Auxiliary recognition method and system for subclinical valve leaflet thrombus after transcatheter aortic valve replacement and signal acquisition device

Abstract

The invention provides a subclinical valve leaflet thrombus auxiliary identification method and system after transcatheter aortic valve replacement and a signal acquisition device, and belongs to the technical field of heart information acquisition and identification. The subclinical valve leaflet thrombus auxiliary identification method is used for auxiliary diagnosis of subclinical valve leaflet thrombus after transcatheter aortic valve replacement and comprises the steps that heart sound signals are collected and processed, preset parameters of the heart sound signals are obtained, and the preset parameters at least comprise time, frequency and energy; determining a systolic period according to the heart sound signal; identifying an energy highest point in the characteristic interval of the contraction period; acquiring a characteristic frequency corresponding to the highest point of the energy, judging whether the characteristic frequency is greater than a threshold frequency or not, and if so, marking the heart sound signal as an abnormal heart sound signal caused by the subclinical valve leaflet thrombus; and if not, marking the heart sound signal as a normal heart sound signal. According to the method, the problem that the applicable crowd range is limited due to the fact that multi-dimensional computed tomography is mainly adopted in subclinical leaflet thrombus detection is solved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of cardiac information collection and identification, and in particular to a method, system and signal collection device for auxiliary identification of subclinical leaflet thrombosis after transcatheter aortic valve replacement. Background Art

[0002] Subclinical leaflet thrombosis is a common complication after transcatheter aortic valve replacement, with an incidence of 15% to 30%. The presence of subclinical leaflet thrombosis leads to reduced leaflet motion, affects the effective valve area of ​​the aortic valve, increases the transvalvular pressure gradient and flow velocity, and ultimately affects valve durability.

[0003] Currently, subclinical leaflet thrombosis is mainly detected by multidimensional computed tomography (MDCT), which can identify the hallmark features of low-density leaflet thickening and reduced leaflet activity associated with valve dysfunction and durability, and then diagnose whether subclinical leaflet thrombosis exists. However, multidimensional computed tomography is not suitable for the elderly, chronic renal insufficiency, and those who are allergic to contrast agents. Summary of the invention

[0004] The present invention provides a method, system and signal acquisition device for auxiliary identification of subclinical leaflet thrombosis after transcatheter aortic valve replacement, so as to solve the technical problem that the detection of subclinical leaflet thrombosis in the prior art mainly adopts multi-dimensional computed tomography, which has a limited applicable population range.

[0005] In order to solve the above technical problems, the present disclosure provides a method for assisting in identifying subclinical leaflet thrombosis, which is used to assist in diagnosing subclinical leaflet thrombosis after transcatheter aortic valve replacement, comprising: Collecting heart sound signals, and processing the heart sound signals to obtain preset parameters of the heart sound signals, wherein the preset parameters at least include time, frequency and energy; determining a systolic period according to the heart sound signal; identifying the highest energy point within the characteristic interval of the contraction period; The characteristic frequency corresponding to the highest energy point is obtained, and it is determined whether the characteristic frequency is greater than a threshold frequency. If so, the heart sound signal is marked as an abnormal heart sound signal caused by subclinical leaflet thrombosis; if not, the heart sound signal is marked as a normal heart sound signal.

[0006] In order to solve the above technical problems, the present disclosure also provides a subclinical leaflet thrombosis auxiliary identification system for auxiliary diagnosis of subclinical leaflet thrombosis after transcatheter aortic valve replacement. The subclinical leaflet thrombosis auxiliary identification system is used to implement the above subclinical leaflet thrombosis auxiliary identification method. The subclinical leaflet thrombosis auxiliary identification system includes: A heart sound collection unit, used for collecting heart sound signals; A heart sound processing unit, used to process the collected heart sound signal to obtain preset parameters of the heart sound signal, wherein the preset parameters at least include time, frequency and energy; A processor unit is used to determine the contraction period according to the heart sound signal, identify the highest energy point in the characteristic interval of the contraction period, obtain the characteristic frequency corresponding to the highest energy point, and judge whether the characteristic frequency is greater than a threshold frequency. If so, output the recognition result that the heart sound signal is an abnormal heart sound signal caused by subclinical leaflet thrombosis; if not, output the recognition result that the heart sound signal is a normal heart sound signal.

[0007] In order to solve the above technical problems, the present disclosure further provides a heart sound and electrocardiogram signal acquisition device, which is used to implement the step of synchronously acquiring human heart sound signals and electrocardiogram signals in the above subclinical leaflet thrombosis auxiliary identification method, and the heart sound and electrocardiogram signal acquisition device includes: Electrodes, used for collecting the electrocardiogram signal; A sound sensor, used for synchronously collecting the heart sound signal; A processing unit is used to synchronously digitize the heart sound signal and the electrocardiogram signal.

