Companion animal musculoskeletal disorder diagnostic assistive device
Patent Information
- Application Number
- KR1020250048311
- Authority / Receiving Office
- KR · KR
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-04-14
- Publication Date
- 2026-10-21
Smart Images
Figure PAT00003_ABST
Abstract
Description
Technology Field
[0001] The present invention relates to animal medical devices and healthcare technologies for assisting in the diagnosis of orthopedic diseases in companion animals, and more specifically, to a diagnostic assistance device for companion animal musculoskeletal diseases that supports the early detection of musculoskeletal diseases by analyzing the load applied to a specific leg through the use of multiple pressure sensors to measure and analyze the weight distribution when a companion animal stands on a plate. Background Technology
[0003] In modern society, medical technology for companion animals is advancing in various fields, and diagnostic techniques for musculoskeletal diseases through weight distribution analysis are receiving particular attention. Knee joint diseases in companion animals, such as patellar luxation and cruciate ligament rupture, occur frequently, especially in small and some medium-sized dogs; as the disease progresses, they are characterized by an inability to bear weight on a specific leg and a prominent limp.
[0004] Conventional diagnostic methods for musculoskeletal disorders primarily involve veterinary palpation and X-ray imaging; however, these approaches have limitations, as they often rely on subjective judgment and make it difficult to immediately detect real-time changes in body weight distribution. Furthermore, accurate diagnosis is frequently challenging because pets tend to become tense or move during examinations, and when initial symptoms are mild, the condition often worsens without the owner recognizing any abnormalities.
[0005] In particular, there is a growing need for technology capable of quantitatively measuring whether the load on specific legs is reduced by analyzing how body weight is distributed when a pet is standing. This necessitates a solution that overcomes the limitations of existing diagnostic methods and enables early diagnosis and continuous monitoring.
[0006] Korean Published Patent No. 10-2024-0047513 relates to a method for analyzing body fat and monitoring health of pets and a system using the same, comprising: a sound extraction step in which a control unit extracts sound according to a predetermined standard based on sound information of a pet collected from a microphone; a breath sound analysis step in which the control unit transmits the breath sound extracted in the sound extraction step to a breath sound recognition unit, and the breath sound recognition unit analyzes the received breath sound by a pre-trained artificial intelligence neural network; an image analysis step in which a fur color recognition unit compares collected image information of a pet with previously stored image information of a pet to determine whether the degree of deformation of the fur color falls within a predetermined standard range; and a verification step in which a signal of potential onset is received by the control unit from each recognition unit, and a verification unit verifies the potential onset based on a thermal image collected from a thermal imaging camera. Prior art literature
[0008] Korean Published Patent No. 10-2024-0047513 (April 12, 2024) The problem to be solved
[0009] One embodiment of the present invention aims to provide a diagnostic assistance device for musculoskeletal diseases in pets that can determine the possibility of musculoskeletal disease at an early stage by measuring and analyzing the weight distribution of the pet in real time and detecting changes in the load placed on a specific leg.
[0010] One embodiment of the present invention aims to provide a diagnostic assistance device for musculoskeletal diseases in companion animals that can quantitatively analyze load data per leg using a pressure sensor array. means of solving the problem
[0012] Among the embodiments, a diagnostic aid for musculoskeletal diseases in pets comprises: a plate; a pressure sensor array disposed on the plate to measure loads applied to a plurality of legs of a pet; a load data collection unit for collecting load data for said loads; a weight ratio calculation unit for calculating a weight ratio between said load data; a disease diagnosis unit for diagnosing the presence or absence of a musculoskeletal disease in a specific leg based on said weight ratio; and a display unit for displaying a warning message regarding the musculoskeletal disease of said specific leg on a display.
[0013] The pressure sensor array is implemented as a two-dimensional array of force-sensitive resistors (FSR), and the corresponding load can be calculated by summing the pressures measured in the sensing area of the force-sensitive resistors for each of the plurality of legs.
[0014] The pressure sensor array can detect an overlay phenomenon in the sensing area of a specific leg among the plurality of legs, and if the overlay phenomenon is detected, it can display a re-measurement request message on the display.
[0015] The load data collection unit performs multiple sampling on the load data at regular time intervals and can remove instantaneous outlier data by applying a moving average filter to the load data.
[0016] The above weight ratio calculation unit can calculate the relative ratio of the load placed on each of the plurality of legs based on the total body weight of the pet.
[0017] The above disease diagnosis unit can determine the possibility of a musculoskeletal disease in a specific leg by detecting, through a rule-based algorithm, that the weight distribution ratio placed on the specific leg decreases below a preset threshold.
[0018] When the weight distribution ratio applied to the specific leg is confirmed through the rule-based algorithm, the disease diagnosis unit may simultaneously use a machine learning-based algorithm that inputs long-term accumulated load data into a musculoskeletal disease diagnosis model to correct the likelihood of the disease.
[0019] The above disease diagnosis unit can predict the likelihood of progression of the musculoskeletal disease by comparing and analyzing the load data with past load data to monitor load changes of a specific leg and detecting the persistence of the load changes over a certain period.
[0020] The above display unit visualizes load changes by leg in the form of a heatmap or graph to intuitively indicate the level of suspected disease, and can display real-time load data and past load data for comparison.
