Information processing device, information processing program and machine learning device
The system uses machine learning to analyze patient conditions and environments for early detection of dementia symptoms, enhancing care quality by enabling timely intervention.
Patent Information
- Application Number
- JP2023084266
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-23
- Publication Date
- 2024-12-05
AI Technical Summary
In nursing care facilities, caregivers often fail to notice the onset of dementia symptoms in elderly patients, leading to delayed intervention and potential risks.
An information processing device and system that utilizes machine learning to estimate the occurrence of dementia symptoms in real time by analyzing condition and environmental indices of patients, including movement, sleep-wake state, vitals, and living environment data, using a machine learning model to predict symptom onset.
Enables early detection and accurate recording of dementia symptoms, allowing caregivers to provide timely and appropriate care, thereby improving the quality of care and facilitating better symptom management.
Smart Images

Figure 2024167938000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an information processing device, an information processing program, and a machine learning device. [Background technology]
[0002] In Japan, the standard of living has improved with the rapid economic growth since the war, and the sanitary environment and medical standards have led to a remarkable increase in life expectancy. This, combined with a declining birth rate, has resulted in an aging society with a high aging rate. Dementia is one of the problems that an aging society faces (e.g., Patent Document 1). [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2022-133183 A Summary of the Invention [Problem to be solved by the invention]
[0004] In care facilities and other facilities where elderly people live, when a patient with dementia begins to show symptoms, there is a risk that caregivers will not notice the onset of the symptoms or will take time to notice, resulting in a failure to respond appropriately.
[0005] The present invention has been made in view of the above circumstances. That is, an object of the present invention is to provide an information processing device, an information processing program, and a machine learning device that are capable of estimating the onset of dementia symptoms in real time. [Means for solving the problem]
[0006] The above-mentioned object of the present invention is achieved by the following means.
[0007] (1) An information processing device comprising: an acquisition unit that acquires index information including at least one of a condition index relating to the condition of a target dementia patient at a first time and a second time prior to the first time, and an environmental index relating to the living environment of the target dementia patient at each of the first time and the second time; and an estimation unit that estimates occurrence information relating to the occurrence of dementia symptoms of the target dementia patient at the first time based on the acquired index information.
[0008] (2) The information processing device according to (1) above, wherein the acquisition unit acquires the index information including a state index for each of the first time and the second time, and the environmental index for each of the first time and the second time.
[0009] (3) The information processing device described in (1) above, wherein the index information further includes at least one of the condition index relating to the condition of the target dementia patient at a third time prior to the second time, and the environmental index relating to the living environment of the target dementia patient at the third time.
[0010] (4) The information processing device described in (1) above, wherein the status index includes at least one of an index representing the movement of the target dementia patient, an index representing the sleep-wake state of the target dementia patient, and an index representing the vital signs of the target dementia patient.
[0011] (5) The information processing device according to (4) above, wherein the motion includes at least one of movement, stopping, and staggering of the target dementia patient.
[0012] (6) The information processing device according to (4) above, wherein the vital signs include at least one of the heart rate, respiration, and blood pressure of the target dementia patient.
[0013] (7) The information processing device according to (1) above, wherein the environmental index includes at least one of an index representing a temperature of the living environment, an index representing an air pressure of the living environment, and an index representing a humidity of the living environment.
[0014] (8) The information processing device described in (1) above, wherein the occurrence information includes information regarding whether or not the dementia symptom has occurred in the target dementia patient, and information regarding the type of the dementia symptom that has occurred.
[0015] (9) The information processing device according to (8) above, wherein the generation information may include information relating to a plurality of the types.
[0016] (10) The information processing device according to (1) above, wherein the estimation unit estimates the generated information using a machine learning model.
[0017] (11) The information processing device described in (10) above, in which the machine learning model is trained using learning indicator information including at least one of a learning state indicator relating to the state of a dementia patient at each of a first learning time and a second learning time prior to the first learning time, and a learning environment indicator relating to the living environment of the dementia patient at each of the first learning time and the second learning time, as an explanatory variable, and learning occurrence information relating to the occurrence of dementia symptoms of the dementia patient at the first learning time as an objective variable.
[0018] (12) The information processing device according to (1) above, further comprising an output unit that outputs the estimated generation information.
[0019] (13) The information processing device according to (1) above, wherein the estimation unit estimates the generated information at intervals of less than 5 minutes.
[0020] (14) The information processing device described in (1) above, wherein the index information includes at least one of information regarding a change in the state index between the first time and the second time and information regarding a change in the environmental index between the first time and the second time.
[0021] (15) An information processing program for causing a computer to execute a process including acquiring index information including at least one of a condition index relating to the condition of a target dementia patient at a first time and a second time prior to the first time, and an environmental index relating to the living environment of the target dementia patient at each of the first time and the second time, and estimating occurrence information relating to the occurrence of dementia symptoms of the target dementia patient at the first time based on the acquired index information.
