Home rehabilitation method and system for lymphedema patient

Abstract

The invention provides a home rehabilitation method and system for a lymphedema patient. The method comprises the steps of obtaining circumference data, volume data, skin images, daily activity ability data and living habit data of affected limbs of a target rehabilitation patient; abnormal features in the skin image are obtained, correlation analysis is carried out on the abnormal features, the circumference data and the volume data, and the lymphedema severity degree is evaluated; based on the time sequence, performing variation trend prediction analysis on the circumference data and the volume data to obtain a variation trend analysis result; dividing into different groups based on the activity ability data and the living habit data of different patients, matching the groups of target rehabilitation patients based on the activity ability data and the living habit data of the target rehabilitation patients, and analyzing results based on the group characteristics of the target rehabilitation patients, the lymphedema severity of the target rehabilitation patients and the change trend. According to the method, through comprehensive evaluation, accurate trend prediction and personalized rehabilitation scheme formulation, the rehabilitation effect of lymphedema is improved.

Description

Technical Field

[0001] The present application relates to the field of home health care technology, and specifically to a home rehabilitation method and system for patients with lymphedema. Background Art

[0002] At present, many lymphedema patients tend to adopt a standardized rehabilitation program when they are rehabilitated at home, which may not be completely suitable for every patient. Due to the condition of lymphedema and individual differences of patients, the rehabilitation needs of each patient are unique. However, the current home rehabilitation guidance often does not fully take these differences into account, resulting in a lack of targeted rehabilitation programs.

[0003] During home rehabilitation, the patient's physical condition and illness may change over time and with the progress of treatment. However, due to the lack of personalized advice and guidance, it is often difficult for patients to adjust their rehabilitation plans in real time according to their own conditions.

[0004] Due to the lack of personalized advice and guidance, patients may face more uncertainty during their home rehabilitation process. They may not know when to adjust their rehabilitation plan, how to adjust it, and what the effect of the adjustment will be. This uncertainty may increase patients' anxiety and stress and affect their recovery process.

[0005] In summary, the lack of personalized advice and guidance for patients with lymphedema during home rehabilitation is an urgent problem to be solved. This problem not only affects the rehabilitation effect of patients, but also increases their anxiety and stress. Therefore, we need to pay more attention to the home rehabilitation of patients with lymphedema and provide them with more personalized and targeted advice and guidance. Summary of the invention

[0006] In order to overcome the problem in the prior art that home rehabilitation guidance for patients with lymphedema often does not fully consider individual differences, resulting in a lack of pertinence in rehabilitation programs, the present application provides a home rehabilitation method and system for patients with lymphedema, which adopts the following technical solutions:

[0007] In a first aspect, the present application provides a home rehabilitation method for a patient with lymphedema, comprising:

[0008] Obtain the circumference data, volume data, skin images, daily activity ability data and living habit data of the affected limbs of the target rehabilitation patients;

[0009] Acquire abnormal features in the skin image, perform correlation analysis on the abnormal features, the circumference data and the volume data, and evaluate the severity of lymphedema;

[0010] Based on the time series, performing change trend prediction analysis on the circumference data and the volume data to obtain a change trend analysis result;

[0011] Based on the activity ability data and the living habit data of different patients, they are divided into different groups. Based on the activity ability data and the living habit data of the target rehabilitation patients, the target rehabilitation patients' groups are matched. Based on the group characteristics of the target rehabilitation patients, the severity of the target rehabilitation patients' lymphedema and the change trend analysis results, a personalized rehabilitation plan is formulated.

[0012] Furthermore, the obtaining of the circumference data of the affected limb of the target rehabilitation patient includes:

[0013] Obtain the circumference data of the affected limb of the target rehabilitation patient through a smart measuring tape or a wearable circumference measuring belt;

[0014] The volume of the affected limb of the target rehabilitation patient is measured by a three-dimensional imaging device using structured light or laser scanning. The target rehabilitation patient scans the three-dimensional imaging device around the affected limb. The three-dimensional imaging device emits light in a specific pattern and captures the reflected information to quickly construct a three-dimensional model of the limb and calculate the volume data of the affected limb.