[0021] Among the embodiments, a diagnostic aid for musculoskeletal diseases in pets comprises: a plate formed to allow a pet to stand on; a pressure sensor array disposed on the plate to measure the load placed on a plurality of legs of the pet; a load data collection unit that collects load data measured through the pressure sensor array; a weight ratio calculation unit that processes the load data to calculate the ratio of the relative load placed on each leg to the total body weight of the pet; a disease diagnosis unit that analyzes the weight ratio to detect whether the weight ratio placed on a specific leg decreases below a preset threshold and predicts the likelihood of disease progression in the specific leg; and a display unit that displays the likelihood of musculoskeletal disease and the level of suspected disease of the pet in the form of a heatmap or graph based on the likelihood of disease progression in the specific leg.
[0022] The load data collection unit performs multiple sampling on the load data at regular time intervals and can remove instantaneous outlier data by applying a moving average filter to the load data.
[0023] The above weight ratio calculation unit can calculate the relative ratio of the load placed on each of the plurality of legs based on the total body weight of the pet.
[0024] The above disease diagnosis unit can determine the possibility of a musculoskeletal disease in a specific leg by detecting, through a rule-based algorithm, that the weight distribution ratio placed on the specific leg decreases below a preset threshold.
[0025] When the weight distribution ratio applied to the specific leg is confirmed through the rule-based algorithm, the disease diagnosis unit may simultaneously use a machine learning-based algorithm that inputs long-term accumulated load data into a musculoskeletal disease diagnosis model to correct the likelihood of the disease.
[0026] The above disease diagnosis unit can predict the likelihood of progression of the musculoskeletal disease by comparing and analyzing the load data with past load data to monitor load changes of a specific leg and detecting the persistence of the load changes over a certain period. Effects of the invention
[0028] The disclosed technology may have the following effects. However, this does not mean that a specific embodiment must include all of the following effects or only the following effects; therefore, the scope of the rights of the disclosed technology should not be understood as being limited by this.
[0029] A diagnostic assistance device for musculoskeletal diseases in pets according to one embodiment of the present invention can determine the possibility of musculoskeletal diseases at an early stage by measuring and analyzing the weight distribution of a pet in real time and detecting changes in the load placed on a specific leg.
[0030] A diagnostic assistance device for musculoskeletal diseases in companion animals according to one embodiment of the present invention can quantitatively analyze load data for each leg using a pressure sensor array. Brief explanation of the drawing
[0032] FIG. 1 is a drawing illustrating a diagnostic assistance system for musculoskeletal diseases in companion animals according to the present invention. Figure 2 is a diagram illustrating the system configuration of the diagnostic assistance device for musculoskeletal diseases in companion animals shown in Figure 1. Figure 3 is a diagram illustrating the configuration of the diagnostic assistance device for musculoskeletal diseases in companion animals shown in Figure 1. FIG. 4 is a flowchart illustrating the functional configuration of a diagnostic assistance device for musculoskeletal diseases in companion animals according to the present invention. FIG. 5 is a drawing illustrating an embodiment of a diagnostic assistance device for musculoskeletal diseases in companion animals. Specific details for implementing the invention
[0033] The description of the present invention is merely an example for structural or functional explanation, and therefore the scope of the present invention should not be interpreted as being limited by the examples described in the text. That is, since the examples are subject to various modifications and may take various forms, the scope of the present invention should be understood to include equivalents capable of realizing the technical concept. Furthermore, the objectives or effects presented in the present invention do not imply that a specific example must include all of them or only such effects; therefore, the scope of the present invention should not be understood as being limited by them.
[0034] Meanwhile, the meaning of the terms described in this application should be understood as follows.
[0035] Terms such as "first," "second," etc., are intended to distinguish one component from another, and the scope of rights shall not be limited by these terms. For example, the first component may be named the second component, and similarly, the second component may be named the first component.
[0036] When it is stated that one component is "connected" to another component, it should be understood that it may be directly connected to that other component, or that there may be other components in between. Conversely, when it is stated that one component is "directly connected" to another component, it should be understood that there are no other components in between. Meanwhile, other expressions describing the relationships between components, such as "between" and "exactly between," or "adjacent to" and "directly adjacent to," should be interpreted in the same way.
[0037] A singular expression should be understood to include a plural expression unless the context clearly indicates otherwise, and terms such as "include" or "have" are intended to specify the existence of the implemented features, numbers, steps, actions, components, parts, or combinations thereof, and should be understood not to preclude the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.
[0038] In each step, identifiers (e.g., a, b, c, etc.) are used for convenience of explanation and do not describe the order of the steps; the steps may occur differently from the specified order unless a specific order is clearly indicated in the context. That is, the steps may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.
[0039] The present invention may be implemented as computer-readable code on a computer-readable recording medium, and the computer-readable recording medium includes all types of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. Additionally, the computer-readable recording medium may be distributed across networked computer systems, so that computer-readable code can be stored and executed in a distributed manner.
[0040] Unless otherwise defined, all terms used herein have the same meaning as generally understood by those skilled in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having meanings consistent with the context of the relevant technology and should not be interpreted as having an ideal or overly formal meaning unless explicitly defined in this application.
[0042] FIG. 1 is a drawing illustrating a diagnostic assistance system for musculoskeletal diseases in companion animals according to the present invention.
