Processing device, program, method and processing system
A portable processing system with a knee-attached acceleration sensor simplifies the estimation of knee joint health during exercise, addressing the burden of large-scale devices and enabling effective monitoring of osteoarthritis.
Patent Information
- Application Number
- JP2020157937
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2020-09-18
- Publication Date
- 2024-11-21
- Estimated Expiration
- 2040-09-18
AI Technical Summary
Existing large-scale evaluation devices for knee joint health during exercise impose a heavy burden on users with knee symptoms, such as osteoarthritis, making them difficult to use effectively.
A portable processing system that includes an acceleration sensor attached to the knee, which detects exercise-related acceleration data, processes it using a processor, and estimates the state of the knee joint, including osteoarthritis, through a memory and output interface, allowing for easier user interaction.
The system provides an easier and more accessible means for users to estimate and monitor the condition of their knee joints during exercise, facilitating better management of osteoarthritis and other symptoms.
Smart Images

Figure 0007587812000001 
Figure 0007587812000002 
Figure 0007587812000003
Abstract
Description
[Technical field]
[0001] The present disclosure relates to a processing device, a program, a method, and a processing system capable of estimating or assisting in the estimation of a state of a human being during exercise. [Background technology]
[0002] It has been known that the knee joint is the largest joint in the human body and plays a major role in ensuring smooth and stable leg movement, especially during exercise such as walking and changing direction. However, the knee joint can cause various symptoms due to wear and tear on the bones, cartilage, ligaments, etc. of the knee joint. For example, osteoarthritis of the knee caused by wear and tear on the cartilage of the knee joint is known to cause pain during exercise such as walking.
[0003] For example, Patent Document 1 describes an exercise evaluation device that evaluates the exercise state of a subject by analyzing image data captured from either the front or back and image data captured from either the left or right side of the subject, and calculates parameters related to body movement. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] JP 2016-140591 A Summary of the Invention [Problem to be solved by the invention]
[0005] However, using such a large-scale evaluation device to estimate or assist in estimating the state during exercise places a heavy burden on users who have symptoms in their knee joints. Therefore, in various embodiments of the present disclosure, a processing device, a program, a method, and a processing system that can be more easily used by users when estimating or assisting in estimating the state during exercise are provided. [Means for solving the problem]
[0006] According to one aspect of the present disclosure, there is provided a processing device including: an input / output interface configured to receive acceleration detected by a wired or wireless connection from an acceleration sensor attached to or around the knee of a human leg for detecting at least the acceleration during movement of the human; a memory configured to store the received acceleration and related information related to the knee in addition to a predetermined instruction command; an output interface configured to output the predetermined information; and a processor configured to perform processing to estimate a state of the human's knee based on the acceleration by executing the predetermined instruction command, identify the related information stored in the memory based on the estimated state, and output the identified related information to the output interface.
[0007] According to one aspect of the present disclosure, there is provided a processing device including: "an input / output interface configured to receive acceleration detected by a wired or wireless connection from an acceleration sensor attached to or around the knee of a human leg for detecting at least the acceleration of the human during movement; a memory configured to store the received acceleration and related information related to the knee in addition to a predetermined instruction command; an output interface configured to output the predetermined information; and a processor configured to identify the related information stored in the memory based on the acceleration by executing the predetermined instruction command, and to process the identified related information to the output interface."
[0008] According to one aspect of the present disclosure, there is provided a processing device including: "an input / output interface configured to receive acceleration detected by a wired or wireless connection from an acceleration sensor attached to or around the knee of a human leg for detecting at least the acceleration of the human during movement; a memory configured to store the received acceleration and related information related to the knee in addition to a predetermined instruction command; an output interface configured to output the predetermined information; and a processor configured to estimate a degree of osteoarthritis of the human based on the acceleration by executing the predetermined instruction command, identify the related information stored in the memory based on the estimated degree, and output the identified related information to the output interface."
[0009] According to one aspect of the present disclosure, there is provided a program that causes a computer including an input / output interface configured to receive acceleration detected by a wired or wireless connection from an acceleration sensor attached to or around the knee of a human leg for detecting at least the acceleration during movement of the human, a memory configured to store the received acceleration and related information related to the knee, and an output interface configured to output predetermined information, to function as a processor configured to estimate a state of the human's knee based on the acceleration, identify the related information stored in the memory based on the estimated state, and output the identified related information to the output interface.
[0010] According to one aspect of the present disclosure, there is provided a program that causes a computer including an input / output interface configured to receive acceleration detected by a wired or wireless connection from an acceleration sensor attached to or around the knee of a human leg for detecting at least the acceleration during movement of the human, a memory configured to store the received acceleration and related information related to the knee, and an output interface configured to output predetermined information, to function as a processor configured to estimate a state of the human's knee based on the acceleration, identify the related information stored in the memory based on the estimated state, and output the identified related information to the output interface.
[0011] According to one aspect of the present disclosure, there is provided a program that causes a computer including an input / output interface configured to receive acceleration detected by a wired or wireless connection from an acceleration sensor attached to or around the knee of a human leg for detecting at least the acceleration of the human during movement, a memory configured to store the received acceleration and related information related to the knee, and an output interface configured to output predetermined information, to function as a processor configured to identify the related information stored in the memory based on the acceleration, and to perform processing to output the identified related information to the output interface.
[0012] According to one aspect of the present disclosure, there is provided a method for a computer including an input / output interface configured to receive acceleration detected by a wired or wireless connection from an acceleration sensor attached to or around the knee of a human leg for detecting at least the acceleration during movement of the human, a memory configured to store the received acceleration and related information related to the knee in addition to predetermined instructions, and an output interface configured to output predetermined information, the method being performed by a processor executing the predetermined instructions, the method including the steps of: estimating a state of the human's knee based on the acceleration; identifying the related information stored in the memory based on the estimated state; and outputting the identified related information to the output interface.
[0013] According to one aspect of the present disclosure, there is provided a method for a computer including an input / output interface configured to receive acceleration detected by a wired or wireless connection from an acceleration sensor attached to or around the knee of a human leg for detecting at least the acceleration of the human during movement, a memory configured to store the received acceleration and related information related to the knee in addition to predetermined instructions, and an output interface configured to output predetermined information, the method being performed by a processor executing the predetermined instructions, the method including a step of identifying the related information stored in the memory based on the acceleration, and a step of outputting the identified related information to the output interface.
[0014] According to one aspect of the present disclosure, there is provided a method for a computer including an input / output interface configured to receive acceleration detected by a wired or wireless connection from an acceleration sensor attached to or around the knee of a human leg for detecting at least the acceleration of the human during movement, a memory configured to store the received acceleration and related information related to the knee in addition to predetermined instructions, and an output interface configured to output predetermined information, the method being performed by a processor executing the predetermined instructions, the method including the steps of: estimating a degree of osteoarthritis of the human based on the acceleration; identifying the related information stored in the memory based on the estimated degree; and outputting the identified related information to the output interface. Effect of the Invention
[0015] According to the present disclosure, it is possible to provide a processing device, a program, a method, and a processing system that can be more easily used by a user when estimating or assisting in the estimation of a state during exercise.
[0016] It should be noted that the above effects are merely illustrative for the convenience of explanation and are not limiting. In addition to or instead of the above effects, any effect described in this disclosure or any effect obvious to a person skilled in the art may be achieved. [Brief description of the drawings]
[0017] [Figure 1] FIG. 1 is a diagram showing a state in which a processing system 1 according to the present disclosure is in use. [Diagram 2] FIG. 2 is a schematic diagram of a processing system 1 according to an embodiment of the present disclosure. [Diagram 3] FIG. 3 is a block diagram showing a configuration of the processing system 1 according to the embodiment of the present disclosure. [Figure 4] FIG. 4 is a diagram showing the appearance of a detection device 200 according to an embodiment of the present disclosure. [Diagram 5]FIG. 5 is a diagram showing the appearance of an assisting device 400 according to an embodiment of the present disclosure. [Figure 6] FIG. 6 is a diagram showing an example of output values detected by the detection device 200 according to an embodiment of the present disclosure. [Figure 7A] FIG. 7A is a diagram illustrating an example of an acceleration table stored in the processing device 100 according to an embodiment of the present disclosure. [Figure 7B] FIG. 7B is a diagram illustrating an example of a user table stored in the processing device 100 according to an embodiment of the present disclosure. [Figure 7C] FIG. 7C is a diagram illustrating an example of a KAM conversion table stored in the processing device 100 according to an embodiment of the present disclosure. [Figure 7D] FIG. 7D is a diagram showing an example of a prognosis conversion table stored in the processing device 100 according to an embodiment of the present disclosure. [Figure 7E] FIG. 7E is a diagram illustrating an example of an engine table stored in the processing device 100 according to an embodiment of the present disclosure. [Figure 7F] FIG. 7F is a diagram illustrating an example of an auxiliary information table stored in the processing device 100 according to an embodiment of the present disclosure. [Figure 8] FIG. 8 is a diagram showing a process flow executed in the processing device 100 according to the embodiment of the present disclosure. [Figure 9] FIG. 9 is a diagram showing a process flow executed in the processing device 100 according to the embodiment of the present disclosure. [Figure 10] FIG. 10 is a diagram showing a process flow executed in the processing device 100 according to an embodiment of the present disclosure. [Figure 11] FIG. 11 is a diagram showing a process flow executed in the processing device 100 according to an embodiment of the present disclosure. [Figure 12] FIG. 12 is a diagram illustrating an example of acceleration detected by the detection device 200 according to an embodiment of the present disclosure. [Figure 13] FIG. 13 is a diagram showing a process flow executed in the processing device 100 according to an embodiment of the present disclosure. [Figure 14]FIG. 14 is a diagram showing an example of a screen displayed on the processing device 100 according to an embodiment of the present disclosure. [Figure 15] FIG. 15 is a diagram showing an example of a screen displayed on the processing device 100 according to an embodiment of the present disclosure. [Figure 16] FIG. 16 is a diagram showing an example of a screen displayed on the processing device 100 according to an embodiment of the present disclosure. [Figure 17] FIG. 17 is a diagram illustrating a process flow for generating a trained estimation model according to an embodiment of the present disclosure. [Figure 18] FIG. 18 is a diagram showing a processing flow executed in the processing device 100 according to an embodiment of the present disclosure. [Figure 19] FIG. 19 is a diagram showing the correlation between the actually measured acceleration and the KAM value. [Figure 20] FIG. 20 is a diagram showing the correlation between the actually measured output value and the KAM value. [Figure 21] FIG. 21 is a diagram showing the correlation between the actually measured output value and the KAM value. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0018] Various embodiments of the present disclosure will now be described with reference to the accompanying drawings, in which common elements are designated by the same reference numerals.