[0015] Based on preset shooting conditions, obtain skin image information of the affected limb of the target rehabilitation patient;

[0016] Based on the smart motion tracker worn by the target rehabilitation patients, the daily activity data of the target rehabilitation patients are obtained;

[0017] Obtain the living habit data of target rehabilitation patients based on smart home devices or smart health monitoring devices.

[0018] Furthermore, the abnormal features in the skin image are obtained, and the abnormal features are correlated with the circumference data and the volume data for analysis to assess the severity of lymphedema, specifically as follows:

[0019] Inputting the skin image into the trained CNN model to obtain abnormal features of the skin image, wherein the abnormal features of the skin include redness, swelling, ulcer, fibrosis, etc.;

[0020] Obtaining statistical features of the circumference data and the volume data, wherein the statistical features are mean, standard deviation and maximum value;

[0021] Combining the abnormal features of the skin image with the statistical features to obtain a multi-dimensional feature vector;

[0022] The multidimensional feature vector was used as the independent variable and the severity of the consequences of lymphedema was used as the dependent variable to obtain the severity of lymphedema.

[0023] Furthermore, based on the time series, the change trend prediction analysis is performed on the circumference data and the volume data to obtain the change trend analysis result, which is specifically manifested as follows:

[0024] Acquire a historical circumference dataset and a volume dataset of the target rehabilitation patient, and sort the historical circumference dataset and the volume dataset based on a time series to form a time series dataset;

[0025] Perform a stationary test on the time series data set to determine the difference order d that makes the series stationary;

[0026] Calculate the autocorrelation function and partial autocorrelation function of the time series data set, and determine the parameter autoregressive term p and moving average term q;

[0027] An autoregressive moving average model is constructed based on the determined parameter difference order d, autoregressive term p and moving average term q;

[0028] Based on a preset time step and an autoregressive moving average model, predicted values ​​of a preset number of time points of the circumference data and the volume data are obtained, a prediction curve is drawn based on the predicted values, and the changing trend of lymphedema is judged based on the direction of the prediction curve; if the prediction curve shows an upward trend, it means that the lymphedema may be worsening; if the prediction curve decreases, it means that the lymphedema has improved; if the curve is relatively stable, it means that the lymphedema is in a stable state.

[0029] Furthermore, the activity data and the life habit data of different patients are divided into different groups, and the groups of target rehabilitation patients are matched based on the activity data and the life habit data of the target rehabilitation patients. Based on the group characteristics of the target rehabilitation patients, the severity of lymphedema of the target rehabilitation patients and the change trend analysis results, a personalized rehabilitation plan is formulated, which is specifically manifested as follows:

[0030] Integrate the activity data and lifestyle data of different patients into a unified data set;

[0031] Extract key features from the activity data and lifestyle data in the dataset; for activity data, extract the average number of steps per day, quantitative indicators of exercise intensity, and the diversity of exercise types; for lifestyle data, extract quantitative indicators of diet structure, comprehensive scores of sleep quality, classification indicators of work intensity, and other classification indicators;

[0032] Patients are divided into different groups based on key characteristics, each group represents a collection of patients with similar characteristics;

[0033] Acquire the activity ability and living habit data of the target rehabilitation patient, calculate the similarity measure between the activity ability and living habit data characteristics of the target rehabilitation patient and the characteristics of each divided group, and divide the target rehabilitation patient into the group with the highest similarity;

[0034] Based on the characteristics of the target rehabilitation patient group, a personalized rehabilitation plan that meets the characteristics of the target rehabilitation patient group is generated.

[0035] Furthermore, the patients are divided into different groups based on key features, each group representing a set of patients with similar features, including:

[0036] Randomly select K initial cluster centers (the value range of K starts from 2 and gradually increases), assign each data point to the group to which the nearest cluster center belongs, calculate the sum of squares of the distances from the data points to the cluster center in each group (called the sum of squared errors, SSE), and calculate the sum of SSEs for all groups. As the K value increases, the sum of SSEs will gradually decrease. When the K value increases to a certain extent, the reduction in SSE will become insignificant, and the K value at this time is a more appropriate number of clusters;

[0037] Randomly select k data points as initial cluster centers;

[0038] For each data point, calculate its Euclidean distance to each cluster center and assign the data point to the group with the closest cluster center;

[0039] Recalculate the average value of all data points in each group on each feature as the new cluster center;

[0040] Repeat the allocation of data points and updating of cluster centers until the cluster centers no longer change or the preset number of iterations is reached. At this time, each data point is assigned to the corresponding group, forming k different groups.