[0022] (16) A machine learning device comprising: a memory unit in which learning data is stored that includes learning indicator information as an explanatory variable, the learning indicator information including at least one of a learning state indicator relating to the state of a dementia patient at a first learning time and a learning second time prior to the first learning time, and a learning environment indicator relating to the living environment of the dementia patient at each of the first learning time and the second learning time, and learning occurrence information relating to the occurrence of dementia symptoms of the dementia patient at the first learning time as a target variable; and a model generation unit that performs machine learning on the relationship between the learning indicator information and the learning occurrence information based on the stored learning data, to generate a machine learning model. Effect of the Invention
[0023] In the information processing device and information processing program according to the present invention, occurrence information regarding the onset of dementia symptoms at the first time is estimated based on index information indicating at least one of the state and the living environment of a target dementia patient at each of the first time and the second time. The second time is a time before the first time. Therefore, it is possible to estimate the onset of dementia symptoms in real time. [Brief description of the drawings]
[0024] [Figure 1] FIG. 1 is a diagram showing the overall configuration of a monitoring system. [Diagram 2] FIG. 13 is a diagram showing an example of a detection unit installed in a subject's room. [Diagram 3] FIG. 2 is a block diagram showing a hardware configuration of a detection unit. [Figure 4] FIG. 2 is a block diagram showing a hardware configuration of a server. [Diagram 5] FIG. 4 is a diagram illustrating an example of a status indicator stored in a storage unit of a server. [Figure 6] 6 is a diagram showing an example of a state index and an example of an environmental index following FIG. 5. [Figure 7] FIG. 2 is a block diagram showing a hardware configuration of an administrator terminal. [Figure 8] FIG. 2 is a block diagram showing a hardware configuration of a staff terminal. [Figure 9] 2 is a block diagram showing a functional configuration of a control unit of the server. [Figure 10] 11A and 11B are diagrams illustrating an example of index information and generation information. [Figure 11] 10 is a flowchart illustrating an example of an operation of the server. [Figure 12] 1 is a flowchart illustrating an example of a learning process of a machine learning model. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0025] Hereinafter, an embodiment of the present invention will be described with reference to the attached drawings. In the description of the drawings, the same elements are given the same reference numerals, and duplicated explanations will be omitted. In addition, the dimensional ratios of the drawings are exaggerated for the convenience of explanation, and may differ from the actual ratios.
[0026] <Embodiment> [Configuration of monitoring system 1] (Overall composition) FIG. 1 is a diagram showing an overall configuration of a monitoring system 1 according to an embodiment, and FIG. 2 is a diagram showing an example of a detection unit 10 installed in a room of a subject 70. As shown in FIG.
[0027] As shown in Fig. 1, the monitoring system 1 has a plurality of detection units 10, a server 20, an administrator terminal 30, and one or more staff terminals 40. These are connected to each other so as to be able to communicate with each other via a network 50 such as a LAN (Local Area Network), a telephone network, or a data communication network, by wire or wirelessly. The network 50 may include a repeater, a bridge, a router, a cross-connect, or other relay device that relays communication signals. In the example shown in Fig. 1, the staff terminal 40 is connected to each of the detection units 10, the server 20, and the administrator terminal 30 so as to be able to communicate with each other via a network 50 such as a wireless LAN (for example, a LAN conforming to the IEEE802.11 standard) including an access point 51.
[0028] The monitoring system 1 is disposed at an appropriate location according to the subject 70. The subject 70 is, for example, a patient who needs nursing due to illness or injury, a care recipient who needs nursing due to a decline in physical ability due to aging, a person living alone, or a patient hospitalized in a hospital facility. In particular, from the viewpoint of enabling early detection and early response, the subject 70 may be a person who needs to be detected when a predetermined inconvenient event such as an abnormal state occurs to the subject. In this embodiment, the subject 70 is a dementia patient. The monitoring system 1 is suitably disposed in buildings such as elderly welfare facilities, hospitals, and residences according to the type of the subject 70. In the example shown in FIG. 1, the monitoring system 1 is disposed in a building of a facility having a plurality of rooms (living rooms) in which a plurality of subjects 70 reside and a plurality of rooms including a nurse's station.
[0029] The detection units 10 are arranged, for example, in each room which is the observation area of the subject 70. In the example shown in FIG. 1, four detection units 10 are arranged in each room of the subjects 70, namely, A, B, C, and D. The observation area of the detection units 10 includes a bed 60. Staff members 80 who provide nursing care or nursing care (for example, care) to the subject 70 each carry a staff terminal 40 which is a mobile terminal. However, the position and number of each component included in the monitoring system 1 are not limited to the example shown in FIG. 1. For example, the server 20 does not have to be arranged in the nurse's station, and may be an external server unit connected to the network 50.
[0030] (Detection unit 10) Fig. 3 is a block diagram showing a hardware configuration of the detection unit 10. As shown in Fig. 3, the detection unit 10 has a control unit 11, a communication unit 12, a camera 13, a care call unit 14, and a voice input / output unit 15, which are connected to each other by a bus.
[0031] The control unit 11 is configured with a CPU (Central Processing Unit) and memories such as a RAM (Random Access Memory) and a ROM (Read Only Memory), and controls each part of the detection unit 10 and performs calculation processing according to a program. The control unit 11 may further include an HDD (Hard Disk Drive) as a memory.
[0032] The communication unit 12 is an interface circuit (eg, a LAN card) for communicating with other devices, such as the server 20, the manager terminal 30, or the staff terminal 40, via the network 50.