[0019] 1. Overview of Processing System 1 The processing system 1 according to the present disclosure includes a processing device 100 and a detection device 200, and is used to estimate or assist in estimating the condition of the knee of a user (human) by processing an output value detected by the detection device 200 attached to the user in the processing device 100. In particular, the processing system 1 is attached to the knee of the user or its surroundings, and is used to estimate or assist in estimating the degree and prognosis of knee osteoarthritis using an output value detected by the detection device 200 during the user's exercise. Therefore, hereinafter, a case where the processing system 1 according to the present disclosure is used to estimate or assist in estimating the degree and prognosis of knee osteoarthritis will be mainly described. However, the degree and prognosis of knee osteoarthritis are only examples of the condition, and the attachment position of the detection device is also only one example.
[0020] FIG. 1 is a diagram showing a state in which the processing system 1 according to the present disclosure is used. Specifically, it is a diagram showing a state in which the detection device 200 of the processing system 1 is attached to a user 10 and used. According to FIG. 1, the detection device 200a of the processing system 1 is attached to a lower part of the right knee 11a of the right leg 12a of the user 10 by wrapping the assisting tool 400a around the right leg 12a. Similarly, the detection device 200b of the processing system 1 is attached to a lower part of the left knee 11b of the left leg 12b of the user 10 by wrapping the assisting tool 400b around the left leg 12b. After that, the user wearing the detection devices 200a and 200b is made to walk in a predetermined direction, and the detection devices 200a and 200b detect an output value (e.g., acceleration) generated during this walking motion. Then, the detection devices 200a and 200b transmit the detected output values to the processing device 100 of the processing system 1 (not shown in FIG. 1).
[0021] In the present disclosure, the user to whom the detection device 200 is attached may include any human being, such as a patient, a test subject, or a person to be diagnosed. The detection device 200 according to the present disclosure may be used not only in a medical institution, but also in any place, such as a sports gym, an osteopathic clinic, or an osteopathic clinic, or even the user's workplace or home, and therefore the attributes of the person to whom the detection device 200 is attached do not matter. In the present disclosure, the operator simply means a person who operates the processing device 100. Therefore, the operator may be the same as the user described above, or may be a different person from the user, such as a medical professional or a gym trainer.
[0022] 1 shows an example where the detection device 200a or 200b is attached below the knee (front side), but it may be attached above the knee, on the knee, or on another part of the leg. Also, the detection device 200a or 200b is not limited to being attached on the front side of the leg 12a or 12b, but may be attached on either the rear side or the side. Furthermore, while FIG. 1 shows an example where two detection devices 200, detection devices 200a and 200b, are used, the number of detection devices 200 may be one on one side of a leg, or two or more may be attached at multiple positions on the leg 12a and / or 12b.
[0023] Typically, an acceleration sensor is used as the detection device 200 to detect acceleration during movement. However, it is not limited to an acceleration sensor, and any sensor capable of detecting the movement of the user 10, particularly the bending and straightening of the knees, such as a gyro sensor, a geomagnetic sensor, or a stretch sensor, can be used, and the output value corresponding thereto can be used to estimate or assist in estimating the state of movement. It is also possible to use a combination of multiple sensors, such as an acceleration sensor and a gyro sensor.
[0024] Moreover, the state estimated or assisted in estimation by the processing system 1 is the state during exercise. This exercise is typically walking by the user, but may also include various other exercises such as running, bending and stretching, jumping, etc. And, it is not necessary to perform these exercises only for estimating the state or assisted in estimating the state, and for example, the detection device 200 may be worn by the user 10 on a daily basis to detect the output value during exercise during daily life.
[0025] The assisting tool 400 may be anything that can assist the user in attaching the detection device 200 to the user. Typically, a flexible band-shaped body as shown in Fig. 5 is used, but it may be a bandage, taping tape, dressing, bandage, wound dressing, adhesive tape, supporter, etc. Furthermore, the assisting tool 400 does not need to be configured as a separate body that can be separated from the detection device 200, and a double-sided tape directly attached to the detection device 200, a wristwatch-like band, etc. can also be used as the assisting tool 400.
[0026] 2. Configuration of Processing System 1 FIG. 2 is a schematic diagram of a processing system 1 according to an embodiment of the present disclosure. The processing system 1 includes a detection device 200 attached to a user and detecting an output value during the user's exercise, and a processing device 100 communicably connected to the detection device 200 and processing the detected output value. Such a processing system 1 is connected to a server device 300 via a network for wireless communication. The server device 300 includes a processor, a memory, a communication interface, etc., and appropriately transmits and receives instructions, commands, information, etc. required for processing by the processing device 100. Typically, upon receiving a request from the processing device 100, the server device 300 transmits related information such as organization information and supplementary information stored in the server device 300, and updates and stores the information by receiving updated information from time to time. The processing device 100 and the detection device 200 will be described in detail later.
[0027] FIG. 3 is a block diagram showing a configuration of a processing system 1 according to an embodiment of the present disclosure. According to FIG. 3, the processing system 1 includes a processing device 100 and a detection device 200 communicably connected to the processing device 100 wirelessly or by wire. The processing device 100 receives an operation input by a user and controls detection of an output value by the detection device 200 during exercise. The processing device 100 also processes the output value detected by the detection device 200 to estimate or assist the user's state during exercise. Furthermore, the processing device 100 allows the user to check information indicating the output value detected by the detection device 200, a value calculated based on the output value, and the result of the estimation or assistance.
[0028] The processing system 1 includes a processing device 100 including a processor 111, a memory 112, an operation input interface 113, a display 114, and a communication interface 115, and a detection device 200 including a processor 211, a sensor 212, a memory 213, and a communication interface 214. These components are electrically connected to each other via a control line and a data line. The processing system 1 does not need to include all the components shown in FIG. 3, and it is possible to configure the processing system 1 by omitting some of the components, or to add other components. For example, the processing system 1 can include a battery for driving each component, a communication interface for transmitting the results of processing by the processing system 1 to the outside, and receiving instructions and commands from the outside, and the like.
[0029] The processing system 1 includes the processing device 100 and the detection device 200 as separate, separable entities. However, the present invention is not limited to this, and the processing device 100 and the detection device 200 can be configured as an integrated unit, for example, as in a wearable terminal device. The processing device 100 is not limited to being configured as a single component, and when at least a part of its processing is executed by another component (e.g., a cloud server device) connected by wire or wirelessly, the processing device 100 may be referred to as the processing device 100 including the other component.
[0030] First, the processing device 100 will be described with reference to Fig. 3. The processor 111 functions as a control unit that controls the other components of the processing system 1 based on a program stored in the memory 112. The processor 111 controls the driving of each component of the detection device 200 based on the program stored in the memory 112, stores output values received from the detection device 200 in the memory 112, and processes the stored output values. Specifically, the processor 111 executes the following processes based on the programs stored in the memory 112: receiving an instruction input from the user to the operation input interface 113, turning on the detection device 200, and instructing the sensor 212 to perform detection; receiving an output value transmitted from the detection device 200 via the communication interface 115 and storing it in the memory 112; estimating or assisting in estimating the state of the knee joint during the user's exercise based on the output value stored in the memory 112; outputting an output value after the leg lands among the output values received from the detection device 200; estimating or assisting in the degree or prognosis of knee osteoarthritis based on the output value received from the detection device 200; outputting related information according to the output value received from the detection device 200, the state of the knee joint, or the degree of knee osteoarthritis; updating related information at a predetermined timing; and the like. The processor 111 is mainly composed of one or more CPUs, but may be appropriately combined with a GPU or the like.