[0043] Referring to FIG. 1, a pet musculoskeletal disease diagnosis assistance system (100) may include a plate (110), a pressure sensor array (120), a pet musculoskeletal disease diagnosis assistance device (130), and a database (150).
[0044] The plate (110) can be formed to allow a pet to stand on it. Here, the plate (110) may correspond to a structure formed to allow a pet to stand on it, and may be formed to include a pressure sensor array (120) to measure the load applied to each leg of the pet. The plate (110) may be composed of a grid-like array or a single structure, and may be treated with an anti-slip coating so that the pet can naturally stand on it. Additionally, the plate (110) may be connected to a network with a pet musculoskeletal disease diagnostic aid device (130) and may be implemented as a smart diagnostic platform including a wireless data transmission function, rather than being limited to performing a simple pedestal function, and may be implemented in various forms such as an IoT-based monitoring system and a cloud-linked analysis system as needed.
[0045] A pressure sensor array (120) is placed on a plate (110) to measure loads applied to multiple legs of a pet. Here, the pressure sensor array (120) may correspond to a sensor array that detects and measures the load applied to each leg of a pet, and, for example, may be placed on the plate (110) to perform the role of collecting weight distribution data for each leg. Additionally, the pressure sensor array (120) may be implemented as a sensor network including a capacitive pressure sensor array, a fiber Bragg Grating (FBG) pressure sensor, or a piezoresistive sensor, and may receive power and load data from the plate (110) to analyze the pet's weight change pattern in real time and perform a correction function on the collected load data automatically when necessary.
[0046] In one embodiment, the pressure sensor array (120) may be implemented as a two-dimensional array of force-sensitive resistors (FSRs), and the corresponding load can be calculated by summing the pressure measured in the sensing area of the force-sensitive sensors for each of the plurality of legs. Here, the force-sensitive sensors may correspond to sensors whose resistance value changes according to the magnitude of externally applied pressure or load, and, for example, may perform the role of measuring pressure changes and weight distribution due to the weight of the pet. Additionally, the force-sensitive sensors may have individual sensing areas, and, for example, may calculate the total load placed on a specific leg by summing the pressure values measured for each leg of the pet. The pressure sensor array (120) may collect the weight distributed on each leg of the pet based on the force-sensitive sensors and update the load data according to the change in the position of the pet's legs in real time and store it in the database (150).
[0047] In one embodiment, the pressure sensor array (120) may detect an overlay phenomenon in the sensing area of a specific leg among a plurality of legs, and if the overlay phenomenon is detected, display a re-measurement request message on the display. Here, the overlay phenomenon may correspond to a situation where the sensor data is distorted as the sensing area of the pressure sensor array (120) is simultaneously activated on at least two legs. The pressure sensor array (120) may compare and analyze the data detected by each sensor to check whether the pressure distribution applied to a specific leg is abnormally overlapping, and if an overlay phenomenon occurs, determine that the reliability of the measurement data has decreased and display a re-measurement request message on the display unit (60). For example, the pressure sensor array (120) may display "Measurement error: Sensor interference detected. Please guide the pet to stand normally on the plate.", "Re-measurement needed: Leg position is inaccurate. Please measure again after properly positioning the pet.", and "Overlay phenomenon detected: The sensing area of a specific leg is overlapping. Re-measurement is required." By displaying a re-measurement request message on the display, the user can guide the pet to stand correctly on the plate (110).
[0048] The pet musculoskeletal disease diagnosis assistance device (130) may be implemented as a server corresponding to a computer or program that performs the pet musculoskeletal disease diagnosis assistance method according to the present invention. For example, the pet musculoskeletal disease diagnosis assistance device (130) may provide a pet musculoskeletal disease diagnosis service, and may be implemented as a server that provides functions such as analyzing the pet's load data in real time, evaluating the possibility of musculoskeletal disease, and providing diagnosis results to the user, and may enable each step of the pet musculoskeletal disease diagnosis assistance method according to the present invention to be performed on the server.
[0049] In addition, companion animal musculoskeletal disease diagnostic services may correspond to artificial intelligence (AI)-based diagnostic solutions that analyze weight distribution data to assess the likelihood of disease at an early stage, but are not necessarily limited thereto and may further include remote veterinary services or companion animal health monitoring services that provide companion animal musculoskeletal disease diagnostic services. Companion animal musculoskeletal diseases may include patellar luxation, cruciate ligament rupture, hip dysplasia, arthritis, and osteochondrodysplasia.
[0051] The musculoskeletal disease diagnostic aid (130) for pets can be connected to the plate (110) and pressure sensor array (120) via a wired network or a wireless network such as Bluetooth, WiFi, or LTE, and can transmit and receive data to and from the plate (110) and pressure sensor array (120) via the wired and wireless networks.
[0052] Additionally, the musculoskeletal disease diagnosis assistance device (130) for pets can be implemented to operate in connection with an independent external system (not shown in FIG. 1). For example, the musculoskeletal disease diagnosis assistance device (130) for pets can operate in conjunction with a cloud-based healthcare management system that provides pet health monitoring and diagnostic data analysis solutions to users, or in conjunction with a veterinary diagnostic support system that provides AI-based disease prediction and remote medical support solutions.