[0041] In a second aspect, the present application also provides a home rehabilitation system for patients with lymphedema, comprising:

[0042] A data acquisition module, used to obtain the circumference data, volume data, skin image, daily activity ability data and life habit data of the affected limb of the target rehabilitation patient;

[0043] a lymphedema severity assessment module, used to obtain abnormal features in the skin image, associate and analyze the abnormal features with the circumference data and the volume data, and assess the severity of lymphedema;

[0044] A change trend analysis module, used to perform change trend prediction analysis on the circumference data and the volume data based on a time series, and obtain a change trend analysis result;

[0045] The rehabilitation program generation module is used to divide different patients into different groups based on their activity ability data and the living habit data, match the target rehabilitation patient groups based on their activity ability data and the living habit data, and formulate personalized rehabilitation programs based on the group characteristics of the target rehabilitation patients, the severity of lymphedema of the target rehabilitation patients and the change trend analysis results.

[0046] In a third aspect, the present application provides an electronic device, including:

[0047] One or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, cause the device to perform the method as described in the first aspect.

[0048] In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes the method described in the first aspect.

[0049] In a fifth aspect, the present application provides a computer program, which, when executed by a computer, is used to execute the method described in the first aspect.

[0050] In one possible design, the program in the fifth aspect may be stored in whole or in part on a storage medium packaged together with the processor, or may be stored in whole or in part on a memory not packaged together with the processor.

[0051] This application has the following beneficial effects:

[0052] 1. This application can comprehensively understand the information of the target rehabilitation patients from multiple angles by obtaining the circumference data, volume data, skin images, daily activity ability data and living habit data of the affected limbs of the target rehabilitation patients, providing a rich data basis for the formulation of rehabilitation plans.

[0053] 2. This application evaluates the severity of lymphedema by correlating abnormal features in skin images with circumference data and volume data. This application makes full use of the intrinsic connection between different types of data; the abnormal features of skin images (such as redness, swelling, ulcers, fibrosis, etc.) can intuitively reflect the manifestation of lymphedema at the skin level, while the circumference and volume data measure the swelling of the limbs from a quantitative perspective; through correlation analysis, the pathophysiological process of lymphedema can be more deeply understood, and this application provides a more comprehensive and integrated severity assessment result.

[0054] 3. This application can timely detect whether lymphedema is getting worse, getting better, or remaining stable by performing time series analysis on circumference data and volume data, thereby alleviating the patient's anxiety and stress, and thus providing forward-looking guidance for rehabilitation measures.

[0055] 4. This application performs change trend prediction analysis on the circumference data and the volume data based on an autoregressive moving average model to obtain valuable change trend analysis results, thereby providing a scientific basis for formulating home rehabilitation plans for patients with lymphedema.

[0056] 5. This application divides different patients into different groups according to their activity ability data and living habit data, and matches the target rehabilitation patients with the corresponding groups. This application fully considers the differences and similarities between individuals; each group has specific activity ability and living habit characteristics. By matching the target patients to the appropriate group, the common characteristics and experience of the group can be used to draw on to formulate a personalized rehabilitation plan. The personalized rehabilitation plan formulated in this application comprehensively considers the group characteristics, the severity of lymphedema, and the results of the change trend analysis of the target rehabilitation patients, ensuring the scientificity and rationality of the rehabilitation plan. The severity of lymphedema in this application determines the initial intensity and focus of the rehabilitation plan. For example, patients with higher severity may require more active treatment measures and stricter lifestyle interventions. The group characteristics provide personalized lifestyle adjustment and activity training suggestions for the rehabilitation plan to make it more in line with the patient's actual situation and life pattern. The results of the trend analysis provide a basis for the dynamic adjustment of the rehabilitation plan, so that the plan can be optimized and improved in time as the disease progresses. This application can better meet the special needs of patients by considering multiple factors in a personalized rehabilitation plan, improve the compliance and effectiveness of rehabilitation, promote patients to recover faster, and improve the rehabilitation effect of lymphedema. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 is an exemplary system architecture diagram to which the embodiments of the present application can be applied;