[0031] The memory 112 is composed of a RAM, a ROM, a non-volatile memory, a HDD, etc., and functions as a storage unit. The memory 112 stores instructions and commands for various controls of the processing system 1 according to this embodiment as a program. Specifically, the memory 112 stores programs for the processor 111 to execute the following processes: accepting an instruction input to the operation input interface 113 by a user, turning on the detection device 200, and instructing detection by the sensor 212; receiving an output value transmitted from the detection device 200 via the communication interface 115 and storing it in the memory 112; estimating or assisting the state of the knee joint during the user's exercise based on the output value stored in the memory 112; outputting an output value after the leg lands among the output values received from the detection device 200; estimating or assisting the degree or prognosis of knee osteoarthritis based on the output value received from the detection device 200; outputting related information according to the output value received from the detection device 200, the state of the knee joint, or the degree of knee osteoarthritis; updating related information at a predetermined timing. In addition to the program, the memory 112 also stores an acceleration table, a user table, a KAM conversion table, an engine table, an auxiliary information table, etc. When machine learning is used for predicting the KAM value or estimating the state of the knee joint, the memory 112 stores a learned KAM value estimation model. The memory 112 may be a storage medium connected to an external device for communication, or may be a combination of such storage media.
[0032] The operation input interface 113 functions as an operation input unit that accepts user's instruction input to the processing device 100 and the detection device 200. Examples of the operation input interface 113 include a "start button" for instructing the detection device 200 to start or end detection, a "confirmation button" for making various selections, a "back / cancel button" for returning to the previous screen or canceling an input confirmation operation, a cross key button for moving icons and the like displayed on the display 114, an on / off key for turning the power of the processing device 100 on and off, and the like. Note that the operation input interface 113 may also use a touch panel that is superimposed on the display 114 and has an input coordinate system corresponding to the display coordinate system of the display 114. The method of detecting the user's instruction input by the touch panel may be any method, such as a capacitance type or a resistive film type.
[0033] Display 114 functions as a display unit for displaying output values detected by detection device 200 or values calculated based on the output values, and for displaying results estimated based on the output values. It is configured with a liquid crystal panel, but is not limited to a liquid crystal panel and may be configured with an organic EL display, a plasma display, or the like.
[0034] The communication interface 115 functions as a communication unit for transmitting and receiving various commands related to the start of detection and the like, output values detected by the detection device 200, and the like to the detection device 200 connected by wire or wirelessly, and for transmitting and receiving information to and from the server device 300. Examples of the communication interface 115 include various things such as a connector for wired communication such as USB or SCSI, a transmitting and receiving device for wireless communication such as LTE, Bluetooth (registered trademark), wifi, or infrared, various connection terminals for printed circuit boards or flexible circuit boards, and combinations thereof.
[0035] An example of such a processing device 100 is a portable terminal device capable of wireless communication, such as a smartphone. However, the processing device 100 can also be suitably applied to any other device capable of executing the processing according to the present disclosure, such as a tablet terminal, a laptop computer, a desktop computer, a feature phone, a personal digital assistant, or a PDA.
[0036] Next, the detection device 200 will be described. The processor 211 functions as a control unit that controls other components of the detection device 200 based on a program stored in the memory 213. Based on the program stored in the memory 213, the processor 211 specifically executes a process of controlling detection of an output value by the sensor 212, a process of storing the detected output value in the memory 213, and a process of transmitting the output value stored in the memory 213 to the processing device 100 via the communication interface 214. The processor 111 is mainly composed of one or more CPUs, but may be appropriately combined with a GPU or the like.
[0037] The memory 213 is composed of a RAM, a ROM, a non-volatile memory, a HDD, etc., and functions as a storage unit. The memory 213 stores instructions and commands for various controls of the detection device 200 according to this embodiment as a program. Specifically, the memory 213 stores a program for the processor 211 to execute a process of controlling detection of an output value by the sensor 212, a process of storing the detected output value in the memory 213, a process of transmitting the output value stored in the memory 213 to the processing device 100 via the communication interface 214, and the like. In addition to the program, the memory 213 also stores the output value detected by the sensor 212. Note that the memory 112 may use a storage medium connected to an external device in a communicable manner, or may be used in combination with such storage media.
[0038] The sensor 212 is driven by an instruction from the processor 211, and functions as a detection unit for detecting an output value during the user's exercise. An acceleration sensor is used as an example of the sensor 212. The acceleration sensor detects the rate of change of the amount of movement (speed) per unit time. There are various types of acceleration sensors, such as a capacitance type, a piezoelectric type, and a heat detection type, and any type can be suitably used. It is preferable that the acceleration sensor detects at least the acceleration in the horizontal direction, and further detects the acceleration in the vertical direction and / or the acceleration in the depth direction. A gyro sensor can also be used in combination with the acceleration sensor for the sensor 212. In this case, the gyro sensor can obtain three output values, namely, the angular velocity with respect to the horizontal axis, the angular velocity with respect to the vertical axis, and the angular velocity with respect to the depth axis. That is, in addition to the total of three accelerations in the horizontal direction, the vertical direction, and the depth direction, the above three angular velocities (that is, output values of a total of six axes) can be used. In addition to this example, it is possible to use a suitable combination of sensors capable of detecting the movements of the user 10, particularly the bending and straightening of the knees and shaking, such as a geomagnetic sensor and an expansion and contraction sensor.
[0039] The communication interface 214 functions as a communication unit for transmitting and receiving various commands related to the start of detection and the like, and output values detected by the detection device 200, to the processing device 100 connected by wire or wirelessly. Examples of the communication interface 214 include connectors for wired communication such as USB and SCSI, transmitting and receiving devices for wireless communication such as LTE, Bluetooth (registered trademark), wifi, and infrared, various connection terminals for printed circuit boards and flexible circuit boards, and combinations thereof.
[0040] Fig. 4 is a diagram showing the appearance of the detection device 200 according to an embodiment of the present disclosure. Specifically, an example of the appearance of the detection device 200 when an acceleration sensor is used as the sensor 212 of the detection device 200 is shown. According to Fig. 4, the detection device 200 has a power switch 216 for switching the power of the detection device 200 on / off on the upper surface thereof. The detection device 200 also has a USB terminal 215 as an example of the communication interface 214. Furthermore, the detection device 200 includes an indicator 217 for notifying a driving state such as an abnormality.
[0041] Such a detection device 200 is attached to the knee or its surroundings (typically, the front of the lower knee) of a user using an assisting tool 400, for example. FIG. 5 is a diagram showing the appearance of the assisting tool 400 according to an embodiment of the present disclosure. The assisting tool 400 has a length in the short side direction corresponding to the length of the detection device 200 in the short side direction, and a length in the long side direction sufficient to cover the circumference of the user's leg. Such an assisting tool 400 is typically produced by a flexible sheet-like material. The assisting tool 400 has a pair of fixing members 412 and 413 at both ends. An example of such fixing members 412 and 413 is a hook-and-loop fastener, but any other member capable of joining ends to each other, such as a button or an adhesive tape, can be used.
[0042] The assisting tool 400 has a bag member 414 for accommodating the detection device 200 at approximately the center in the longitudinal direction. The bag member 414 has a size corresponding to the size of the detection device 200. Therefore, by inserting the detection device 200 into the bag member 414 of the assisting tool 400 and attaching the assisting tool 400 with the detection device 200 inserted therein to the leg, it is possible to prevent the detection device 200 from shifting position due to movement inside the assisting tool 400 and to appropriately detect only vibrations due to movement. In other words, the bag member 414 is used to more reliably position the detection device 200.
[0043] It should be noted that such an auxiliary tool 400 is merely an example. As described above, the auxiliary tool 400 may be a bandage, a taping tape, a dressing, a bandage, a wound dressing, an adhesive tape, a supporter, etc. Furthermore, the auxiliary tool 400 does not need to be configured as a separate body that can be separated from the detection device 200, and a double-sided tape directly attached to the detection device 200, a wristwatch-like band, etc. can also be used as the auxiliary tool 400.