[0053] The database (150) may correspond to a storage device that stores various information required during the operation of the pet musculoskeletal disease diagnosis assistance device (130). For example, the database (150) may store disease diagnosis-related data such as records of the pet's load measurement and weight distribution analysis results, and is not necessarily limited to this, but may store sensor measurement data, past diagnosis history data, and machine learning model training data generated during the operation of the pet musculoskeletal disease diagnosis assistance device (130).
[0054] In FIG. 1, the database (150) is shown as a device independent of the pet musculoskeletal disease diagnostic aid device (130), but is not necessarily limited thereto and can be implemented by being included in the pet musculoskeletal disease diagnostic aid device (130).
[0056] Figure 2 is a diagram illustrating the system configuration of the diagnostic assistance device for musculoskeletal diseases in companion animals shown in Figure 1.
[0057] Referring to FIG. 2, the musculoskeletal disease diagnosis assistance device (130) for pets may include a processor (210), memory (230), user input / output unit (250), network input / output unit (270), and communication port unit (290).
[0058] The processor (210) can execute a procedure to assist in the diagnosis of musculoskeletal diseases in pets according to an embodiment of the present invention, manage memory (230) that is read or written during this process, and schedule the synchronization time between volatile memory and non-volatile memory in memory (230). The processor (210) can control the overall operation of the assist in the diagnosis of musculoskeletal diseases in pets (130) and is electrically connected to memory (230), user input / output unit (250), and network input / output unit (270) to control the data flow between them. The processor (210) can be implemented as a CPU (Central Processing Unit) or GPU (Graphics Processing Unit) of the assist in the diagnosis of musculoskeletal diseases in pets (130).
[0059] The memory (230) may include an auxiliary storage device implemented as non-volatile memory such as an SSD (Solid State Disk) or HDD (Hard Disk Drive) and used to store all data required for the pet musculoskeletal disease diagnostic aid device (130), and may include a main memory device implemented as volatile memory such as RAM (Random Access Memory). Additionally, the memory (230) may store a set of instructions that execute the pet musculoskeletal disease diagnostic aid method according to the present invention by being executed by an electrically connected processor (210).
[0060] The user input / output unit (250) includes an environment for receiving user input and an environment for outputting specific information to the user, and may include an input device including an adapter such as a touch pad, touch screen, virtual keyboard, or pointing device, and an output device including an adapter such as a monitor or touch screen. In one embodiment, the user input / output unit (250) may correspond to a computing device connected via remote access, and in such case, the pet musculoskeletal disease diagnosis assistance device (130) may be performed as an independent server.
[0061] The network input / output unit (270) provides a communication environment for connecting to the plate (110) and the pressure sensor array (120) via a network, and may include an adapter for communication such as a LAN (Local Area Network), MAN (Metropolitan Area Network), WAN (Wide Area Network), and VAN (Value Added Network). Additionally, the network input / output unit (270) may be implemented to provide short-range communication functions such as WiFi and Bluetooth, or wireless communication functions of 4G or higher, for wireless transmission of data.
[0062] The communication port section (290) can be implemented as a port mapping table that performs data routing during the process of transmitting and receiving data through a network. Here, the communication port section (290) can distinguish communication sessions between the pet musculoskeletal disease diagnostic aid device (130) and the server and prevent data collisions during the process of transmitting and receiving data by assigning a unique source port to the pet musculoskeletal disease diagnostic aid device (130).
[0064] Figure 3 is a diagram illustrating the configuration of the diagnostic assistance device for musculoskeletal diseases in companion animals shown in Figure 1.
[0065] Referring to FIG. 3, the musculoskeletal disease diagnosis assistance device (130) for pets may include a load data collection unit (310), a weight ratio calculation unit (330), a disease diagnosis unit (350), a display unit (370), and a control unit (390).
[0066] The musculoskeletal disease diagnosis assistance device (130) for companion animals does not necessarily have to include all of the above functional components simultaneously; depending on each embodiment, some of the components may be omitted, or some or all of the components may be selectively included. Additionally, the musculoskeletal disease diagnosis assistance device (130) for companion animals may be implemented as an independent module that selectively includes some of the above components, and the method for diagnosing musculoskeletal diseases in companion animals according to the present invention may be performed through the interlocking of each module. The operation of each component is described in detail below.
[0068] The load data collection unit (310) can collect load data for loads. Here, the load data collection unit (310) can collect load data for each leg of the pet by measuring pressure data from each sensing point when the pet steps onto the plate (110). Additionally, the load data collection unit (310) can analyze weight transfer patterns when the pet walks or moves on the plate (110). For example, the load data collection unit (310) can continuously collect load data based on the pressure sensor array (120) and store it in the database (150) to enable analysis of the pet's gait and walking cycle. In one embodiment, the load data collection unit (310) can classify the collected load data based on various criteria such as measurement time, load value per individual leg, relative load ratio to the pet's total body weight, and walking pattern, and store it in the database (150).
[0069] In one embodiment, the load data collection unit (310) can collect load data measured through the pressure sensor array (120). Here, the load data collection unit (310) can collect load data by individually measuring the pressure applied to each leg of the pet based on the force-sensitive resistor (FSR) of the pressure sensor array (120). Additionally, the load data collection unit (310) is not necessarily limited to this and can collect load data by measuring the load on each leg of the pet based on various pressure sensors, such as a capacitive pressure sensor array, a fiber Bragg grating (FBG), or a piezoresistive sensor.