[0008] The positive and progressive effects of this disclosure: The technical solution disclosed in the present invention utilizes the acoustic property that subclinical leaflet thrombosis can cause high-energy noise in the characteristic interval of the contraction period. By judging whether the characteristic frequency corresponding to the highest energy point of the heart sound signal in the characteristic interval of the contraction period is greater than the threshold frequency, it is identified whether the heart sound signal is abnormal, thereby realizing the processing and recognition of the heart sound signal, which is human body information. The obtained recognition result can be used as an intermediate result information to assist in the diagnosis of whether subclinical leaflet thrombosis is formed after transcatheter aortic valve replacement. This auxiliary diagnosis can be applicable to various populations, and effectively solves the technical problem that the detection of subclinical leaflet thrombosis in the prior art mainly adopts multi-dimensional computed tomography, which is applicable to a limited range of populations. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A flow chart of a method for assisting in identifying subclinical leaflet thrombosis provided in one embodiment of the present disclosure.

[0010] Figure 2 A heart sound time-frequency energy diagram generated according to a heart sound signal and an electrocardiogram collected synchronously in one embodiment of the present disclosure are shown.

[0011] Figure 3 It is a schematic diagram of defining the contraction period in one embodiment of the present disclosure.

[0012] Figure 4A schematic diagram of a subclinical leaflet thrombosis auxiliary identification system provided in accordance with an embodiment of the present disclosure.

[0013] Figure 5 A schematic diagram of a heart sound and electrocardiogram signal acquisition device provided in an embodiment of the present disclosure.

[0014] The above and other features, advantages, etc. of each embodiment of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the accompanying drawings are schematic and the elements are not necessarily drawn to scale. DETAILED DESCRIPTION

[0015] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present disclosure pertains. The terms used herein in the specification of the application are only for describing specific embodiments and are not intended to limit the present disclosure. The term "comprising" and any corresponding variations in the specification and claims of the present disclosure are intended to cover non-exclusive inclusions.

[0016] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present disclosure. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0017] The present disclosure is proposed based on a study on assisting the diagnosis of whether subclinical leaflet thrombosis is formed after transcatheter aortic valve replacement. To facilitate the explanation of the present disclosure, this study is first introduced below.

[0018] The principles on which this study is based are as follows.

[0019] During the cardiac cycle, heart sounds are produced when the valve opens and closes as blood flows through it. When subclinical leaflet thrombosis is present, it will lead to reduced leaflet movement, affect the effective valve area of ​​the aortic valve, increase the transvalvular pressure difference and flow rate, and ultimately affect the durability of the valve. That is, the presence of subclinical leaflet thrombosis will change the hemodynamic characteristics, reduce the cross-sectional area of ​​the valve orifice, increase local resistance, pressure difference and flow rate, and turn the blood flow to a turbulent state. This change in hemodynamic characteristics will lead to abnormal murmurs that can be identified in the aortic valve auscultation area. Therefore, this study aims to verify the identification of the above-mentioned murmurs to assist in the diagnosis of subclinical leaflet thrombosis.

[0020] The methods used in this study are as follows.

[0021] Patients with severe symptomatic aortic stenosis who underwent successful transcatheter aortic-valve replacement were enrolled. Patients were divided into three groups according to the severity of subclinical leaflet thrombosis: group 1 (no subclinical leaflet thrombosis), group 2 (mild subclinical leaflet thrombosis, characterized by the presence of hypodense leaflet thickening but not to the extent described in group 3 below), and group 3 (moderate to severe subclinical leaflet thrombosis, characterized by at least one leaflet thickening determined as grade 3 or 4 with a ≥50% reduction in leaflet motion, or two leaflets thickening determined as grade 2 or a ≥50% reduction in leaflet motion). For clarity, patients were reclassified into two categories: no moderate to severe subclinical leaflet thrombosis (groups 1 and 2) and moderate to severe subclinical leaflet thrombosis (group 3). Multidimensional computed tomography was performed on patients 30 days and 6 months after discharge to detect low-density leaflet thickening and reduced leaflet activity to determine subclinical leaflet thrombosis, which is also the gold standard for subclinical leaflet thrombosis detection. A 4-level grading standard was used to describe the degree of leaflet thickening: <25% (limited to the base), >25% and ≤50%, >50% and ≤75%, >75%. A 4-level grading standard was used to describe the degree of reduced leaflet activity: none (no reduced leaflet activity), reduced leaflet activity <50%, reduced leaflet activity ≥50%, and leaflet inactivity. The patient's heart sound signals and electrocardiogram signals were collected synchronously, and the acoustic characteristics of the collected heart sound signals and electrocardiogram signals were analyzed, and the acoustic characteristic data were statistically analyzed.

[0022] The results of this study are as follows.

[0023] A total of 116 patients consented and participated in the study. In the first month of follow-up after surgery, multidimensional computed tomography detected a 25% prevalence of subclinical leaflet thrombosis, of which 11.2% were classified as moderate to severe subclinical leaflet thrombosis. Analysis of the results of phono-ECG synchronization revealed that patients in Group 3 had a high-energy murmur in the early systole, while patients without subclinical leaflet thrombosis did not have this murmur. At 6 months, both multidimensional computed tomography and phono-ECG synchronization showed that subclinical leaflet thrombosis completely resolved in 9 patients (70%) in Group 3 who received anticoagulation. Therefore, based on the deterioration of transvalvular hemodynamics after transcatheter aortic valve replacement, detecting the size of the murmur in a specific interval of the heart sound signal can be used as an effective method for auxiliary diagnosis of subclinical leaflet thrombosis, that is, the auxiliary identification method of subclinical leaflet thrombosis disclosed in the present invention.

