Method and device for determining type of exudate amount of wound surface, and monitoring device and system

Abstract

The invention provides a wound exudate amount type determination method. The method comprises the following steps: acquiring wound humidity data at a plurality of moments; performing curve fitting on the wound surface humidity data based on a first-order system model, and determining a system gain and a time constant of the first-order system model; based on the system gain and the time constant, a corresponding wound surface seepage amount type is determined through a pre-established dichotomy model, and the dichotomy model is established based on pre-provided wound case data. In addition, the invention further relates to a wound surface seepage amount type determining device applying the wound surface seepage amount type determining method, and further relates to a wound surface humidity monitoring device and a wound surface humidity monitoring system comprising the wound surface seepage amount type determining device.

Description

Technical Field

[0001] The present application belongs to the field of signal processing technology, and in particular relates to a method for determining the type of wound exudate and a device for determining the type of wound exudate using the method, and also relates to a wound moisture monitoring device including the wound exudate type determination device, and a wound moisture monitoring system including the wound moisture monitoring device. Background Art

[0002] Maintaining appropriate wound moisture is crucial for promoting wound healing during wound care. Studies have shown that dry scabs formed during wound healing in a dry environment hinder epithelialization, whereas wounds healing in a moist environment regenerate epidermally much faster than those healing in a dry environment. Maintaining a moist wound surface and a relatively low oxygen environment prevents tissue dehydration and cell death, accelerates angiogenesis, promotes the breakdown of necrotic tissue and fibrin, and enhances the interaction of growth factors with target cells. The use of moisturizing dressings has been shown to provide an optimal environment for accelerating wound healing and promoting tissue growth. Therefore, appropriate dressing selection and replacement significantly accelerate wound healing. However, existing methods for selecting and replacing moisturizing dressings are costly and time-consuming. Consequently, in clinical practice, healthcare professionals typically rely on direct observation of the dressing and wound surface appearance, relying on experience to determine dressing selection, dressing replacement timing, and the wound's healing state. This not only increases the burden of repetitive, low-skilled work for healthcare professionals but also increases the potential risks of exposing the patient's wound surface.

[0003] Therefore, it is desirable to provide a method for determining the type of wound exudate, which can accurately determine the type of wound exudate in a non-invasive manner, thereby reducing the workload of medical staff and eliminating the risk of wound exposure in patients. Summary of the Invention

[0004] This section introduces the concepts of the present application in a simplified form, which are further reflected in the detailed description below. This section is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

[0005] According to the first aspect of the present disclosure, a method for determining the type of wound exudate is provided, which includes: obtaining wound moisture data at multiple moments; performing curve fitting on the wound moisture data based on a first-order system model to determine the system gain and time constant of the first-order system model; based on the system gain and the time constant, using a pre-established binary classification model to determine the corresponding wound exudate type, wherein the binary classification model is established based on pre-provided wound case data.

[0006] According to some exemplary embodiments, acquiring wound surface moisture data at multiple moments includes: acquiring the wound surface moisture data from a moisture sensor in a dressing arranged in the wound surface area of ​​the wound.

[0007] According to some exemplary embodiments, the curve fitting of the wound surface moisture data based on the first-order system model to determine the system gain and time constant of the first-order system model includes: based on the first-order system model, using a nonlinear least squares method to curve fit the wound surface moisture data to determine the system gain and time constant of the first-order system model.

[0008] According to some exemplary embodiments, the pre-established binary classification model includes: a classification hyperplane determined using a support vector machine algorithm in a feature plane constituted by system gain and time constant of a first-order system model corresponding to a pre-provided wound case.

[0009] According to a second aspect of the present disclosure, a device for determining the type of wound exudate is provided, comprising: a wound moisture data acquisition module, a system parameter determination module, and a wound exudate type determination module. The wound moisture data acquisition module is configured to acquire wound moisture data at multiple moments. The system parameter determination module is configured to perform curve fitting on the wound moisture data based on a first-order system model to determine the system gain and time constant of the first-order system model. The wound exudate type determination module is configured to determine the corresponding wound exudate type based on the system gain and the time constant using a pre-established binary classification model, wherein the binary classification model is established based on pre-provided wound case data.