[0070] In one embodiment, the load data collection unit (310) may provide information on the weight distribution of the pet by applying a multi-sensor fusion technique to analyze additional data such as contact area, pressure change rate, and walking cycle. Here, the multi-sensor fusion technique may correspond to a data processing technique that integrates data collected from different types of sensors to generate more precise and reliable information. If necessary, the load data collection unit (310) may collect the pet's ability to maintain balance and movement patterns by additionally utilizing sensors such as an accelerometer and a gyroscope in addition to the force detection sensor. The load data collection unit (310) may detect the balance and movement of the pet based on multiple sensors, and is not necessarily limited to this, but may fuse data collected from each sensor to analyze walking patterns and detect changes in the load applied to a specific leg of the pet.
[0071] In one embodiment, the load data collection unit (310) performs multiple sampling of load data at regular time intervals and can remove instantaneous outlier data by applying a moving average filter to the load data. Here, the load data collection unit (310) can continuously collect load data by performing sampling of load data at specific time intervals (e.g., 100ms to 500ms, etc.) and detect outlier data through comparison between the collected load data. For example, the load data collection unit (310) can calculate the average value of the sampled load data by applying a moving average filter and determine load data that differs from the average value by more than a certain standard as outlier data.
[0072] In one embodiment, the load data collection unit (310) can detect and remove outlier data based on the threshold deviation of the sampled load data. For example, the load data collection unit (310) can calculate the average of the load data collected over a specific period of time and determine and remove it as an outlier if the current sample value differs from the average value by more than a set threshold value (e.g., ±15%). Additionally, the load data collection unit (310) can analyze the distribution of the sampled load data, perform a comparison with the average value, and determine load data that falls outside the range of the statistical standard deviation as an outlier. The load data collection unit (310) is not necessarily limited to this and can apply a median filter to the load data to sort a certain number of recent samples to obtain the median, and determine and remove data that deviates from the median as an outlier.
[0073] The weight ratio calculation unit (330) can calculate the weight ratio between load data. For example, the weight ratio calculation unit (330) can measure the load placed on each leg of the pet and calculate the proportion of the total body weight. Additionally, in the process of calculating the weight ratio between load data, the weight ratio calculation unit (330) can analyze the weight distribution pattern according to the breed, age, and body type of the pet and set a normal load distribution standard according to the breed, age, and body type of the pet. For example, the weight ratio calculation unit (330) can derive a general weight distribution ratio by referring to the average weight database by pet breed and calculate the average load ratio placed on a specific leg by utilizing data of pets of the same breed and similar body type. Additionally, the weight ratio calculation unit (330) can set a normal load movement range by considering the degree of musculoskeletal development according to the age of the pet, reflecting changes in the average weight distribution by age, such as growth stage, adult dog, and senior dog, and analyzing long-term load change patterns.
[0074] In one embodiment, the weight ratio calculation unit (330) can process load data to calculate the ratio of the relative load placed on each leg relative to the total body weight of the pet. Here, the weight ratio calculation unit (330) can derive the weight distribution of each leg by performing the function of measuring the load placed on each leg of the pet and calculating the relative load ratio by comparing it with the total body weight. For example, the weight ratio calculation unit (330) can calculate the relative load ratio by measuring the load placed on each leg and comparing it with the total body weight of the pet, and can derive load measurement results including the front leg (left), front leg (right), hind leg (left), and hind leg (right) as a result of measuring the load placed on each leg when the total body weight of the pet is 10 kg. Here, the load measurement results of each leg can be expressed as a percentage (%), but are not necessarily limited thereto and can be visualized using a heatmap and a graph. Through this, the weight ratio calculation unit (330) can provide the user with the degree of weight distribution of the pet and perform a comparative analysis with normal weight distribution data by breed and age.
[0075] In one embodiment, the weight ratio calculation unit (330) can calculate the relative ratio of the load placed on each of the multiple legs based on the total body weight of the pet. For example, when the total body weight of the pet is 10 kg, the weight ratio calculation unit (330) can measure the load placed on each leg and derive relative load ratios such as front leg (left): 32%, front leg (right): 30%, hind leg (left): 19%, and hind leg (right): 19% based on the load data. Additionally, the weight ratio calculation unit (330) can continuously measure the load placed on each of the multiple legs of the pet to analyze the load change pattern over time and evaluate the possibility of musculoskeletal disease if the load placed on a specific leg decreases below a certain threshold or if the imbalance persists.
[0076] The disease diagnosis unit (350) can diagnose whether there is a musculoskeletal disease in a specific leg based on the weight ratio. Here, the disease diagnosis unit (350) can analyze the weight ratio to detect a pattern of decreasing weight applied to a specific leg and use it as an indicator of a musculoskeletal disease. For example, the disease diagnosis unit (350) can determine the possibility of a musculoskeletal disease if the load ratio of a specific leg decreases below a certain threshold value when compared to a pre-set normal load distribution ratio. For example, the disease diagnosis unit (350) can diagnose that there is a high possibility of a disease if a pet, whose normal weight distribution is front leg (60%) and hind leg (40%), has a load reduction of 15% or less in a specific leg.