[0058] Figure 2This is a flow chart of a method for home rehabilitation of a lymphedema patient according to an embodiment of the present application;

[0059] Figure 3 This is a flowchart of lymphedema severity assessment according to an embodiment of the present application;

[0060] Figure 4 This is a flow chart of the change trend analysis results of an embodiment of the present application;

[0061] Figure 5 A flow chart of a group classification process according to an embodiment of the present application;

[0062] Figure 6 This is a system flow chart of an embodiment of the present application;

[0063] Figure 7 It is a schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0065] 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 application. The appearance of the phrase in various locations 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.

[0066] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0067] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0068] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0069] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4) players, laptop computers and desktop computers, etc.

[0070] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0071] It should be noted that the home rehabilitation method for lymphedema patients provided in the embodiments of the present application is generally executed by a server / terminal device, and accordingly, the home rehabilitation system for lymphedema patients is generally set in the server / terminal device.

[0072] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0073] Continue to refer Figure 2 , the figure shows a flow chart of a method for home rehabilitation of a lymphedema patient of the present application, the method comprising the following steps:

[0074] Step 201, obtaining the circumference data, the volume data, the skin image, the daily activity ability data and the life habit data of the affected limb of the target rehabilitation patient;

[0075] In a possible implementation, the circumference data of the affected limb of the target rehabilitation patient is obtained by a smart tape measure or a wearable circumference measuring belt. The smart tape measure or the wearable circumference measuring belt has a built-in high-precision sensor and a Bluetooth module. During use, the target rehabilitation patient wears the smart tape measure or the wearable circumference measuring belt on the affected limb. During measurement, the smart tape measure or the wearable circumference measuring belt automatically obtains accurate circumference data and transmits it to a digital platform in real time via Bluetooth.

[0076] In a possible implementation, the volume of the affected limb of the target rehabilitation patient is measured by a three-dimensional imaging device using structured light or laser scanning. The target rehabilitation patient scans the three-dimensional imaging device around the affected limb. The three-dimensional imaging device quickly constructs a three-dimensional model of the limb by emitting a specific pattern of light and capturing reflection information, and calculates the volume data of the affected limb. The three-dimensional imaging device is connected to the digital platform, automatically uploads the volume data, and provides a visual three-dimensional model display, so that the target rehabilitation patient and the doctor can more intuitively understand the changes in limb volume.

[0077] In a possible implementation, based on preset shooting conditions, skin image information of the affected limb of the target rehabilitation patient is obtained, and based on image enhancement technology, the collected skin image information is processed to obtain skin features of the affected limb. The preset shooting conditions include prescribed shooting distance, angle, light conditions, etc.

[0078] In a possible implementation, based on the smart motion tracker worn by the target rehabilitation patient, the daily activity data of the target rehabilitation patient is obtained, and the daily activity data includes the number of steps, walking distance, exercise intensity, exercise time, range of limb movement, etc., wherein the smart motion tracker includes but is not limited to a smart bracelet, a smart insole or a patch-type motion sensor, etc. The smart motion tracker transmits the daily activity data to a digital platform via Bluetooth or Wi-Fi, analyzes the daily activity data based on a preset algorithm, and obtains indicators related to the activity ability of the target rehabilitation patient.

[0079] In a possible implementation, the life habit data of the target rehabilitation patient is obtained based on smart home devices or smart health monitoring devices; for example, the weight change data of the target rehabilitation patient is obtained through a smart scale; the sleep quality, sleep time, and sleep posture data of the target rehabilitation patient are obtained through a smart mattress or sleep monitoring device; and the daily activity patterns and life rhythm of the target rehabilitation patient are understood through the use records of smart home appliances.