[0010] According to some exemplary embodiments, the wound surface moisture data acquisition module is further configured to: acquire the wound surface moisture data from a moisture sensor arranged in a dressing in the wound surface area of ​​the wound.

[0011] According to some exemplary embodiments, the system parameter determination module is further configured to: perform curve fitting on the wound surface moisture data using a nonlinear least squares method based on the first-order system model to determine the system gain and time constant of the first-order system model.

[0012] According to some exemplary embodiments, the pre-established binary classification model includes: a classification hyperplane determined using a support vector machine algorithm in a feature plane constituted by system gain and time constant of a first-order system model corresponding to a pre-provided wound case.

[0013] According to the third aspect of the present disclosure, a wound surface humidity monitoring device is provided, comprising: a humidity sensor, a wound surface exudate type determination device according to the second aspect of the present disclosure and its exemplary embodiments, a single-chip microcomputer, and a power management device. The humidity sensor is configured to measure the humidity at the wound surface and generate wound surface humidity data at multiple moments. The single-chip microcomputer is configured to: obtain the wound surface humidity data from the humidity sensor, transmit the wound surface humidity data to the wound surface exudate type determination device, and receive the determination result output from the wound surface exudate type determination device. The power management device is configured to power the humidity sensor, the wound surface exudate type determination device, and the MCU.

[0014] According to a fourth aspect of the present disclosure, a wound moisture monitoring system is provided, comprising: at least one wound moisture monitoring device according to the third aspect of the present disclosure, a host computer management system, and a cloud server. The host computer management system is configured to receive data from the at least one wound moisture monitoring device and control the at least one wound moisture monitoring device. The cloud server is configured to receive data to be stored from the host computer management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Other or additional features, advantages and details are presented by way of example only in the following detailed description of the embodiments. In the drawings:

[0016] Figure 1 A method for determining the type of wound exudate according to an exemplary embodiment of the present disclosure is schematically illustrated in the form of a flow chart;

[0017] Figure 2A and Figure 2B The effect of different system gains and time constants on the step response of the first-order system model is schematically shown;

[0018] Figure 3 The relationship between different types of wound exudate and the system parameters of the first-order system model is schematically shown;

[0019] Figure 4 The characteristic plane diagram including the high-permeability type and the low-permeability type is schematically shown;

[0020] Figure 5 Schematic diagram based on Figure 4 The classification hyperplane determined by the feature plane graph shown;

[0021] Figure 6 A device for determining the type of wound exudate according to an exemplary embodiment of the present disclosure is schematically shown in the form of a block diagram;

[0022] Figure 7A wound surface moisture monitoring device according to an exemplary embodiment of the present disclosure is schematically shown in the form of a block diagram;

[0023] Figure 8 A wound moisture monitoring system according to an exemplary embodiment of the present disclosure is schematically illustrated in the form of a block diagram.

[0024] It should be understood that throughout the drawings, corresponding reference numerals identify similar or corresponding components or features. It should also be understood that the drawings are not necessarily drawn to scale and are merely schematic illustrations of exemplary embodiments of the present application and are not intended to limit the present application. DETAILED DESCRIPTION

[0025] The following describes exemplary embodiments of the present application in conjunction with the accompanying drawings. It should be understood that the following description is merely exemplary in nature and is not intended to limit the present application, its application, or uses.

[0026] See also Figure 1 , which schematically illustrates a method for determining the type of wound exudate according to an exemplary embodiment of the present disclosure in the form of a flow chart. Figure 1 As shown, the wound exudate type determination method 100 may include steps 110 , 120 and 130 .