[0024] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0025] The first aspect of the embodiment of the present disclosure is introduced below: a method for assisting in identifying subclinical leaflet thrombosis.

[0026] The subclinical leaflet thrombosis auxiliary identification method disclosed herein is used to assist in the diagnosis of subclinical leaflet thrombosis after transcatheter aortic valve replacement. Here, the auxiliary diagnosis is first further explained. This method is for the identification of subclinical leaflet thrombosis, especially the abnormal heart sound signals caused by moderate to severe subclinical leaflet thrombosis. It is essentially still the identification of cardiac information, and its identification result is still a cardiac information identification result. It is just that with the help of the identification result of this method, it can assist in the diagnosis of the formation of subclinical leaflet thrombosis. This method does not directly diagnose the disease of subclinical leaflet thrombosis, but uses the cardiac information identification results obtained by this method to assist in the diagnosis.

[0027] Figure 1 Flow chart of the method for assisting in identifying subclinical leaflet thrombosis provided in the embodiment of the present disclosure. Figure 1 As shown, a subclinical leaflet thrombosis auxiliary identification method for auxiliary diagnosis of subclinical leaflet thrombosis after transcatheter aortic valve replacement comprises the following steps: S101, collecting heart sound signals, and processing the heart sound signals to obtain preset parameters of the heart sound signals, where the preset parameters include at least time, frequency, and energy; S102, determining the systolic period according to the heart sound signal; S103, identifying the highest energy point in the characteristic interval of the contraction period; S104, obtaining the characteristic frequency corresponding to the highest energy point, and determining whether the characteristic frequency is greater than a threshold frequency. If so, S105 marks the heart sound signal as an abnormal heart sound signal caused by subclinical leaflet thrombosis; if not, S106 marks the heart sound signal as a normal heart sound signal.

[0028] In this embodiment, three preset parameters of time, frequency and energy are used to quantitatively analyze the collected heart sound signals. Specifically, the quantitative analysis method in this embodiment adopts the wavelet transform method, which can obtain better time / frequency characteristics. Of course, in other optional implementations, short-time Fourier transform and other time-frequency analysis methods can also be used. The energy in this embodiment is calculated based on the heart sound waveform, such as Figure 2 As shown, it shows the time-frequency energy diagram of heart sounds. In the diagram, the horizontal axis is time and the vertical axis is frequency. The depth of the color in the diagram indicates the energy level. The darker the color, the greater the energy. Generally, energy is related to the influence of amplitude and frequency. The larger the amplitude, the higher the energy value; the larger the frequency, the higher the energy level. Since the amplitude varies with body weight, acquisition position and posture, and the frequency, as an inherent characteristic of sound waves, will not change due to the influence of acquisition conditions or environment, frequency is selected as the judgment indicator in the present disclosure.

[0029] Since energy reflects the size of the heart sound, when higher abnormal energy appears during systole, it indicates the presence of a systolic murmur, for example, Figure 2 The typical abnormal murmur of subclinical thrombosis shown in the figure can be used to assist in the diagnosis of subclinical leaflet thrombosis by identifying the abnormal murmur. Specifically, when a murmur occurs during the systolic period, the highest energy point within the murmur range is identified, and correspondingly, the characteristic frequency corresponding to the highest energy point is obtained. The characteristic frequency is compared with the threshold frequency corresponding to the subclinical leaflet thrombosis. If the characteristic frequency is greater than the threshold frequency, it means that a murmur caused by subclinical leaflet thrombosis has occurred, thereby assisting in the diagnosis that the subject has a high probability of having subclinical leaflet thrombosis in the body. It should be noted here that the threshold frequency corresponding to the subclinical leaflet thrombosis is a value obtained through the summary of clinical data, and the relevant statistical methods and data will be described in more detail below.

[0030] The above method of this embodiment identifies whether the heart sound signal is abnormal by judging whether the characteristic frequency corresponding to the highest energy point of the heart sound signal in the characteristic interval of the contraction period is greater than the threshold frequency corresponding to the subclinical leaflet thrombosis, thereby realizing the processing and identification of the heart sound signal, which is the physiological information of the human body. The recognition result obtained by the auxiliary identification method of subclinical leaflet thrombosis can be used as an intermediate result information to assist in the diagnosis of whether subclinical leaflet thrombosis is formed after transcatheter aortic valve replacement. This auxiliary diagnosis can be applicable to various populations, and effectively solves the technical problem that the detection of subclinical leaflet thrombosis in the prior art mainly adopts multi-dimensional computed tomography, which has a limited range of applicable populations.

[0031] Further, in an embodiment of the present disclosure, determining the systolic period according to the heart sound signal includes: Collecting ECG signals synchronized with heart sound signals; determining a first heart sound and a second heart sound of a heart sound signal according to the electrocardiogram signal; The systolic period is determined based on the first and second heart sounds.