[0080] Step 202, obtaining abnormal features in the skin image, and performing correlation analysis on the abnormal features, the circumference data and the volume data to assess the severity of lymphedema;

[0081] In a possible implementation, the abnormal features in the skin image are obtained, and the abnormal features are correlated with the circumference data and the volume data for analysis to assess the severity of lymphedema. Please refer to Figure 3 , the specific contents include:

[0082] Step 31, input the skin image into the trained CNN model to obtain abnormal features of the skin image; wherein the abnormal features of the skin include redness, swelling, ulcer, fibrosis, etc.

[0083] Step 32, obtaining statistical features of the circumference data and the volume data, wherein the statistical features are mean, standard deviation and maximum value.

[0084] Step 33, combining the abnormal features of the skin image with the statistical features to obtain a multi-dimensional feature vector;

[0085] Step 34, using the multidimensional feature vector as an independent variable and the severity of the consequences of lymphedema as a dependent variable to obtain the severity of lymphedema.

[0086] Step 203: Based on the time series, a change trend prediction analysis is performed on the circumference data and the volume data to obtain a change trend analysis result.

[0087] In a possible implementation, based on the time series, the circumference data and the volume data are subjected to change trend prediction analysis to obtain the change trend analysis result. Please refer to Figure 4 , specifically:

[0088] Step 41, obtaining the historical circumference dataset and the volume dataset of the target rehabilitation patient, and sorting the historical circumference dataset and the volume dataset based on a time series to form a time series dataset;

[0089] Step 42, perform a stationary test on the time series data set to determine the difference order d that makes the series stationary;

[0090] Step 43, calculating the autocorrelation function and partial autocorrelation function of the time series data set, and determining the parameter autoregressive term p and the moving average term q; wherein the autocorrelation function reflects the relationship between the time series and its own lagged value, and the partial autocorrelation function shows the correlation after controlling the influence of the intermediate lagged value;

[0091] Step 44, constructing an autoregressive moving average model based on the determined parameter difference order d, autoregressive term p and moving average term q;

[0092] Step 45, based on a preset time step and an autoregressive moving average model, obtain predicted values ​​of the circumference data and the volume data at a preset number of time points, draw a prediction curve based on the predicted values, and judge the changing trend of lymphedema based on the direction of the prediction curve; if the prediction curve shows an upward trend, it means that the lymphedema may be worsening; if the prediction curve decreases, it means that the lymphedema is improved; if the curve is relatively stable, it means that the lymphedema is in a stable state.

[0093] Step 204, based on the activity ability data and living habit data of different patients, they are divided into different groups, based on the activity ability data and the living habit data of the target rehabilitation patients, the target rehabilitation patients are matched with the group, and based on the group characteristics of the target rehabilitation patients, the severity of lymphedema of the target rehabilitation patients and the change trend analysis results, a personalized rehabilitation plan is formulated.

[0094] In a possible implementation, the activity data and the living habit data of different patients are divided into different groups, and the target rehabilitation patients are matched with the groups based on their activity data and the living habit data. Based on the group characteristics of the target rehabilitation patients, the severity of lymphedema of the target rehabilitation patients and the change trend analysis results, a personalized rehabilitation plan is formulated. Please refer to Figure 5 , specifically:

[0095] Step 51, integrating the activity data and life habit data of different patients into a unified data set;

[0096] Step 52, extract key features from the activity data and lifestyle data in the data set; for activity data, extract the average number of steps per day, quantitative indicators of exercise intensity (such as the range of change of average heart rate during exercise), and the diversity of exercise types; for lifestyle data, extract quantitative indicators of diet structure (such as the proportion of various nutrients), comprehensive score of sleep quality, classification indicators of work intensity (sitting for a long time, standing for a long time, physical labor, etc.) and other classification indicators (whether smoking, drinking);

[0097] Step 53, dividing the patients into different groups based on the key features, each group representing a set of patients with similar features;

[0098] Step 54, obtaining the activity ability and living habit data of the target rehabilitation patient, calculating the similarity measure between the activity ability and living habit data characteristics of the target rehabilitation patient and the characteristics of each divided group, and dividing the target rehabilitation patient into the group with the highest similarity;

[0099] Step 55, based on the characteristics of the target rehabilitation patient group, generate a personalized rehabilitation program that meets the characteristics of the target rehabilitation patient group.