[0044] FIG. 6 is a diagram showing an example of an output value detected by the detection device 200 according to an embodiment of the present disclosure. Specifically, an acceleration sensor is used as the sensor 212 of the detection device 200, and is attached to the front of the user's lower knee (for example, only the left leg) to detect both vertical acceleration (vertical axis direction in FIG. 6) and horizontal acceleration (horizontal axis direction in FIG. 6) during walking. Generally, in walking, after the heel of one leg (for example, the left leg) of the user lands on the ground, the knee joint in the extended state begins to bend, and the user's body including the knee begins to move in the direction of travel. After that, the leg that landed at the heel reaches a state where almost the entire sole of the foot is landed on the ground. Next, as the user continues walking, the heel gradually begins to separate from the ground, and finally, the toes move as if kicking the ground, resulting in the toes being completely separated from the ground. On the other hand, in the opposite leg (for example, the right leg), the toes begin to lift off the ground when the heel of the left leg hits the ground, and the heel lands on the ground when the toes of the left leg begin to lift off the ground. In this way, walking is performed by periodically repeating the stance phase from when the heel hits the ground to when the toes lift off, and the lift off phase from when the toes lift off to when the heel hits the ground.
[0045] In Fig. 6, when focusing on the acceleration in the vertical direction (i.e., the longitudinal axis direction), the first acceleration peak is detected when the heel of one leg lands on the ground, and then the next acceleration peak is detected when the heel of the opposite leg lands on the ground. Therefore, the period from the rise of the first peak to the fall of the next peak can be called the stance phase S1. These two peaks are then detected periodically each time a stance phase such as stance phase S2 occurs.
[0046] At this time, when focusing on the horizontal acceleration (i.e., the horizontal axis), the first peak is detected within a predetermined period after the start of the stance phase. For example, in the case of a disease such as osteoarthritis of the knee, when the stance phase begins and a load is applied to the knee joint, a horizontal thrust occurs. Therefore, by detecting the horizontal movement after the start of the stance phase, it is possible to effectively estimate the condition of the knee joint or the condition of osteoarthritis of the knee.
[0047] Here, the KAM (external knee varus moment) value is used as an index for evaluating the degree and prognosis of knee osteoarthritis. It is said that if the KAM value is above a certain value, the risk of progression of osteoarthritis of the knee is high after a certain period of time, and if it is below another certain value, the risk of progression is low (Reference 1: T Miyazakira, Dynamic load at baseline can predict radiographic disease progression in medial compartment knee osteoarthritis, Ann Rheum Dis., 2002, No. 61, pp. 617-622, Reference 2: Kim L Bennell et all, Higher dynamic medial knee load predicts greater cartilage loss over 12 months in medial knee osteoarthritis, Ann Rheum Dis., 2011, No. 70, pp. 1770-1774, Reference 3: Nicholas M. Brisson, Baseline Knee Adduction Moment Interacts With Body Mass Index to Predict Loss of Medial Tibial Cartilage Volume Over 2.5 Years in Knee Osteoarthritis, JOURNAL OF ORTHOPAEDIC RESEARCH, 2017, NOVEMBER, pp.2476-2483). Here, there is a certain correlation between the KAM value and the horizontal acceleration detected by an acceleration sensor attached to the knee or around the knee. Therefore, by calculating the KAM value from the detected horizontal acceleration, it is possible to estimate or assist the degree or prognosis of knee osteoarthritis. Specifically, after the start of the stance phases S1 and S2 specified by the vertical acceleration (i.e., the vertical axis), the values of the peak widths H1 and H2 of the horizontal acceleration (i.e., the horizontal axis) detected within the predetermined periods T1 and T2 are calculated, and the KAM value is estimated based on the values.
[0048] It was also found that when a user has symptoms of knee osteoarthritis, the time until a horizontal acceleration peak is detected is shorter and the number of peaks detected within a predetermined period after the start of the stance phase is greater than that of a user without the symptoms. Therefore, the times D1 and D2 until a horizontal acceleration peak is detected after the start of the stance phase S1 and S2, and the number of peaks detected within the predetermined periods T1 and T2, can be used as indicators for evaluating the degree and prognosis of knee osteoarthritis in place of or in combination with the peak widths H1 and H2.
[0049] In this way, by using the output values (vertical acceleration and horizontal acceleration) detected by the detection device 200 shown in Fig. 6, it is possible to estimate the KAM value and evaluate the state of the knee joint during human movement, specifically the degree of knee osteoarthritis and its prognosis. Among the output values detected by the detection device 200, the vertical acceleration is used to identify the human movement cycle, i.e., the stance phase. Therefore, other values can be used as long as they are synchronized with the horizontal acceleration value and the stance phase can be identified, and the vertical acceleration value is not necessarily required.
[0050] In the present disclosure, either of the following two types of "KAM value" can be used. There is a two-dimensional curve (KAM value curve) in which the horizontal axis is time and the vertical axis is the KAM value calculated at each time. In this case, the highest peak value (KAM peak value) detected in the stance phase can be used as the first KAM value. This KAM peak value can reflect the value at the moment when the largest force is applied to the knee joint in the stance phase. The area value (KAM area value) between the KAM value curve in the stance phase and the horizontal axis (straight line) can be used as the second KAM value. This KAM area value can reflect the value of the entire load applied to the knee joint in the stance phase. In fact, in the above-mentioned document 1, the KAM peak value is used to evaluate the degree and prognosis of osteoarthritis of the knee, and in the above-mentioned documents 2 and 3, the KAM area value is used to evaluate the degree and prognosis of osteoarthritis of the knee.
[0051] 3. Information stored in the processing device 100 FIG. 7A is a diagram showing an example of an acceleration table stored in the processing device 100 according to an embodiment of the present disclosure. The acceleration table is prepared for each user and stored in association with user ID information that identifies the user. FIG. 7A shows an example of an acceleration table for a user whose user ID information is "U1". According to FIG. 7A, the acceleration table stores acceleration information in association with time information. The "time information" is information that identifies the time at which each acceleration was measured in the detection device 200. The information may be specific date and time information using a timer included in the detection device 200, or may be the elapsed time from the start of measurement. The "acceleration information" is information indicating a specific acceleration value detected at the corresponding time information. When the "time information" and the "acceleration information" are detected by the detection device 200, they are transmitted from the detection device 200 and stored in the memory 112 of the processing device 100 that received them. In FIG. 7A, horizontal acceleration is typically stored in association with each time information as the acceleration information. However, the present invention is not limited to this, and in addition to the horizontal acceleration, the vertical acceleration may also be stored in association with each piece of time information.
[0052] FIG. 7B is a diagram showing an example of a user table stored in the processing device 100 according to an embodiment of the present disclosure. According to FIG. 7B, the user table stores user name information, peak number information, application time information, peak width information, KAM value information, prognosis information, and level information in association with user ID information. The "user ID information" is information generated each time a user to whom the detection device 200 is attached and acceleration is to be measured is newly registered, and is information unique to each user and is information for identifying each user. The "user name information" is information indicating the name of the user displayed, for example, on the display 114 of the processing device. The "peak number information" is information identified based on acceleration information stored in an acceleration table stored for each user ID information, and is information indicating the number of horizontal acceleration peaks detected within a predetermined period (for example, T1 and T2) in FIG. 6. The "application time information" is information specified based on the acceleration information stored in the acceleration table stored for each user ID information, and indicates the time (e.g., D1 and D2) from the start of the stance phase (e.g., S1 and S2) in FIG. 6 until the peak of the horizontal acceleration is detected. The "peak width information" is information specified based on the acceleration information stored in the acceleration table stored for each user ID information, and indicates the peak width of the horizontal acceleration detected within a predetermined period (e.g., D1 and D2) after the start of the stance phase (e.g., S1 and S2) in FIG. 6. The "KAM value information" is information estimated based on the peak width information and is used to evaluate the prognosis of knee osteoarthritis. The "prognosis information" is information specified based on the KAM value information and is information indicating the estimated result of the prognosis of knee osteoarthritis. The "level information" is information indicating the current knee condition, specifically the estimated result of the degree of knee osteoarthritis, estimated based on at least one of the peak number information, application time information, peak width information, and a combination thereof.
[0053] FIG. 7C is a diagram showing an example of a KAM conversion table stored in the processing device 100 according to an embodiment of the present disclosure. According to FIG. 7C, the KAM conversion table stores KAM value information in association with peak width information. The "peak width information" is information indicating the numerical range of each peak width. The "KAM value information" is information indicating an estimated value of the KAM value corresponding to the numerical range of each peak width. That is, from the peak width information stored in FIG. 7B, a numerical range that applies in the KAM conversion table in FIG. 7C is specified, and the KAM value information corresponding to the numerical range is calculated as an estimated value of the KAM value. Then, the estimated KAM value is stored as the KAM value information in FIG. 7B.
[0054] FIG. 7D is a diagram showing an example of a prognosis conversion table stored in the processing device 100 according to the embodiment of the present disclosure. According to FIG. 7D, the prognosis conversion table stores prognosis information in association with KAM value information estimated using the KAM conversion table of FIG. 7C. As described above, the "KAM value information" is information indicating each KAM value estimated using the KAM conversion table of FIG. 7C. The "prognosis information" is information indicating the evaluation result of the prognosis corresponding to each KAM value. That is, the prognosis evaluation result is calculated by referring to the prognosis conversion table of FIG. 7D from the KAM value information stored in FIG. 7B. Among the prognosis information, "good" means that the prognosis is good, "follow-up observation" means that follow-up observation is required to periodically check the degree of progression of knee osteoarthritis, and "progression" means that knee osteoarthritis is predicted to progress. In this embodiment, the prognosis is evaluated in three stages, but it is of course possible to further evaluate it in multiple stages, such as "fast progression" and "slow progression". The prognostic information evaluated using the prognostic conversion table is stored as the prognostic information of FIG. 7B.