[0033] Camera 13 is placed, for example, on the ceiling or upper part of a wall of a room, captures an area including bed 60 of subject 70 as an observation area, and outputs a captured image (image data). Hereinafter, an image captured by camera 13 is also simply referred to as a "captured image." The captured image includes an image including subject 70. The captured image includes still images and videos. Camera 13 is a near-infrared camera, but a visible light camera may be used instead, or both may be used in combination.
[0034] The control unit 11 recognizes the behavior of the subject 70 from the images captured by the camera 13. The recognized behaviors include "getting up" to get up from the bed 60, "getting out" to leave the bed 60, "falling" to fall off the bed 60, and "falling" to fall onto the floor or the like.
[0035] The control unit 11 detects silhouettes of images (hereinafter referred to as "human silhouettes") from a plurality of captured images (moving images). The human silhouettes can be detected, for example, by extracting a range of pixels with a relatively large difference by a time difference method that extracts the difference between images captured before and after the time of capture. The human silhouettes may be detected by a background difference method that extracts the difference between a captured image and a background image. Whether the subject 70 gets up, gets out of bed, falls, or falls is recognized from the detected human silhouette based on the subject 70's posture (e.g., standing, sitting, lying, etc.) and the relative position with respect to objects installed in the room such as the bed 60. These recognitions may be performed by a program processed by the CPU of the control unit 11, or may be performed by a built-in processing circuit. In addition, without being limited to this, all or most of the recognition processes may be performed on the server 20 side, and the control unit 11 may only transmit the captured images to the server 20. When the control unit 11 recognizes any of the actions, it transmits a notification that an event has occurred to the server 20, etc.
[0036] The care call unit 14 includes a push button switch, and detects a care call when the subject 70 presses the switch. A care call is also called a nurse call. Instead of a push button switch, a care call may be detected by an audio microphone. When the switch of the care call unit 14 is pressed, that is, when a care call is detected, the control unit 11 transmits a notification that a care call has been made (care call notification) to the server 20, etc., via the communication unit 12 and the network 50.
[0037] The voice input / output unit 15 is, for example, a speaker and a microphone, and enables voice communication by transmitting and receiving voice signals to and from the staff terminal 40, etc., via the communication unit 12. The voice input / output unit 15 may be connected to the detection unit 10 via the communication unit 12 as an external device of the detection unit 10.
[0038] Furthermore, the detection unit 10 may further include a Doppler shift type body movement sensor that transmits and receives microwaves toward the bed 60 and detects a Doppler shift of the microwaves caused by body movement (e.g., breathing) of the subject 70. This body movement sensor detects chest body movement (up and down movement of the chest) accompanying breathing of the subject 70, and recognizes that there is a slight body movement abnormality when it detects a disruption in the period of the chest body movement or an amplitude of the chest body movement that is equal to or less than a preset threshold.
[0039] The detection unit 10 may further include a vital sensor that detects the vital signs of the subject 70. The vital sensor detects, for example, the heart rate, respiration, blood pressure, and the like of the subject 70.
[0040] The detection unit 10 may further include an environmental sensor that detects the living environment of the subject 70, such as the temperature, air pressure, and humidity in the room of the subject 70. The detection unit 10 may include an environmental sensor that detects the temperature, air pressure, and humidity in a facility other than the room of the subject 70, or may include an environmental sensor that detects the temperature, air pressure, and humidity outside the facility.
[0041] The staff 80 is a person who responds to various types of tasks for the subject 70 according to the task. The tasks may include medical tasks and nursing tasks. Here, the content of the response to each event will be described in the case where the task of the staff 80 is nursing tasks for the subject 70. The event is determined as "wake up", and if the determination is within a predetermined time (wake up time set by the facility (for example, 7 to 8 a.m.)), morning care is performed. This morning care includes face washing, assistance with brushing teeth, wearing dentures, assistance with changing clothes, etc. In addition, if the event is "getting out of bed", wheelchair transfer and walking assistance may be required. In addition, periodic (fixed time) events other than the events determined by the detection unit 10 include water intake, meal assistance, excretion assistance, wheelchair transfer, walking assistance, and position change (prevention of bedsores). For these periodic events, an alert may be generated by the care call unit 14 or the like at the fixed time.
[0042] The events include a wide range of events that require the staff 80 to respond to the subject 70. For example, the events include an event (referred to as a first event) that the staff 80 should respond to by issuing a notice (alert) to the staff 80, an event (referred to as a second event) that the staff 80 should respond to at a fixed time, and an event (referred to as a third event) that the staff 80 should respond to when they notice it. The first events include, for example, a care call, getting up in bed, getting out of bed, falling, falling, and abnormal micro-movements. The second events include, for example, eating, bathing, changing clothes, and transferring to a wheelchair for a walk, etc. The third events include, for example, excretion care at the verbal request of the subject 70, temperature measurement when a fever is suspected, response when vomiting, and response when dementia symptoms occur.
[0043] The detection unit 10 transmits (outputs) information on the detected event (hereinafter also simply referred to as "event information"), Doppler shift, vital signs, living environment, captured images, and other information to the server 20. The detection unit 10 transmits information to the server 20, for example, in real time.
[0044] (Server 20) FIG. 4 is a block diagram showing the hardware configuration of the server 20. As shown in FIG.