[0100] In a possible implementation, the patients are divided into different groups based on key features, each group representing a collection of patients with similar features, see Figure 6 , the specific contents include:

[0101] Step 61, randomly select K initial cluster centers (the value range of K starts from 2 and gradually increases), assign each data point to the group to which the nearest cluster center belongs, calculate the sum of the squares of the distances from the data points in each group to the cluster center, and calculate the sum of the squares of the distances of all groups. As the K value increases, the sum of the squares of the distances will gradually decrease. When the K value increases to a certain extent, the reduction in the sum of the squares of the distances will become insignificant. At this time, the K value is a more appropriate number of clusters.

[0102] Step 62, randomly select k data points as initial cluster centers;

[0103] Step 63, for each data point, calculate the Euclidean distance between it and each cluster center, and assign the data point to the group where the closest cluster center is located;

[0104] Step 64, recalculate the average value of all data points in each group on each feature as the new cluster center;

[0105] Step 651, repeatedly assigning data points and updating cluster centers until the cluster centers no longer change or the preset number of iterations is reached, at which point each data point is assigned to a corresponding group, forming k different groups.

[0106] For example, based on the characteristics of the target rehabilitation patient group, a personalized rehabilitation program that meets the characteristics of the target rehabilitation patient group is generated:

[0107] Rehabilitation programs related to activity ability: When the target rehabilitation patient group is characterized by a low activity level group, a rehabilitation program for increasing daily activity can be generated; when the target rehabilitation patient group is characterized by a high activity level group, a rehabilitation program for optimizing exercise methods or adjusting exercise intensity can be generated.

[0108] Rehabilitation plans related to lifestyle habits: When the target rehabilitation patient group is characterized by a poor diet structure group, a rehabilitation plan for diet adjustment is generated, and patients are prompted to develop regular eating habits; when the target rehabilitation patient group is characterized by a poor sleep quality group, a rehabilitation plan for improving the sleeping environment and adjusting sleeping habits is generated, and sleep assistance measures are given to patients with difficulty falling asleep or interrupted sleep.

[0109] Development of a comprehensive rehabilitation program targeting mobility and lifestyle habits. For example, for a patient with a low activity level, poor diet and poor sleep quality, the rehabilitation program may include a plan to gradually increase the number of steps, simple exercise training, development of a healthy diet plan, improvement of the sleeping environment and adjustment of sleeping habits. At the same time, the intensity and progress of each measure may be appropriately adjusted considering the severity of the patient's lymphedema and physical condition.

[0110] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0111] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0112] Continue to refer Figure 6 The home rehabilitation system for patients with lymphedema described in this embodiment includes:

[0113] The data acquisition module 601 is used to acquire the circumference data, volume data, skin image, daily activity ability data and life habit data of the affected limb of the target rehabilitation patient;

[0114] A lymphedema severity assessment module 602 is used to obtain abnormal features in the skin image, associate and analyze the abnormal features with the circumference data and the volume data, and assess the severity of lymphedema;

[0115] A change trend analysis module 603 is used to perform change trend prediction analysis on the circumference data and the volume data based on a time series to obtain a change trend analysis result;

[0116] The rehabilitation program generation module 604 is used to divide the patients into different groups based on their activity ability data and the living habit data, match the target rehabilitation patients' groups based on their activity ability data and the living habit data, and formulate a personalized rehabilitation program based on the group characteristics of the target rehabilitation patients, the severity of the target rehabilitation patients' lymphedema and the change trend analysis results.

[0117] To solve the above technical problems, the present application also provides a computer device. Figure 7 , Figure 7 This is a basic structural block diagram of the computer device in this embodiment.