[0032] Figure 3 The cardiac hemodynamic curves and the corresponding phonocardiogram and electrocardiogram are shown. The three curves above the figure represent the time-pressure curves of the aorta, left atrium and left ventricle, respectively. The horizontal axis of each curve is time (not shown in the figure) and the vertical axis is pressure (not shown in the figure). The cardiac hemodynamic significance of the intersection of each curve is: the intersection a of the curve indicates that the mitral valve is closed, the intersection b of the curve indicates that the aortic valve is open, the intersection c of the curve indicates that the aortic valve is closed, and the intersection d of the curve indicates that the mitral valve is open. Figure 2The two curves in the lower middle are respectively an electrocardiogram and a phonocardiogram. The electrocardiogram shows P wave, Q wave, R wave, S wave and T wave, and the phonocardiogram shows the first heart sound S1, the second heart sound S2, the third heart sound S3 and the fourth heart sound S4. In this embodiment, the phonocardiogram and the electrocardiogram are depicted by using the synchronously collected phonocardiogram signal and the electrocardiogram signal. The first heart sound and the second heart sound in the phonocardiogram can be corresponded according to the R wave, S wave and T wave in the electrocardiogram, and then the systolic period is determined according to the relationship between the first heart sound and the second heart sound and the systolic period.

[0033] Further, in an embodiment of the present disclosure, determining a first heart sound and a second heart sound of a heart sound signal according to an electrocardiogram signal includes: Use the same time axis to display ECG signals and heart sound signals; Identify the R peak in the ECG signal; The first and second heart sounds are identified based on the R peak.

[0034] In this embodiment, in the phonocardiogram and electrocardiogram corresponding to the synchronously collected heart sound signals and electrocardiogram signals, since the peak of the R wave in the electrocardiogram (i.e., the R peak) indicates the beginning of the first heart sound, the beginning of the first heart sound in the phonocardiogram can be determined based on this. This method is simpler and more convenient.

[0035] Further, in an embodiment of the present disclosure, the systolic period is the period from the opening of the aortic valve to the closing of the aortic valve, and the characteristic interval is the period from the beginning of the systolic period to the midline of the systolic period.

[0036] like Figure 3 As shown, the systolic period is the interval between the systolic starting line where the point b indicating the opening of the aortic valve is located and the systolic end line where the point c indicating the closure of the aortic valve is located, and the characteristic interval refers to the interval between the systolic starting line and the systolic midline. The selection of the characteristic interval is based on the clinical data analysis of the above-mentioned auxiliary diagnosis of whether subclinical leaflet thrombosis is formed after transcatheter aortic valve replacement. Specifically, the study found that after transcatheter aortic valve replacement, a high-energy abnormal murmur appeared in the heart sound signal of patients with subclinical leaflet thrombosis. After statistics, it was found that the murmur appeared in a specific interval, which was defined as the characteristic interval. The characteristic interval is located in the early stage of the systolic period. For a more convenient quantitative description, the present disclosure defines the systolic period as the period from the opening of the aortic valve to the closure of the aortic valve based on clinical statistics, and selects the period from the beginning of the systolic period to the midline of the systolic period as the characteristic interval according to the range of the abnormal murmur. Thus, a quantitative and specific judgment standard is provided for auxiliary diagnosis of whether a patient has subclinical leaflet thrombosis.

[0037] Further, in the embodiment of the present disclosure, the threshold frequency is 25 Hz. In other optional implementations, the threshold frequency can be selected as 20 Hz or other frequencies greater than 20 Hz.

[0038] In this embodiment, the selection of the threshold frequency of 25 Hz is also based on the clinical data analysis of the above-mentioned study on the auxiliary diagnosis of subclinical leaflet thrombosis after transcatheter aortic valve replacement. The study found that on day 30, the median sound frequencies of the highest energy points in the target spectra of groups 1, 2, and 3 were 20 Hz (quartile: 17–23 Hz), 22 Hz (quartile: 19–24 Hz), and 53 Hz (quartile: 45–67 Hz), respectively. In patients with moderate to severe subclinical leaflet thrombosis, non-baseline murmurs were observed from the beginning of systole to the midline of systole, characterized by an energy frequency lower than the first heart sound. It should be noted that the characteristic frequency refers to the frequency corresponding to the highest energy point in the murmur range, not the frequency corresponding to the energy of the first heart sound itself. The receiver operating characteristic curve (ROC curve) showed that the phono-ECG synchronization detection method with a threshold frequency of 25 Hz had the highest diagnostic efficiency for moderate to severe subclinical leaflet thrombosis, with a sensitivity of 84.62%, a specificity of 91.26%, and an area under the curve (AUC) of 0.920 (95% CI: 0.855–0.962, p<0.001). The positive likelihood ratio (LR+) was 9.68, the negative likelihood ratio (LR-) was 0.17, and the Kappa value was 0.61 (p<0.001), indicating that the diagnosis of subclinical leaflet thrombosis had a strong consistency. Cases were selected to further evaluate the phono-ECG synchronization detection and multidimensional computed tomography detection in patients with and without subclinical leaflet thrombosis. In 13 patients with moderate to severe subclinical leaflet thrombosis who received anticoagulation treatment 30 days to 6 months after transcatheter aortic valve replacement, the prevalence of low-density leaflet thickening was observed to drop significantly to 70% (9 / 13), and valve function was fully restored. Accordingly, the abnormal murmur associated with subclinical leaflet thrombosis disappeared, indicating that the auxiliary diagnosis of subclinical leaflet thrombosis was consistent with the diagnosis results of multidimensional computed tomography. This study demonstrates the effectiveness of the identification method disclosed in the present invention for the auxiliary diagnosis of subclinical leaflet thrombosis, as well as the effectiveness of selecting 25 Hz as an abnormal murmur to determine whether the murmur is caused by subclinical leaflet thrombosis.