[0045] The server 20 includes a control unit 21, a communication unit 22, and a storage unit 23. Here, the server 20 corresponds to a specific example of an information processing device of the present invention. The server 20 estimates the presence or absence of dementia symptoms of the subject 70 at the first time, for example, using information such as Doppler shift, vital signs, living environment, and captured images at the first time and the second time detected by the detection unit 10 during the first period. The second time is a time before the first time. The dementia symptoms are so-called BPSD (Behavioral and Psychological Symptoms of Dementia).
[0046] The server 20 may be installed in the same building as the room for the subject 70, or may be installed in a remote location and connectable via a network. For example, the server 20 may be a cloud server virtually constructed by a plurality of servers arranged on a network such as the Internet. Each component is connected to each other via a bus so as to be able to communicate with each other. The control unit 21 and the communication unit 22 have the same functions as the control unit 11 and the communication unit 22 of the detection unit 10, respectively, and therefore detailed description thereof will be omitted. Specific functions of the control unit 21 will be described later.
[0047] The storage unit 23 stores an information processing program according to the present embodiment. The above components of the server 20 are controlled by the control unit 21 according to the program. The storage unit 23 stores various information such as an event list, a captured image, a Doppler shift of the subject 70, the living environment of the subject 70, a care recipient list, a care list, and index information. The care recipient list includes information such as the subject 70's name, the level of nursing care certification, whether or not the subject has dementia, and if so, the level of dementia, and whether or not the subject uses a wheelchair. The care list also includes the care history of each subject 70, such as the amount of food intake, amount of water intake, and excretion status. The care list also includes the care history when each subject 70 developed dementia symptoms.
[0048] The index information includes at least one of the state index of the subject 70 at the first time and the second time, and the environmental index at the first time and the second time. The state index is an index related to the state of the subject 70 at a predetermined time. The state of the subject 70 at a predetermined time includes the state of the subject 70 for a predetermined period going back from the predetermined time. The environmental index is an index related to the living environment of the subject 70 at a predetermined time. The living environment of the subject 70 at a predetermined time includes the living environment of the subject 70 for a predetermined period going back from the predetermined time. It is preferable that the index information includes the state index at the first time and the second time, and the environmental index at the first time and the second time. This makes it possible to estimate the occurrence or nonoccurrence of dementia symptoms of the subject 70 with higher accuracy.
[0049] 5 and 6 show examples of the state index and the environment index. The state index preferably includes at least one of an index representing the movement of the subject 70, an index representing the sleep / wake state of the subject 70, and an index representing the vital signs of the subject 70. This is because the movement, sleep / wake state, and vital signs of the subject 70 are considered to be closely related to the onset of dementia symptoms in the subject 70. The index representing the movement of the subject 70 is, for example, an index related to ADL (Activities of Daily Living).
[0050] The movement of the subject 70 includes, for example, at least one of the following: the subject 70 moving, stopping, and staggering.
[0051] For example, the indices representing the movement of the subject 70 include index 1 and index 2 of the amount of movement, indexes 3 to 5 of the range of movement, and index 6 of the speed of movement. Index 1 and index 2 are calculated based on the total stay time and total movement distance of the subject 70 outside the bed 60, respectively. Index 3 to index 5 are calculated based on the area of the visited area of the subject 70 outside the bed 60. Index 6 is calculated based on the long-distance movement speed of the subject 70 outside the bed 60.
[0052] For example, the indices representing the subject 70 stopping include a stopping index 8, long-term stopping indexes 9 and 10, and a short-term stopping index 11. Index 8 is calculated based on the total working time of the subject 70 in daily activities outside of the bed 60. Index 9 and index 10 are calculated based on the time and number of times the subject 70 stops for activities other than daily activities outside of the bed 60. Index 11 is calculated based on the number of times the subject 70 stops for activities other than daily activities outside of the bed 60.
[0053] For example, the index representing the unsteadiness of the subject 70 is the unsteadiness degree index 7. The index 7 is calculated based on the unsteadiness degree of the trajectory of the subject 70 outside the bed 60.
[0054] The index representing the sleep / wakefulness state of the subject 70 is, for example, the sleep / wakefulness index 12. The index 12 is calculated based on flags of the sleep state and the wakefulness state of the subject 70.
[0055] The vital signs of the subject 70 include, for example, at least one of the heart rate, respiration, and blood pressure of the subject 70. For example, an index representing the heart rate of the subject 70 is index 13, an index representing the respiration of the subject 70 is index 14, and an index representing the blood pressure of the subject 70 is index 15.
[0056] The environmental index includes at least one of an index representing the temperature of the living environment of the subject 70, an index representing the air pressure of the living environment of the subject 70, and an index representing the humidity of the living environment of the subject 70. The temperature, air pressure, and humidity are, for example, the temperature, air pressure, and humidity of the room of the subject 70. For example, the index representing the temperature of the living environment of the subject 70 is index 18, the index representing the air pressure of the living environment of the subject 70 is index 16, and the index representing the humidity of the living environment of the subject 70 is index 17.