[0077] Additionally, the disease diagnosis unit (350) can perform a diagnosis of a musculoskeletal disease in a pet by applying a machine learning-based disease correction algorithm to learn long-term load data changes. Here, the disease diagnosis unit (350) can provide load data as input to a machine learning model to analyze the load change pattern of a specific leg and predict whether the disease is progressing. For example, the disease diagnosis unit (350) can analyze the past three months of load data of the pet based on a machine learning model and compare normal weight distribution with abnormal signs to predict a high probability that a musculoskeletal disease is progressing if the weight placed on a specific leg continuously decreases.
[0078] In one embodiment, the disease diagnosis unit (350) can analyze the weight ratio to detect whether the weight ratio placed on a specific leg decreases below a preset threshold and predict the possibility of disease progression in the specific leg. Here, the disease diagnosis unit (350) monitors the load ratio placed on each leg of the pet in real time and analyzes whether the load on the specific leg decreases by comparing it with a normal weight distribution, and can diagnose a musculoskeletal disease if the weight placed on the specific leg decreases based on a preset threshold (e.g., 15% or less).
[0079] Additionally, the disease diagnosis unit (350) can distinguish between temporary weight shifts and the progression of musculoskeletal diseases by accumulating and analyzing the pet's load data over a certain period to detect long-term changes. For example, the disease diagnosis unit (350) can measure and store the pet's leg load data daily or at set time intervals (e.g., every hour), analyze the data accumulated over a certain period to calculate the average load ratio of each leg, and compare it with a normal weight distribution pattern. Through this, the disease diagnosis unit (350) can distinguish between the pet's short-term weight changes and long-term weight loss patterns to determine whether it is a simple temporary weight change or if a disease is progressing.
[0080] In one embodiment, the disease diagnosis unit (350) can determine the possibility of a musculoskeletal disease in a specific leg by detecting, through a rule-based algorithm, that the weight distribution ratio placed on the specific leg decreases below a preset threshold. Here, the rule-based algorithm may correspond to a method of analyzing data based on predefined conditions (rules, thresholds) and detecting specific patterns to derive a conclusion, for example, it may correspond to an algorithm that performs a specific action when a specific value exceeds or falls below a standard compared to a preset threshold. The disease diagnosis unit (350) can determine the possibility of a musculoskeletal disease in the specific leg by applying the rule-based algorithm to detect whether the weight ratio placed on the specific leg decreases below a preset threshold. Here, the disease diagnosis unit (350) can determine the possibility of a disease by setting a normal load ratio based on the average weight distribution data of the pet and when the weight of the specific leg falls below the threshold.
[0081] In one embodiment, the disease diagnosis unit (350) may use a machine learning-based algorithm to correct the likelihood of disease by inputting long-term accumulated load data into a musculoskeletal disease diagnosis model when the weight distribution ratio applied to the specific leg is confirmed through a rule-based algorithm. Here, the disease diagnosis unit (350) may use a rule-based algorithm to detect whether the weight distribution ratio applied to the specific leg deviates from the normal range, and then input long-term accumulated load data into a machine learning-based musculoskeletal disease diagnosis model for more precise analysis to correct the likelihood of disease. For example, the disease diagnosis unit (350) may apply a rule-based algorithm to determine whether the load ratio of the specific leg decreases below a preset threshold when compared to the normal weight distribution of the pet, and input long-term accumulated load data into a machine learning model to learn the weight distribution change pattern and distinguish between temporary weight changes and disease progression.
[0082] In one embodiment, the disease diagnosis unit (350) can predict the likelihood of progression of a musculoskeletal disease by comparing and analyzing load data with past load data to monitor load changes on a specific leg and detecting the persistence of load changes over a certain period. The disease diagnosis unit (350) can determine the likelihood of disease progression by accumulating and storing load data for each leg of the pet for a certain period, analyzing the change pattern by comparing it with currently measured real-time load data, and evaluating whether the change is short-term or long-term when a tendency for the weight placed on a specific leg to decrease compared to the past appears. For example, the disease diagnosis unit (350) can measure load data for each leg of the pet at weekly intervals and determine that there is a high likelihood of disease progression if a continuous decrease in load is detected.
[0083] The display unit (370) can display a warning message regarding a musculoskeletal disease of a specific leg on the display. When the disease diagnosis unit (350) determines the possibility of a musculoskeletal disease of a specific leg, the display unit (370) can visually display an explanation regarding the possibility of the musculoskeletal disease on the display. For example, the display unit (370) can provide information regarding the musculoskeletal disease to the user by generating a warning message using text-based warning messages, color codes (e.g., red warning indicators), heatmaps, and graphs. Additionally, the display unit (370) can provide a warning message according to the expected stage of the musculoskeletal disease. For example, if the display unit (370) detects a minor abnormality in a specific leg of a pet, it can generate a warning message regarding the need for careful observation, such as, "The weight placed on the left hind leg is 10% lower than the normal range. It is possible that this is a change due to temporary fatigue, but observation is required to see if it changes continuously." It is not necessarily limited to this.