[0039] Further, in this embodiment, the subclinical leaflet thrombosis auxiliary identification method also includes: establishing a user database model, and performing machine learning and comparison analysis on user data, and warning users who may have abnormal heart sound signals caused by subclinical leaflet thrombosis; wherein the user data at least includes: heart sound signals, electrocardiogram signals and recognition results. Among them, it also includes data filtering and validity analysis of the collected information. For valid data, a signal processing method based on continuous wavelet transform is used to perform preliminary feature extraction, and an artificial intelligence algorithm based on deep learning is used to further extract heart sound signals and electrocardiogram signals, so as to obtain accurate electrocardiograms, phonocardiograms and corresponding energy distribution spectra. After using the analysis algorithm to process and analyze the currently collected user data, the user data is compared, that is, the analyzed user data is compared with the user's historical data, and at the same time, it is compared with the known disease data to determine whether the heart sound signals and electrocardiogram signals are developing in the direction of forming abnormal murmurs caused by subclinical leaflet thrombosis, or have formed abnormal murmurs caused by subclinical leaflet thrombosis, and then determine the user's physical health status. The analysis results of user data can be directly displayed and alarmed, and the analysis results can be submitted to the nurse station and other diagnosis and treatment auxiliary systems, data centers and the patient's attending doctors through the network. If the user information is found to be abnormal, such as a significant change compared with the user's historical data, and the data pattern is close to the known disease data, an alarm will be issued to remind the user to pay attention to the risk. Furthermore, when it is determined based on data analysis that the frequency threshold of the current user is much higher than the characteristic threshold, it means that the user is in an emergency state. At this time, the database system can send a rescue signal to the outside world. For example, a help signal is sent to the emergency center or a pre-set emergency contact to improve the timeliness of rescue.

[0040] The second aspect of the present disclosure is introduced below: a subclinical leaflet thrombosis auxiliary identification system.

[0041] The subclinical leaflet thrombosis auxiliary identification system provided in this embodiment is used to assist in the diagnosis of subclinical leaflet thrombosis after transcatheter aortic valve replacement, and implement the above-mentioned subclinical leaflet thrombosis auxiliary identification method. Figure 4 As shown, the subclinical leaflet thrombosis auxiliary identification system 400 includes: a heart sound acquisition unit 401, used to acquire heart sound signals; a heart sound processing unit 402, used to process the acquired heart sound signals and obtain preset parameters of the heart sound signals, the preset parameters at least including time, frequency and energy; a processor unit 403, used to determine the contraction period according to the heart sound signals, and identify the highest energy point in the characteristic interval of the contraction period, obtain the characteristic frequency corresponding to the highest energy point, and determine whether the characteristic frequency is greater than the threshold frequency. If so, the output heart sound signal is the identification result of the abnormal heart sound signal caused by subclinical leaflet thrombosis; if not, the output heart sound signal is the identification result of the normal heart sound signal.

[0042] The subclinical leaflet thrombosis auxiliary identification system 400 provided in this embodiment identifies whether the heart sound signal is abnormal by judging whether the characteristic frequency corresponding to the highest energy point of the heart sound signal in the characteristic interval of the contraction period is greater than the threshold frequency, thereby realizing the processing and identification of the heart sound signal, which is human information, and then using the obtained identification result as an intermediate result information to assist in the diagnosis of whether subclinical leaflet thrombosis is formed after transcatheter aortic valve replacement. This auxiliary diagnosis can be applicable to various populations, and effectively solves the technical problem that the detection of subclinical leaflet thrombosis in the existing technology mainly adopts multi-dimensional computed tomography, which is applicable to a limited range of populations.

[0043] Furthermore, in an embodiment of the present disclosure, the subclinical leaflet thrombus auxiliary identification system 400 also includes: an ECG acquisition unit 404, for synchronously acquiring ECG signals when the heart sound acquisition unit 401 acquires heart sound signals; an ECG processing unit 405, for processing the ECG signals acquired by the ECG acquisition unit 404; wherein the processor unit 403 is capable of determining the first heart sound and the second heart sound of the heart sound signal based on the ECG signal, and determining the contraction period based on the first heart sound and the second heart sound.

[0044] Furthermore, in an embodiment of the present disclosure, the subclinical leaflet thrombosis auxiliary identification system 400 also includes: a database unit 406, which is used to establish a user database model, and perform machine learning and comparative analysis on user data, to warn users who may have abnormal heart sound signals caused by subclinical leaflet thrombosis; wherein the user data includes at least: heart sound signals, electrocardiogram signals and recognition results.