[0027] In step 110, wound moisture data at multiple moments is obtained;

[0028] In some embodiments, the step of obtaining wound surface humidity data at multiple times in step 110 can be accomplished by obtaining wound surface humidity data at multiple times from a humidity sensor placed in a dressing in the wound surface area of ​​the wound. A humidity sensor is a sensor device that converts changes in humidity into changes in the properties of its own humidity-sensitive element, thereby measuring ambient humidity. Depending on the type of humidity-sensitive element, humidity sensors can be categorized as resistive or capacitive. Capacitive humidity sensors are widely used due to their high sensitivity, fast response speed, ease of manufacture, and ease of miniaturization and integration. Capacitive humidity sensors are generally made using polymer thin film capacitors. When ambient humidity changes, the dielectric constant of the humidity-sensitive capacitor changes accordingly, causing its capacitance to also change. The change in capacitance is generally proportional to the relative humidity, enabling capacitive humidity sensors to measure humidity. The humidity sensor can be mounted on a flexible printed circuit board to accommodate wound surface areas of varying shapes on the human body. In the technical solutions taught by the present disclosure, the humidity sensor can be placed in the dressing in the wound surface area of ​​the wound. In this way, wound surface humidity data can be obtained without exposing the wound. In other embodiments, step 110 may also obtain wound moisture data from a database or a network connection. The present disclosure does not impose any limitation on the specific method of obtaining wound moisture data.

[0029] Continue to see Figure 1 In step 120, curve fitting is performed on the wound surface moisture data based on the first-order system model to determine the system gain and time constant of the first-order system model.

[0030] In step 120, a first-order system model can be used to fit the humidity data changes corresponding to different wound exudate types. Based on the system parameters of the first-order system model (e.g., system gain and time constant), the wound exudate type can be quantitatively identified, and the wound exudate type of the wound can be determined. A first-order system model is a system model that can be described by a first-order differential equation, such as a first-order differential equation that satisfies the following equation 1:

[0031] τy′(t)+y(t)=kx(t) Equation 1

[0032] Where x(t) is the input, y(t) is the output, k is the system gain, and τ is the time constant.

[0033] Applying Laplace transform to the first-order system, we can obtain the transfer function G(s) of the system model, which is shown in the following equation 2:

[0034]

[0035] The step response of the first-order system model can be used to fit the time-varying humidity data corresponding to different wound exudate types. Specifically, let the input x(t) be the step function u(t), and the transfer function G(s) can be used to solve it to obtain the step response of the output y(t). Then, a Laplace transform can be applied to the step function u(t), resulting in the following result as shown in Equation 3:

[0036]

[0037] Based on Equations 2 and 3 and using the Laplace transform property, we can obtain the step response Y(s) of the first-order system model, as shown in Equation 4 below:

[0038]

[0039] Applying the inverse Laplace transform to the step response Y(s) shown in Equation 4 yields the time-domain expression for the output y(t) when the input x(t) is a step function u(t), as shown in Equation 5:

[0040]

[0041] In the expression of the step response of a first-order system model, the system gain k and the time constant τ jointly determine the shape of the output. The system gain k determines the size of the final convergence value of the step response of the first-order system model, while the time constant τ determines the length of the convergence time of the step response of the first-order system model.

[0042] See also Figure 2A and Figure 2B , which schematically shows the effect of different system gains and time constants on the step response of the first-order system model. Figure 2A As shown, the step responses of the first-order system model corresponding to the three curves have the same time constant τ, but different system gains k, where the values ​​of the system gain k are 1, 2, and 3, respectively. Therefore, the three curves have the same convergence time, but different final convergence values, where the larger the value of the system gain, the larger the final convergence value. Figure 2B As shown, the step responses of the first-order system model corresponding to the three curves shown have the same system gain k, but different time constants τ, where the values ​​of the time constant τ are 1, 2, and 3, respectively. Therefore, the three curves have the same final convergence value but different convergence times, where the larger the value of the time constant, the longer the convergence time.

[0043] Using the time-domain expression of the step response of the first-order system model, a curve fit can be performed based on the wound surface moisture data obtained at multiple moments to obtain the corresponding model parameters based on the fitting results. For example, a nonlinear least squares fitting algorithm can be used to minimize the objective function to obtain the parameter vector (k, τ) of the system gain k and time constant τ. The objective function can be shown as follows in Equation 6:

[0044]

[0045] Among them, y i is the humidity value of the i-th data, t i is the time point of the i-th data sampling.