[0055] FIG. 7E is a diagram showing an example of an institution table stored in the processing device 100 according to the embodiment of the present disclosure. The institution table is a table prepared in association with each of the prognosis information stored in FIG. 7D. That is, different institution tables are stored according to the prognosis information stored in FIG. 7D, and different information is stored in the institution tables. The example of FIG. 7E shows, as an example of the institution table, an institution table referenced when "progression" is selected as the prognosis information in FIG. 7B. The auxiliary information table stores information on medical institutions and doctors who can perform at least one of diagnosis and treatment, and information on institutions that support prognosis. Specifically, according to FIG. 7E, attribute information, location information, time information, and the like are stored in association with institution ID information. "Institution ID information" is information generated each time a new institution that is a source of information is registered, and is information unique to each institution, and is information for identifying each institution. "Attribute information" is information indicating the type of institution identified by each institution ID information. For example, "hospital" means that the institution is a hospital, "chiropractic clinic" means that the institution is a chiropractic clinic, and "gym" means that the institution is a sports gym. "Location information" is information indicating the location of the institution specified by each institution ID information. Examples of the location information include coordinate information such as latitude / longitude with a specific position as the origin, and address information. Time information is information indicating the opening time and regular holidays (days off consultations) of the institution specified by each institution ID information. This information is updated periodically or whenever new information is input. Note that, although attribute information and the like are given as examples of information stored in the institution table, it is of course possible to store other information as well. For example, various information such as the names of the attending physician and chief trainer, medical department information, treatment results information, evaluation information, and information on the appearance and internal view of the institution can be stored. Although not particularly illustrated, it is also possible to further store the institution table in association with each level information, similar to the prognosis information. In other words, it is possible to store different engine tables according to the level information stored in FIG. 7D, and store different information in the engine tables.
[0056] FIG. 7F is a diagram showing an example of an auxiliary information table stored in the processing device 100 according to the embodiment of the present disclosure. The auxiliary information table is a table prepared in association with each of the prognosis information stored in FIG. 7D. That is, different auxiliary information tables are stored according to the level information stored in FIG. 7D, and different information is stored in each of the auxiliary information tables. The example of FIG. 7F shows an auxiliary information table that is referred to when "progression" is selected as the prognosis information in FIG. 7B, as one example of the table. The auxiliary information table stores information for assisting doctors who perform at least one of diagnosis and treatment, or information for assisting users (patients) in purchasing items. Specifically, according to FIG. 7F, attribute information, content information, and the like are stored in association with auxiliary information ID information. "Auxiliary information ID information" is information generated each time information related to the prognosis of progressing knee osteoarthritis is registered, and is information unique to each piece of information, and is information for identifying each piece of information. "Attribute information" is information indicating the type of information identified by each auxiliary information ID information. For example, "treatment method" means that the information is related to the treatment method, "purchase of goods" means that the information is used to purchase goods such as instruments that are useful for suppressing the progression of osteoarthritis of the knee, and "paper" means that the information is related to the prognosis of osteoarthritis of the knee. "Content information" is information that indicates the specific content of the information specified by each auxiliary information ID information. For example, in the case of a treatment method, a link to a web page describing the treatment method and the specific treatment method are stored, in the case of a purchase of goods, detailed information on the goods and the address of the purchaser are stored, and in the case of a paper, the specific content of the paper, the author's name, and information on the affiliated institution are stored. This information is updated periodically or whenever new information is input. Although attribute information and the like are given as an example of information stored in the auxiliary information table, it is of course possible to store other information as well. For example, it is possible to store various things such as the experiences of other users, citation and cited information, etc. In addition, although not shown in particular, it is also possible to store an auxiliary information table in association with each level information, as with prognosis information.In other words, it is also possible to store different auxiliary information tables according to the level information stored in FIG. 7D, and to store different information in the auxiliary information tables.
[0057] 4. Processing flow executed by the processing device 100 [Processing related to mode selection] Fig. 8 is a diagram showing a process flow executed in the processing device 100 according to an embodiment of the present disclosure. Specifically, Fig. 8 shows a process flow executed by the processor 111 at a predetermined cycle after a program according to an embodiment of the present disclosure is started in the processing device 100.
[0058] First, when the processor 111 receives an interrupt signal indicating that an instruction input for starting the program has been accepted by the operation input interface 113, the processor 111 displays a top screen on the display 114 (S111). The top screen, which is not particularly shown, includes an icon for transitioning to a measurement mode for measuring an output value of a user in the detection device 200 and a result display mode for displaying the measurement results. Thereafter, the processor 111 determines whether or not a mode has been selected based on an interrupt signal indicating that an operation input by an operator to an icon has been accepted from the operation input interface 113 (S112). If it is determined that no mode has been selected, the processor 111 maintains the top screen displayed as it is and ends the processing flow.
[0059] On the other hand, if it is determined that a mode has been selected, processor 111 determines whether or not the measurement mode was selected based on the coordinates input by the operator (S113). If it is determined that the measurement mode is selected, processor 111 controls display 114 to display a measurement screen, and ends the processing flow. On the other hand, if it is determined that the measurement mode is not selected, processor 111 controls display 114 to display a result screen, and ends the processing flow.
[0060] Although not specifically shown in the figure, the measurement screen displays an area for inputting or selecting the user's user name information, user ID information, etc., as well as a start button icon for starting measurement.
[0061] [Processing related to starting measurement] FIG. 9 is a diagram showing a processing flow executed by the processing device 100 according to the embodiment of the present disclosure. Specifically, FIG. 9 shows a processing flow executed by the processor 111 at a predetermined cycle after the measurement mode is selected in FIG. 8 and the measurement screen is displayed. Although not particularly shown in FIG. 9, before the processing shown in FIG. 9, the measurer or user inputs or selects user name information, user ID information, and the like on the measurement screen, and the processor 111 stores the input or selected information in the memory 112. In addition, the detection device 200 is attached to the lower part of the knee of one leg of the user in advance by the aid 400, and the user is in a state where all preparations are completed for starting exercise (for example, walking). In addition, in the explanation of the processing flow from FIG. 9 onwards, for convenience of explanation, the case where the detection device 200 is attached to only the knee of one leg will be explained.
[0062] 9, the processor 111 judges whether or not an operation input to the measurement button icon by the operator has been accepted by the operation input interface 113 (S211). Then, when it is judged that an operation input to the start button icon has been accepted, the processor 111 controls the communication interface 115 to transmit a measurement start instruction signal for instructing the detection device 200 to start measurement (S212). After that, the processor 111 controls the display 114 to display a measurement standby screen (S213). Note that, although not shown in the figure, the measurement standby screen displays an end button icon for ending the measurement and the like.
[0063] Here, the processing on the side of the detection device 200 will be described. After being worn by a user, the processor 211 of the detection device 200 receives a measurement start signal via the communication interface 214, and drives the sensor 212 to start detecting acceleration at a predetermined cycle (FIG. 7A). The processor 211 then stores the detected acceleration as an output value in the memory 213 in association with the time of detection. The processor 211 then executes this processing until it receives a measurement end instruction signal from the processing device 100.
[0064] In the above description, the measurement start instruction signal is transmitted by detecting pressing of a start button displayed on the display 114. However, the present invention is not limited to this, and the signal may be transmitted by the processor 111 detecting pressing of a start button provided as a physical key in the operation input interface 113. In addition, for example, when a pressing operation of the power switch 216 of the detection device 200 is accepted, the detection device 200 may transmit a measurement start signal to the processing device 100, and then the processor 111 may perform control so as to display a measurement standby screen.
[0065] This completes the process flow relating to the start of measurement.
[0066] [Processing performed while waiting for measurement] Fig. 10 is a diagram showing a process flow executed in the processing device 100 according to the embodiment of the present disclosure. Specifically, Fig. 10 shows a process flow executed by the processor 111 at a predetermined cycle after the measurement standby screen is displayed in Fig. 9.
[0067] 10, the processor 111 receives an operation input to the end button icon by the operator via the operation input interface 113, and judges whether the measurement has ended (S311). If it is judged that the measurement has ended, the processor 111 controls the communication interface 115 to transmit a measurement end instruction signal to instruct the detection device 200 to end the measurement (S312).
[0068] Here, in the detection device 200 that has received a measurement end instruction signal from the processing device 100 via the communication interface 214, the processor 211 controls the sensor 212 to end the detection of acceleration. Then, the processor 211 controls the sensor 212 to transmit the output value and time information stored in the memory 213 until the end to the processing device 100 via the communication interface 214.