[0045] In addition, the subclinical leaflet thrombus auxiliary identification system 400 of this embodiment also includes a communication unit (not shown in the figure) for realizing data transmission between the heart sound acquisition unit 401, the heart sound processing unit 402, the electrocardiogram acquisition unit 404, the electrocardiogram processing unit 405, the processor unit 403 and the database unit 406. The communication unit can adopt various types of communication methods, such as wired, wireless communication links or optical fiber cables. It should be noted that the above-mentioned wireless connection methods may include but are not limited to 3G / 4G / 5G / 6G connections, Wi-Fi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB connections, local area networks (LANs), wide area networks (WANs), Internet (e.g., the Internet) and peer-to-peer networks (e.g., adhoc peer-to-peer networks) and other network connection methods currently known or developed in the future. The communication unit can communicate using any currently known or future developed network protocol such as HTTP (HyperTextTransferProtocol, Hypertext Transfer Protocol), and can be interconnected with digital data communications (e.g., communication networks) of any form or medium.

[0046] In addition, in some optional embodiments, the subclinical leaflet thrombus auxiliary identification system 400 also includes a user-end device and a server-end device, and the database unit 406 can be set in the server-end device. The user can use the user-end device to interact with the server-end device through the communication unit to receive or send data. Various user-end applications can be installed on the user-end device, such as video live broadcast and playback applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc. The user-end device can be various electronic devices with a touch screen and / or support web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 (Moving Picture Experts Compression Standard Audio Layer 3) players, MP4 (Moving Picture Experts Compression Standard Audio Layer 4) players, head-mounted display devices, laptops, digital broadcast receivers, PDAs (personal digital assistants), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and mobile terminals such as digital TVs, desktop computers, etc.

[0047] In addition, in some optional embodiments, the database unit 406 may store information such as user name, gender, age, height, weight, medical history, heart monitoring data, etc. The database unit 406 may receive the human life feature data transmitted from the user terminal device, automatically store, archive, automatically analyze, extract and identify the features, etc., and then transmit the analysis results (such as analysis reports, health advice, or disease warnings, etc.) to the user terminal device through the communication unit. Of course, the database unit 406 may not send its analysis results, but the user may log in to the cloud data center through the user terminal device to view it. In addition, under the premise of user permission, the collected human life feature data and analysis results can also be called by professional medical personnel or institutions as a reference for further medical examination or diagnosis. Also under the premise of user permission, third-party medical research, data analysis, data statistics and data mining experts can conduct more in-depth analysis and research on the data. Their research results can be uploaded to the database unit 406 for users to view. Users can also select and customize different analysis and feature extraction algorithms on the database unit 406, and pay the use fee to the algorithm developer through the database unit 406.

[0048] In addition, in some optional embodiments, the database unit 406 can process the relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system of simulating, extending and expanding human intelligence, perceiving the environment, acquiring knowledge and using knowledge to obtain the best results using digital computers or machines controlled by digital computers. The database unit 406 can learn based on a data set of human feature monitoring data from one or more users, and the machine learning algorithm can find patterns and relationships between several independent variables and interdependent variables that can be derived from the data. Continuous consideration of these variables or other learned variables that are continuously updated from the algorithm can allow the machine learning algorithm to probabilistically determine, for example, classify, diagnose and / or predict the patient's status. As an example, the machine learning algorithm can be configured to adopt any one or more of Bayesian, random forest, decision tree, linear regression, deep learning, neural network and / or dimensionality reduction technology.

[0049] The third aspect of the present disclosure is introduced below: a device for collecting heart sounds and electrocardiogram signals.

[0050] like Figure 5 As shown, this embodiment also provides a heart sound and ECG signal acquisition device 500, which is used to synchronously acquire human heart sound signals and ECG signals. The heart sound and ECG signal acquisition device 500 includes: electrodes 501, which are used to acquire ECG signals; sound sensors 502, which are used to synchronously acquire heart sound signals; and processing units 503, which are used to synchronously digitize heart sound signals and ECG signals. Among them, the electrodes 501 are used as an ECG acquisition unit, the sound sensors 502 are used as a heart sound acquisition unit, and the processing unit 503 is an integrated unit of an ECG processing unit and a heart sound processing unit.

[0051] In addition, in some optional embodiments, a circuit module is provided in the processing unit 503. The sound sensor 502 is integrated with the electrode 501 and connected to the circuit module to transmit the collected heart sound signal and electrocardiogram signal to the circuit module for processing to obtain stable heart sound signal and electrocardiogram signal.