[0046] As a non-limiting example, a system parameter identification method based on the Levenberg-Marquardt nonlinear least squares fitting algorithm can be used to obtain the parameter vector (k, τ) by minimizing the above objective function. The core of the Levenberg-Marquardt nonlinear least squares fitting algorithm is to introduce a damping factor λ. By combining the Gauss-Newton method and the gradient descent method, and dynamically adjusting λ, a more appropriate optimization strategy can be selected at different stages of the optimization process to obtain the parameter vector (k, τ).

[0047] Clinically collected wound surface humidity data demonstrates that both the system gain k and the time constant τ are related to the amount of exudate present in the wound surface. If the humidity gradient between a highly exudative wound surface and a moisturizing dressing is large, the moisturizing dressing absorbs the exudate quickly, ultimately converging to a higher humidity value. This is reflected in the step response of the aforementioned first-order system model as a rapid convergence rate and a large convergence value. This is reflected in the model parameters as a small time constant τ and a large system gain k. If the gradient between a hypoexudative wound surface and the moisturizing dressing is moderately small, the opposite of the above results will occur. Furthermore, excessively dry wounds can cause the system gain k to become negative, indicating a decreasing humidity trend. Therefore, the system gain k and the time constant τ can be used to describe the type of wound exudate.

[0048] It should be understood that, in the present disclosure, the types of wound exudate include high exudate and low exudate. High exudate refers to a wound exudate situation in which the amount of exudate can make the dressing covering the wound surface change from a dry state to a saturated state after a dressing change interval, while low exudate refers to a wound exudate situation in which the amount of exudate cannot make the dressing covering the wound surface change from a dry state to a saturated state after a dressing change interval. The length of the dressing change interval depends on the specific type of disease. For example, for ulcerative wounds caused by diabetes, the dressing change interval can generally be 72 hours.

[0049] See also Figure 3 , which schematically shows the relationship between the types of wound exudate and the system parameters of the first-order system model. The selected cases are all ulcerative wounds caused by diabetes. Figure 3 As shown in the various views, fitting the raw data using the first-order system model yields relatively good results in various scenarios, with the curves of the fitted and raw data generally consistent. Furthermore, the wound exudate type of different wounds can be quantitatively identified using appropriate system parameters (e.g., system gain k and time constant τ). Thus, the wound exudate type can be determined based on the system gain k and time constant τ.

[0050] Continue to see Figure 1 In step 130, based on the system gain and the time constant, a pre-established binary classification model is used to determine the corresponding wound exudate type, wherein the binary classification model is established based on pre-provided wound case data.

[0051] Research has shown that differences in wound exudate levels are common across different wound cases, based on the parameter vector (k, τ) of the system gain k and the time constant τ. Therefore, a two-dimensional feature vector can be constructed based on the system gain k and the time constant τ. A feature plane can then be created, and the collected wound cases can be presented on the feature plane. This allows for visualization of inter-class differences between high-exudate and low-exudate types.

[0052] See also Figure 4 , which schematically shows a characteristic plane diagram including a high exudate type and a low exudate type, wherein the selected cases are all ulcerative wounds caused by diabetes, and the characteristic plane diagram shows the inter-class difference between the two. Figure 4 As shown in the figure, the characteristic plane plot uses the time constant τ as the horizontal coordinate and the system gain k as the vertical coordinate, presenting the wound exudate types of multiple collected cases on the plane. Among them, the blue squares represent cases with low exudate type, and the orange squares represent cases with high exudate type. As can be seen from the figure, there is a clear difference between the high exudate type and the low exudate type. Therefore, the wound exudate type can be classified by using a pre-established appropriate binary classification model based on the parameter vector (k, τ) of the first-order system model corresponding to the wound case, so as to identify the wound exudate type.

[0053] As a non-limiting example, a binary classification model can be pre-established using a support vector machine (SVM) approach. SVM is a machine learning method widely used in classification tasks that effectively segments data points by finding an optimal hyperplane. The SVM method has good generalization capabilities and the ability to adapt to high-dimensional spaces.