[0069] In the processing device 100, the processor 111 judges whether or not it has received the output value and time information from the detection device 200 via the communication interface 115 (S313). Then, if it is judged that it has been received, the processor 111 stores the received output value (acceleration information) in association with the user ID information input or selected on the measurement screen in the acceleration table of the memory 112 in correspondence with the time information (S314). Next, the processor 111 performs various estimation processes based on the output values stored in the memory 112 (S315). The details of this process will be described later. Then, the processor 111 stores various information obtained in the process of the estimation process in association with the user ID information in the user table of the memory 112 (S316).
[0070] In the above description, the measurement end instruction signal is transmitted by detecting pressing of an end button displayed on the display 114. However, the present invention is not limited to this, and the signal may be transmitted by the processor 111 detecting pressing of an end button provided as a physical key in the operation input interface 113. Also, for example, when a pressing operation of the power switch 216 of the detection device 200 is accepted, the detection device 200 may end the measurement and transmit an output value or the like to the processing device 100.
[0071] This completes the process flow performed during measurement standby.
[0072] [Estimation process] Fig. 11 is a diagram showing a process flow executed in the processing device 100 according to an embodiment of the present disclosure. Specifically, Fig. 11 shows a specific process flow of the estimation process performed in S315 of Fig. 10.
[0073] According to Fig. 11, the processor 111 first reads out acceleration information associated with the user ID information input or selected on the measurement screen from the acceleration table stored in the memory 112 (S411). Fig. 6 is an example of a curve generated based on the read acceleration information. Therefore, the following description will be made with reference to Fig. 6.
[0074] Next, processor 111 identifies each stance phase based on the read acceleration information (S412). Specifically, the first acceleration peak is detected from the acceleration in the vertical direction (i.e., the vertical axis direction in FIG. 6) among the read accelerations. This first peak is a peak detected when the leg on which detection device 200 is attached lands on the ground. Note that processor 111 may determine that this peak is the first peak when acceleration exceeding a predetermined threshold is detected, or may identify the peak by displaying the acceleration curve shown in FIG. 6 on display 114 and accepting an operation input from the operator. Thereafter, the process related to the detection of the peak is performed in the same manner.
[0075] Next, after the first peak is detected, a period of time during which only noise components are detected continues, and then a second peak is detected. This second peak is detected when the leg opposite to the leg on which the detection device 200 is attached lands on the ground. Therefore, the processor 111 determines that the period from the rise of the first peak to the detection of the fall of the second peak is the stance phase S1. Hereinafter, the period between the rise of the third peak and the fall of the fourth peak is specified as the stance phase S2, but further stance phases may be specified by detecting the fifth and subsequent peaks.
[0076] Next, the processor 111 sets a first threshold (time) for each of the identified stance phases S1 and S2 (S413). Specifically, for the period identified as the stance phase S1, the time from the start of the period until a predetermined period T1 has elapsed is set as the first threshold. This predetermined period T1 is preferably set to a period equivalent to 40% of the stance phase S1, more preferably a period equivalent to 25%. Similarly, the first threshold is also set for the stance phase S2. Note that the ratio of the stance phases S1 and S2 is used in setting the first threshold, but this is not limiting and a predetermined fixed value (for example, 50 ms after the start of the stance phase) may be used as the first threshold.
[0077] Next, the processor 111 detects a peak of acceleration in the horizontal direction (i.e., the horizontal axis direction in FIG. 6) during the period T1 up to the set first threshold (time), calculates the peak width, and stores the calculated peak width in the peak width information of the user table in association with the user ID information (S414). Specifically, a peak of acceleration in the horizontal direction is detected from the start of the stance phase S1 until the first threshold is reached. Then, the difference between the maximum value and the minimum value of the detected peak is calculated as the peak width H1. Similarly, the peak width H2 of the horizontal acceleration in the stance phase S2 is also calculated. Then, the average value of the calculated peak widths H1 and H2 is used as the peak value information in S414. Note that in this embodiment, the average value is used, but either the larger value or the smaller value may be used, or both values may be used.
[0078] Next, processor 111 refers to the KAM conversion table (FIG. 7C) stored in memory 112, estimates a KAM value from the peak width value calculated in S414, and stores the estimated KAM value as KAM value information in the user table in association with the user ID information (S415). For example, if the peak width calculated in S414 is greater than or equal to w6 and less than w7, m7 is estimated as the KAM value.
[0079] Then, the processor 111 refers to the prognosis conversion table (FIG. 7D) stored in the memory 112, estimates the prognosis of knee osteoarthritis from the KAM value stored in S415, and stores the estimated prognosis in the prognosis information of the user table in association with the user ID information (S416). For example, if the KAM value stored in S415 is m7, the prognosis is estimated to be "progression."
[0080] Next, the processor 111 calculates the number of peaks detected in the horizontal acceleration from the start of the stance phases S1 and S2 to the first threshold, and stores the calculated number of peaks in the peak number information of the user table in association with the user ID information (S417). Specifically, in the example of FIG. 6, since there are two peaks exceeding a predetermined threshold (output value) in the period T1 until the first threshold has elapsed in the stance phase S1, the number of peaks is calculated as "2". Similarly, since there are two peaks exceeding a predetermined threshold (output value) in the period T2 until the first threshold has elapsed in the stance phase S2, the number of peaks is calculated as "2". Then, the average value of the calculated number of peaks is used as the peak number information in S417. Note that, although the average value is used in this embodiment, the larger number or the smaller number may be used, or both numbers may be used.
[0081] Next, processor 111 calculates the appearance times of the peaks first detected in the horizontal acceleration in stance phases S1 and S2, and stores the calculated appearance times in the appearance time information of the user table in association with the user ID information (S418). Specifically, in the example of Fig. 6, period D1 is calculated by subtracting the start time of stance phase S1 from the time when the first peak was detected in stance phase S1, and period D2 is calculated by subtracting the start time of stance phase S2 from the time when the first peak was detected in stance phase S2.
[0082] Here, the peak width calculated in S414 is a numerical value related to the magnitude of the horizontal displacement of the knee joint. In addition, the more the knee osteoarthritis progresses, the more the horizontal wobble of the knee joint increases, and the number of peaks calculated in S417 is a numerical value related to the degree of the horizontal wobble. Furthermore, in knee symptoms such as knee osteoarthritis, the thinner the cartilage of the knee joint, the more the symptoms progress, and the thinner the cartilage, the faster the speed at which vibration is transmitted to the knee joint. The peak appearance time calculated in S418 is information related to the thickness of this cartilage. Therefore, each piece of information on the peak width calculated in S414, the number of peaks calculated in S417, and the peak appearance time calculated in S418 in the horizontal acceleration is useful information for estimating the current knee condition, for example, the level of knee osteoarthritis. Therefore, the processor 111 estimates the current level of the knee condition using these pieces of information stored in the memory, and stores the estimated value in the user table in association with the user ID information (S419). As an example of the estimation, each piece of information obtained is scored based on a preset classification table. Then, each score obtained is multiplied by a predetermined weighting coefficient, and a total value is calculated by adding up the weighted values obtained. Then, the level of the knee condition is estimated based on the total value. Note that this is only an example as described above, and other methods can be used. For example, a predetermined threshold value may be set for each of the peak width, the number of peaks, and the peak appearance time, and if any one of the values exceeds the threshold value, or if two of the values exceed the threshold value, or if all three values exceed the threshold value, the current knee condition may be estimated to be osteoarthritis.
[0083] Here, FIG. 12 is a diagram showing an example of acceleration detected by the detection device 200 according to an embodiment of the present disclosure. According to FIG. 12, multiple peaks of acceleration in the horizontal direction, i.e., in the period T1 of the stance phase S1, are detected. One of them is a peak Pa detected immediately after the start of the stance phase. However, in this embodiment, the peak Pa is determined as noise and is "ignored" in the processes of S414, S417, and S418. When the leg to which the detection device 200 is attached lands on the ground at the beginning of the stance phase, horizontal vibration of the entire leg due to landing may be detected. This is because such vibration is not caused by a horizontal deviation of the knee joint itself due to osteoarthritis, but needs to be identified as noise.
[0084] Specifically, when the stance phase S1 is specified in S412, the processor 111 determines whether each peak detected in S414, S417, and S418 is a peak detected during a period T2 from the start of the stance phase S1 until the second threshold (time) has elapsed. If a peak is detected during that period, the processor 111 determines that the peak is noise and does not detect it in each process. In the process of noise identification, for example, a period equivalent to 10% of the period of the stance phase S1 may be set as the threshold, or a predetermined fixed value (for example, 10 ms) may be set as the threshold. Furthermore, the time of a peak Pb detected immediately after the start of the stance phase S1 in the acceleration in the vertical direction, i.e., the vertical direction, may be set as the threshold, and a peak in the acceleration in the horizontal direction, i.e., the horizontal direction, detected before this time may be identified as noise.