[0052] In addition, in some optional embodiments, the heart sound and electrocardiogram signal acquisition device 500 also includes an adhesive patch. The adhesive patch is made of medical grade silicone material and is used to fix the heart sound and electrocardiogram signal acquisition device 500 to human skin. The setting of the adhesive patch can ensure the normal use of the heart sound and electrocardiogram signal acquisition device 500 and minimize the impact on the user's daily life and work, which is convenient for users to wear and test for a long time. In the prior art, the detection of subclinical leaflet thrombosis mainly adopts multi-dimensional computed tomography, but its applicability is subject to many restrictions. For example, it has high requirements for specialized hospital facilities, and it is not suitable for elderly patients or patients with renal insufficiency. The above-mentioned wearable heart sound and electrocardiogram signal acquisition device 500 has become an effective solution. The device breaks through the above-mentioned limitations by adopting remote non-invasive detection. The device enables the patient himself to continue to use it outside the hospital environment. On the other hand, the wearable heart sound and electrocardiogram signal acquisition device 500 can promote remote medical guidance and comprehensive management of the entire monitoring process. This feature is particularly beneficial for the elderly and rural patients because it allows continuous and easy-to-use monitoring outside the clinical environment. In addition, the device can be integrated with mobile phone applications to further ensure that patients can manage their own health independently while maintaining close communication with medical institutions.

[0053] Below, the features of the above-mentioned embodiments according to the present disclosure are briefly summarized and listed.

[0054] According to one or more embodiments of the present disclosure, a method for assisting in identifying subclinical leaflet thrombosis is provided, which is used to assist in diagnosing subclinical leaflet thrombosis after transcatheter aortic valve replacement, comprising: Collecting heart sound signals, and processing the heart sound signals to obtain preset parameters of the heart sound signals, wherein the preset parameters at least include time, frequency and energy; determining a systolic period according to the heart sound signal; identifying the highest energy point within the characteristic interval of the contraction period; The characteristic frequency corresponding to the highest energy point is obtained, and it is determined whether the characteristic frequency is greater than a threshold frequency. If so, the heart sound signal is marked as an abnormal heart sound signal caused by subclinical leaflet thrombosis; if not, the heart sound signal is marked as a normal heart sound signal.

[0055] According to one or more embodiments of the present disclosure, a method for assisting in identifying subclinical leaflet thrombus is provided, wherein determining the systolic period according to the heart sound signal comprises: Collecting an electrocardiogram signal synchronized with the heart sound signal; determining a first heart sound and a second heart sound of the heart sound signal according to the electrocardiogram signal; The systolic period is determined based on the first heart sound and the second heart sound.

[0056] According to one or more embodiments of the present disclosure, a method for assisting in identifying subclinical leaflet thrombus is provided, wherein determining a first heart sound and a second heart sound of the heart sound signal according to the electrocardiogram signal comprises: Displaying the electrocardiogram signal and the heart sound signal using the same time axis; Identifying an R peak in the electrocardiogram signal; The first heart sound and the second heart sound are identified based on the R peak.

[0057] According to one or more embodiments of the present disclosure, a method for auxiliary identification of subclinical leaflet thrombosis is provided, wherein the contraction period is the period from the opening of the aortic valve to the closing of the aortic valve, and the characteristic interval is the period from the beginning of the contraction period to the midline of the contraction period.

[0058] According to one or more embodiments of the present disclosure, a method for assisting in identifying subclinical leaflet thrombosis is provided, wherein the threshold frequency is at least 20 Hz.

[0059] According to one or more embodiments of the present disclosure, a method for assisting in identifying subclinical leaflet thrombosis is provided, and the method for assisting in identifying subclinical leaflet thrombosis further includes: Establish a user database model, and perform machine learning and comparative analysis on user data to warn users who may have abnormal heart sound signals caused by subclinical leaflet thrombosis; The user data includes at least: the heart sound signal, the electrocardiogram signal and the recognition result.

[0060] According to one or more embodiments of the present disclosure, a subclinical leaflet thrombosis auxiliary identification system is provided for assisting the diagnosis of subclinical leaflet thrombosis after transcatheter aortic valve replacement. The subclinical leaflet thrombosis auxiliary identification system is used to implement the above-mentioned subclinical leaflet thrombosis auxiliary identification method. The subclinical leaflet thrombosis auxiliary identification system includes: A heart sound collection unit, used for collecting heart sound signals; A heart sound processing unit, used to process the collected heart sound signal to obtain preset parameters of the heart sound signal, wherein the preset parameters at least include time, frequency and energy; A processor unit is used to determine the contraction period according to the heart sound signal, identify the highest energy point in the characteristic interval of the contraction period, obtain the characteristic frequency corresponding to the highest energy point, and judge whether the characteristic frequency is greater than a threshold frequency. If so, output the recognition result that the heart sound signal is an abnormal heart sound signal caused by subclinical leaflet thrombosis; if not, output the recognition result that the heart sound signal is a normal heart sound signal.

[0061] According to one or more embodiments of the present disclosure, a subclinical leaflet thrombosis auxiliary identification system is provided, and the subclinical leaflet thrombosis auxiliary identification system further includes: An ECG acquisition unit, configured to synchronously acquire an ECG signal when the heart sound acquisition unit acquires the heart sound signal; An ECG processing unit, used for processing the collected ECG signal; The processor unit is capable of determining a first heart sound and a second heart sound of the heart sound signal according to the electrocardiogram signal, and determining the systolic period according to the first heart sound and the second heart sound.