[0118] The computer device 7 includes a memory 7a, a processor 7b, and a network interface 7c that are interconnected through a system bus. It should be noted that the figure only shows a computer device 7 with components 7a-7c, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0119] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0120] The memory 7a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 7a can be an internal storage unit of the computer device 7, such as a hard disk or memory of the computer device 7. In other embodiments, the memory 7a can also be an external storage device of the computer device 7, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 7. Of course, the memory 7a can also include both the internal storage unit of the computer device 7 and its external storage device. In this embodiment, the memory 7a is generally used to store the operating system and various application software installed on the computer device 7, such as the program code of the home rehabilitation method for patients with lymphedema, etc. In addition, the memory 7a can also be used to temporarily store various types of data that have been output or are to be output.

[0121] The processor 7b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 7b is generally used to control the overall operation of the computer device 7. In this embodiment, the processor 7b is used to run the program code stored in the memory 7a or process data, such as running the program code of the home rehabilitation method for the lymphedema patient.

[0122] The network interface 7c may include a wireless network interface or a wired network interface. The network interface 7c is generally used to establish a communication connection between the computer device 7 and other electronic devices.

[0123] The present application also provides another embodiment, namely, providing a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a program of a home rehabilitation method for patients with lymphedema, and the home rehabilitation of patients with lymphedema can be executed by at least one processor so that the at least one processor executes the steps of the home rehabilitation method for patients with lymphedema as described above.

[0124] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0125] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A home rehabilitation method for patients with lymphedema, characterized in that: include: Obtain the circumference data, volume data, skin images, daily activity ability data and living habit data of the affected limbs of the target rehabilitation patients; Acquire abnormal features in the skin image, perform correlation analysis on the abnormal features, the circumference data and the volume data, and evaluate the severity of lymphedema; Based on the time series, performing change trend prediction analysis on the circumference data and the volume data to obtain a change trend analysis result; Based on the activity ability data and the living habit data of different patients, they are divided into different groups. Based on the activity ability data and the living habit data of the target rehabilitation patients, the target rehabilitation patients' groups are matched. Based on the group characteristics of the target rehabilitation patients, the severity of the target rehabilitation patients' lymphedema and the change trend analysis results, a personalized rehabilitation plan is formulated.

2. The home rehabilitation method for patients with lymphedema according to claim 1, characterized in that: The step of obtaining the circumference data of the affected limb of the target rehabilitation patient includes: Obtain the circumference data of the affected limb of the target rehabilitation patient through a smart measuring tape or a wearable circumference measuring belt; The volume of the affected limb of the target rehabilitation patient is measured by a three-dimensional imaging device using structured light or laser scanning. The target rehabilitation patient scans the three-dimensional imaging device around the affected limb. The three-dimensional imaging device emits light in a specific pattern and captures the reflected information to quickly construct a three-dimensional model of the limb and calculate the volume data of the affected limb. Based on preset shooting conditions, obtain skin image information of the affected limb of the target rehabilitation patient; Based on the smart motion tracker worn by the target rehabilitation patients, the daily activity data of the target rehabilitation patients are obtained; Obtain the living habit data of target rehabilitation patients based on smart home devices or smart health monitoring devices.

3. The home rehabilitation method for patients with lymphedema according to claim 1, characterized in that: The obtaining of abnormal features in the skin image, correlation analysis of the abnormal features with the circumference data and the volume data, and evaluation of the severity of lymphedema are specifically performed as follows: Inputting the skin image into the trained CNN model to obtain abnormal features of the skin image, wherein the abnormal features of the skin include redness, swelling, ulcer, fibrosis, etc.; Obtaining statistical features of the circumference data and the volume data, wherein the statistical features are mean, standard deviation and maximum value; Combining the abnormal features of the skin image with the statistical features to obtain a multi-dimensional feature vector; The multidimensional feature vector was used as the independent variable and the severity of the consequences of lymphedema was used as the dependent variable to obtain the severity of lymphedema.