[0057] The indexes 1 to 18 are calculated, for example, based on information detected by the detection unit 10. For example, the indexes 1 to 18 calculated by the detection unit 10 are transmitted to the server 20 and stored in the storage unit 23. The detection unit 10 detects information, for example, every minute, and calculates the indexes 1 to 18. Alternatively, the server 20 may calculate the indexes 1 to 18 based on the information transmitted from the detection unit 10 and store them in the storage unit 23. The detection unit 10 may calculate a part of the indexes 1 to 18, and the server 20 may calculate the other part. Alternatively, an external device may calculate a part or all of the indexes 1 to 18 based on the information transmitted from the detection unit 10, and the indexes 1 to 18 transmitted from the external device to the server 20 may be stored in the storage unit 23.
[0058] The memory unit 23 further stores a machine learning model trained by machine learning. In this embodiment, the server 20 uses this machine learning model to estimate the presence or absence of dementia symptoms in the subject 70. The memory unit 23 may store learning data used for learning.
[0059] The above information may be stored in a location other than the storage unit 23 of the server 20, and may be stored in various storages such as a cloud server connected to the server 20 via a network. In addition, the above information is not limited to being constructed as one database, and may be stored in a distributed manner in multiple databases that are associated with each other.
[0060] The server 20, by using the event information and the captured image received from the detection unit 10 alone or in cooperation with the detection unit 10, determines (identifies) which subject 70 the event recognized by the detection unit 10, such as getting up, getting out of bed, falling, or calling a nurse, pertains to. This determination is made by determining the subject 70 (i.e., the occupant of the room) associated with the room number in which the detection unit 10 that recognized the event is installed. If the subject 70 carries an IC tag, the subject 70 may be determined by reading the IC tag with an RFID reader provided in each room. If there are multiple subjects 70 in one room, such as in a shared room, the subject 70 may be determined by placing a detection unit 10 for each bed 60.
[0061] When the server 20 receives event information from the detection unit 10, it sends an event notification to the staff terminal 40, including the name of the subject 70 who caused the event, the room number, and the details of the event, thereby notifying the staff 80 of the occurrence of the event and instructing them on how to respond to the event.
[0062] (Administrator terminal 30) 7 is a block diagram showing the hardware configuration of the administrator terminal 30. The administrator terminal 30 is a so-called PC (Personal Computer), and has a control unit 31, a communication unit 32, a display unit 33, and an input unit 34, which are interconnected by a bus.
[0063] The control unit 31 has the same configuration as the control unit 11 of the detection unit 10, and includes a CPU, a RAM, a ROM, and the like.
[0064] The communication unit 32 is an interface for various local connections, such as a network interface for wired communication based on standards such as Ethernet (registered trademark), and an interface for wireless communication based on standards such as Bluetooth (registered trademark) and IEEE802.11, and communicates with each terminal connected to the network 50.
[0065] The display unit 33 is, for example, a liquid crystal display, and displays various information.
[0066] The input unit 34 includes a keyboard, a numeric keypad, a mouse, etc., and is used to input various types of information.
[0067] In this embodiment, the administrator terminal 30 is used as a terminal for an administrator 90. The administrator 90 is, for example, a manager who supervises the staff 80.
[0068] The manager terminal 30 receives instructions from the manager 90 or the like regarding the analysis and output of care information, and transmits the received instructions to the server 20.
[0069] (Staff terminal 40) 8 is a block diagram showing the hardware configuration of the staff terminal 40. The staff terminal 40 has a control unit 41, a wireless communication unit 42, a display unit 43, an input unit 44, and a voice input / output unit 45, which are interconnected by a bus.
[0070] The control unit 41 has the same configuration as the control unit 11 of the detection unit 10, and includes a CPU, a RAM, a ROM, and the like.
[0071] The wireless communication unit 42 is capable of wireless communication using standards such as Wi-Fi and Bluetooth (registered trademark), and wirelessly communicates with each device via an access point 51 or directly.
[0072] The display unit 43 and the input unit 44 are, for example, touch panel type displays, and a touch sensor as the input unit 44 is superimposed on the display surface of the display unit 43 composed of a liquid crystal or the like. Various instructions are notified to the staff 80 by the display unit 43 and the input unit 44. In addition, the display unit 43 and the input unit 44 display an operation screen displaying an event notification, and accept various operations such as input of a response to accept a response to an event and input of a care record through the operation screen. When a dementia symptom occurs in the subject 70, for example, the staff 80 inputs, via the input unit 44, which dementia symptom has occurred for which subject 70, into the staff terminal 40. The staff 80 may input the date and time of the dementia symptom occurrence.
[0073] The voice input / output unit 45 is, for example, a speaker and a microphone, and enables the staff member 80 to make voice calls between other staff terminals 40 via the wireless communication unit 42. The staff terminal 40 can be configured by, for example, a portable communication terminal device such as a tablet computer, a smartphone, or a mobile phone.
[0074] [Functions of control unit 21] Next, specific functions of the control unit 21 of the server 20 will be described with reference to FIG. 9 and FIG.
[0075] 9 is a block diagram showing the functional configuration of the control unit 21. The control unit 21 functions as an acquisition unit 211, an estimation unit 212, and an output unit 213 by reading a program stored in the storage unit 23 and executing processing.
[0076] Fig. 10 illustrates an example of index information acquired by the control unit 21 and occurrence information regarding the occurrence of dementia symptoms of subjects 70 (persons A, B, C, and D) estimated based on the index information. Fig. 10 illustrates an example in which the occurrence of dementia symptoms of subject 70 at 8:00 on January 2nd is estimated.