[0054] The SVM method in classification tasks aims to determine a hyperplane that maximizes the distance between two types of data points. For linearly separable binary classification tasks, the goal of the SVM method is to find the optimal hyperplane that satisfies the conditions described in the following equation 7:

[0055] w·x+b=0 Formula 7 Among them, w is the normal vector of the hyperplane, which determines the direction of the hyperplane; b is the offset, which determines the intercept of the hyperplane; x is the input data point, for Figure 4 The example shown is the parameter vector (k,τ).

[0056] The distance from a data point to the hyperplane is determined by the following formula 8:

[0057]

[0058] The goal of the SVM method is to maximize the classification margin At the same time, ensure that the data points are correctly classified, that is, satisfy the constraints described in the following formula 9:

[0059]

[0060] where y i ∈{-1,1} indicates the category to which the data point belongs.

[0061] Therefore, SVM can be described as the optimization problem described in the following equation 10:

[0062]

[0063] By introducing the Lagrange multiplier method, the above problem can be transformed into a dual problem and solved efficiently. Therefore, using the SVM method, a classification hyperplane can be determined within the characteristic plane composed of the system gain and time constant of the first-order system model corresponding to the pre-provided wound case. Subsequently, a binary classification model including this classification hyperplane can be used to classify the parameter vector (k, τ) determined based on the acquired wound moisture data, thereby determining the wound exudate type.

[0064] See also Figure 5 , which schematically shows the use of SVM method based on Figure 4 The classification hyperplane is established based on the wound case data shown in Figure 2. Figure 5 As shown in the figure, the established classification hyperplane can maximize the interval between the two types of data points, thereby achieving reliable binary classification of the data points. When the classification hyperplane has been determined using the SVM method, when multiple wound moisture data are subsequently obtained, the classification hyperplane can be used to determine the current wound exudate type.

[0065] For binary classification models, commonly used performance evaluation indicators include accuracy, precision, recall, false alarm rate, and missed alarm rate. Their calculation formulas are shown in Table 1 below.

[0066] Table 1 Common performance evaluation indicators of binary classification models

[0067]

[0068] Assuming that the classification categories include category 0 and category 1, then: TP is the number of category 0 predicted as category 0, TN is the number of category 1 predicted as category 1, FP is the number of category 1 predicted as category 0, and FN is the number of category 0 predicted as category 1.

[0069] Taking the wound exudate type to be determined in the present disclosure as an example, the low exudate type can be classified as category 0, and the high exudate type can be classified as category 1. Based on the collected data, the binary classification model established using the SVM method in the present disclosure has an accuracy rate of 93.33%, a precision rate of 100%, a recall rate of 85.71%, a false alarm rate of 0%, and a missed alarm rate of 14.29%.

[0070] It should be understood that the technical solution of using the SVM method to establish a binary classification model taught in this disclosure is merely exemplary and not restrictive. Depending on actual needs, a K-nearest neighbor algorithm, a decision tree algorithm, a multilayer perceptron, or any other suitable method may be used to establish the desired binary classification model based on pre-provided wound case data.

[0071] Therefore, according to the method for determining the type of wound exudate disclosed in the present invention, it is possible to use signal processing and system identification methods to establish a wound moisture change curve model, extract model characteristic parameters to describe the dynamic change process of wound moisture over time, grasp the correlation between wound characteristics and moisture curve response, and achieve accurate identification of wound exudate type. Therefore, the wound exudate type can be determined based on the acquired wound moisture data, thereby eliminating the risk of patient wound exposure, reducing the workload of medical staff, and helping to achieve non-invasive continuous monitoring of wound moisture, thereby prompting medical staff to change the time node for dressing, reflecting the recovery stage of the wound, and providing personalized care for patients.