[0062] According to one or more embodiments of the present disclosure, a subclinical leaflet thrombosis auxiliary identification system is provided, and the subclinical leaflet thrombosis auxiliary identification system further includes: A database unit, used to establish a user database model, and perform machine learning and comparative analysis on user data, and to warn users who may have abnormal heart sound signals caused by subclinical leaflet thrombosis; The user data includes at least: the heart sound signal, the electrocardiogram signal and the recognition result.

[0063] According to one or more embodiments of the present disclosure, a heart sound and electrocardiogram signal acquisition device is provided, which is used to synchronously acquire a human heart sound signal and an electrocardiogram signal. The heart sound and electrocardiogram signal acquisition device includes: Electrodes, used for collecting the electrocardiogram signal; A sound sensor, used for synchronously collecting the heart sound signal; A processing unit is used to synchronously digitize the heart sound signal and the electrocardiogram signal.

[0064] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0065] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0066] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A method for assisting identification of subclinical leaflet thrombosis, characterized in that: Used to assist in the diagnosis of subclinical leaflet thrombosis after transcatheter aortic valve replacement, including: Collecting heart sound signals, and processing the heart sound signals to obtain preset parameters of the heart sound signals, wherein the preset parameters at least include time, frequency and energy; determining a systolic period according to the heart sound signal; identifying the highest energy point within the characteristic interval of the contraction period; The characteristic frequency corresponding to the highest energy point is obtained, and it is determined whether the characteristic frequency is greater than a threshold frequency. If so, the heart sound signal is marked as an abnormal heart sound signal caused by subclinical leaflet thrombosis; if not, the heart sound signal is marked as a normal heart sound signal.

2. The method according to claim 1, characterized in that: Determining the systolic period according to the heart sound signal comprises: Collecting an electrocardiogram signal synchronized with the heart sound signal; determining a first heart sound and a second heart sound of the heart sound signal according to the electrocardiogram signal; The systolic period is determined based on the first heart sound and the second heart sound.

3. The method according to claim 2, characterized in that The step of determining the first heart sound and the second heart sound of the heart sound signal according to the electrocardiogram signal comprises: Displaying the electrocardiogram signal and the heart sound signal using the same time axis; Identifying an R peak in the electrocardiogram signal; The first heart sound and the second heart sound are identified based on the R peak.

4. The method according to claim 1, characterized in that The systolic period is the period from the opening of the aortic valve to the closing of the aortic valve, and the characteristic interval is the period from the beginning of the systolic period to the midline of the systolic period.

5. The method according to claim 1, characterized in that: The threshold frequency is at least 20 Hz.

6. The method according to claim 2, characterized in that The subclinical leaflet thrombosis auxiliary identification method further comprises: Establish a user database model, and perform machine learning and comparative analysis on user data to warn users who may have abnormal heart sound signals caused by subclinical leaflet thrombosis; The user data includes at least: the heart sound signal, the electrocardiogram signal and the recognition result.

7. A subclinical leaflet thrombosis auxiliary identification system, characterized in that: Used to assist in the diagnosis of subclinical leaflet thrombosis after transcatheter aortic valve replacement, the subclinical leaflet thrombosis auxiliary identification system is used to implement the method according to any one of claims 1 to 6, and the subclinical leaflet thrombosis auxiliary identification system comprises: A heart sound collection unit, used for collecting heart sound signals; A heart sound processing unit, used to process the collected heart sound signal to obtain preset parameters of the heart sound signal, wherein the preset parameters at least include time, frequency and energy; A processor unit is used to determine the contraction period according to the heart sound signal, identify the highest energy point in the characteristic interval of the contraction period, obtain the characteristic frequency corresponding to the highest energy point, and judge whether the characteristic frequency is greater than a threshold frequency. If so, output the recognition result that the heart sound signal is an abnormal heart sound signal caused by subclinical leaflet thrombosis; if not, output the recognition result that the heart sound signal is a normal heart sound signal.

8. The system according to claim 7, characterized in that The subclinical leaflet thrombosis auxiliary identification system also includes: An ECG acquisition unit, configured to synchronously acquire an ECG signal when the heart sound acquisition unit acquires the heart sound signal; An ECG processing unit, used for processing the collected ECG signal; The processor unit is capable of determining a first heart sound and a second heart sound of the heart sound signal according to the electrocardiogram signal, and determining the systolic period according to the first heart sound and the second heart sound.

9. The system according to claim 8, characterized in that The subclinical leaflet thrombosis auxiliary identification system also includes: A database unit, used to establish a user database model, and perform machine learning and comparative analysis on user data, so as to warn users who may have abnormal heart sound signals caused by subclinical leaflet thrombosis; The user data includes at least: the heart sound signal, the electrocardiogram signal and the recognition result.

10. A heart sound and electrocardiogram signal acquisition device, used to implement the step of synchronously acquiring human heart sound signals and electrocardiogram signals in any one of claims 2, 3 and 6, the heart sound and electrocardiogram signal acquisition device comprising: Electrodes, used for collecting the electrocardiogram signal; A sound sensor, used for synchronously collecting the heart sound signal; A processing unit is used to synchronously digitize the heart sound signal and the electrocardiogram signal.

Images