[0085] [Processing related to displaying the results screen] Fig. 13 is a diagram showing a processing flow executed in the processing device 100 according to an embodiment of the present disclosure. Specifically, Fig. 13 shows a processing flow executed by the processor 111 for outputting a result screen that is displayed when it is determined in S113 of Fig. 8 that the measurement mode is not in effect, or after various pieces of information estimated in S316 of Fig. 10 are stored in the memory 112.
[0086] According to FIG. 13, first, the processor 111 accepts an operation input by an operator through the operation input interface 113, and selects user ID information associated with a user for whom information is to be displayed (S511). Then, the processor 111 refers to the user table and reads out prognosis information and level information associated with the selected user ID information. The processor 111 refers to the auxiliary information table corresponding to each of the read out prognosis information and level information. At this time, the processor 111 may specify all of the information stored in the referred auxiliary information table as auxiliary information, or may specify only a part of the information by filtering (S512). For example, the processor 111 can narrow down the information stored in the referred auxiliary information table based on various information such as the sex, height, weight, and age of the user that is stored in advance in the user table in association with the user ID information.
[0087] Similarly, the processor 111 refers to the corresponding institution table based on the read prognosis information and level information. At this time, the processor 111 may specify all of the information stored in the referenced institution table as institution information, or may specify only a part of the information by filtering (S513). For example, based on the user's address information previously stored in the user table in association with the user ID information and the location information stored in the institution table, the processor 111 can narrow down the institutions corresponding to the institution ID information that exists within a predetermined distance from the address, or to 10 institutions in order of proximity to the address.
[0088] Next, processor 111 reads out from the user table the peak width information, peak number information, appearance time information, KAM value information, prognosis information and level information associated with the user ID information selected in S511, as well as the acceleration table information associated with that user ID information, and controls display 114 to output a result screen (S515).
[0089] 5. Example of result screen Fig. 14, Fig. 15, and Fig. 16 are diagrams showing examples of screens displayed on the processing device 100 according to an embodiment of the present disclosure. Specifically, Fig. 14 is a diagram showing an example of a result screen that is initially displayed when the result screen is output in S515 of Fig. 13. Also, Fig. 15 and Fig. 16 are diagrams showing examples of result screens transitioned to by accepting a display instruction for each piece of information on the result screen of Fig. 14.
[0090] According to FIG. 14, the user information corresponding to the user ID information selected in S511 of FIG. 13 is displayed in the user information display area 21. In addition, in the output value display area 22 below, the output value (acceleration) detected by the detection device 200 is displayed as a curve having time in the X-axis direction and output value in the Y-axis direction. In addition, below, there are an appearance time information display area 23, a peak width information display area 24, a prognosis information display area 25, a level information display area 26, a KAM value information display area 39, and a peak number information display area 40, and the information read out in S515 of FIG. 13 is displayed in the corresponding area. In other words, by doctors viewing the information displayed in the output value display area 22 and each display area 23 to 26, 39, and 40, it becomes possible to assist doctors in estimating the current degree of the knee condition (for example, osteoarthritis) and the prognosis of osteoarthritis. Adjacent to these areas are an auxiliary information display icon 27 and an engine information display icon 28, and by accepting an operator's operation input for each icon, a result screen is displayed on which each piece of information is displayed. Furthermore, adjacent to these areas, a "next user icon 29" and a "previous user icon 30" are displayed, respectively, for moving to the result screen of a user associated with the previous or next user ID information in the order stored in the user table.
[0091] FIG. 15 shows an example of a result screen to which the screen transitions when the operation input of the operator to the auxiliary information display icon 27 in FIG. 14 is accepted by the operation input interface 113. According to FIG. 15, like the result screen in FIG. 14, the user information corresponding to the user ID information selected in S511 in FIG. 13 is displayed in the user information display area 31. In addition, below the result screen in FIG. 14, there is an auxiliary information display area 32, in which the auxiliary information specified in S512 in FIG. 13 is displayed. In the example in FIG. 15, information on treatment methods such as conservative treatment and surgical treatment, which are information useful for diagnosis and treatment by the doctors who are the operators, and information on where to purchase auxiliary instruments are displayed, are displayed from the information stored in the auxiliary information table. In addition, a "return icon 33" is displayed adjacent to the auxiliary information display area 32, and by accepting an operation input to the icon, the screen returns to the result screen shown in FIG. 14.
[0092] FIG. 16 shows an example of a result screen to which the screen transitions when the operation input of the operator to the institution information display icon 28 in FIG. 14 is accepted by the operation input interface 113. According to FIG. 16, like the result screen in FIG. 14, the user information corresponding to the user ID information selected in S511 in FIG. 13 is displayed in the user information display area 34. In addition, below that, there is an institution information display area 35, in which the institution information specified in S513 in FIG. 13 is displayed. In the example of FIG. 15, from among the information stored in the institution table, each institution within a predetermined distance based on the user's address information is displayed together with an icon. Specifically, the current location icon 36 indicates the position specified by the user's address information, and the icon of each institution is displayed on a map centered on that position based on the position information of each identified institution. Then, when the operation input of the operator to any of these icons is accepted, the detailed information display area 37 pops up and is displayed in a superimposed manner. Specifically, the institution table is referenced based on the institution ID information of the institution corresponding to the icon that accepted the operation input, and various information stored in the institution table (institution name, address, telephone number, consultation hours information (time information), availability of specialist, reservation address) is displayed. In addition, a "back icon 33" is displayed adjacent to the institution information display area 35, and accepting an operation input to that icon returns to the result screen shown in FIG.
[0093] 6. Example of using a trained estimation model In the estimation process of FIG. 11, the case of using the KAM conversion table of FIG. 7C has been described. However, it is also possible to use a trained KAM value estimation model in combination with or in place of this. FIG. 17 is a diagram showing a process flow relating to generation of a trained estimation model according to an embodiment of the present disclosure. Specifically, FIG. 17 is a process for generating a trained estimation model for estimating a KAM value used for estimating the prognosis of knee osteoarthritis in S416 of FIG. 11. The process flow may be executed by the processor 111 of the processing device 100, or may be executed by a processor of another processing device.
[0094] According to FIG. 17, a step of acquiring an output value from the detection device 200 is executed (S611). The output value is an output value detected by the detection device 200 attached under the knee of a user with knee osteoarthritis. In addition, it is possible to use the horizontal acceleration detected at a predetermined cycle in a predetermined period as the output value, or other output values can be used. Examples of other output values include output values of a total of six axes, using vertical acceleration, depth acceleration, angular velocity about a horizontal axis, angular velocity about a vertical axis, and angular velocity about a depth axis in addition to the horizontal acceleration. Then, a predetermined number of such output values are acquired for deep learning.
[0095] Next, the output value acquired in S611 and the KAM value previously measured as a correct label by another method are input as learning data to a convolutional neural network (CNN) for generating an estimation model, and learning is performed in a learning device including the convolutional neural network so as to output the KAM value (S612). Then, by repeating the learning in S612, a trained estimation model for finally estimating the KAM value is generated (S613). Note that the KAM value as a correct label is measured by a method using motion capture, for example.
[0096] Here, when detecting the output value in the detection device 200, the KAM value may be calculated separately using another method for the obtained trained estimation model, and verification may be performed using the output value and the KAM value (S614). Then, the parameter values used in the convolutional neural network can be adjusted based on the feedback of the result.
[0097] In the present disclosure, as described above, either the KAM peak value or the KAM area value can be used as the KAM value used for output and verification. In addition, although the learning method using a convolutional neural network is exemplified above, other deep learning methods may be used, and other machine learning methods may be used. For example, it is possible to prepare a plurality of combinations of output values and KAM values from the detection device 200, in which the correspondence between the output values and KAM values has been confirmed in advance, and to generate a learned estimation model by using these as teacher data.
[0098] Fig. 18 is a diagram showing a process flow executed in the processing device 100 according to an embodiment of the present disclosure. Specifically, Fig. 18 shows a specific process flow up to estimating the KAM value in the estimation process performed in S315 in Fig. 10.
[0099] According to FIG. 18, the processor 111 first reads out an output value associated with the user ID information input or selected on the measurement screen from the acceleration table stored in the memory 112 (S711). Although only acceleration information is stored in FIG. 7A, as described above, six-axis output values including angular velocity information may be stored. Therefore, as the output value read out in S711, not only acceleration information but also six-axis output values including angular velocity information can be read out. Next, the processor 111 applies the read-out output value to the learned estimation model for estimating the KAM value generated in FIG. 17 (S712). Then, the processor 111 estimates the KAM value using the estimation model (S713). The processor 111 stores the estimated KAM value as KAM value information in the user table in association with the user ID information. The process after estimating and storing the KAM value is similar to that of S416 in FIG. 11.
[0100] In this way, in the present embodiment, it is possible to provide a processing device, a program, a method, and a processing system that can be more easily used by a user when estimating or assisting in estimating a state during exercise. Specifically, by using the output value detected by the detection device 200, it is possible to more easily estimate or assist in estimating the current state of the knee, for example, the state of knee osteoarthritis, and estimate or assist in estimating the prognosis of knee osteoarthritis.