[0072] See also Figure 6 , which adaptively illustrates a device for determining the type of wound exudate according to an exemplary embodiment of the present disclosure in the form of a block diagram. Figure 6 As shown, the wound exudate type determination device 200 may include a wound moisture data acquisition module 210, a system parameter determination module 220, and a wound exudate type determination module 230. The wound moisture data acquisition module 210 may be configured to acquire wound moisture data at multiple moments. The system parameter determination module 220 may be configured to perform curve fitting on the wound moisture data using a first-order system model to determine the system gain and time constant of the first-order system model. The wound exudate type determination module 230 may be configured to determine the corresponding wound exudate type based on the system gain and the time constant using a pre-established binary classification model, wherein the binary classification model is established based on pre-provided wound case data.

[0073] In some embodiments, the wound surface moisture data acquisition module 210 can also be configured to acquire the wound surface moisture data from a moisture sensor in a dressing disposed in the wound area of ​​the wound. In other embodiments, the wound surface moisture data acquisition module 210 can also be configured to acquire wound surface moisture data at multiple times from a remote database via a network. In some embodiments, the system parameter determination module 220 can also be configured to perform curve fitting on the wound moisture data using a nonlinear least squares method to determine the system gain and time constant of the first-order system model. As an example, the nonlinear least squares method used can be a Levenberg-Marquardt nonlinear least squares fitting algorithm. In some embodiments, the pre-established binary classification model in the wound surface exudate type determination module 230 can include a classification hyperplane determined using a support vector machine algorithm within a feature plane formed by the system gain and time constant of the first-order system model corresponding to a pre-provided wound case. In other embodiments, the pre-established binary classification model in the wound surface exudate type determination module 230 can also include a binary classification model established using a K-nearest neighbor algorithm, a decision tree algorithm, or a multi-layer perceptron based on pre-provided wound case data.

[0074] It should be understood that the wound exudate type determination device and the modules included therein taught in the various embodiments of the present disclosure can be implemented in hardware, software, firmware or any combination thereof, thereby achieving the fundamental disclosure. Figures 1 to 5 The content shown in the figure teaches the various steps of the method for determining the type of wound exudate. It should also be understood that if implemented in software, the steps of the method for determining the type of wound exudate can be stored as one or more instructions or codes on or transmitted via a computer-readable medium and executed by a hardware-based processor.

[0075] From the above analysis, it can be seen that the wound exudate type determination device disclosed in the present invention can determine the wound exudate type based on the acquired wound moisture data, eliminating the risk of patient wound exposure, reducing the workload of medical staff, and helping to achieve non-invasive continuous monitoring of wound moisture, thereby prompting medical staff to change the dressing time, reflecting the recovery stage of the wound, and providing personalized care for patients.

[0076] See also Figure 7 , which adaptively illustrates a wound surface moisture monitoring device according to an exemplary embodiment of the present disclosure in the form of a block diagram. Figure 7As shown, the wound surface humidity monitoring device 300 may include a humidity sensor 310, a single-chip microcomputer (MCU) 320, a wound surface exudate type determination device 330 and a power management device 340. The humidity sensor 310 can be configured to measure the humidity at the wound surface and generate wound surface humidity data at multiple moments. It may include a resistive humidity sensor or a capacitive humidity sensor. Among them, the capacitive humidity sensor has the characteristics of high sensitivity, fast response speed, easy manufacturing, easy miniaturization and integration, and is therefore increasingly widely used. In some embodiments, the humidity sensor 310 may be a high-precision capacitive humidity sensor mounted on a flexible circuit board (FPC), thereby adapting to different shapes of wound surface areas on the human body, significantly improving the adaptability of the device and the comfort of the patient during wearing. As an example, a humidity sensor model SHT35-DIS can be selected. The wound surface exudate type determination device 330 can be implemented as the wound surface exudate type determination device 200 described in detail above, thereby, it can be used to implement the above-mentioned method based on Figures 1 to 5 The steps of the wound exudate type determination method described in the embodiment shown in FIG. The MCU 320 can be configured to: obtain the wound moisture data from the moisture sensor 310, transmit the wound moisture data to the wound exudate type determination device 330, and receive the determination result output by the wound exudate type determination device 330. In some embodiments, the MCU 320 can use a low-power single-chip microcontroller chip to reduce power consumption and increase battery life. In some embodiments, the calculation task of fitting the wound moisture data in the wound exudate type determination device 330 can be performed by the MCU 320 to fully utilize the computing power of the MCU 320. In addition, in some embodiments, the MCU 320 can also include support for Bluetooth Low Energy (BLE), an integrated high-efficiency power management unit (PMU), and an on-chip security module to facilitate the lightweighting of the wound moisture monitoring device. For example, a single-chip microcontroller model EFR32BG22C112F352GM32 can be used. The power management device 340 can be configured to provide power to the moisture sensor 310, the wound exudate type determination device 330, and the MCU 320. Specifically, the power management device 340 can include a protection circuit 341 and a power management module 342. The protection circuit 341 can be used to implement short-circuit protection for the wound moisture monitoring device, for example. The power management module 342 can be used to supply power to each component according to its status.