[0077] The acquisition unit 211 acquires the index information. As described above, the index information includes at least one of the state index at each of the first time and the second time and the environmental index at each of the first time and the second time. The acquisition unit 211 acquires the index information from, for example, the storage unit 23. The acquisition unit 211 acquires the index information, for example, every minute. The first time is, for example, 8:00 on January 2. The second time is, for example, 5 minutes before 8:00 on January 2, that is, 7:55 on January 2. It is preferable that the index information further includes at least one of the state index related to the state of the subject 70 at a third time before the second time and the environmental index related to the living environment of the subject 70 at the third time. This makes it possible to estimate the occurrence of dementia symptoms with higher accuracy. For example, the index information further includes the state index and the environmental index 10 minutes (7:50), 30 minutes (7:30), and 60 minutes (6) before 8:00 on January 2.
[0078] The acquisition unit 211 acquires indexes 1 to 18 of the subject 70 at, for example, 8:00, 7:55, 7:50, 7:30, and 6:00 on January 2nd. The index information acquired by the acquisition unit 211 preferably includes at least one of information on a change in the state index between the first time and the second time, and information on a change in the environment index between the first time and the second time. This makes it possible to estimate the occurrence information of the subject 70 with higher accuracy.
[0079] For example, the index information includes information regarding a comparison between index 1 to index 18 at 8:00 on January 2 and indexes 1 to 18 at 7:55, 7:50, 7:30, and 6:00 on January 2. This information regarding the comparison is calculated, for example, by division.
[0080] The estimation unit 212 estimates occurrence information regarding the occurrence of dementia symptoms of the subject 70 at the first time based on the index information acquired by the acquisition unit 211. That is, the estimation unit 212 estimates the occurrence information of the subject 70 in real time. The occurrence information preferably includes information regarding the presence or absence of dementia symptoms and information regarding the type of dementia symptoms that occurs. When the occurrence information includes information regarding the type of dementia symptoms, the caregiver or the like can respond to the subject 70 in a more detailed manner. The estimation unit 212 estimates the occurrence information using, for example, a machine learning model. This makes it possible to estimate the presence or absence of dementia symptoms of the subject 70 with higher accuracy. The generation of the machine learning model will be described later.
[0081] For example, the estimation unit 212 estimates that at 8:00 on January 2nd, dementia symptoms of verbal abuse and unclean behavior have occurred for Mr. A, visual hallucinations for Mr. B, and delusions for Mr. C. Other types of dementia symptoms include, for example, wandering, auditory hallucinations, going out without permission, accompanying someone, irritability, depression, drowsiness, and loud voice. The occurrence information estimated by the estimation unit 212 may include information on multiple types of dementia symptoms.
[0082] The estimation unit 212 estimates that, for example, at 8:00 on January 2nd, Mr. D does not have any dementia symptoms.
[0083] The estimation unit 212 preferably estimates the occurrence information of the subject 70 at intervals of 5 minutes or less, for example, estimating the occurrence information of the subject 70 every minute. This makes it possible to shorten the time from when the subject 70 develops a dementia symptom to when a caregiver or the like notices the onset of the dementia symptom.
[0084] The output unit 213 outputs the occurrence information of the subject 70 estimated by the estimation unit 212. For example, the output unit 213 outputs the occurrence information by transmitting the occurrence information to the staff terminal 40 via the communication unit 22. The staff terminal 40, for example, displays the received occurrence information on the display unit 43. For example, the display unit 43 displays that at 8:00 on January 2nd, Mr. A is highly likely to develop dementia symptoms such as abusive language and unclean behavior. The display unit 43 may display a response instruction to the staff 80 in response to the occurrence of the dementia symptoms of the subject 70. When the estimation unit 212 estimates that the subject 70 does not have a dementia symptom at the first time, the output unit 213 may not output the occurrence information.
[0085] The detection unit 10, the server 20, the administrator terminal 30, and the staff terminal 40 may include components other than those described above, or may not include some of the components described above.
[0086] [Server 20 Operation] Next, the operation of the server 20 in the monitoring system 1 will be described.
[0087] 11 is a flowchart showing the operation of the server 20. This flowchart can be executed by the control unit 21 in accordance with a program stored in the storage unit 23 of the server 20.
[0088] The control unit 21 first acquires index information of the subject 70 (step S101). For example, the control unit 21 reads and acquires the index information stored in the storage unit 23. This index information includes, for example, state information and environmental information of the subject 70 at each of the first time and the second time.
[0089] Next, the control unit 21 estimates occurrence information regarding the occurrence of dementia symptoms of the subject 70 at the first time based on the index information acquired in the processing of step S101 (step S102). For example, the control unit 21 estimates the occurrence information of the subject 70 by inputting the index information acquired in the processing of step S101 into a machine learning model. The control unit 21 estimates the occurrence information of the subject 70, for example, every minute.
[0090] Thereafter, the control unit 21 outputs the occurrence information estimated in the process of step S102 (step S103), and ends the process.
[0091] [Generating machine learning models] Next, a method for generating a machine learning model used by the control unit 21 will be described.
