filtered second negative wave; An extraction unit, used for extracting the latency duration corresponding to the second negative wave after filtering; A calculation unit, used to calculate the body temperature data, the blood pressure data, the duration of the latent period, the age data of the patient to be tested, and the optic nerve pathology data of the patient to be tested as inputs of a pre-trained intracranial pressure prediction model to obtain intracranial pressure detection data of the patient to be tested; The intracranial pressure prediction model is trained using the body temperature data, blood pressure data, latency duration of the second negative wave, age data and optic nerve pathology data corresponding to the sample patients as sample inputs, and the intracranial pressure measurement data of the sample patients as sample outputs.

[0062] The working process, working details and technical effects of the intracranial pressure detection device provided in the second aspect of this embodiment can be referred to the first aspect of the embodiment and will not be repeated here.

[0063] like Figure 3 As shown, the third aspect of an embodiment of the present application provides an electronic device, comprising a memory, a processor and a transceiver that are communicatively connected in sequence, wherein the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the intracranial pressure detection method as described in the first aspect of the embodiment.

[0064] For specific examples, the memory may include but is not limited to random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out memory (FIFO) and / or first-in-last-out memory (FILO), etc.; the processor may be but is not limited to a microprocessor of the STM32F105 series, an ARM (Advanced RISC-Machines), an X86 or other architecture processor, or a processor with an integrated NPU (neural-network processing units); the transceiver may be but is not limited to a WiFi (Wireless Fidelity) wireless transceiver, a Bluetooth wireless transceiver, a General Packet Radio Service (GPRS) wireless transceiver, a ZigBee protocol (a low-power local area network protocol based on the IEEE802.15.4 standard, ZigBee) wireless transceiver, a 3G transceiver, a 4G transceiver and / or a 5G transceiver, etc.

[0065] In a fourth aspect of this embodiment, there is provided a computer-readable storage medium storing instructions including the intracranial pressure detection method described in the first aspect of the embodiment, that is, the computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the intracranial pressure detection method described in the first aspect is executed. The computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive, and / or a memory stick, etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0066] The fifth aspect of this embodiment provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the intracranial pressure detection method as described in the first aspect of the embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0067] It should be understood that certain details are provided in the following description to facilitate a complete understanding of the example embodiments. However, it should be understood by those of ordinary skill in the art that the example embodiments can be implemented without these certain details. For example, the system can be shown in a block diagram to avoid obscuring the example with unnecessary details. In other examples, well-known processes, structures, and techniques may not be shown in unnecessary detail to avoid obscuring the example embodiments.

[0068] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for detecting intracranial pressure, characterized in that: include: Acquiring body temperature data, blood pressure data and the second negative wave of multiple detected flash visual evoked potentials of the patient to be tested; performing signal fusion processing on the plurality of second negative waves to obtain a processed second negative wave; The processed second negative wave is filtered by wavelet filtering to obtain a filtered second negative wave; Extract the latency duration corresponding to the second negative wave after filtering; The body temperature data, the blood pressure data, the duration of the latent period, the age data of the patient to be tested, and the optic nerve pathology data of the patient to be tested are used as inputs of a pre-trained intracranial pressure prediction model to perform calculations to obtain intracranial pressure detection data of the patient to be tested; The intracranial pressure prediction model is trained using the body temperature data, blood pressure data, latency duration of the second negative wave, age data and optic nerve pathology data corresponding to the sample patients as sample inputs, and the intracranial pressure measurement data of the sample patients as sample outputs.

2. The intracranial pressure detection method according to claim 1, characterized in that: The filtering of the processed second negative wave by wavelet filtering to obtain the filtered second negative wave includes: Decomposing the processed second negative wave at different scales to obtain low-frequency sub-band signals and high-frequency sub-band signals; Performing signal enhancement processing on the low-frequency sub-band signal and the high-frequency sub-band signal; The low-frequency sub-band signal after signal enhancement processing and the high-frequency sub-band signal after signal enhancement processing are subjected to inverse discrete wavelet transform to obtain the second negative wave after filtering.

3. The intracranial pressure detection method according to claim 1, characterized in that: The performing signal fusion processing on the plurality of second negative waves to obtain a processed second negative wave comprises: Superimposing a plurality of the second negative waves to obtain a superimposed second negative wave; The amplitude of each signal in the superimposed second negative wave is divided by the number of superpositions to obtain the processed second negative wave.

4. The intracranial pressure detection method according to claim 1, characterized in that: The extraction of the latency duration corresponding to the second negative wave after filtering includes: Determine the timestamp corresponding to the peak of the second negative wave after filtering; Based on the timestamp corresponding to the peak of the second negative wave after filtering, the latency duration corresponding to the second negative wave after filtering is determined.

5. The intracranial pressure detection method according to claim 1, characterized in that: The method further comprises: Acquire an ultrasonic reflection image of the eye area of ​​the patient to be tested; constructing an ultrasound image of the eye region of the patient to be tested based on the ultrasound reflection image; identifying the optic nerve sheath in the ultrasound image by image recognition; measuring the diameter of the optic nerve sheath in the ultrasound image; Predicting the intracranial pressure data of the patient to be tested based on the optic nerve sheath diameter in the ultrasound image to obtain the intracranial pressure prediction data of the patient to be tested; If the difference between the intracranial pressure prediction data and the intracranial pressure detection data is lower than a first preset threshold, the intracranial pressure detection data of the patient to be tested is used as the final intracranial pressure detection data of the patient to be tested.

6. The intracranial pressure detection method according to claim 1, characterized in that: The method further comprises: When the intracranial pressure detection data of the patient to be tested is higher than a second preset threshold, a warning message is generated.

7. The intracranial pressure detection method according to claim 1, characterized in that: The intracranial pressure prediction model is a feedforward neural network model.

8. An intracranial pressure detection device, characterized in that: include: An acquisition unit, used for acquiring the body temperature data, blood pressure data and the second negative wave of the detected multiple flash visual evoked potentials of the patient to be tested; A fusion unit, configured to perform signal fusion processing on the plurality of second negative waves to obtain a processed second negative wave; A filtering unit, used for filtering the processed second negative wave by wavelet filtering to obtain a filtered second negative wave; An extraction unit, used for extracting the latency duration corresponding to the second negative wave after filtering; A calculation unit, used to calculate the body temperature data, the blood pressure data, the duration of the latent period, the age data of the patient to be tested, and the optic nerve pathology data of the patient to be tested as inputs of a pre-trained intracranial pressure prediction model to obtain intracranial pressure detection data of the patient to be tested; The intracranial pressure prediction model is trained using the body temperature data, blood pressure data, latency duration of the second negative wave, age data and optic nerve pathology data corresponding to the sample patients as sample inputs, and the intracranial pressure measurement data of the sample patients as sample outputs.

9. An electronic device, characterized in that: It comprises a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the intracranial pressure detection method as described in any one of claims 1 to 7.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or the instruction is executed by a computer, the intracranial pressure detection method according to any one of claims 1 to 7 is implemented.

Images