[0084] In one embodiment, the display unit (370) may provide a warning message recommending a veterinary examination when the reduction in load on a specific leg of a pet persists for a long period or when the possibility of progression of a musculoskeletal disease exceeds a threshold, and may provide a list of hospitals based on the user's location. For example, the display unit (370) may be linked with GPS or a network to detect the user's current location and search for and provide a list of hospitals specializing in pet care or hospitals capable of orthopedic treatment. Here, the display unit (370) may generate a list of hospitals based on the musculoskeletal disease of the pet, but is not limited thereto; if an emergency situation is detected, it may prioritize recommending hospitals that operate 24 hours a day or hospitals capable of emergency treatment, and may be linked to allow the guardian to immediately make a phone call or make an online reservation with the selected hospital.
[0085] In one embodiment, the display unit (370) may display the likelihood of musculoskeletal disease and the level of suspected disease in the pet in the form of a heatmap or graph based on the possibility of disease progression in a specific leg. The display unit (370) may analyze the weight placed on each leg of the pet and provide this to the user by expressing it in color if the load placed on a specific leg deviates from the normal distribution. For example, the display unit (370) may display a leg showing a normal weight distribution in green, a leg with slightly reduced weight in yellow, and a leg with severely reduced weight in red. Additionally, the display unit (370) may provide a graph of weight distribution change over time by displaying the degree of change in the ratio of weight placed on a specific leg over a certain period (e.g., 1 week to 1 month, etc.) in the form of a line graph.
[0086] In one embodiment, the display unit (370) visualizes the load change by leg in the form of a heatmap or graph to intuitively display the level of suspected disease, and can display real-time load data and past load data together for comparison. Here, the display unit (370) can visually provide the user with changes in the pet's condition by comparing the currently measured real-time load data with past data. For example, the display unit (370) can analyze the weight transfer trend by leg based on a machine learning model by comparing with past data and provide a detailed analysis report on the pet's load change.
[0087] The control unit (390) controls the overall operation of the pet musculoskeletal disease diagnosis assistance device (130) and can manage the control flow or data flow between the load data collection unit (310), the weight ratio calculation unit (330), the disease diagnosis unit (350), and the display unit (370).
[0089] FIG. 4 is a flowchart illustrating the functional configuration of a diagnostic assistance device for musculoskeletal diseases in companion animals according to the present invention.
[0090] Referring to FIG. 4, the pet musculoskeletal disease diagnostic aid device (130) can measure the load applied to a plurality of legs of the pet through a pressure sensor array (120) placed on a plate (110) (step S410). The pet musculoskeletal disease diagnostic aid device (130) can collect load data measured through the pressure sensor array (120) based on a load data collection unit (310) (step S430). The pet musculoskeletal disease diagnostic aid device (130) can process the load data based on a weight ratio calculation unit (330) to calculate the ratio of the relative load applied to each leg relative to the total body weight of the pet (step S450).
[0091] The pet musculoskeletal disease diagnostic aid device (130) can analyze the weight ratio based on the disease diagnosis unit (350) to detect whether the weight ratio placed on a specific leg decreases below a preset threshold and predict the possibility of disease progression in the specific leg (step S470). The pet musculoskeletal disease diagnostic aid device (130) can display the possibility of musculoskeletal disease and the level of suspected disease in the pet in the form of a heatmap or graph based on the possibility of disease progression in the specific leg based on the display unit (370) (step S490).
[0093] FIG. 5 is a drawing illustrating an embodiment of a diagnostic assistance device for musculoskeletal diseases in companion animals.
[0094] Referring to FIG. 5, the musculoskeletal disease diagnostic aid device (130) for pets may include a plate (110) designed to allow a pet to stand on it, and the plate (110) may include a pressure sensor array (120) for measuring the load of the pet. Additionally, the musculoskeletal disease diagnostic aid device (130) for pets may be formed as a railing or guardrail structure for the safety of the pet and may serve to guide the pet to not move.
[0095] In one embodiment, the pet musculoskeletal disease diagnostic aid device (130) is implemented by including a pressure sensor array (120) capable of individually measuring the weight of each leg on a plate (110), thereby allowing the weight applied to the four legs to be measured in real time while the pet is standing naturally. Additionally, the pet musculoskeletal disease diagnostic aid device (130) can determine whether there is a musculoskeletal disease by detecting an anomaly in the pet's weight distribution based on the measured load data. For example, the pet musculoskeletal disease diagnostic aid device (130) can record load changes over a certain period to analyze long-term weight loss patterns and predict the likelihood of disease progression by comparing and analyzing the real-time measured load data with past data.
[0096] Additionally, the pet musculoskeletal disease diagnostic aid device (130) can display real-time weight data, load distribution, analysis results, etc. of the pet by providing a display screen so that the user can visually check the weight distribution of the pet. Here, the pet musculoskeletal disease diagnostic aid device (130) can record load changes over a certain period to analyze long-term weight loss patterns and provide a message recommending a veterinary examination to the guardian if there is a high possibility of disease progression. For example, the pet musculoskeletal disease diagnostic aid device (130) can provide a graphic interface that allows visual checking of the pet's weight distribution, and, for example, can provide load ratios by leg through a heatmap or graph. Additionally, the pet musculoskeletal disease diagnostic aid device (130) can provide a warning message to the user on the display if the weight placed on a specific leg decreases or increases abnormally.