[0092] 12 is a flowchart showing a method for generating a machine learning model. For example, the control unit 21 functions as a model generation unit and generates a machine learning model. Here, the server 20 corresponds to a specific example of a machine learning device.
[0093] In the process of FIG. 12, machine learning is performed using learning data prepared in advance. The learning data includes many data sets of explanatory variables and objective variables. The explanatory variables are learning index information of the dementia patient, and the objective variables are learning occurrence information of the dementia patient. The learning index information includes at least one of a learning state index related to the state of the dementia patient at each of the learning first time and the learning second time before the learning first time, and a learning environment index related to the living environment of the dementia patient at each of the learning first time and the learning second time. The learning state index and the learning environment index can be obtained based on, for example, information detected by the detection unit 10. The learning occurrence information is information related to the occurrence of dementia symptoms of the dementia patient at the learning first time. The learning occurrence information can be obtained, for example, from the care history of the dementia patient inputted by the staff 80 to the staff terminal 40. The learning index information and the learning occurrence information are, for example, past information of the multiple subjects 70. The past information of the multiple subjects 70 may be sample-adjusted. The learning index information and the learning generation information may be stored in the storage unit 23.
[0094] The learning device (not shown) may be, for example, a standalone high-performance computer using a CPU and GPU processor, or a cloud computer. In the following, a learning method using a neural network configured by combining perceptrons such as deep learning in the learning device will be described, but the learning method is not limited to this, and various other methods may be applied. For example, random forest, decision tree, support vector machine (SVM), logistic regression, k-nearest neighbor method, topic model, etc. may be applied.
[0095] (Step S111) The learning device loads the learning data. If it is the first time, it loads the first set of learning data, and if it is the i-th time, it loads the i-th set of learning data.
[0096] (Step S112) The learning device inputs the explanatory variables from the loaded learning data into the neural network.
[0097] (Step S113) The learning device compares the estimation results of the neural network with the objective variable.
[0098] (Step S114) The learning device adjusts the parameters based on the comparison results, for example, by performing a process based on back-propagation, so as to reduce the difference in the comparison results.
[0099] (Step S115) If the learning device has completed processing of all data from the 1st to ith sets (YES), the process proceeds to step S116; if not (NO), the process returns to step S111, the next learning data is read, and the processes from step S111 onwards are repeated.
[0100] (Step S116) The learning device determines whether or not to continue learning. If learning is to continue (YES), the process returns to step S111 and executes the processes from the first set to the i-th set again in steps S111 to S115. If learning is not to continue (NO), the process proceeds to step S117.
[0101] (Step S117) The learning device stores the machine learning model trained by machine learning in the processes up to this point and ends (END). Storage destinations include the memory unit 23 of the server 20. In the above-described operation of the server 20, the machine learning model thus generated is used to estimate occurrence information regarding the onset of dementia symptoms in the subject 70. The learning device may learn the learning data for each facility, or may learn the learning data for each subject 70.
[0102] [Effects of the server 20 and the monitoring system 1] In the server 20 and the monitoring system 1 according to the present embodiment, occurrence information of the subject 70 at the first time is estimated based on index information representing the state or living environment of the subject 70 at the first time and at a second time before the first time. Therefore, it is possible to estimate the occurrence of dementia symptoms at the first time, i.e., in real time. The effect of this will be described below.
[0103] When a caregiver such as a staff member notices the onset of dementia symptoms in a subject, the caregiver must provide appropriate care to the subject. In addition, the caregiver must keep a record of the onset of dementia symptoms in the subject. However, if the caregiver does not notice the onset of dementia symptoms in the subject for a long period of time, the caregiver cannot provide appropriate care to the subject. This may result in a decline in the quality of care within the facility. In addition, the caregiver cannot keep accurate records of the onset of dementia symptoms in the subject, making it difficult for the caregiver to share the subject's condition with other caregivers.
[0104] In contrast, the server 20 and the monitoring system 1 estimate the onset of dementia symptoms in the subject 70 in real time, allowing caregivers such as staff 80 to discover the onset of dementia symptoms early and take early action. In addition, the staff 80 can accurately record the onset of the dementia symptoms, and the condition of the subject 70 is shared in detail among the staff 80. This improves the quality of care for the subject 70 in the facility.
[0105] The above-described configuration of the monitoring system 1 is a main configuration for explaining the features of the above-described embodiment, but is not limited to the above-described configuration and may be modified in various ways within the scope of the claims. Also, configurations of general monitoring systems are not excluded.
[0106] For example, in the above embodiment, an example has been described in which the server 20 predicts the occurrence information of the subject 70 every minute, but the server 20 may predict the occurrence information of the subject 70 at intervals shorter than one minute. Alternatively, the server 20 may predict the occurrence information of the subject 70 at intervals longer than one minute.
[0107] In addition, in the above embodiment, an example was described in which the server 20 outputs the generated information by transmitting it to the staff terminal 40, but the server 20 may also output the generated information by transmitting it to the administrator terminal 30, or may output the generated information by transmitting it to an external display device, etc.
[0108] In addition, in the above embodiment, an example was described in which the server 20 estimates the occurrence information of the subject 70 using a machine learning model, but the server 20 may estimate the occurrence information of the subject 70 using other methods such as statistical processing.
[0109] In addition, some or all of the functions of the server 20 may be provided by the manager terminal 30, the staff terminal 40, or the detection unit 10.