[0077] Therefore, the wound moisture monitoring device 300 is a lightweight, low-power, long-lasting wound moisture monitoring device, which can overcome the problems existing in the existing technology, such as large equipment size, low deployment adaptability, short battery life, and difficulty in meeting clinical continuous monitoring needs, thereby greatly improving the adaptability and deployment flexibility of the wound moisture monitoring device in the actual clinical environment.

[0078] See also Figure 8 , which adaptively illustrates a wound moisture monitoring system according to an exemplary embodiment of the present disclosure in the form of a block diagram. Figure 8 As shown, the wound surface moisture monitoring system 400 includes Figure 7 The wound surface moisture monitoring device 300, the host computer management system 410 and the cloud server 420 shown are shown. In some embodiments, the wound surface moisture monitoring system 400 may include two or more wound surface moisture monitoring devices 300. The host computer management system 410 may be configured to receive data from at least one of the wound surface moisture monitoring devices and control at least one of the wound surface moisture monitoring devices. For example, the host computer management system 410 may be communicatively connected to the wound surface moisture monitoring device 300 via a suitable communication method (e.g., Bluetooth communication) so as to receive data and send control instructions. The cloud server 420 may include any suitable server capable of implementing cloud storage. In some embodiments, such a server can, through functions such as cluster applications, grid technology, and distributed storage file systems, bring together a large number of different types of storage devices in the network through application software or application interfaces to work together and provide data storage and business access functions to the outside world.

[0079] Therefore, the wound surface moisture monitoring system according to the present disclosure can conveniently acquire and manage data, which is helpful for nursing staff to grasp the changing status of the patient's wound surface at any time.

[0080] The terms used in this disclosure are only used to describe the embodiments in this disclosure and are not intended to limit this disclosure. As used in this disclosure, the singular forms "a", "an" and "the" are intended to also include the plural forms, unless the context clearly indicates otherwise. It will also be understood that the terms "include" and "comprise" when used in this disclosure refer to the presence of the features described, but do not exclude the presence of one or more other features or the addition of one or more other features. As used in this disclosure, the term "and / or" includes any and all combinations of one or more of the associated listed items. It will be understood that although the terms "first", "second", "third" etc. can be used to describe various features in this disclosure, these features should not be limited by these terms. These terms are only used to distinguish one feature from another.

[0081] Unless otherwise defined, all terms (including technical and scientific terms) used in this disclosure have the same meaning as commonly understood by those skilled in the art to which this disclosure belongs. It is also understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the relevant art and / or the context of this specification, and will not be interpreted in an idealized or overly formal sense unless explicitly defined in this disclosure.

[0082] In this disclosure, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories), or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0083] In the description of the present disclosure, the description of the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction and without violating technical principles, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, or may omit some technical features from the different embodiments or examples described in this specification, and the embodiments or examples obtained based on such combination, combination or omission are also considered to fall within the scope of the present disclosure.

[0084] The method described in the present disclosure includes one or more steps or actions. These method steps and / or actions do not have to be performed in the order described in the present disclosure, but can be performed in a different order. For example, these method steps and / or actions can be performed simultaneously or in the opposite order, as long as they do not conflict with the principles of the technical solutions described in the present disclosure. In addition, according to actual needs, the steps and / or actions in the method described in the present disclosure can be replaced with different steps and / or actions, or can also include additional steps and / or actions.