4. The home rehabilitation method for patients with lymphedema according to claim 1, characterized in that: Based on the time series, the change trend prediction analysis is performed on the circumference data and the volume data to obtain the change trend analysis result, which is specifically manifested as follows: Acquire a historical circumference dataset and a volume dataset of the target rehabilitation patient, and sort the historical circumference dataset and the volume dataset based on a time series to form a time series dataset; Perform a stationary test on the time series data set to determine the difference order d that makes the series stationary; Calculate the autocorrelation function and partial autocorrelation function of the time series data set, and determine the parameter autoregressive term p and moving average term q; An autoregressive moving average model is constructed based on the determined parameter difference order d, autoregressive term p and moving average term q; Based on a preset time step and an autoregressive moving average model, the predicted values ​​of the circumference data and the volume data at a preset number of time points are obtained, a prediction curve is drawn based on the predicted values, and the change trend of lymphedema is judged based on the trend of the prediction curve; if the prediction curve shows an upward trend, it means that the lymphedema may be getting worse; if the prediction curve drops, it means that the lymphedema is improved; If the curve is relatively stable, it means that the lymphedema is in a stable state.

5. The home rehabilitation method for lymphedema patients according to claim 1, characterized in that: The activity data and the life habit data of different patients are divided into different groups, the activity data and the life habit data of the target rehabilitation patients are matched with the groups of the target rehabilitation patients, and the personalized rehabilitation plan is formulated based on the group characteristics of the target rehabilitation patients, the severity of the lymphedema of the target rehabilitation patients and the change trend analysis results, which are specifically manifested as follows: Integrate the activity data and lifestyle data of different patients into a unified data set; Extract key features from the activity data and lifestyle data in the dataset; For activity data, the average number of steps per day, quantitative indicators of exercise intensity, and the diversity of exercise types are extracted; for lifestyle data, quantitative indicators of diet structure, comprehensive scores of sleep quality, classification indicators of work intensity, and other classification indicators are extracted; Patients are divided into different groups based on key characteristics, each group represents a collection of patients with similar characteristics; Acquire the activity ability and living habit data of the target rehabilitation patient, calculate the similarity measure between the activity ability and living habit data characteristics of the target rehabilitation patient and the characteristics of each divided group, and divide the target rehabilitation patient into the group with the highest similarity; Based on the characteristics of the target rehabilitation patient group, a personalized rehabilitation plan that meets the characteristics of the target rehabilitation patient group is generated.

6. The home rehabilitation method for patients with lymphedema according to claim 5, characterized in that: The patients are divided into different groups based on key characteristics, each group representing a collection of patients with similar characteristics, including: Randomly select K initial cluster centers (the value range of K starts from 2 and gradually increases), assign each data point to the group to which the nearest cluster center belongs, calculate the sum of the squared distances from the data points in each group to the cluster center, and calculate the sum of the squared distances of all groups. As the K value increases, the sum of the squared distances will gradually decrease. When the K value increases to a certain extent, the reduction in the sum of the squared distances will become insignificant. At this time, the K value is a more appropriate number of clusters. Randomly select k data points as initial cluster centers; For each data point, calculate its Euclidean distance to each cluster center and assign the data point to the group with the closest cluster center; Recalculate the average value of all data points in each group on each feature as the new cluster center; Repeat the allocation of data points and updating of cluster centers until the cluster centers no longer change or the preset number of iterations is reached. At this time, each data point is assigned to the corresponding group, forming k different groups.

7. A home rehabilitation system for patients with lymphedema, used to implement the home rehabilitation method for patients with lymphedema according to claims 1-6, characterized in that: include: A data acquisition module, used to obtain the circumference data, volume data, skin image, daily activity ability data and life habit data of the affected limb of the target rehabilitation patient; a lymphedema severity assessment module, used to obtain abnormal features in the skin image, associate and analyze the abnormal features with the circumference data and the volume data, and assess the severity of lymphedema; A change trend analysis module, used to perform change trend prediction analysis on the circumference data and the volume data based on a time series, and obtain a change trend analysis result; The rehabilitation program generation module is used to divide different patients into different groups based on their activity ability data and the living habit data, match the target rehabilitation patient groups based on their activity ability data and the living habit data, and formulate personalized rehabilitation programs based on the group characteristics of the target rehabilitation patients, the severity of lymphedema of the target rehabilitation patients and the change trend analysis results.

8. An electronic device, characterized in that: include: one or more processors; Memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, enable the device to perform the steps of the home rehabilitation method for lymphedema patients as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed on a computer, enables the computer to execute the steps of the home rehabilitation method for lymphedema patients as claimed in any one of claims 1 to 6.

Images