[0110] Furthermore, the detection unit 10, the server 20, the manager terminal 30 and the staff terminal 40 may each be configured as a plurality of devices, or any one of the devices may be included in the other devices and configured as a single device.
[0111] In addition, in the above-described flowchart, some steps may be omitted, other steps may be added, some of the steps may be executed simultaneously, one step may be divided into multiple steps and executed, and the execution order of the steps may be changed.
[0112] In addition, the means and methods for performing various processes in the monitoring system 1 according to the above-described embodiment can be realized by either a dedicated hardware circuit or a programmed computer. The above-mentioned program may be provided by a computer-readable recording medium such as a USB memory or a DVD (Digital Versatile Disc)-ROM, or may be provided online via a network such as the Internet. In this case, the program recorded in the computer-readable recording medium is usually transferred to and stored in a storage unit such as a hard disk. In addition, the above-mentioned program may be provided as a standalone application software, or may be incorporated as a function into the software of a device such as a detection unit. [Explanation of symbols]
[0113] 1. Monitoring system, 10 detection unit, 11 Control section, 12 Communications Department, 13 Camera, 14 Care Call Department, 15 Audio input / output unit, 20 servers, 21 Control section, 22 Communications Department, 23 storage section, 30 Administrator terminal, 31 Control section, 32 Communications Department, 33 Display section, 34 Input section, 40 Staff terminals, 41 control section, 42 Radio communication section, 43 Display section, 44 Input section, 45 Audio input / output unit, 46 Position acquisition unit, 50 networks, 51 access points, 60 beds, 70 Targets, 80 staff, 90 Managers.
Claims
1. an acquisition unit that acquires index information including at least one of a condition index related to a condition of a target dementia patient at a first time and a second time prior to the first time, and an environmental index related to a living environment of the target dementia patient at the first time and the second time; an estimation unit that estimates occurrence information regarding an occurrence of a dementia symptom of the target dementia patient at the first time based on the acquired index information; An information processing device comprising:
2. The information processing apparatus according to claim 1 , wherein the acquisition unit acquires the index information including a state index at each of the first time and the second time, and the environmental index at each of the first time and the second time.
3. The information processing device of claim 1, wherein the index information further includes at least one of the condition index relating to the condition of the target dementia patient at a third time prior to the second time and the environmental index relating to the living environment of the target dementia patient at the third time.
4. The information processing device according to claim 1 , wherein the condition index includes at least one of an index representing the movement of the target dementia patient, an index representing the sleep-wake state of the target dementia patient, and an index representing the vital signs of the target dementia patient.
5. The information processing device according to claim 4 , wherein the motion includes at least one of movement, stopping, and staggering of the target dementia patient.
6. The information processing device according to claim 4 , wherein the vital signs include at least one of a heart rate, a respiration rate, and a blood pressure of the target dementia patient.
7. The information processing apparatus according to claim 1 , wherein the environmental index includes at least one of an index representing a temperature of the living environment, an index representing an air pressure of the living environment, and an index representing a humidity of the living environment.
8. The information processing device according to claim 1 , wherein the occurrence information includes information regarding the occurrence or nonoccurrence of the dementia symptom in the target dementia patient, and information regarding the type of the dementia symptom that occurs.
9. The information processing apparatus according to claim 8 , wherein the generation information includes information regarding a plurality of the types.
10. The information processing device according to claim 1 , wherein the estimation unit estimates the generated information by using a machine learning model.
11. The information processing device described in claim 10, wherein the machine learning model is trained using learning index information including at least one of a learning state index relating to the state of a dementia patient at each of a first learning time and a second learning time prior to the first learning time, and a learning environment index relating to the living environment of the dementia patient at each of the first learning time and the second learning time as an explanatory variable, and learning occurrence information relating to the occurrence of dementia symptoms of the dementia patient at the first learning time as an objective variable.
12. The information processing apparatus according to claim 1 , further comprising an output unit that outputs the estimated occurrence information.
13. The information processing device according to claim 1 , wherein the estimation unit estimates the generated information at intervals of five minutes or less.
14. 2 . The information processing device according to claim 1 , wherein the index information includes at least one of information regarding a change in the state index between the first time and the second time and information regarding a change in the environmental index between the first time and the second time.
15. acquiring index information including at least one of a condition index related to a condition of a target dementia patient at a first time and a second time prior to the first time, and an environmental index related to a living environment of the target dementia patient at the first time and the second time; estimating occurrence information regarding occurrence of a dementia symptom of the target dementia patient at the first time based on the acquired index information; An information processing program for causing a computer to execute processing including the above.
16. a memory unit in which learning data is stored that includes, as an explanatory variable, learning indicator information including at least one of a learning state indicator related to a state of a dementia patient at each of a learning first time and a learning second time prior to the learning first time, and a learning environment indicator related to a living environment of the dementia patient at each of the learning first time and the learning second time, and learning occurrence information related to the occurrence of a dementia symptom of the dementia patient at the learning first time as a response variable; a model generation unit that performs machine learning on the relationship between the learning index information and the learning generation information based on the stored learning data, and generates a machine learning model; A machine learning device comprising:
Citation Information
Patent Citations
Information processing device and information processing method
JP2022133183A