[0098] Although the present invention has been described above with reference to preferred embodiments, those skilled in the art will understand that various modifications and changes can be made to the invention without departing from the spirit and scope of the invention as described in the following claims. Explanation of the symbols
[0100] 100: Companion Animal Musculoskeletal Disease Diagnostic Assistance System 110: Plate 120: Pressure sensor array 130: Diagnostic assistance device for musculoskeletal diseases in companion animals 150: Database 210: Processor 230: Memory 250: User I / O 270: Network I / O Section 290: Communication port section 310: Load data acquisition unit 330: Weight ratio calculation unit 350: Disease Diagnosis Department 370: Display section 390: Control unit
Claims
Claim 1 A musculoskeletal disease diagnosis aid for a pet, comprising: a plate; a pressure sensor array disposed on the plate to measure loads applied to a plurality of legs of a pet; a load data collection unit for collecting load data for the loads; a weight ratio calculation unit for calculating a weight ratio between the load data; a disease diagnosis unit for diagnosing the presence or absence of a musculoskeletal disease in a specific leg based on the weight ratio; and a display unit for displaying a warning message regarding the musculoskeletal disease of the specific leg on a display. Claim 2 A diagnostic aid for musculoskeletal diseases in companion animals, wherein, in claim 1, the pressure sensor array is implemented as a two-dimensional array of force-sensitive resistors (FSR), and the corresponding load is calculated by summing the pressures measured in the sensing area of the force-sensitive resistors for each of the plurality of legs. Claim 3 A diagnostic aid for musculoskeletal diseases in pets according to claim 2, wherein the pressure sensor array detects an overlay phenomenon in a sensing area relating to a specific leg among the plurality of legs, and when the overlay phenomenon is detected, displays a re-measurement request message on the display. Claim 4 A diagnostic aid for musculoskeletal diseases in companion animals, wherein, in claim 1, the load data collection unit performs multiple sampling on the load data at regular time intervals and applies a moving average filter to the load data to remove instantaneous outlier data. Claim 5 A diagnostic aid for musculoskeletal diseases in pets according to claim 1, wherein the weight ratio calculation unit calculates the relative ratio of the load placed on each of the plurality of legs based on the total body weight of the pet. Claim 6 A musculoskeletal disease diagnostic aid for pets according to claim 1, wherein the disease diagnostic unit detects that the weight distribution ratio placed on a specific leg decreases below a preset threshold through a rule-based algorithm and determines the possibility of a musculoskeletal disease of the specific leg. Claim 7 A musculoskeletal disease diagnosis assistance device for pets according to claim 6, wherein the disease diagnosis unit, when the weight distribution ratio applied to the specific leg is confirmed through the rule-based algorithm, inputs long-term accumulated load data into a musculoskeletal disease diagnosis model to correct the possibility of the disease. Claim 8 A diagnostic aid for musculoskeletal diseases in companion animals, wherein, in claim 1, the disease diagnosis unit compares and analyzes the load data with past load data to monitor load changes of a specific leg and detects the persistence of the load change over a certain period to predict the possibility of progression of the musculoskeletal disease. Claim 9 A diagnostic aid for musculoskeletal diseases in pets according to claim 1, wherein the display unit visualizes changes in load per leg in the form of a heatmap or graph to intuitively indicate the level of suspected disease, and displays real-time load data and past load data for comparison. Claim 10 A musculoskeletal disease diagnostic aid for a pet, comprising: a plate formed to allow a pet to stand on; a pressure sensor array disposed on the plate to measure the load placed on a plurality of legs of the pet; a load data collection unit that collects load data measured through the pressure sensor array; a weight ratio calculation unit that processes the load data to calculate the ratio of the relative load placed on each leg relative to the total body weight of the pet; a disease diagnosis unit that analyzes the weight ratio to detect whether the ratio of the body weight placed on a specific leg decreases below a preset threshold and predicts the possibility of disease progression in the specific leg; and a display unit that displays the possibility of musculoskeletal disease and the level of suspected disease of the pet in the form of a heatmap or graph based on the possibility of disease progression in the specific leg. Claim 11 A diagnostic aid for musculoskeletal diseases in companion animals, characterized in that, in claim 10, the load data collection unit performs multiple sampling on the load data at regular time intervals and applies a moving average filter to the load data to remove instantaneous outlier data. Claim 12 A diagnostic aid for musculoskeletal diseases in pets, characterized in that, in claim 10, the weight ratio calculation unit calculates the relative ratio of the load placed on each of the plurality of legs based on the total body weight of the pet. Claim 13 A musculoskeletal disease diagnostic aid for pets according to claim 1, wherein the disease diagnostic unit detects that the weight distribution ratio placed on a specific leg decreases below a preset threshold through a rule-based algorithm and determines the possibility of a musculoskeletal disease of the specific leg. Claim 14 A musculoskeletal disease diagnosis assistance device for pets, characterized in that, in claim 13, the disease diagnosis unit, when the weight distribution ratio applied to the specific leg is confirmed through the rule-based algorithm, inputs long-term accumulated load data into a musculoskeletal disease diagnosis model to correct the possibility of the disease. Claim 15 A diagnostic aid for musculoskeletal diseases in companion animals, characterized in that, in claim 10, the disease diagnosis unit compares and analyzes the load data with past load data to monitor load changes of a specific leg and detects the persistence of the load change over a certain period to predict the possibility of progression of the musculoskeletal disease.