[0101] 7. Other embodiments In the above embodiment, a case has been described in which acceleration during movement is detected using an acceleration sensor as the detection device 200. However, instead of or in combination with the acceleration sensor, any sensor capable of detecting the movement of the user 10, particularly the bending and straightening of the knees, such as a gyro sensor, a geomagnetic sensor, or an expansion sensor, can be used.
[0102] 8. Example showing correlation between output value and KAM value (example of KAM value estimation method in FIG. 11) FIG. 19 is a diagram showing the correlation between the actually measured acceleration peak width at the beginning of the stance phase and the KAM value. Specifically, FIG. 19 is a diagram showing the relationship between the peak width at the beginning of the stance phase calculated based on the horizontal acceleration among a total of 44 output values actually measured by the detection device 200 attached to the lower part of the knee of both legs, using 22 subjects with osteoarthritis of the knee as subjects, and the KAM value (KAM peak value) measured by motion capture. The KAM value was measured by detecting the movement of the reflective markers placed on the standard 46 bony indices of the subjects using the motion capture system "Oqus" (using 8 cameras at 200 frames / second) manufactured by Qualisys and the floor reaction force meter "AM6110" (2000Hz) manufactured by Bertec. Then, the kinematic behavior of the knee was calculated from the obtained movement of the reflective markers using "Visual 3D" manufactured by C-motion Company, to obtain the KAM value curve and calculate the KAM peak value. On the other hand, for acceleration, a small wireless multi-function sensor "TSND151" manufactured by ATR-Promotions was attached to the lower knees of both legs of the subject, and output values (acceleration) during walking were obtained. The stance phase was identified from the obtained output values, and the initial peak width was calculated. The Pearson correlation coefficient (p) was calculated based on each obtained value, and if p<0.05, it was evaluated that there was a correlation between the two. According to FIG. 19, in the measurement, the correlation coefficient between the two values was shown to be p<0.001, and it was confirmed that there was a high correlation between the KAM value and the peak width of the acceleration. In other words, it was confirmed that the KAM value can be estimated by detecting the peak width of the acceleration at the beginning of the stance phase with the detection device 200.
[0103] 9. Example showing correlation between output value and KAM value (example of KAM value estimation method in FIG. 18) In addition, the 22 subjects with osteoarthritis of the knee used in the example of FIG. 17 were used as subjects, and a total of 44 output values were actually measured by the detection device 200 attached to the lower part of the knee of both legs. Of these, a total of 6 output values of horizontal acceleration, vertical acceleration, depth acceleration, angular velocity about the horizontal axis, angular velocity about the vertical axis, and angular velocity about the depth axis were used. First, a trained estimation model was generated using the output values of 18 subjects randomly selected from the output values of the 22 subjects and the KAM area value or KAM peak value prepared as the correct answer label. The KAM area value or KAM peak value of the correct answer label was calculated from the KAM value curve obtained by the same method using motion capture for the same 18 subjects as above. Next, in order to verify the generated estimation model, the output values of the remaining 4 subjects were applied to the generated estimation model to estimate the KAM value. The KAM value estimated by the estimation model was verified by comparing it with the KAM area value or KAM peak value calculated from the KAM value curve obtained by the same motion capture method as described above.
[0104] FIG. 20 is a diagram showing the correlation between the KAM area value estimated by applying the output values of four people to the generated estimation model and the KAM area value calculated by motion capture. Specifically, FIG. 20 shows a graph in which the horizontal axis indicates the number of times (0 to 239 times) that learning was repeated in the estimation model, and the vertical axis indicates the correlation coefficient between the KAM area value obtained by applying the estimation model and the KAM area value obtained by using motion capture. According to FIG. 20, a correlation coefficient of 0.4 or more, which is generally evaluated as "correlated," was stably obtained in the 47th step and thereafter. In particular, an extremely high correlation coefficient of 0.934 was obtained in 239 learning steps. This shows that the KAM area value estimated using the estimation model can be sufficiently used for evaluation of osteoarthritis of the knee, as well as the KAM area value obtained by motion capture.
[0105] FIG. 21 is a diagram showing the correlation between the KAM peak value estimated by applying the output values of four people to the generated estimation model and the KAM peak value calculated by motion capture. Specifically, FIG. 21 shows a graph in which the horizontal axis indicates the number of times (0 to 239 times) that learning was repeated in the estimation model, and the vertical axis indicates the correlation coefficient between the KAM peak value obtained by applying the estimation model and the KAM peak value obtained by using motion capture. According to FIG. 21, a correlation coefficient of 0.4 or more, which is generally evaluated as "correlated," was stably obtained in the 29th step and thereafter. In particular, an extremely high correlation coefficient of 0.633 was obtained in 218 learning steps. This shows that the KAM peak value estimated using the estimation model can be sufficiently used for evaluation of osteoarthritis of the knee, as well as the KAM peak value obtained by motion capture.
[0106] It is also possible to configure a system by appropriately combining or replacing the elements described in each embodiment.
[0107] The processes and procedures described in this specification can be realized not only by those explicitly described in the embodiments, but also by software, hardware, or a combination of these. Specifically, the processes and procedures described in this specification can be realized by implementing logic corresponding to the processes in a medium such as an integrated circuit, a volatile memory, a non-volatile memory, a magnetic disk, or an optical storage. In addition, the processes and procedures described in this specification can be implemented as computer programs and executed by various computers including a processing device and a server device.
[0108] Although the processes and procedures described herein are described as being executed by a single device, software, component, or module, such processes or procedures may be executed by multiple devices, multiple software, multiple components, and / or multiple modules. Furthermore, although the various information described herein is described as being stored in a single memory or storage unit, such information may be stored in multiple memories provided in a single device or multiple memories distributed across multiple devices. Furthermore, the software and hardware elements described herein may be realized by integrating them into fewer components or breaking them down into more components. [Explanation of symbols]
[0109] 1 Processing System 100 Processing equipment 200 Detection Device 300 Server device 400 Auxiliary Equipment
Claims
1. an input / output interface attached to at least one knee of a human leg or around the knee, configured to receive, in a wired or wireless manner, acceleration detected from one or more acceleration sensors for detecting at least the acceleration of the human during motion; a memory configured to store the received acceleration and associated information related to the knee, in addition to a predetermined instruction command; an output interface configured to output predetermined information; a processor configured to perform processing for estimating an index indicating an external knee varus moment of the at least one knee of the human based on the acceleration by executing the predetermined instruction command, identifying the relevant information stored in the memory based on the estimated index, and outputting the identified relevant information to the output interface; Including, The indicator indicative of the external knee joint varus moment can be estimated based on acceleration obtained from a single acceleration sensor. Processing unit.
2. The processing device according to claim 1 , wherein the related information includes information on a medical institution capable of at least one of diagnosing and treating the knee.
3. The processing device according to claim 1 or 2, wherein the relevant information includes information to assist a physician in diagnosing and / or treating the knee.
4. 4. The processing device according to claim 1, wherein the related information stored in the memory is updated at a predetermined timing.
5. The processing device according to claim 1 , wherein the associated information is information that differs depending on the estimated index.
6. A computer including an input / output interface configured to receive acceleration detected by a wired or wireless connection from one or more acceleration sensors attached to at least one knee of a human leg or around the knee, the acceleration sensors detecting at least the acceleration of the human during motion, a memory configured to store the received acceleration and relevant information related to the knee, and an output interface configured to output predetermined information, a processor configured to: estimate an indicator indicative of an external knee varus moment of the at least one knee of the human based on the acceleration; identify the relevant information stored in the memory based on the estimated indicator; and output the identified relevant information to the output interface; A program that functions as The indicator indicating the external knee joint varus moment can be estimated based on acceleration obtained from a single acceleration sensor.
7. A method for performing a method for a computer including an input / output interface configured to receive acceleration detected by a wired or wireless connection from one or more acceleration sensors attached to or around at least one knee of a human leg for detecting acceleration during at least the movement of the human, a memory configured to store the received acceleration and related information related to the knee in addition to a predetermined instruction command, and an output interface configured to output the predetermined information, the method being performed by a processor executing the predetermined instruction command, estimating an index indicative of an external knee varus moment of the at least one knee of the person based on the acceleration; identifying the relevant information stored in the memory based on the estimated indicator; outputting the identified related information to the output interface; A method comprising: The method, wherein the index indicative of the external knee varus moment can be estimated based on acceleration obtained from a single acceleration sensor.
Citation Information
Patent Citations
Health care system, information management device, method thereof, computer program, and computer readable recording medium
JP2002358371A
Judging method and judging device for gonarthorosis
JP2004261525A
Methods and systems for evaluating and assisting in the diagnosis of knee joint conditions.
JP2013528419A
Medical information processing device, system, and program
JP2015036858A
Motion analysis and evaluation device, motion analysis and evaluation method, and program
JP2016140591A