[0085] Although at least one exemplary embodiment has been described in the foregoing detailed description, it should be understood that there are a large number of variations. It should also be understood that the exemplary embodiment or multiple exemplary embodiments described herein are merely examples and are not intended to limit the scope, applicability, or configuration of the present application in any way. On the contrary, the foregoing detailed description will provide a convenient guide for those skilled in the art to implement one or more exemplary embodiments. It should be understood that various changes, modifications, or alterations may be made to the functions and arrangements of the elements without departing from the scope of the present application as set forth in the appended claims and their equivalents. The scope of protection of the present disclosure is limited only by the appended claims.

Claims

1. A method for determining the type of wound exudate, characterized in that: include: Obtain wound surface moisture data at multiple times; Performing curve fitting on the wound surface moisture data based on a first-order system model to determine a system gain and a time constant of the first-order system model; Based on the system gain and the time constant, a pre-established binary classification model is used to determine the corresponding wound exudate type, wherein the binary classification model is established based on pre-provided wound case data.

2. The wound exudate classification method according to claim 1, characterized in that: The acquiring of wound surface moisture data at multiple moments includes acquiring the wound surface moisture data from a moisture sensor in a dressing disposed in the wound surface area of ​​the wound.

3. The wound exudate classification method according to claim 1, characterized in that: Performing curve fitting on the wound surface moisture data based on the first-order system model to determine the system gain and time constant of the first-order system model includes: Based on the first-order system model, a nonlinear least squares method is used to perform curve fitting on the wound surface moisture data to determine the system gain and time constant of the first-order system model.

4. The wound exudate classification method according to claim 1, characterized in that: The pre-established two-classification model includes: a classification hyperplane determined by using a support vector machine algorithm in a feature plane composed of a system gain and a time constant of a first-order system model corresponding to a pre-provided wound case.

5. A device for determining the type of wound exudate, characterized in that: include: A wound surface moisture data acquisition module is configured to: acquire wound surface moisture data at multiple moments; a system parameter determination module, configured to: perform curve fitting on the wound surface moisture data based on a first-order system model to determine a system gain and a time constant of the first-order system model; The wound exudate type determination module is configured to: determine the corresponding wound exudate type based on the system gain and the time constant using a pre-established binary classification model, wherein the binary classification model is established based on pre-provided wound case data.

6. The device for determining the type of wound exudate according to claim 5, characterized in that: The wound surface moisture data acquisition module is further configured to: acquire the wound surface moisture data from a moisture sensor arranged in a dressing in the wound surface area of ​​the wound.

7. The device for determining the type of wound exudate according to claim 5, characterized in that: The system parameter determination module is further configured to: perform curve fitting on the wound surface moisture data using a nonlinear least squares method based on the first-order system model to determine the system gain and time constant of the first-order system model.

8. The device for determining the type of wound exudate according to claim 5, characterized in that: The binary classification model includes a classification hyperplane determined by using a support vector machine algorithm in a feature plane composed of a system gain and a time constant of a first-order system model corresponding to a pre-provided wound case.

9. A wound surface moisture monitoring device, characterized in that: include: A humidity sensor is configured to measure the humidity at the wound surface and generate wound surface humidity data at multiple moments; The device for determining the type of wound exudate according to any one of claims 5 to 8; a single-chip computer configured to: obtain the wound surface humidity data from the humidity sensor, transmit the wound surface humidity data to the wound surface exudate type determination device, and receive a determination result outputted from the wound surface exudate type determination device; A power management device is configured to supply power to the humidity sensor, the wound exudate type determination device, and the MCU.

10. A wound surface moisture monitoring system, characterized in that: include: At least one wound moisture monitoring device according to claim 9; A host computer management system is configured to: receive data from at least one of the wound surface moisture monitoring devices and control at least one of the wound surface moisture monitoring devices; The cloud server is configured to receive data that needs to be stored from the host computer management system.

Images